Skip to content

an open-source alternative to the dots, bots and muses of the world, run an office of claude code/codex like agents on your laptop, sandboxes or anywhere, uses your existing subscriptions

chore(blog): rebuild static output for the 30-post batch + screenshots

Chaitanya Giri0cdc60d3cfde
diff --git a/blog/screenshots/index-desktop.png b/blog/screenshots/index-desktop.png
index c56d0712..e7114929 100644
Binary files a/blog/screenshots/index-desktop.png and b/blog/screenshots/index-desktop.png differ
diff --git a/blog/screenshots/index-mobile.png b/blog/screenshots/index-mobile.png
index 3012a9a9..9f1c3d8b 100644
Binary files a/blog/screenshots/index-mobile.png and b/blog/screenshots/index-mobile.png differ
diff --git a/blog/screenshots/post-desktop.png b/blog/screenshots/post-desktop.png
index a9dcdd26..339d78b2 100644
Binary files a/blog/screenshots/post-desktop.png and b/blog/screenshots/post-desktop.png differ
diff --git a/blog/screenshots/post-mobile.png b/blog/screenshots/post-mobile.png
index db85a92c..e85f27da 100644
Binary files a/blog/screenshots/post-mobile.png and b/blog/screenshots/post-mobile.png differ
diff --git a/blog/screenshots/post2-desktop.png b/blog/screenshots/post2-desktop.png
new file mode 100644
index 00000000..d41fb8b2
Binary files /dev/null and b/blog/screenshots/post2-desktop.png differ
diff --git a/blog/screenshots/post2-mobile.png b/blog/screenshots/post2-mobile.png
new file mode 100644
index 00000000..07b1e7ed
Binary files /dev/null and b/blog/screenshots/post2-mobile.png differ
diff --git a/docs/blog/ai-agent-glossary/index.html b/docs/blog/ai-agent-glossary/index.html
new file mode 100644
index 00000000..f278fbeb
--- /dev/null
+++ b/docs/blog/ai-agent-glossary/index.html
@@ -0,0 +1,347 @@
+<!doctype html>
+<html lang="en">
+<head>
+<meta charset="UTF-8" />
+<meta name="viewport" content="width=device-width, initial-scale=1.0" />
+<title>The AI Coding Agent Glossary: Harness, Orchestrator, Hive, Subagent — Munder Difflin Blog</title>
+<meta name="description" content="Plain-English definitions of the AI coding agent terms everyone trips over — harness, orchestrator, hive, subagent, agent memory — each in one line." />
+<link rel="canonical" href="https://munderdiffl.in/blog/ai-agent-glossary/" />
+
+<link rel="icon" type="image/png" href="https://munderdiffl.in/logo.png" />
+<link rel="apple-touch-icon" href="https://munderdiffl.in/logo.png" />
+<meta name="theme-color" content="#F5F2E8" />
+
+<!-- Open Graph -->
+<meta property="og:site_name" content="Munder Difflin Blog" />
+<meta property="og:type" content="article" />
+<meta property="og:title" content="The AI Coding Agent Glossary: Harness, Orchestrator, Hive, Subagent — Munder Difflin Blog" />
+<meta property="og:description" content="Plain-English definitions of the AI coding agent terms everyone trips over — harness, orchestrator, hive, subagent, agent memory — each in one line." />
+<meta property="og:url" content="https://munderdiffl.in/blog/ai-agent-glossary/" />
+<meta property="og:image" content="https://munderdiffl.in/media/og.png" />
+<meta property="og:locale" content="en_US" />
+<meta property="article:published_time" content="2026-06-02T00:00:00.000Z" />
+<meta property="article:author" content="Chaitanya Giri" />
+<meta property="article:tag" content="Concepts" />
+<meta property="article:tag" content="Multi-Agent" />
+<meta property="article:tag" content="Glossary" />
+<meta property="article:tag" content="Getting Started" />
+
+
+<!-- Twitter -->
+<meta name="twitter:card" content="summary_large_image" />
+<meta name="twitter:title" content="The AI Coding Agent Glossary: Harness, Orchestrator, Hive, Subagent — Munder Difflin Blog" />
+<meta name="twitter:description" content="Plain-English definitions of the AI coding agent terms everyone trips over — harness, orchestrator, hive, subagent, agent memory — each in one line." />
+<meta name="twitter:image" content="https://munderdiffl.in/media/og.png" />
+
+<link rel="alternate" type="application/atom+xml" title="Munder Difflin Blog" href="https://munderdiffl.in/blog/feed.xml" />
+<link rel="preconnect" href="https://fonts.googleapis.com" />
+<link rel="preconnect" href="https://fonts.gstatic.com" crossorigin />
+<link href="https://fonts.googleapis.com/css2?family=Geist:wght@400;500;600&family=JetBrains+Mono:wght@400;500;600;700&display=swap" rel="stylesheet" />
+<link rel="stylesheet" href="/blog/assets/blog.css" />
+
+<script type="application/ld+json">
+{
+ "@context": "https://schema.org",
+ "@type": "BlogPosting",
+ "headline": "The AI Coding Agent Glossary: Harness, Orchestrator, Hive, Subagent",
+ "description": "Plain-English definitions of the AI coding agent terms everyone trips over — harness, orchestrator, hive, subagent, agent memory — each in one line.",
+ "image": ["https://munderdiffl.in/media/og.png"],
+ "datePublished": "2026-06-02T00:00:00.000Z",
+ "dateModified": "2026-06-02T00:00:00.000Z",
+ "author": { "@type": "Person", "name": "Chaitanya Giri" },
+ "publisher": {
+ "@type": "Organization",
+ "name": "Munder Difflin",
+ "logo": { "@type": "ImageObject", "url": "https://munderdiffl.in/logo.png" }
+ },
+ "mainEntityOfPage": { "@type": "WebPage", "@id": "https://munderdiffl.in/blog/ai-agent-glossary/" },
+ "keywords": "multi-agent ai framework, ai agent glossary, orchestrator vs harness, agentic terms",
+ "articleSection": "Concepts",
+ "inLanguage": "en-US",
+ "url": "https://munderdiffl.in/blog/ai-agent-glossary/"
+}
+</script>
+<script type="application/ld+json">
+{
+ "@context": "https://schema.org",
+ "@type": "BreadcrumbList",
+ "itemListElement": [
+ { "@type": "ListItem", "position": 1, "name": "Home", "item": "https://munderdiffl.in/" },
+ { "@type": "ListItem", "position": 2, "name": "Blog", "item": "https://munderdiffl.in/blog/" },
+ { "@type": "ListItem", "position": 3, "name": "The AI Coding Agent Glossary: Harness, Orchestrator, Hive, Subagent", "item": "https://munderdiffl.in/blog/ai-agent-glossary/" }
+ ]
+}
+</script>
+
+<script type="application/ld+json">
+{
+ "@context": "https://schema.org",
+ "@type": "FAQPage",
+ "mainEntity": [
+ { "@type": "Question", "name": "What's the difference between an agent harness and an agent framework?", "acceptedAnswer": { "@type": "Answer", "text": "A framework (LangGraph, CrewAI) is a library you build an agent application with from scratch. A harness wraps agents you already run — like Claude Code sessions — and adds coordination on top, without rebuilding the agent." } },
+ { "@type": "Question", "name": "What's the difference between an orchestrator and a harness?", "acceptedAnswer": { "@type": "Answer", "text": "A harness is the whole coordination layer — memory, messaging, visibility, and routing. An orchestrator is one part of it: the coordinator that decomposes intent and routes work to the right agents." } },
+ { "@type": "Question", "name": "What is a hive of agents?", "acceptedAnswer": { "@type": "Answer", "text": "A hive is a coordinated group of agents that share memory and message each other, behaving as one team rather than isolated sessions. It's the running 'team' a harness manages." } }
+
+ ]
+}
+</script>
+
+
+</head>
+<body>
+<a class="skip-link" href="#main">Skip to content</a>
+<nav id="nav">
+ <a class="brand" href="/blog/" aria-label="Munder Difflin Blog home">
+ <span class="brand-mark">MD</span>
+ <span class="brand-word">MUNDER DIFFLIN<span class="sep">/</span><span class="blog">BLOG</span></span>
+ </a>
+ <span class="spacer"></span>
+ <div class="links">
+ <a href="/blog/">Latest</a>
+ <a href="/blog/topics/">Topics</a>
+ <a href="/blog/about/">About</a>
+ <a href="https://munderdiffl.in">↗ Product</a>
+ </div>
+ <div class="nav-actions">
+ <a class="btn sm" href="https://munderdiffl.in/blog/feed.xml" aria-label="RSS feed">⤵ RSS</a>
+ <a class="btn sm primary" href="https://munderdiffl.in/#install">⤓ Download</a>
+ </div>
+</nav>
+
+<main id="main">
+
+<article>
+ <header class="post-head wrap">
+ <nav class="crumbs" aria-label="Breadcrumb">
+ <a href="/blog/">Blog</a>
+ <span>/</span>
+ <a href="/blog/topics/concepts/">Concepts</a>
+ </nav>
+ <h1>The AI Coding Agent Glossary: Harness, Orchestrator, Hive, Subagent</h1>
+ <p class="dek">Plain-English definitions of the AI coding agent terms everyone trips over — harness, orchestrator, hive, subagent, agent memory — each in one line.</p>
+ <div class="byline">
+ <span class="av" aria-hidden="true">CG</span>
+ <strong>Chaitanya Giri</strong>
+ <span class="dot" aria-hidden="true">·</span>
+ <time datetime="2026-06-02">Jun 2, 2026</time>
+ <span class="dot" aria-hidden="true">·</span>
+ <span>3 min read</span>
+ <span class="tag kind">Concepts</span>
+ </div>
+ </header>
+
+ <div class="post-wrap wrap">
+ <div class="prose">
+ <div class="callout tldr"><span class="ic">TL;DR</span><p>The agent world is thick with jargon —
+<strong>harness</strong>, <strong>orchestrator</strong>, <strong>hive</strong>,
+<strong>subagent</strong>, <strong>agent memory</strong>. Here's each term in one quotable line, so
+you can read (and write) about [multi-agent AI](/blog/what-is-a-multi-agent-harness/) without
+tripping. Bookmark it.</p></div>
+<p>Every fast-moving field grows its own vocabulary, and AI coding agents have grown a lot of it fast.
+This is a snackable reference: each term defined in a sentence you could quote, with a link out when
+there’s more to say.</p>
+<h2 id="core-building-blocks" tabindex="-1">Core building blocks <a class="anchor" href="#core-building-blocks" aria-hidden="true">#</a></h2>
+<h3 id="agent" tabindex="-1">Agent <a class="anchor" href="#agent" aria-hidden="true">#</a></h3>
+<p><strong>An agent is a running AI session with a goal and tools — it reads, acts, and repeats in a loop until
+the task is done.</strong> In practice, each <a href="/blog/what-are-claude-code-agents/">Claude Code session</a> is an
+agent.</p>
+<h3 id="subagent" tabindex="-1">Subagent <a class="anchor" href="#subagent" aria-hidden="true">#</a></h3>
+<p><strong>A subagent is a short-lived helper an agent spawns inside its own run to fan out a piece of work.</strong>
+Great for parallelism within one task; it doesn’t persist or share memory across your whole workflow.</p>
+<h3 id="tool" tabindex="-1">Tool <a class="anchor" href="#tool" aria-hidden="true">#</a></h3>
+<p><strong>A tool is a capability an agent can call — read a file, run a command, search the web.</strong> Tools are
+what let an agent <em>do</em> things instead of just talk.</p>
+<h2 id="the-coordination-layer" tabindex="-1">The coordination layer <a class="anchor" href="#the-coordination-layer" aria-hidden="true">#</a></h2>
+<h3 id="harness" tabindex="-1">Harness <a class="anchor" href="#harness" aria-hidden="true">#</a></h3>
+<p><strong>A harness is the software that wraps the agents you already run and coordinates them — roles,
+messaging, memory, orchestration, and visibility.</strong> It’s the layer that turns several sessions into a
+team. More: <a href="/blog/what-is-a-multi-agent-harness/">what is a multi-agent harness</a>.</p>
+<h3 id="framework" tabindex="-1">Framework <a class="anchor" href="#framework" aria-hidden="true">#</a></h3>
+<p><strong>A framework is a library you build an agent application <em>with</em>, from scratch (LangGraph, CrewAI,
+AutoGen).</strong> A harness wraps agents you have; a framework is how you’d build one.</p>
+<h3 id="orchestrator" tabindex="-1">Orchestrator <a class="anchor" href="#orchestrator" aria-hidden="true">#</a></h3>
+<p><strong>An orchestrator is the coordinator that decomposes your intent and routes work to the right
+agents,</strong> escalating only the critical decisions. In Munder Difflin it’s the <a href="/#how">GOD agent</a> you
+talk to in plain language.</p>
+<h3 id="hive" tabindex="-1">Hive <a class="anchor" href="#hive" aria-hidden="true">#</a></h3>
+<p><strong>A hive is a coordinated group of agents that share memory and message each other, acting as one
+team.</strong> It’s the running “office” a harness manages.</p>
+<h2 id="memory-messaging" tabindex="-1">Memory &amp; messaging <a class="anchor" href="#memory-messaging" aria-hidden="true">#</a></h2>
+<h3 id="agent-long-term-memory" tabindex="-1">Agent (long-term) memory <a class="anchor" href="#agent-long-term-memory" aria-hidden="true">#</a></h3>
+<p><strong>Long-term memory is durable storage an agent reads on startup and writes to as it learns, so
+knowledge survives between sessions.</strong> Without it, agents start cold every run — see <a href="/blog/give-claude-code-long-term-memory/">how to give
+Claude Code long-term memory</a>.</p>
+<h3 id="semantic-memory" tabindex="-1">Semantic memory <a class="anchor" href="#semantic-memory" aria-hidden="true">#</a></h3>
+<p><strong>Semantic memory lets an agent recall notes by <em>meaning</em> rather than filename — embed the notes,
+fetch the few most relevant.</strong> It’s what keeps recall instant as the knowledge base grows.</p>
+<h3 id="mailbox-inter-agent-messaging" tabindex="-1">Mailbox / inter-agent messaging <a class="anchor" href="#mailbox-inter-agent-messaging" aria-hidden="true">#</a></h3>
+<p><strong>A mailbox lets one agent hand a message or result to another directly, instead of routing through
+you.</strong> It’s how a hive coordinates without a human courier.</p>
+<h2 id="workflow-patterns" tabindex="-1">Workflow patterns <a class="anchor" href="#workflow-patterns" aria-hidden="true">#</a></h2>
+<h3 id="git-worktree" tabindex="-1">Git worktree <a class="anchor" href="#git-worktree" aria-hidden="true">#</a></h3>
+<p><strong>A git worktree is a separate working copy of one repo, so parallel agents edit isolated checkouts
+and don’t clobber each other.</strong> A common foundation for <a href="/blog/how-to-run-multiple-claude-code-agents/">running agents in
+parallel</a>.</p>
+<h3 id="human-in-the-loop" tabindex="-1">Human-in-the-loop <a class="anchor" href="#human-in-the-loop" aria-hidden="true">#</a></h3>
+<p><strong>Human-in-the-loop means the system pauses for your approval on the decisions that matter — spend,
+destructive actions, scope — and runs autonomously otherwise.</strong></p>
+<h3 id="local-first" tabindex="-1">Local-first <a class="anchor" href="#local-first" aria-hidden="true">#</a></h3>
+<p><strong>Local-first means the harness, agents, and memory run on your own machine,</strong> for privacy,
+predictable cost, and offline capability — <a href="/blog/why-local-first-matters-for-ai-agents/">why that matters</a>.</p>
+<h2 id="putting-it-together" tabindex="-1">Putting it together <a class="anchor" href="#putting-it-together" aria-hidden="true">#</a></h2>
+<p>In one sentence using all of it: <em>a <strong>harness</strong> runs a <strong>hive</strong> of <strong>agents</strong> (each its own loop with
+<strong>tools</strong>), gives them shared <strong>semantic memory</strong> and <strong>mailboxes</strong>, and lets an <strong>orchestrator</strong> route
+work — <strong>local-first</strong>, with a <strong>human in the loop</strong> for the critical calls.</em></p>
+<p>If any term sparked a “wait, which tool does that?”, the <a href="/blog/best-claude-code-multi-agent-tools/">roundup of multi-agent Claude Code
+tools</a> maps the vocabulary onto real software.</p>
+<hr>
+<p>Munder Difflin is a harness, a hive, an orchestrator, and shared memory in one local app. <a href="/#install">Download
+Munder Difflin</a> to see the glossary come to life — free and open source.</p>
+
+
+
+ <section class="faq" aria-label="Frequently asked questions">
+ <h2 id="faq">FAQ</h2>
+
+ <div class="qa">
+ <p class="q">What&#39;s the difference between an agent harness and an agent framework?</p>
+ <p class="a">A framework (LangGraph, CrewAI) is a library you build an agent application with from scratch. A harness wraps agents you already run — like Claude Code sessions — and adds coordination on top, without rebuilding the agent.</p>
+ </div>
+
+ <div class="qa">
+ <p class="q">What&#39;s the difference between an orchestrator and a harness?</p>
+ <p class="a">A harness is the whole coordination layer — memory, messaging, visibility, and routing. An orchestrator is one part of it: the coordinator that decomposes intent and routes work to the right agents.</p>
+ </div>
+
+ <div class="qa">
+ <p class="q">What is a hive of agents?</p>
+ <p class="a">A hive is a coordinated group of agents that share memory and message each other, behaving as one team rather than isolated sessions. It&#39;s the running &#39;team&#39; a harness manages.</p>
+ </div>
+
+ </section>
+
+
+
+ <hr />
+ <div class="share">
+ <span class="lbl">Tags</span>
+ <a class="tag" href="/blog/tags/concepts/">Concepts</a><a class="tag" href="/blog/tags/multi-agent/">Multi-Agent</a><a class="tag" href="/blog/tags/glossary/">Glossary</a><a class="tag" href="/blog/tags/getting-started/">Getting Started</a>
+ </div>
+
+ </div>
+
+
+ <aside class="toc-rail" aria-label="Table of contents">
+ <div class="tt">On this page</div>
+ <ol>
+ <li class="lvl-2"><a href="#core-building-blocks">Core building blocks</a></li><li class="lvl-3"><a href="#agent">Agent</a></li><li class="lvl-3"><a href="#subagent">Subagent</a></li><li class="lvl-3"><a href="#tool">Tool</a></li><li class="lvl-2"><a href="#the-coordination-layer">The coordination layer</a></li><li class="lvl-3"><a href="#harness">Harness</a></li><li class="lvl-3"><a href="#framework">Framework</a></li><li class="lvl-3"><a href="#orchestrator">Orchestrator</a></li><li class="lvl-3"><a href="#hive">Hive</a></li><li class="lvl-2"><a href="#memory-messaging">Memory &amp;amp; messaging</a></li><li class="lvl-3"><a href="#agent-long-term-memory">Agent (long-term) memory</a></li><li class="lvl-3"><a href="#semantic-memory">Semantic memory</a></li><li class="lvl-3"><a href="#mailbox-inter-agent-messaging">Mailbox / inter-agent messaging</a></li><li class="lvl-2"><a href="#workflow-patterns">Workflow patterns</a></li><li class="lvl-3"><a href="#git-worktree">Git worktree</a></li><li class="lvl-3"><a href="#human-in-the-loop">Human-in-the-loop</a></li><li class="lvl-3"><a href="#local-first">Local-first</a></li><li class="lvl-2"><a href="#putting-it-together">Putting it together</a></li>
+ </ol>
+ </aside>
+
+ </div>
+
+ <footer class="post-foot wrap"><div class="prevnext">
+ <a class="pn prev" href="/blog/from-one-terminal-to-a-team/"><span class="k">← Older</span><span class="t">From One Terminal to a Team: Scaling Your Claude Code Workflow</span></a>
+ <a class="pn next" href="/blog/vibe-kanban-alternative/"><span class="k">Newer →</span><span class="t">A vibe-kanban Alternative for Coordinating AI Agents</span></a>
+ </div>
+ <section class="related">
+ <h2>Related in Concepts</h2>
+ <div class="post-grid">
+ <article class="card">
+ <a class="thumb t-concepts" href="/blog/munder-difflin-faq/" aria-hidden="true" tabindex="-1">
+ <span>CONCEPTS</span>
+ </a>
+ <div class="body">
+ <div class="meta">
+ <time datetime="2026-06-02">Jun 2, 2026</time>
+ <span class="dot" aria-hidden="true"></span>
+ <span>1 min</span>
+ </div>
+ <h3><a href="/blog/munder-difflin-faq/">Munder Difflin FAQ: Everything People Ask</a></h3>
+ <p class="dek">Answers to the top Munder Difflin questions — what it is, is it free, does it run locally, which platforms, and how it differs from many terminals.</p>
+ <div class="foot">
+ <span class="tag kind">Concepts</span>
+ <a class="more" href="/blog/munder-difflin-faq/" aria-label="Read: Munder Difflin FAQ: Everything People Ask">Read →</a>
+ </div>
+ </div>
+</article>
+<article class="card">
+ <a class="thumb t-concepts" href="/blog/what-are-claude-code-agents/" aria-hidden="true" tabindex="-1">
+ <span>CONCEPTS</span>
+ </a>
+ <div class="body">
+ <div class="meta">
+ <time datetime="2026-06-02">Jun 2, 2026</time>
+ <span class="dot" aria-hidden="true"></span>
+ <span>3 min</span>
+ </div>
+ <h3><a href="/blog/what-are-claude-code-agents/">What Are Claude Code Agents? And How to Use Many at Once</a></h3>
+ <p class="dek">Claude Code agents explained in plain English — what an agent actually is, how subagents differ, and the leap from one agent to a coordinated team.</p>
+ <div class="foot">
+ <span class="tag kind">Concepts</span>
+ <a class="more" href="/blog/what-are-claude-code-agents/" aria-label="Read: What Are Claude Code Agents? And How to Use Many at Once">Read →</a>
+ </div>
+ </div>
+</article>
+<article class="card">
+ <a class="thumb t-concepts" href="/blog/what-is-a-multi-agent-harness/" aria-hidden="true" tabindex="-1">
+ <span>CONCEPTS</span>
+ </a>
+ <div class="body">
+ <div class="meta">
+ <time datetime="2026-05-22">May 22, 2026</time>
+ <span class="dot" aria-hidden="true"></span>
+ <span>2 min</span>
+ </div>
+ <h3><a href="/blog/what-is-a-multi-agent-harness/">What Is a Multi-Agent Harness? (Plain-English Guide)</a></h3>
+ <p class="dek">A multi-agent harness coordinates several AI coding agents into one team — here&#39;s what that means, and how it differs from a single agent or a framework.</p>
+ <div class="foot">
+ <span class="tag kind">Concepts</span>
+ <a class="more" href="/blog/what-is-a-multi-agent-harness/" aria-label="Read: What Is a Multi-Agent Harness? (Plain-English Guide)">Read →</a>
+ </div>
+ </div>
+</article>
+
+ </div>
+ </section>
+
+ </footer>
+</article>
+
+</main>
+<footer>
+ <div class="wrap">
+ <div class="foot-top">
+ <a class="foot-brand brand" href="/blog/">
+ <span class="brand-mark">MD</span>
+ <span class="brand-word">MUNDER DIFFLIN<span class="sep">/</span><span class="blog">BLOG</span></span>
+ </a>
+ <div class="foot-links">
+ <a href="/blog/">Latest</a>
+ <a href="/blog/topics/">Topics</a>
+ <a href="/blog/about/">About</a>
+ <a href="https://munderdiffl.in/blog/feed.xml">RSS</a>
+ <a href="https://github.com/chaitanyagiri/munder-difflin">GitHub</a>
+ <a href="https://munderdiffl.in">munderdiffl.in ↗</a>
+ </div>
+ </div>
+ <div class="foot-meta">
+ © 2026 Munder Difflin · Local-first · MIT-licensed ·
+ Built on <a href="https://munderdiffl.in">Electron, React, Pixi.js, xterm.js &amp; node-pty</a>.
+ Run an office of agents while you sleep.
+ </div>
+ </div>
+</footer>
+
+<script>
+ // sticky-nav border on scroll
+ (function () {
+ var nav = document.getElementById('nav');
+ if (!nav) return;
+ var onScroll = function () { nav.classList.toggle('scrolled', window.scrollY > 8); };
+ onScroll(); window.addEventListener('scroll', onScroll, { passive: true });
+ })();
+</script>
+
+</body>
+</html>
diff --git a/docs/blog/assets/blog.css b/docs/blog/assets/blog.css
index 22f8284a..33332f33 100644
--- a/docs/blog/assets/blog.css
+++ b/docs/blog/assets/blog.css
@@ -341,6 +341,39 @@ nav .links a:hover, nav .links a[aria-current="page"] { color: var(--ink); }
.callout.tldr .ic { color: var(--maroon); }
.callout.tldr strong { color: var(--ink); }
+/* comparison / feature tables (used heavily by the comparison cluster).
+ GitHub-style block+scroll so wide tables stay readable on mobile while the
+ columns keep aligning; neo-brutalist frame to match the rest of the system. */
+.prose table {
+ display: block;
+ width: max-content;
+ max-width: 100%;
+ overflow-x: auto;
+ border-collapse: collapse;
+ border: var(--border-bold);
+ box-shadow: var(--shadow-card-sm);
+ margin: 1.6em 0;
+ font-size: 14.5px;
+ line-height: 1.5;
+}
+.prose thead { background: var(--cream-2); }
+.prose th, .prose td {
+ border: var(--hair);
+ padding: 9px 13px;
+ text-align: left;
+ vertical-align: top;
+}
+.prose th {
+ font-family: var(--font-mono);
+ font-weight: 700;
+ color: var(--ink);
+ border-bottom: var(--border);
+ white-space: nowrap;
+}
+.prose tbody td:first-child { font-weight: 600; color: var(--ink); }
+.prose tbody tr:nth-child(even) { background: rgba(27, 27, 27, 0.035); }
+.prose table a:hover { background: var(--yellow); }
+
/* in-post FAQ block (visible Q&A backing the FAQPage JSON-LD) */
.faq { margin-top: 2em; }
.faq h2 { margin-top: 0; }
diff --git a/docs/blog/atomic-file-mailboxes-for-agents/index.html b/docs/blog/atomic-file-mailboxes-for-agents/index.html
new file mode 100644
index 00000000..dee21a4e
--- /dev/null
+++ b/docs/blog/atomic-file-mailboxes-for-agents/index.html
@@ -0,0 +1,400 @@
+<!doctype html>
+<html lang="en">
+<head>
+<meta charset="UTF-8" />
+<meta name="viewport" content="width=device-width, initial-scale=1.0" />
+<title>Atomic File Mailboxes: How Agents Message Each Other — Munder Difflin Blog</title>
+<meta name="description" content="Can Claude Code agents talk to each other? Yes — the outbox-router-inbox design that lets agents message safely using plain files and atomic renames." />
+<link rel="canonical" href="https://munderdiffl.in/blog/atomic-file-mailboxes-for-agents/" />
+
+<link rel="icon" type="image/png" href="https://munderdiffl.in/logo.png" />
+<link rel="apple-touch-icon" href="https://munderdiffl.in/logo.png" />
+<meta name="theme-color" content="#F5F2E8" />
+
+<!-- Open Graph -->
+<meta property="og:site_name" content="Munder Difflin Blog" />
+<meta property="og:type" content="article" />
+<meta property="og:title" content="Atomic File Mailboxes: How Agents Message Each Other — Munder Difflin Blog" />
+<meta property="og:description" content="Can Claude Code agents talk to each other? Yes — the outbox-router-inbox design that lets agents message safely using plain files and atomic renames." />
+<meta property="og:url" content="https://munderdiffl.in/blog/atomic-file-mailboxes-for-agents/" />
+<meta property="og:image" content="https://munderdiffl.in/media/og.png" />
+<meta property="og:locale" content="en_US" />
+<meta property="article:published_time" content="2026-05-31T00:00:00.000Z" />
+<meta property="article:author" content="Chaitanya Giri" />
+<meta property="article:tag" content="Internals" />
+<meta property="article:tag" content="Messaging" />
+<meta property="article:tag" content="Multi-Agent" />
+<meta property="article:tag" content="Claude Code" />
+
+
+<!-- Twitter -->
+<meta name="twitter:card" content="summary_large_image" />
+<meta name="twitter:title" content="Atomic File Mailboxes: How Agents Message Each Other — Munder Difflin Blog" />
+<meta name="twitter:description" content="Can Claude Code agents talk to each other? Yes — the outbox-router-inbox design that lets agents message safely using plain files and atomic renames." />
+<meta name="twitter:image" content="https://munderdiffl.in/media/og.png" />
+
+<link rel="alternate" type="application/atom+xml" title="Munder Difflin Blog" href="https://munderdiffl.in/blog/feed.xml" />
+<link rel="preconnect" href="https://fonts.googleapis.com" />
+<link rel="preconnect" href="https://fonts.gstatic.com" crossorigin />
+<link href="https://fonts.googleapis.com/css2?family=Geist:wght@400;500;600&family=JetBrains+Mono:wght@400;500;600;700&display=swap" rel="stylesheet" />
+<link rel="stylesheet" href="/blog/assets/blog.css" />
+
+<script type="application/ld+json">
+{
+ "@context": "https://schema.org",
+ "@type": "BlogPosting",
+ "headline": "Atomic File Mailboxes: How Agents Message Each Other",
+ "description": "Can Claude Code agents talk to each other? Yes — the outbox-router-inbox design that lets agents message safely using plain files and atomic renames.",
+ "image": ["https://munderdiffl.in/media/og.png"],
+ "datePublished": "2026-05-31T00:00:00.000Z",
+ "dateModified": "2026-05-31T00:00:00.000Z",
+ "author": { "@type": "Person", "name": "Chaitanya Giri" },
+ "publisher": {
+ "@type": "Organization",
+ "name": "Munder Difflin",
+ "logo": { "@type": "ImageObject", "url": "https://munderdiffl.in/logo.png" }
+ },
+ "mainEntityOfPage": { "@type": "WebPage", "@id": "https://munderdiffl.in/blog/atomic-file-mailboxes-for-agents/" },
+ "keywords": "can claude code agents talk to each other, ai agent messaging, agent mailbox, inter-agent communication",
+ "articleSection": "Internals",
+ "inLanguage": "en-US",
+ "url": "https://munderdiffl.in/blog/atomic-file-mailboxes-for-agents/"
+}
+</script>
+<script type="application/ld+json">
+{
+ "@context": "https://schema.org",
+ "@type": "BreadcrumbList",
+ "itemListElement": [
+ { "@type": "ListItem", "position": 1, "name": "Home", "item": "https://munderdiffl.in/" },
+ { "@type": "ListItem", "position": 2, "name": "Blog", "item": "https://munderdiffl.in/blog/" },
+ { "@type": "ListItem", "position": 3, "name": "Atomic File Mailboxes: How Agents Message Each Other", "item": "https://munderdiffl.in/blog/atomic-file-mailboxes-for-agents/" }
+ ]
+}
+</script>
+
+<script type="application/ld+json">
+{
+ "@context": "https://schema.org",
+ "@type": "FAQPage",
+ "mainEntity": [
+ { "@type": "Question", "name": "Can Claude Code agents talk to each other?", "acceptedAnswer": { "@type": "Answer", "text": "Yes. Each agent has an outbox it writes to and an inbox it reads from; a router process moves messages between them. The agents never write into each other's folders, so messaging is safe even with many agents running at once." } },
+ { "@type": "Question", "name": "Why use files for agent messaging instead of a message queue?", "acceptedAnswer": { "@type": "Answer", "text": "Files plus atomic renames give you durability, auditability, and crash-safety for free, with no broker to run. One JSON file per message, delivered by rename, is simpler and more robust than a shared log every agent appends to." } },
+ { "@type": "Question", "name": "What stops two agents from messaging each other forever?", "acceptedAnswer": { "@type": "Answer", "text": "Only requests, queries, and proposals obligate a reply; informational messages are terminal. Every reply increments a hop count, and past a cap the exchange is escalated to a human instead of looping." } }
+
+ ]
+}
+</script>
+
+
+</head>
+<body>
+<a class="skip-link" href="#main">Skip to content</a>
+<nav id="nav">
+ <a class="brand" href="/blog/" aria-label="Munder Difflin Blog home">
+ <span class="brand-mark">MD</span>
+ <span class="brand-word">MUNDER DIFFLIN<span class="sep">/</span><span class="blog">BLOG</span></span>
+ </a>
+ <span class="spacer"></span>
+ <div class="links">
+ <a href="/blog/">Latest</a>
+ <a href="/blog/topics/">Topics</a>
+ <a href="/blog/about/">About</a>
+ <a href="https://munderdiffl.in">↗ Product</a>
+ </div>
+ <div class="nav-actions">
+ <a class="btn sm" href="https://munderdiffl.in/blog/feed.xml" aria-label="RSS feed">⤵ RSS</a>
+ <a class="btn sm primary" href="https://munderdiffl.in/#install">⤓ Download</a>
+ </div>
+</nav>
+
+<main id="main">
+
+<article>
+ <header class="post-head wrap">
+ <nav class="crumbs" aria-label="Breadcrumb">
+ <a href="/blog/">Blog</a>
+ <span>/</span>
+ <a href="/blog/topics/internals/">Internals</a>
+ </nav>
+ <h1>Atomic File Mailboxes: How Agents Message Each Other</h1>
+ <p class="dek">Can Claude Code agents talk to each other? Yes — the outbox-router-inbox design that lets agents message safely using plain files and atomic renames.</p>
+ <div class="byline">
+ <span class="av" aria-hidden="true">CG</span>
+ <strong>Chaitanya Giri</strong>
+ <span class="dot" aria-hidden="true">·</span>
+ <time datetime="2026-05-31">May 31, 2026</time>
+ <span class="dot" aria-hidden="true">·</span>
+ <span>5 min read</span>
+ <span class="tag kind">Internals</span>
+ </div>
+ </header>
+
+ <div class="post-wrap wrap">
+ <div class="prose">
+ <div class="callout tldr"><span class="ic">TL;DR</span><p>Yes,
+<strong>Claude Code agents can talk to each other</strong> — and the safest way is plain files. Each
+agent writes to its own <code>outbox/</code>; a <strong>router</strong> drains it and delivers each
+message into the recipient's <code>inbox/</code> by <strong>atomic rename</strong>. One JSON file per
+message, never a shared log. The result is durable, auditable, crash-safe messaging with no broker and
+no write conflicts.</p></div>
+<p>“Can Claude Code agents talk to each other?” is one of the first questions people ask when they move
+past a single session. The answer is yes — but <em>how</em> they talk is where most designs go wrong. Let a
+shared chat file be appended by every agent and you’ve built a multi-writer conflict. The robust
+approach is a mailbox: outbox, router, inbox, with atomic file operations underneath. Here’s the whole
+design.</p>
+<h2 id="the-shape-outbox-router-inbox" tabindex="-1">The shape: outbox → router → inbox <a class="anchor" href="#the-shape-outbox-router-inbox" aria-hidden="true">#</a></h2>
+<p>Every agent gets a private workspace, and two of the folders in it are for messaging:</p>
+<pre><code>agents/&lt;agent-id&gt;/
+ inbox/ # messages delivered TO me — one JSON file each
+ inbox/.done/ # messages I've handled (kept for audit, not deleted)
+ outbox/ # messages I want to SEND — the router drains these
+ outbox/.sent/ # archived after delivery, so they're never reprocessed
+</code></pre>
+<p>The flow is one direction at a time:</p>
+<ol>
+<li>To send, an agent writes a single JSON file into its <strong>own</strong> <code>outbox/</code>.</li>
+<li>A <strong>router</strong> — one coordinating process — scans every outbox, reads each message, and delivers it
+into the recipient’s <code>inbox/</code>.</li>
+<li>After delivery, the router moves the original from <code>outbox/</code> into <code>outbox/.sent/</code> so it’s never
+sent twice.</li>
+<li>The recipient reads its <code>inbox/</code> at the start of its next turn, acts on each message, and moves the
+handled ones to <code>inbox/.done/</code>.</li>
+</ol>
+<p>The critical rule sits underneath all of it: <strong>an agent only ever writes into its own directory.</strong> It
+never reaches into another agent’s inbox. Delivery is the router’s job. That single-writer discipline
+is what makes the whole thing safe under concurrency — no two processes touch the same file. (It’s the
+same principle behind <a href="/blog/single-committer-git-pattern/">the single-committer git pattern</a>.)</p>
+<h2 id="why-atomic-renames-matter" tabindex="-1">Why atomic renames matter <a class="anchor" href="#why-atomic-renames-matter" aria-hidden="true">#</a></h2>
+<p>Here’s the subtle part. If the router wrote a message into an inbox with a normal “open, write bytes,
+close,” a reader scanning the inbox at the wrong moment could pick up a half-written file and choke on
+invalid JSON.</p>
+<p>The fix is an <strong>atomic rename</strong>: write the message to a temporary filename first, then <code>rename</code> it
+into its final place. On every mainstream filesystem, rename within a directory is atomic — the file
+either isn’t there or is there <em>complete</em>. A reader never sees a partial message. There’s no lock, no
+coordination, no window of inconsistency.</p>
+<pre><code>write inbox/&lt;id&gt;.json.tmp-9f3a ← may be partial mid-write
+rename inbox/&lt;id&gt;.json.tmp-9f3a → inbox/&lt;id&gt;.json ← appears atomically, whole
+</code></pre>
+<p>This one trick is why files beat a naive shared log. A log every agent appends to is a multi-writer
+race; a directory of atomically-renamed files is conflict-free by construction.</p>
+<h2 id="the-message-itself-speech-acts-not-free-text" tabindex="-1">The message itself: speech acts, not free text <a class="anchor" href="#the-message-itself-speech-acts-not-free-text" aria-hidden="true">#</a></h2>
+<p>A message isn’t just a blob of text — it carries intent. The design borrows the one genuinely useful
+idea from decades of agent-communication research, the <strong>speech act</strong>, and drops the rest:</p>
+<pre class="language-jsonc"><code class="language-jsonc">{
+ "id": "2026-05-30T14-03-11-123Z-a1b2", // unique, time-sortable
+ "conversation": "conv-7f3", // groups a thread
+ "in_reply_to": "<prev message id> | null",
+ "from": "agent.researcher",
+ "to": "agent.coder | god | broadcast",
+ "act": "request | inform | propose | query | agree | refuse | done",
+ "subject": "short human-readable summary",
+ "body": "the details",
+ "hops": 3, // increments per reply; capped to kill loops
+ "requires_reply": true,
+ "needs_human": false,
+ "created_at": "ISO-8601"
+}</code></pre>
+<p>An agent writing a message only has to supply the meaningful fields — <code>to</code>, <code>act</code>, <code>subject</code>, <code>body</code>,
+and optionally a <code>conversation</code> to thread it. The harness fills in the <code>id</code>, the authoritative <code>from</code>
+(taken from the owning outbox directory, so an agent can’t spoof another’s identity), the <code>hops</code>, and
+the timestamps.</p>
+<p>The <code>act</code> field is what makes coordination tractable. It tells the recipient — and the router —
+whether a reply is even expected.</p>
+<h2 id="anti-livelock-how-the-conversation-ends" tabindex="-1">Anti-livelock: how the conversation ends <a class="anchor" href="#anti-livelock-how-the-conversation-ends" aria-hidden="true">#</a></h2>
+<p>Two agents told to “coordinate” will, without guardrails, message each other forever. Three rules stop
+that:</p>
+<ul>
+<li><strong>Only some acts obligate a reply.</strong> <code>request</code>, <code>query</code>, and <code>propose</code> expect an answer. <code>inform</code>
+and <code>done</code> are <em>terminal</em> — replying to them is exactly how a loop starts, so the protocol forbids
+it.</li>
+<li><strong>Hops are capped.</strong> Every reply increments the <code>hops</code> counter. Past a fixed cap, the message is
+flagged for a human instead of being delivered again — a livelock fuse.</li>
+<li><strong>Delivery is idempotent.</strong> Each agent keeps a cursor of the last message id it processed, so
+re-seeing a message is a no-op. Combined with moving handled messages to <code>inbox/.done/</code>, an agent
+can’t accidentally act on the same request twice.</li>
+</ul>
+<p>These are small rules with a big payoff: the messaging layer can be busy and still provably converge.</p>
+<h2 id="broadcast-and-escalation" tabindex="-1">Broadcast and escalation <a class="anchor" href="#broadcast-and-escalation" aria-hidden="true">#</a></h2>
+<p>Two special addresses round out the system:</p>
+<ul>
+<li><strong><code>broadcast</code></strong> delivers a copy to every agent except the sender — useful for “I’m taking ownership
+of the auth module, don’t touch it.”</li>
+<li><strong><code>human</code></strong> (or any message flagged <code>needs_human</code>) doesn’t go to an inbox at all. The router diverts
+it to an approvals queue for a person to answer. This is how an agent reaches <em>you</em> for the genuinely
+critical calls, and it’s the same mechanism the orchestrator uses to escalate — covered in
+<a href="/blog/coordinating-ai-coding-agents/">the best way to coordinate AI coding agents</a>.</li>
+</ul>
+<h2 id="why-this-design-holds-up" tabindex="-1">Why this design holds up <a class="anchor" href="#why-this-design-holds-up" aria-hidden="true">#</a></h2>
+<p>Step back and the properties fall out for free:</p>
+<ul>
+<li><strong>Durable.</strong> Messages are files. A crash mid-run loses nothing already written; the router picks up
+where it left off.</li>
+<li><strong>Auditable.</strong> Every message and every delivery is a file, and the coordinating process commits the
+changes to git — so you can read back exactly who said what, in order.</li>
+<li><strong>Brokerless.</strong> There’s no Redis, no RabbitMQ, no daemon to keep alive. The “infrastructure” is a
+directory and the <code>rename</code> syscall.</li>
+<li><strong>Conflict-free.</strong> Single-writer-per-file plus atomic renames means concurrency is safe without
+locks.</li>
+</ul>
+<p>It’s almost boring, which is the point. The most reliable inter-agent messaging is the kind with the
+fewest moving parts.</p>
+<h2 id="faq" tabindex="-1">FAQ <a class="anchor" href="#faq" aria-hidden="true">#</a></h2>
+<p><strong>Does the router poll or watch the filesystem?</strong> A simple poll on a short interval is both cheaper and
+more robust than filesystem-watch APIs, which have well-known quirks across platforms. The router
+scans every outbox on a tick, delivers what it finds, and goes back to sleep.</p>
+<p><strong>Can an agent message itself?</strong> It can, but there’s rarely a reason to. The interesting traffic is
+agent-to-agent and agent-to-orchestrator.</p>
+<hr>
+<p>Munder Difflin runs exactly this mailbox system for a whole hive of Claude Code agents — atomic
+delivery, speech-act messages, hop caps, and a full git audit trail, all local.
+<a href="https://munderdiffl.in/#install">Download Munder Difflin</a> to watch envelopes fly between agents on
+the office floor; it’s free and open source.</p>
+
+
+
+ <section class="faq" aria-label="Frequently asked questions">
+ <h2 id="faq">FAQ</h2>
+
+ <div class="qa">
+ <p class="q">Can Claude Code agents talk to each other?</p>
+ <p class="a">Yes. Each agent has an outbox it writes to and an inbox it reads from; a router process moves messages between them. The agents never write into each other&#39;s folders, so messaging is safe even with many agents running at once.</p>
+ </div>
+
+ <div class="qa">
+ <p class="q">Why use files for agent messaging instead of a message queue?</p>
+ <p class="a">Files plus atomic renames give you durability, auditability, and crash-safety for free, with no broker to run. One JSON file per message, delivered by rename, is simpler and more robust than a shared log every agent appends to.</p>
+ </div>
+
+ <div class="qa">
+ <p class="q">What stops two agents from messaging each other forever?</p>
+ <p class="a">Only requests, queries, and proposals obligate a reply; informational messages are terminal. Every reply increments a hop count, and past a cap the exchange is escalated to a human instead of looping.</p>
+ </div>
+
+ </section>
+
+
+
+ <hr />
+ <div class="share">
+ <span class="lbl">Tags</span>
+ <a class="tag" href="/blog/tags/internals/">Internals</a><a class="tag" href="/blog/tags/messaging/">Messaging</a><a class="tag" href="/blog/tags/multi-agent/">Multi-Agent</a><a class="tag" href="/blog/tags/claude-code/">Claude Code</a>
+ </div>
+
+ </div>
+
+
+ <aside class="toc-rail" aria-label="Table of contents">
+ <div class="tt">On this page</div>
+ <ol>
+ <li class="lvl-2"><a href="#the-shape-outbox-router-inbox">The shape: outbox → router → inbox</a></li><li class="lvl-2"><a href="#why-atomic-renames-matter">Why atomic renames matter</a></li><li class="lvl-2"><a href="#the-message-itself-speech-acts-not-free-text">The message itself: speech acts, not free text</a></li><li class="lvl-2"><a href="#anti-livelock-how-the-conversation-ends">Anti-livelock: how the conversation ends</a></li><li class="lvl-2"><a href="#broadcast-and-escalation">Broadcast and escalation</a></li><li class="lvl-2"><a href="#why-this-design-holds-up">Why this design holds up</a></li><li class="lvl-2"><a href="#faq">FAQ</a></li>
+ </ol>
+ </aside>
+
+ </div>
+
+ <footer class="post-foot wrap"><div class="prevnext">
+ <a class="pn prev" href="/blog/how-the-god-orchestrator-works/"><span class="k">← Older</span><span class="t">Inside the GOD Orchestrator: Routing, Adjudication, Escalation</span></a>
+ <a class="pn next" href="/blog/how-to-run-multiple-claude-code-agents/"><span class="k">Newer →</span><span class="t">How to Run Multiple Claude Code Agents (Without Losing Track)</span></a>
+ </div>
+ <section class="related">
+ <h2>Related in Internals</h2>
+ <div class="post-grid">
+ <article class="card">
+ <a class="thumb t-internals" href="/blog/building-a-terminal-ui-xterm-node-pty/" aria-hidden="true" tabindex="-1">
+ <span>INTERNALS</span>
+ </a>
+ <div class="body">
+ <div class="meta">
+ <time datetime="2026-06-03">Jun 3, 2026</time>
+ <span class="dot" aria-hidden="true"></span>
+ <span>8 min</span>
+ </div>
+ <h3><a href="/blog/building-a-terminal-ui-xterm-node-pty/">Building a Terminal UI with xterm.js and node-pty</a></h3>
+ <p class="dek">Wire xterm.js to a node-pty backend: stream output, write keystrokes back, handle resize, and keep many live terminals fast with a terminal pool.</p>
+ <div class="foot">
+ <span class="tag kind">Internals</span>
+ <a class="more" href="/blog/building-a-terminal-ui-xterm-node-pty/" aria-label="Read: Building a Terminal UI with xterm.js and node-pty">Read →</a>
+ </div>
+ </div>
+</article>
+<article class="card">
+ <a class="thumb t-internals" href="/blog/claude-code-hooks-explained/" aria-hidden="true" tabindex="-1">
+ <span>INTERNALS</span>
+ </a>
+ <div class="body">
+ <div class="meta">
+ <time datetime="2026-06-03">Jun 3, 2026</time>
+ <span class="dot" aria-hidden="true"></span>
+ <span>6 min</span>
+ </div>
+ <h3><a href="/blog/claude-code-hooks-explained/">Claude Code Hooks, Explained (PreToolUse, PostToolUse, Stop)</a></h3>
+ <p class="dek">A practical tour of Claude Code hooks — the PreToolUse, PostToolUse, and Stop lifecycle — and how a Unix-socket hook shim drives a live office floor.</p>
+ <div class="foot">
+ <span class="tag kind">Internals</span>
+ <a class="more" href="/blog/claude-code-hooks-explained/" aria-label="Read: Claude Code Hooks, Explained (PreToolUse, PostToolUse, Stop)">Read →</a>
+ </div>
+ </div>
+</article>
+<article class="card">
+ <a class="thumb t-internals" href="/blog/node-pty-electron-real-terminals/" aria-hidden="true" tabindex="-1">
+ <span>INTERNALS</span>
+ </a>
+ <div class="body">
+ <div class="meta">
+ <time datetime="2026-06-03">Jun 3, 2026</time>
+ <span class="dot" aria-hidden="true"></span>
+ <span>7 min</span>
+ </div>
+ <h3><a href="/blog/node-pty-electron-real-terminals/">Real Terminals in Electron with node-pty</a></h3>
+ <p class="dek">How to run byte-for-byte authentic shells inside Electron with node-pty: the native-rebuild gotcha, the macOS PATH trap, and streaming PTY output over IPC.</p>
+ <div class="foot">
+ <span class="tag kind">Internals</span>
+ <a class="more" href="/blog/node-pty-electron-real-terminals/" aria-label="Read: Real Terminals in Electron with node-pty">Read →</a>
+ </div>
+ </div>
+</article>
+
+ </div>
+ </section>
+
+ </footer>
+</article>
+
+</main>
+<footer>
+ <div class="wrap">
+ <div class="foot-top">
+ <a class="foot-brand brand" href="/blog/">
+ <span class="brand-mark">MD</span>
+ <span class="brand-word">MUNDER DIFFLIN<span class="sep">/</span><span class="blog">BLOG</span></span>
+ </a>
+ <div class="foot-links">
+ <a href="/blog/">Latest</a>
+ <a href="/blog/topics/">Topics</a>
+ <a href="/blog/about/">About</a>
+ <a href="https://munderdiffl.in/blog/feed.xml">RSS</a>
+ <a href="https://github.com/chaitanyagiri/munder-difflin">GitHub</a>
+ <a href="https://munderdiffl.in">munderdiffl.in ↗</a>
+ </div>
+ </div>
+ <div class="foot-meta">
+ © 2026 Munder Difflin · Local-first · MIT-licensed ·
+ Built on <a href="https://munderdiffl.in">Electron, React, Pixi.js, xterm.js &amp; node-pty</a>.
+ Run an office of agents while you sleep.
+ </div>
+ </div>
+</footer>
+
+<script>
+ // sticky-nav border on scroll
+ (function () {
+ var nav = document.getElementById('nav');
+ if (!nav) return;
+ var onScroll = function () { nav.classList.toggle('scrolled', window.scrollY > 8); };
+ onScroll(); window.addEventListener('scroll', onScroll, { passive: true });
+ })();
+</script>
+
+</body>
+</html>
diff --git a/docs/blog/best-claude-code-multi-agent-tools/index.html b/docs/blog/best-claude-code-multi-agent-tools/index.html
new file mode 100644
index 00000000..37600f2f
--- /dev/null
+++ b/docs/blog/best-claude-code-multi-agent-tools/index.html
@@ -0,0 +1,454 @@
+<!doctype html>
+<html lang="en">
+<head>
+<meta charset="UTF-8" />
+<meta name="viewport" content="width=device-width, initial-scale=1.0" />
+<title>The Best Tools to Run Multiple Claude Code Agents (2026) — Munder Difflin Blog</title>
+<meta name="description" content="An honest 2026 roundup of tools to run multiple Claude Code agents — Claude Squad, Conductor, Crystal, vibe-kanban, and Munder Difflin — compared." />
+<link rel="canonical" href="https://munderdiffl.in/blog/best-claude-code-multi-agent-tools/" />
+
+<link rel="icon" type="image/png" href="https://munderdiffl.in/logo.png" />
+<link rel="apple-touch-icon" href="https://munderdiffl.in/logo.png" />
+<meta name="theme-color" content="#F5F2E8" />
+
+<!-- Open Graph -->
+<meta property="og:site_name" content="Munder Difflin Blog" />
+<meta property="og:type" content="article" />
+<meta property="og:title" content="The Best Tools to Run Multiple Claude Code Agents (2026) — Munder Difflin Blog" />
+<meta property="og:description" content="An honest 2026 roundup of tools to run multiple Claude Code agents — Claude Squad, Conductor, Crystal, vibe-kanban, and Munder Difflin — compared." />
+<meta property="og:url" content="https://munderdiffl.in/blog/best-claude-code-multi-agent-tools/" />
+<meta property="og:image" content="https://munderdiffl.in/media/og.png" />
+<meta property="og:locale" content="en_US" />
+<meta property="article:published_time" content="2026-06-04T00:00:00.000Z" />
+<meta property="article:author" content="Chaitanya Giri" />
+<meta property="article:tag" content="Comparisons" />
+<meta property="article:tag" content="Multi-Agent" />
+<meta property="article:tag" content="Claude Code" />
+<meta property="article:tag" content="Tools" />
+
+
+<!-- Twitter -->
+<meta name="twitter:card" content="summary_large_image" />
+<meta name="twitter:title" content="The Best Tools to Run Multiple Claude Code Agents (2026) — Munder Difflin Blog" />
+<meta name="twitter:description" content="An honest 2026 roundup of tools to run multiple Claude Code agents — Claude Squad, Conductor, Crystal, vibe-kanban, and Munder Difflin — compared." />
+<meta name="twitter:image" content="https://munderdiffl.in/media/og.png" />
+
+<link rel="alternate" type="application/atom+xml" title="Munder Difflin Blog" href="https://munderdiffl.in/blog/feed.xml" />
+<link rel="preconnect" href="https://fonts.googleapis.com" />
+<link rel="preconnect" href="https://fonts.gstatic.com" crossorigin />
+<link href="https://fonts.googleapis.com/css2?family=Geist:wght@400;500;600&family=JetBrains+Mono:wght@400;500;600;700&display=swap" rel="stylesheet" />
+<link rel="stylesheet" href="/blog/assets/blog.css" />
+
+<script type="application/ld+json">
+{
+ "@context": "https://schema.org",
+ "@type": "BlogPosting",
+ "headline": "The Best Tools to Run Multiple Claude Code Agents (2026)",
+ "description": "An honest 2026 roundup of tools to run multiple Claude Code agents — Claude Squad, Conductor, Crystal, vibe-kanban, and Munder Difflin — compared.",
+ "image": ["https://munderdiffl.in/media/og.png"],
+ "datePublished": "2026-06-04T00:00:00.000Z",
+ "dateModified": "2026-06-04T00:00:00.000Z",
+ "author": { "@type": "Person", "name": "Chaitanya Giri" },
+ "publisher": {
+ "@type": "Organization",
+ "name": "Munder Difflin",
+ "logo": { "@type": "ImageObject", "url": "https://munderdiffl.in/logo.png" }
+ },
+ "mainEntityOfPage": { "@type": "WebPage", "@id": "https://munderdiffl.in/blog/best-claude-code-multi-agent-tools/" },
+ "keywords": "best claude code multi-agent tools, claude code multi-agent tool, agentic coding tools, best tools to run multiple claude code agents",
+ "articleSection": "Comparisons",
+ "inLanguage": "en-US",
+ "url": "https://munderdiffl.in/blog/best-claude-code-multi-agent-tools/"
+}
+</script>
+<script type="application/ld+json">
+{
+ "@context": "https://schema.org",
+ "@type": "BreadcrumbList",
+ "itemListElement": [
+ { "@type": "ListItem", "position": 1, "name": "Home", "item": "https://munderdiffl.in/" },
+ { "@type": "ListItem", "position": 2, "name": "Blog", "item": "https://munderdiffl.in/blog/" },
+ { "@type": "ListItem", "position": 3, "name": "The Best Tools to Run Multiple Claude Code Agents (2026)", "item": "https://munderdiffl.in/blog/best-claude-code-multi-agent-tools/" }
+ ]
+}
+</script>
+
+<script type="application/ld+json">
+{
+ "@context": "https://schema.org",
+ "@type": "FAQPage",
+ "mainEntity": [
+ { "@type": "Question", "name": "What is the best tool to run multiple Claude Code agents?", "acceptedAnswer": { "@type": "Answer", "text": "There's no single best — it depends on what you want. Claude Squad is the leanest terminal option; Conductor is the most polished on macOS; Crystal is a good open-source desktop GUI; vibe-kanban gives you a task board; and Munder Difflin adds shared memory, inter-agent messaging, and a GOD orchestrator so the agents act as one coordinated team." } },
+ { "@type": "Question", "name": "Are these Claude Code multi-agent tools free?", "acceptedAnswer": { "@type": "Answer", "text": "Most are free and several are open source (Claude Squad, Crystal, vibe-kanban, and Munder Difflin are open source; Munder Difflin is MIT-licensed). Conductor is a free, native macOS app. Always check each project's current license and pricing before you commit." } },
+ { "@type": "Question", "name": "Do I need a multi-agent tool to use Claude Code?", "acceptedAnswer": { "@type": "Answer", "text": "No. One Claude Code session handles most tasks. You start wanting a multi-agent tool once you're running three or more sessions at once and the coordination overhead — who's doing what, who knows what, who edits which file — starts costing you time." } }
+
+ ]
+}
+</script>
+
+
+</head>
+<body>
+<a class="skip-link" href="#main">Skip to content</a>
+<nav id="nav">
+ <a class="brand" href="/blog/" aria-label="Munder Difflin Blog home">
+ <span class="brand-mark">MD</span>
+ <span class="brand-word">MUNDER DIFFLIN<span class="sep">/</span><span class="blog">BLOG</span></span>
+ </a>
+ <span class="spacer"></span>
+ <div class="links">
+ <a href="/blog/">Latest</a>
+ <a href="/blog/topics/">Topics</a>
+ <a href="/blog/about/">About</a>
+ <a href="https://munderdiffl.in">↗ Product</a>
+ </div>
+ <div class="nav-actions">
+ <a class="btn sm" href="https://munderdiffl.in/blog/feed.xml" aria-label="RSS feed">⤵ RSS</a>
+ <a class="btn sm primary" href="https://munderdiffl.in/#install">⤓ Download</a>
+ </div>
+</nav>
+
+<main id="main">
+
+<article>
+ <header class="post-head wrap">
+ <nav class="crumbs" aria-label="Breadcrumb">
+ <a href="/blog/">Blog</a>
+ <span>/</span>
+ <a href="/blog/topics/comparisons/">Comparisons</a>
+ </nav>
+ <h1>The Best Tools to Run Multiple Claude Code Agents (2026)</h1>
+ <p class="dek">An honest 2026 roundup of tools to run multiple Claude Code agents — Claude Squad, Conductor, Crystal, vibe-kanban, and Munder Difflin — compared.</p>
+ <div class="byline">
+ <span class="av" aria-hidden="true">CG</span>
+ <strong>Chaitanya Giri</strong>
+ <span class="dot" aria-hidden="true">·</span>
+ <time datetime="2026-06-04">Jun 4, 2026</time>
+ <span class="dot" aria-hidden="true">·</span>
+ <span>6 min read</span>
+ <span class="tag kind">Comparisons</span>
+ </div>
+ </header>
+
+ <div class="post-wrap wrap">
+ <div class="prose">
+ <div class="callout tldr"><span class="ic">TL;DR</span><p>The tools for running
+<strong>multiple Claude Code agents</strong> fall into three camps: <strong>terminal session
+managers</strong> (Claude Squad), <strong>parallel-worktree desktop apps</strong> (Conductor,
+Crystal), <strong>task boards</strong> (vibe-kanban), and <strong>coordinated hives</strong> (Munder
+Difflin). The first three help you run agents <em>side by side</em>; a hive adds shared memory,
+messaging, and an orchestrator so they run <em>as a team</em>. Pick by how much coordination you
+actually need.</p></div>
+<p>If you’ve outgrown a single Claude Code window, the next question is <em>which tool</em> helps you run
+several at once without the chaos. The landscape moved fast in 2025–2026, so here’s an honest,
+plain-English roundup of the main options — what each does well, where it stops, and who it’s for.</p>
+<blockquote>
+<p><strong>A note on fairness:</strong> this space changes quickly. Features, platforms, and licenses below are
+accurate to the best of our knowledge at the time of writing — always check each project’s repo or
+site for current details. Munder Difflin is our own tool; we’ve tried to describe the others on
+their own terms, not as straw men.</p>
+</blockquote>
+<h2 id="the-four-shapes-of-multi-agent-claude-code" tabindex="-1">The four shapes of “multi-agent Claude Code” <a class="anchor" href="#the-four-shapes-of-multi-agent-claude-code" aria-hidden="true">#</a></h2>
+<p>Before the tools, the categories — because they answer different questions:</p>
+<ul>
+<li><strong>Terminal session managers</strong> run each agent in its own shell and let you switch between them from
+one keyboard-driven interface. Minimal, fast, SSH-friendly.</li>
+<li><strong>Parallel-worktree desktop apps</strong> give each agent an isolated <a href="/blog/how-to-run-multiple-claude-code-agents/">git
+worktree</a> and a GUI to launch tasks and review
+diffs. Great for “try five approaches in parallel.”</li>
+<li><strong>Task boards</strong> model the work as cards you assign to agents and move through columns — a
+project-management view over agentic coding.</li>
+<li><strong>Coordinated hives</strong> add the layer the others leave to you: shared long-term memory, direct
+agent-to-agent messaging, and an orchestrator that routes work. That’s the <a href="/#what">multi-agent
+harness</a> idea.</li>
+</ul>
+<p>Most tools live cleanly in one camp. Knowing which camp you need is most of the decision.</p>
+<h2 id="the-tools-at-a-glance" tabindex="-1">The tools, at a glance <a class="anchor" href="#the-tools-at-a-glance" aria-hidden="true">#</a></h2>
+<table>
+<thead>
+<tr>
+<th>Tool</th>
+<th>What it is</th>
+<th>How it parallelizes</th>
+<th>Shared memory</th>
+<th>Orchestrator</th>
+<th>License</th>
+</tr>
+</thead>
+<tbody>
+<tr>
+<td>Claude Squad</td>
+<td>Terminal (TUI) session manager</td>
+<td>tmux + git worktrees</td>
+<td>No</td>
+<td>No (you assign)</td>
+<td>Open source</td>
+</tr>
+<tr>
+<td>Conductor</td>
+<td>Native macOS desktop app</td>
+<td>Parallel git worktrees</td>
+<td>No</td>
+<td>No (you assign)</td>
+<td>Free, macOS-only</td>
+</tr>
+<tr>
+<td>Crystal</td>
+<td>Open-source desktop app</td>
+<td>Parallel sessions + worktrees</td>
+<td>No</td>
+<td>No (you assign)</td>
+<td>Open source</td>
+</tr>
+<tr>
+<td>vibe-kanban</td>
+<td>Kanban board for agents</td>
+<td>Task cards across agents</td>
+<td>No</td>
+<td>Board, not auto-routing</td>
+<td>Open source</td>
+</tr>
+<tr>
+<td>Munder Difflin</td>
+<td>Local coordinated hive</td>
+<td>Roles + mailboxes + orchestrator</td>
+<td>Yes (MemPalace)</td>
+<td>Yes (GOD agent)</td>
+<td>Open source (MIT)</td>
+</tr>
+</tbody>
+</table>
+<p>The single row that most separates the field is <strong>shared memory + orchestrator</strong>: that’s the jump
+from “running agents in parallel” to “running a team.”</p>
+<h2 id="claude-squad-the-lean-terminal-option" tabindex="-1">Claude Squad — the lean terminal option <a class="anchor" href="#claude-squad-the-lean-terminal-option" aria-hidden="true">#</a></h2>
+<p><a href="https://github.com/smtg-ai/claude-squad">Claude Squad</a> is a terminal UI that manages multiple AI
+coding agents — Claude Code among them — each in its own tmux session, with git worktrees keeping
+their changes isolated. You launch, switch, background, and review agents without leaving the
+terminal.</p>
+<ul>
+<li><strong>Strengths:</strong> featherweight, keyboard-driven, works great over SSH, no GUI overhead. If you live
+in the terminal and want parallel agents <em>now</em>, it’s hard to beat for speed of setup.</li>
+<li><strong>Where it stops:</strong> agents don’t share memory or message each other, and there’s no orchestrator —
+you decide who does what. It’s a superb <em>session manager</em>, not a coordination layer.</li>
+</ul>
+<p>Best for: terminal purists running a handful of independent tasks. If you want a deeper look at why
+isolation alone isn’t coordination, see <a href="/blog/claude-squad-alternative/">Claude Squad alternative</a>.</p>
+<h2 id="conductor-the-polished-macos-experience" tabindex="-1">Conductor — the polished macOS experience <a class="anchor" href="#conductor-the-polished-macos-experience" aria-hidden="true">#</a></h2>
+<p><a href="https://conductor.build">Conductor</a> is a native macOS app for running Claude Code agents in
+parallel, each in its own isolated git worktree, with a clean Mac-native interface for kicking off
+tasks and reviewing their diffs.</p>
+<ul>
+<li><strong>Strengths:</strong> genuinely nice UX, fast diff review, and a low-friction way to run several
+worktree-isolated agents at once on a Mac.</li>
+<li><strong>Where it stops:</strong> it’s macOS-only, and it’s built around <em>parallel isolated workspaces</em> rather
+than a coordinated team — no shared cross-agent memory, no agent-to-agent messaging, no
+plain-language orchestrator. Closed-source, so you can’t read or extend the internals.</li>
+</ul>
+<p>Best for: Mac users who want a refined parallel-worktree workflow. If you’re cross-platform or want a
+coordination layer, see <a href="/blog/conductor-claude-code-alternative/">a Conductor alternative</a>.</p>
+<h2 id="crystal-the-open-source-desktop-gui" tabindex="-1">Crystal — the open-source desktop GUI <a class="anchor" href="#crystal-the-open-source-desktop-gui" aria-hidden="true">#</a></h2>
+<p><a href="https://github.com/stravu/crystal">Crystal</a> is an open-source desktop app that runs multiple Claude
+Code sessions in parallel, each in its own git worktree. You spin up sessions from prompts, run them
+concurrently, and review diffs and test results across worktrees in one window.</p>
+<ul>
+<li><strong>Strengths:</strong> open source, a real GUI, and a tidy model for running several experiments in
+parallel and comparing the results.</li>
+<li><strong>Where it stops:</strong> like the others in this camp, it’s parallel isolated sessions — agents don’t
+pool memory or talk to each other, and there’s no orchestrator routing work between them.</li>
+</ul>
+<p>Best for: developers who want an open, visual, worktree-based parallel workflow without the terminal.
+More on the trade-offs in <a href="/blog/crystal-claude-code-alternative/">a Crystal alternative</a>.</p>
+<h2 id="vibe-kanban-the-task-board-for-agents" tabindex="-1">vibe-kanban — the task board for agents <a class="anchor" href="#vibe-kanban-the-task-board-for-agents" aria-hidden="true">#</a></h2>
+<p><a href="https://github.com/BloopAI/vibe-kanban">vibe-kanban</a> takes a different angle: a kanban board where
+you create tasks as cards, assign them to coding agents (it’s agent-agnostic — Claude Code, Gemini,
+Codex, and more), and move work through columns from to-do to review.</p>
+<ul>
+<li><strong>Strengths:</strong> the board is a familiar, legible mental model; it’s agent-agnostic; and it’s great
+for managing a <em>queue</em> of work and reviewing each agent’s output before it lands.</li>
+<li><strong>Where it stops:</strong> a board is something <em>you</em> drive. Cards don’t carry shared long-term memory
+between agents, agents don’t message each other, and nothing auto-routes work — the orchestration
+is you, moving cards.</li>
+</ul>
+<p>Best for: people who think in tasks and want a board over their agents. When you’d rather the routing
+happen for you, see <a href="/blog/vibe-kanban-alternative/">a vibe-kanban alternative</a>.</p>
+<h2 id="munder-difflin-the-coordinated-hive" tabindex="-1">Munder Difflin — the coordinated hive <a class="anchor" href="#munder-difflin-the-coordinated-hive" aria-hidden="true">#</a></h2>
+<p><a href="/#what">Munder Difflin</a> is our own take, and it’s deliberately in a different camp. It turns the
+Claude Code terminals you already run into a <em>self-coordinating hive</em>: each agent gets a role and a
+mailbox, agents message each other directly, they share long-term <strong>semantic memory</strong> (MemPalace),
+and a <a href="/#how">GOD orchestrator</a> you talk to in plain language decomposes your intent and routes work
+across the team. The whole floor is visualized as avatars at their desks, so you can actually watch
+it run.</p>
+<ul>
+<li><strong>Strengths:</strong> it adds the coordination the other tools leave to you — <a href="/blog/give-claude-code-long-term-memory/">shared
+memory</a>, inter-agent messaging, an orchestrator, and
+visibility. Local-first and MIT-licensed, on macOS, Windows, and Linux.</li>
+<li><strong>Where it stops (honestly):</strong> it’s a younger project, and the office-floor visualization is
+heavier than a TUI. For one or two quick parallel tasks, a lean session manager is less to think
+about — a hive earns its keep once coordination is the real cost.</li>
+</ul>
+<p>Best for: people running enough agents that <em>coordination</em> — not just parallelism — is the problem.</p>
+<h2 id="how-to-choose" tabindex="-1">How to choose <a class="anchor" href="#how-to-choose" aria-hidden="true">#</a></h2>
+<p>Match the tool to the bottleneck:</p>
+<ul>
+<li><strong>“I just want parallel agents, fast.”</strong> → Claude Squad (terminal) or Crystal (GUI).</li>
+<li><strong>“I’m on a Mac and want it to feel native.”</strong> → Conductor.</li>
+<li><strong>“I want to manage work as tasks.”</strong> → vibe-kanban.</li>
+<li><strong>“My agents need to share what they learn and stop colliding.”</strong> → Munder Difflin.</li>
+</ul>
+<p>If you want a structured way to weigh these, we wrote a <a href="/blog/how-to-choose-a-multi-agent-tool/">buyer’s
+checklist</a> and a criteria-based <a href="/blog/claude-code-orchestration-tools-compared/">orchestration tools
+comparison</a>. And if you’ve decided coordination is
+your real problem, the fastest way to feel the difference is to
+<a href="/#install">download Munder Difflin</a> — it’s free and open source.</p>
+<hr>
+<p>The honest summary: there’s no universal “best.” The best tool is the one that solves <em>your</em>
+bottleneck — and the bottleneck shifts from parallelism to coordination the moment you’re running a
+real team of agents.</p>
+
+
+
+ <section class="faq" aria-label="Frequently asked questions">
+ <h2 id="faq">FAQ</h2>
+
+ <div class="qa">
+ <p class="q">What is the best tool to run multiple Claude Code agents?</p>
+ <p class="a">There&#39;s no single best — it depends on what you want. Claude Squad is the leanest terminal option; Conductor is the most polished on macOS; Crystal is a good open-source desktop GUI; vibe-kanban gives you a task board; and Munder Difflin adds shared memory, inter-agent messaging, and a GOD orchestrator so the agents act as one coordinated team.</p>
+ </div>
+
+ <div class="qa">
+ <p class="q">Are these Claude Code multi-agent tools free?</p>
+ <p class="a">Most are free and several are open source (Claude Squad, Crystal, vibe-kanban, and Munder Difflin are open source; Munder Difflin is MIT-licensed). Conductor is a free, native macOS app. Always check each project&#39;s current license and pricing before you commit.</p>
+ </div>
+
+ <div class="qa">
+ <p class="q">Do I need a multi-agent tool to use Claude Code?</p>
+ <p class="a">No. One Claude Code session handles most tasks. You start wanting a multi-agent tool once you&#39;re running three or more sessions at once and the coordination overhead — who&#39;s doing what, who knows what, who edits which file — starts costing you time.</p>
+ </div>
+
+ </section>
+
+
+
+ <hr />
+ <div class="share">
+ <span class="lbl">Tags</span>
+ <a class="tag" href="/blog/tags/comparisons/">Comparisons</a><a class="tag" href="/blog/tags/multi-agent/">Multi-Agent</a><a class="tag" href="/blog/tags/claude-code/">Claude Code</a><a class="tag" href="/blog/tags/tools/">Tools</a>
+ </div>
+
+ </div>
+
+
+ <aside class="toc-rail" aria-label="Table of contents">
+ <div class="tt">On this page</div>
+ <ol>
+ <li class="lvl-2"><a href="#the-four-shapes-of-multi-agent-claude-code">The four shapes of “multi-agent Claude Code”</a></li><li class="lvl-2"><a href="#the-tools-at-a-glance">The tools, at a glance</a></li><li class="lvl-2"><a href="#claude-squad-the-lean-terminal-option">Claude Squad — the lean terminal option</a></li><li class="lvl-2"><a href="#conductor-the-polished-macos-experience">Conductor — the polished macOS experience</a></li><li class="lvl-2"><a href="#crystal-the-open-source-desktop-gui">Crystal — the open-source desktop GUI</a></li><li class="lvl-2"><a href="#vibe-kanban-the-task-board-for-agents">vibe-kanban — the task board for agents</a></li><li class="lvl-2"><a href="#munder-difflin-the-coordinated-hive">Munder Difflin — the coordinated hive</a></li><li class="lvl-2"><a href="#how-to-choose">How to choose</a></li>
+ </ol>
+ </aside>
+
+ </div>
+
+ <footer class="post-foot wrap"><div class="prevnext">
+ <a class="pn prev" href="/blog/claude-code-automation-while-you-sleep/"><span class="k">← Older</span><span class="t">Claude Code Automation: Let Agents Build While You Sleep</span></a>
+ <span></span>
+ </div>
+ <section class="related">
+ <h2>Related in Comparisons</h2>
+ <div class="post-grid">
+ <article class="card">
+ <a class="thumb t-comparisons" href="/blog/claude-code-orchestration-tools-compared/" aria-hidden="true" tabindex="-1">
+ <span>COMPARISONS</span>
+ </a>
+ <div class="body">
+ <div class="meta">
+ <time datetime="2026-06-04">Jun 4, 2026</time>
+ <span class="dot" aria-hidden="true"></span>
+ <span>3 min</span>
+ </div>
+ <h3><a href="/blog/claude-code-orchestration-tools-compared/">Claude Code Orchestration Tools, Compared</a></h3>
+ <p class="dek">Claude Code orchestration tools compared on memory, messaging, visibility, control, and local-first — across Claude Squad, Conductor, Crystal, and more.</p>
+ <div class="foot">
+ <span class="tag kind">Comparisons</span>
+ <a class="more" href="/blog/claude-code-orchestration-tools-compared/" aria-label="Read: Claude Code Orchestration Tools, Compared">Read →</a>
+ </div>
+ </div>
+</article>
+<article class="card">
+ <a class="thumb t-comparisons" href="/blog/claude-squad-vs-munder-difflin/" aria-hidden="true" tabindex="-1">
+ <span>COMPARISONS</span>
+ </a>
+ <div class="body">
+ <div class="meta">
+ <time datetime="2026-06-04">Jun 4, 2026</time>
+ <span class="dot" aria-hidden="true"></span>
+ <span>3 min</span>
+ </div>
+ <h3><a href="/blog/claude-squad-vs-munder-difflin/">Claude Squad vs Munder Difflin: Which Should You Use?</a></h3>
+ <p class="dek">Claude Squad vs Munder Difflin: a lean terminal session manager against a memory-backed, orchestrated, visual hive. Feature table and an honest verdict.</p>
+ <div class="foot">
+ <span class="tag kind">Comparisons</span>
+ <a class="more" href="/blog/claude-squad-vs-munder-difflin/" aria-label="Read: Claude Squad vs Munder Difflin: Which Should You Use?">Read →</a>
+ </div>
+ </div>
+</article>
+<article class="card">
+ <a class="thumb t-comparisons" href="/blog/claude-squad-alternative/" aria-hidden="true" tabindex="-1">
+ <span>COMPARISONS</span>
+ </a>
+ <div class="body">
+ <div class="meta">
+ <time datetime="2026-06-03">Jun 3, 2026</time>
+ <span class="dot" aria-hidden="true"></span>
+ <span>3 min</span>
+ </div>
+ <h3><a href="/blog/claude-squad-alternative/">Looking for a Claude Squad Alternative?</a></h3>
+ <p class="dek">What Claude Squad does well, where it stops, and why a memory-backed, orchestrated hive may be the Claude Squad alternative you&#39;re after.</p>
+ <div class="foot">
+ <span class="tag kind">Comparisons</span>
+ <a class="more" href="/blog/claude-squad-alternative/" aria-label="Read: Looking for a Claude Squad Alternative?">Read →</a>
+ </div>
+ </div>
+</article>
+
+ </div>
+ </section>
+
+ </footer>
+</article>
+
+</main>
+<footer>
+ <div class="wrap">
+ <div class="foot-top">
+ <a class="foot-brand brand" href="/blog/">
+ <span class="brand-mark">MD</span>
+ <span class="brand-word">MUNDER DIFFLIN<span class="sep">/</span><span class="blog">BLOG</span></span>
+ </a>
+ <div class="foot-links">
+ <a href="/blog/">Latest</a>
+ <a href="/blog/topics/">Topics</a>
+ <a href="/blog/about/">About</a>
+ <a href="https://munderdiffl.in/blog/feed.xml">RSS</a>
+ <a href="https://github.com/chaitanyagiri/munder-difflin">GitHub</a>
+ <a href="https://munderdiffl.in">munderdiffl.in ↗</a>
+ </div>
+ </div>
+ <div class="foot-meta">
+ © 2026 Munder Difflin · Local-first · MIT-licensed ·
+ Built on <a href="https://munderdiffl.in">Electron, React, Pixi.js, xterm.js &amp; node-pty</a>.
+ Run an office of agents while you sleep.
+ </div>
+ </div>
+</footer>
+
+<script>
+ // sticky-nav border on scroll
+ (function () {
+ var nav = document.getElementById('nav');
+ if (!nav) return;
+ var onScroll = function () { nav.classList.toggle('scrolled', window.scrollY > 8); };
+ onScroll(); window.addEventListener('scroll', onScroll, { passive: true });
+ })();
+</script>
+
+</body>
+</html>
diff --git a/docs/blog/building-a-terminal-ui-xterm-node-pty/index.html b/docs/blog/building-a-terminal-ui-xterm-node-pty/index.html
new file mode 100644
index 00000000..72766fab
--- /dev/null
+++ b/docs/blog/building-a-terminal-ui-xterm-node-pty/index.html
@@ -0,0 +1,441 @@
+<!doctype html>
+<html lang="en">
+<head>
+<meta charset="UTF-8" />
+<meta name="viewport" content="width=device-width, initial-scale=1.0" />
+<title>Building a Terminal UI with xterm.js and node-pty — Munder Difflin Blog</title>
+<meta name="description" content="Wire xterm.js to a node-pty backend: stream output, write keystrokes back, handle resize, and keep many live terminals fast with a terminal pool." />
+<link rel="canonical" href="https://munderdiffl.in/blog/building-a-terminal-ui-xterm-node-pty/" />
+
+<link rel="icon" type="image/png" href="https://munderdiffl.in/logo.png" />
+<link rel="apple-touch-icon" href="https://munderdiffl.in/logo.png" />
+<meta name="theme-color" content="#F5F2E8" />
+
+<!-- Open Graph -->
+<meta property="og:site_name" content="Munder Difflin Blog" />
+<meta property="og:type" content="article" />
+<meta property="og:title" content="Building a Terminal UI with xterm.js and node-pty — Munder Difflin Blog" />
+<meta property="og:description" content="Wire xterm.js to a node-pty backend: stream output, write keystrokes back, handle resize, and keep many live terminals fast with a terminal pool." />
+<meta property="og:url" content="https://munderdiffl.in/blog/building-a-terminal-ui-xterm-node-pty/" />
+<meta property="og:image" content="https://munderdiffl.in/media/og.png" />
+<meta property="og:locale" content="en_US" />
+<meta property="article:published_time" content="2026-06-03T00:00:00.000Z" />
+<meta property="article:author" content="Chaitanya Giri" />
+<meta property="article:tag" content="Internals" />
+<meta property="article:tag" content="xterm.js" />
+<meta property="article:tag" content="Terminals" />
+<meta property="article:tag" content="Electron" />
+
+
+<!-- Twitter -->
+<meta name="twitter:card" content="summary_large_image" />
+<meta name="twitter:title" content="Building a Terminal UI with xterm.js and node-pty — Munder Difflin Blog" />
+<meta name="twitter:description" content="Wire xterm.js to a node-pty backend: stream output, write keystrokes back, handle resize, and keep many live terminals fast with a terminal pool." />
+<meta name="twitter:image" content="https://munderdiffl.in/media/og.png" />
+
+<link rel="alternate" type="application/atom+xml" title="Munder Difflin Blog" href="https://munderdiffl.in/blog/feed.xml" />
+<link rel="preconnect" href="https://fonts.googleapis.com" />
+<link rel="preconnect" href="https://fonts.gstatic.com" crossorigin />
+<link href="https://fonts.googleapis.com/css2?family=Geist:wght@400;500;600&family=JetBrains+Mono:wght@400;500;600;700&display=swap" rel="stylesheet" />
+<link rel="stylesheet" href="/blog/assets/blog.css" />
+
+<script type="application/ld+json">
+{
+ "@context": "https://schema.org",
+ "@type": "BlogPosting",
+ "headline": "Building a Terminal UI with xterm.js and node-pty",
+ "description": "Wire xterm.js to a node-pty backend: stream output, write keystrokes back, handle resize, and keep many live terminals fast with a terminal pool.",
+ "image": ["https://munderdiffl.in/media/og.png"],
+ "datePublished": "2026-06-03T00:00:00.000Z",
+ "dateModified": "2026-06-03T00:00:00.000Z",
+ "author": { "@type": "Person", "name": "Chaitanya Giri" },
+ "publisher": {
+ "@type": "Organization",
+ "name": "Munder Difflin",
+ "logo": { "@type": "ImageObject", "url": "https://munderdiffl.in/logo.png" }
+ },
+ "mainEntityOfPage": { "@type": "WebPage", "@id": "https://munderdiffl.in/blog/building-a-terminal-ui-xterm-node-pty/" },
+ "keywords": "xterm.js terminal app, xterm.js, terminal emulator, node-pty electron",
+ "articleSection": "Internals",
+ "inLanguage": "en-US",
+ "url": "https://munderdiffl.in/blog/building-a-terminal-ui-xterm-node-pty/"
+}
+</script>
+<script type="application/ld+json">
+{
+ "@context": "https://schema.org",
+ "@type": "BreadcrumbList",
+ "itemListElement": [
+ { "@type": "ListItem", "position": 1, "name": "Home", "item": "https://munderdiffl.in/" },
+ { "@type": "ListItem", "position": 2, "name": "Blog", "item": "https://munderdiffl.in/blog/" },
+ { "@type": "ListItem", "position": 3, "name": "Building a Terminal UI with xterm.js and node-pty", "item": "https://munderdiffl.in/blog/building-a-terminal-ui-xterm-node-pty/" }
+ ]
+}
+</script>
+
+<script type="application/ld+json">
+{
+ "@context": "https://schema.org",
+ "@type": "FAQPage",
+ "mainEntity": [
+ { "@type": "Question", "name": "What is xterm.js?", "acceptedAnswer": { "@type": "Answer", "text": "xterm.js is a terminal emulator for the browser. It renders a terminal grid in the DOM (or on a canvas/WebGL), parses ANSI escape sequences, and exposes write() for output and onData() for keystrokes — so you can pair it with a backend like node-pty to build a real, interactive terminal in a web UI." } },
+ { "@type": "Question", "name": "How do xterm.js and node-pty fit together?", "acceptedAnswer": { "@type": "Answer", "text": "node-pty runs the real shell and produces bytes; xterm.js displays them and captures input. You forward node-pty's output into xterm's write(), and send xterm's onData() keystrokes back to node-pty. The two halves are connected by your IPC layer." } },
+ { "@type": "Question", "name": "Why does my xterm.js terminal go blank when I switch tabs?", "acceptedAnswer": { "@type": "Answer", "text": "Because node-pty keeps no scrollback — if you destroy and recreate the xterm instance, the new one starts empty until the program repaints. Keep one persistent terminal per session and re-parent its element instead of recreating it." } }
+
+ ]
+}
+</script>
+
+
+</head>
+<body>
+<a class="skip-link" href="#main">Skip to content</a>
+<nav id="nav">
+ <a class="brand" href="/blog/" aria-label="Munder Difflin Blog home">
+ <span class="brand-mark">MD</span>
+ <span class="brand-word">MUNDER DIFFLIN<span class="sep">/</span><span class="blog">BLOG</span></span>
+ </a>
+ <span class="spacer"></span>
+ <div class="links">
+ <a href="/blog/">Latest</a>
+ <a href="/blog/topics/">Topics</a>
+ <a href="/blog/about/">About</a>
+ <a href="https://munderdiffl.in">↗ Product</a>
+ </div>
+ <div class="nav-actions">
+ <a class="btn sm" href="https://munderdiffl.in/blog/feed.xml" aria-label="RSS feed">⤵ RSS</a>
+ <a class="btn sm primary" href="https://munderdiffl.in/#install">⤓ Download</a>
+ </div>
+</nav>
+
+<main id="main">
+
+<article>
+ <header class="post-head wrap">
+ <nav class="crumbs" aria-label="Breadcrumb">
+ <a href="/blog/">Blog</a>
+ <span>/</span>
+ <a href="/blog/topics/internals/">Internals</a>
+ </nav>
+ <h1>Building a Terminal UI with xterm.js and node-pty</h1>
+ <p class="dek">Wire xterm.js to a node-pty backend: stream output, write keystrokes back, handle resize, and keep many live terminals fast with a terminal pool.</p>
+ <div class="byline">
+ <span class="av" aria-hidden="true">CG</span>
+ <strong>Chaitanya Giri</strong>
+ <span class="dot" aria-hidden="true">·</span>
+ <time datetime="2026-06-03">Jun 3, 2026</time>
+ <span class="dot" aria-hidden="true">·</span>
+ <span>8 min read</span>
+ <span class="tag kind">Internals</span>
+ </div>
+ </header>
+
+ <div class="post-wrap wrap">
+ <div class="prose">
+ <div class="callout tldr"><span class="ic">TL;DR</span><p>A real terminal UI is two halves wired
+together: <strong>node-pty</strong> runs the shell, <strong>xterm.js</strong> renders it. Forward PTY
+output into <code>term.write()</code>, send <code>term.onData()</code> keystrokes back to the PTY, and
+sync size with the <strong>FitAddon</strong> plus a <code>resize</code> call. The non-obvious win for
+many terminals: keep <strong>one persistent xterm per session</strong> and re-parent its DOM element
+instead of recreating it — because node-pty has no scrollback, recreating means a blank screen.</p></div>
+<p><a href="/blog/node-pty-electron-real-terminals/">node-pty gives you a real shell</a>; xterm.js gives you a place
+to see and drive it. Connecting them is straightforward in the happy path and full of small, important
+details once you have <em>many</em> live terminals — which is exactly the situation an agent harness is in.
+This post builds the wiring up from one terminal to dozens.</p>
+<h2 id="the-two-halves" tabindex="-1">The two halves <a class="anchor" href="#the-two-halves" aria-hidden="true">#</a></h2>
+<p>Keep the model clear and everything else follows:</p>
+<ul>
+<li><strong>node-pty</strong> (backend) runs the actual process in a pseudo-terminal. It emits bytes (<code>onData</code>) and
+accepts bytes (<code>write</code>) and size changes (<code>resize</code>).</li>
+<li><strong>xterm.js</strong> (frontend) is a terminal <em>emulator</em>: it renders the grid, interprets ANSI escape
+sequences into colors and cursor moves, and reports keystrokes back via its own <code>onData</code>.</li>
+</ul>
+<p>Your job is to connect them across whatever boundary sits between — in Electron, that’s IPC between the
+main process (PTY) and the renderer (xterm).</p>
+<pre class="language-text"><code class="language-text">node-pty.onData ──▶ IPC ──▶ xterm.write() (output: shell → screen)
+xterm.onData ──▶ IPC ──▶ node-pty.write() (input: keys → shell)
+resize observer ──▶ IPC ──▶ node-pty.resize() (geometry: panel → shell)</code></pre>
+<h2 id="step-1-create-the-terminal" tabindex="-1">Step 1 — Create the terminal <a class="anchor" href="#step-1-create-the-terminal" aria-hidden="true">#</a></h2>
+<p>Instantiate an xterm <code>Terminal</code>, load the <code>FitAddon</code> (it sizes the grid to its container), and open it
+into a host element:</p>
+<pre class="language-ts"><code class="language-ts"><span class="token keyword">import</span> <span class="token punctuation">{</span> Terminal <span class="token punctuation">}</span> <span class="token keyword">from</span> <span class="token string">'@xterm/xterm'</span><span class="token punctuation">;</span>
+<span class="token keyword">import</span> <span class="token punctuation">{</span> FitAddon <span class="token punctuation">}</span> <span class="token keyword">from</span> <span class="token string">'@xterm/addon-fit'</span><span class="token punctuation">;</span>
+<span class="token keyword">import</span> <span class="token string">'@xterm/xterm/css/xterm.css'</span><span class="token punctuation">;</span>
+
+<span class="token keyword">const</span> term <span class="token operator">=</span> <span class="token keyword">new</span> <span class="token class-name">Terminal</span><span class="token punctuation">(</span><span class="token punctuation">{</span>
+ fontFamily<span class="token operator">:</span> <span class="token string">'monospace'</span><span class="token punctuation">,</span>
+ fontSize<span class="token operator">:</span> <span class="token number">14</span><span class="token punctuation">,</span>
+ lineHeight<span class="token operator">:</span> <span class="token number">1.0</span><span class="token punctuation">,</span>
+ cursorBlink<span class="token operator">:</span> <span class="token boolean">true</span><span class="token punctuation">,</span>
+ scrollback<span class="token operator">:</span> <span class="token number">10000</span><span class="token punctuation">,</span>
+ allowProposedApi<span class="token operator">:</span> <span class="token boolean">true</span>
+<span class="token punctuation">}</span><span class="token punctuation">)</span><span class="token punctuation">;</span>
+<span class="token keyword">const</span> fit <span class="token operator">=</span> <span class="token keyword">new</span> <span class="token class-name">FitAddon</span><span class="token punctuation">(</span><span class="token punctuation">)</span><span class="token punctuation">;</span>
+term<span class="token punctuation">.</span><span class="token function">loadAddon</span><span class="token punctuation">(</span>fit<span class="token punctuation">)</span><span class="token punctuation">;</span>
+term<span class="token punctuation">.</span><span class="token function">open</span><span class="token punctuation">(</span>hostElement<span class="token punctuation">)</span><span class="token punctuation">;</span> <span class="token comment">// ← must be in the document to measure correctly</span>
+<span class="token function">setTimeout</span><span class="token punctuation">(</span><span class="token punctuation">(</span><span class="token punctuation">)</span> <span class="token operator">=></span> fit<span class="token punctuation">.</span><span class="token function">fit</span><span class="token punctuation">(</span><span class="token punctuation">)</span><span class="token punctuation">,</span> <span class="token number">0</span><span class="token punctuation">)</span><span class="token punctuation">;</span></code></pre>
+<p>One subtlety that bites early: <strong>xterm needs its host attached to the document before it can measure
+character size.</strong> <code>open()</code> an element that isn’t in the DOM yet and the geometry comes out wrong.
+That’s why the <code>fit()</code> is deferred a tick — and why, in the pooled design below, we delay <code>open()</code> until
+the first real attach.</p>
+<h2 id="step-2-stream-output-in" tabindex="-1">Step 2 — Stream output in <a class="anchor" href="#step-2-stream-output-in" aria-hidden="true">#</a></h2>
+<p>Subscribe to the PTY’s output and write each chunk to the terminal:</p>
+<pre class="language-ts"><code class="language-ts">window<span class="token punctuation">.</span>cth<span class="token punctuation">.</span><span class="token function">onPtyData</span><span class="token punctuation">(</span>ptyId<span class="token punctuation">,</span> <span class="token punctuation">(</span>chunk<span class="token punctuation">)</span> <span class="token operator">=></span> term<span class="token punctuation">.</span><span class="token function">write</span><span class="token punctuation">(</span>chunk<span class="token punctuation">)</span><span class="token punctuation">)</span><span class="token punctuation">;</span>
+window<span class="token punctuation">.</span>cth<span class="token punctuation">.</span><span class="token function">onPtyExit</span><span class="token punctuation">(</span>ptyId<span class="token punctuation">,</span> <span class="token punctuation">(</span><span class="token punctuation">{</span> exitCode<span class="token punctuation">,</span> signal <span class="token punctuation">}</span><span class="token punctuation">)</span> <span class="token operator">=></span>
+ term<span class="token punctuation">.</span><span class="token function">writeln</span><span class="token punctuation">(</span><span class="token template-string"><span class="token template-punctuation string">`</span><span class="token string">\r\n\x1b[2m─ process exited (code </span><span class="token interpolation"><span class="token interpolation-punctuation punctuation">${</span>exitCode<span class="token interpolation-punctuation punctuation">}</span></span><span class="token string">) ─\x1b[0m</span><span class="token template-punctuation string">`</span></span><span class="token punctuation">)</span><span class="token punctuation">)</span><span class="token punctuation">;</span></code></pre>
+<p><code>term.write()</code> takes the raw bytes including escape sequences — you do <strong>not</strong> strip ANSI; that’s
+xterm’s whole job. Writing a dim “process exited” line on <code>onExit</code> is a nice touch so a dead terminal
+doesn’t just freeze silently.</p>
+<h2 id="step-3-send-keystrokes-back" tabindex="-1">Step 3 — Send keystrokes back <a class="anchor" href="#step-3-send-keystrokes-back" aria-hidden="true">#</a></h2>
+<p><code>term.onData</code> fires for every keystroke (already encoded as the bytes a terminal would send — arrow
+keys as escape sequences, Enter as <code>\r</code>, and so on). Forward them straight to the PTY:</p>
+<pre class="language-ts"><code class="language-ts">term<span class="token punctuation">.</span><span class="token function">onData</span><span class="token punctuation">(</span><span class="token punctuation">(</span>data<span class="token punctuation">)</span> <span class="token operator">=></span> window<span class="token punctuation">.</span>cth<span class="token punctuation">.</span><span class="token function">writePty</span><span class="token punctuation">(</span>ptyId<span class="token punctuation">,</span> data<span class="token punctuation">)</span><span class="token punctuation">)</span><span class="token punctuation">;</span></code></pre>
+<p>That’s the entire input path. You don’t interpret keys yourself; xterm hands you terminal-ready bytes
+and node-pty feeds them to the shell. (If you want a “last command” signal for, say, a UI bubble, you
+can keep a tiny line buffer on the side — accumulate printable chars, flush on <code>\r</code>, and skip escape
+sequences — without touching the forwarding.)</p>
+<h2 id="step-4-handle-resize-properly" tabindex="-1">Step 4 — Handle resize properly <a class="anchor" href="#step-4-handle-resize-properly" aria-hidden="true">#</a></h2>
+<p>This is where lazy implementations look broken. A terminal has a <strong>character grid</strong> (cols × rows), and
+both halves must agree on it. When the panel changes size:</p>
+<ol>
+<li>Re-fit xterm to its container so it recomputes cols/rows.</li>
+<li>Tell the PTY the new geometry so the shell reflows.</li>
+</ol>
+<pre class="language-ts"><code class="language-ts"><span class="token keyword">const</span> ro <span class="token operator">=</span> <span class="token keyword">new</span> <span class="token class-name">ResizeObserver</span><span class="token punctuation">(</span><span class="token punctuation">(</span><span class="token punctuation">)</span> <span class="token operator">=></span> <span class="token punctuation">{</span>
+ fit<span class="token punctuation">.</span><span class="token function">fit</span><span class="token punctuation">(</span><span class="token punctuation">)</span><span class="token punctuation">;</span>
+ window<span class="token punctuation">.</span>cth<span class="token punctuation">.</span><span class="token function">resizePty</span><span class="token punctuation">(</span>ptyId<span class="token punctuation">,</span> term<span class="token punctuation">.</span>cols<span class="token punctuation">,</span> term<span class="token punctuation">.</span>rows<span class="token punctuation">)</span><span class="token punctuation">;</span>
+ term<span class="token punctuation">.</span><span class="token function">refresh</span><span class="token punctuation">(</span><span class="token number">0</span><span class="token punctuation">,</span> Math<span class="token punctuation">.</span><span class="token function">max</span><span class="token punctuation">(</span><span class="token number">0</span><span class="token punctuation">,</span> term<span class="token punctuation">.</span>rows <span class="token operator">-</span> <span class="token number">1</span><span class="token punctuation">)</span><span class="token punctuation">)</span><span class="token punctuation">;</span> <span class="token comment">// force a repaint</span>
+<span class="token punctuation">}</span><span class="token punctuation">)</span><span class="token punctuation">;</span>
+ro<span class="token punctuation">.</span><span class="token function">observe</span><span class="token punctuation">(</span>containerElement<span class="token punctuation">)</span><span class="token punctuation">;</span>
+window<span class="token punctuation">.</span><span class="token function">addEventListener</span><span class="token punctuation">(</span><span class="token string">'resize'</span><span class="token punctuation">,</span> <span class="token punctuation">(</span><span class="token punctuation">)</span> <span class="token operator">=></span> <span class="token punctuation">{</span> fit<span class="token punctuation">.</span><span class="token function">fit</span><span class="token punctuation">(</span><span class="token punctuation">)</span><span class="token punctuation">;</span> window<span class="token punctuation">.</span>cth<span class="token punctuation">.</span><span class="token function">resizePty</span><span class="token punctuation">(</span>ptyId<span class="token punctuation">,</span> term<span class="token punctuation">.</span>cols<span class="token punctuation">,</span> term<span class="token punctuation">.</span>rows<span class="token punctuation">)</span><span class="token punctuation">;</span> <span class="token punctuation">}</span><span class="token punctuation">)</span><span class="token punctuation">;</span></code></pre>
+<p>A <code>ResizeObserver</code> on the container catches layout changes a window-<code>resize</code> listener misses (a
+splitter drag, a panel collapse). Skip the <code>resizePty</code> call and full-screen TUIs wrap at the old width
+— the classic “why is <code>htop</code> drawing garbage” bug.</p>
+<h2 id="step-5-the-hard-part-many-terminals-at-once" tabindex="-1">Step 5 — The hard part: many terminals at once <a class="anchor" href="#step-5-the-hard-part-many-terminals-at-once" aria-hidden="true">#</a></h2>
+<p>Everything above works for one terminal. The interesting problems start when you have a sidebar of
+agents and the user switches between them, or pops one fullscreen. The naive approach — create an xterm
+when a view mounts, dispose it on unmount — produces a notorious bug: <strong>the terminal is blank until
+something repaints it.</strong></p>
+<p>The cause is fundamental: <strong>node-pty keeps no scrollback.</strong> The scrollback buffer lives in <em>xterm</em>, not
+the PTY. So if you dispose the xterm and make a fresh one, the new instance has an empty buffer and
+stays blank until the running program happens to redraw — which for an idle shell might be never (or
+“until I drag the splitter,” as the bug reports always say).</p>
+<p>The fix is a <strong>persistent terminal pool</strong>: one xterm instance per PTY session, created once and kept
+alive for the app’s lifetime, decoupled from any particular view.</p>
+<pre class="language-ts"><code class="language-ts"><span class="token comment">// One Terminal per ptyId, alive for the whole app. Views borrow its element.</span>
+<span class="token keyword">const</span> pool <span class="token operator">=</span> <span class="token keyword">new</span> <span class="token class-name">Map<span class="token operator">&lt;</span><span class="token builtin">string</span><span class="token punctuation">,</span> TerminalEntry<span class="token operator">></span></span><span class="token punctuation">(</span><span class="token punctuation">)</span><span class="token punctuation">;</span>
+
+<span class="token keyword">function</span> <span class="token function">acquireTerminal</span><span class="token punctuation">(</span>ptyId<span class="token operator">:</span> <span class="token builtin">string</span><span class="token punctuation">)</span><span class="token operator">:</span> TerminalEntry <span class="token punctuation">{</span>
+ <span class="token keyword">const</span> existing <span class="token operator">=</span> pool<span class="token punctuation">.</span><span class="token function">get</span><span class="token punctuation">(</span>ptyId<span class="token punctuation">)</span><span class="token punctuation">;</span>
+ <span class="token keyword">if</span> <span class="token punctuation">(</span>existing<span class="token punctuation">)</span> <span class="token keyword">return</span> existing<span class="token punctuation">;</span>
+
+ <span class="token keyword">const</span> host <span class="token operator">=</span> document<span class="token punctuation">.</span><span class="token function">createElement</span><span class="token punctuation">(</span><span class="token string">'div'</span><span class="token punctuation">)</span><span class="token punctuation">;</span> <span class="token comment">// detached host</span>
+ <span class="token keyword">const</span> term <span class="token operator">=</span> <span class="token keyword">new</span> <span class="token class-name">Terminal</span><span class="token punctuation">(</span><span class="token punctuation">{</span> scrollback<span class="token operator">:</span> <span class="token number">10000</span><span class="token punctuation">,</span> <span class="token comment">/* … */</span> <span class="token punctuation">}</span><span class="token punctuation">)</span><span class="token punctuation">;</span>
+ <span class="token keyword">const</span> fit <span class="token operator">=</span> <span class="token keyword">new</span> <span class="token class-name">FitAddon</span><span class="token punctuation">(</span><span class="token punctuation">)</span><span class="token punctuation">;</span>
+ term<span class="token punctuation">.</span><span class="token function">loadAddon</span><span class="token punctuation">(</span>fit<span class="token punctuation">)</span><span class="token punctuation">;</span>
+ <span class="token comment">// Subscribe to the PTY stream ONCE — the buffer keeps filling even while</span>
+ <span class="token comment">// this terminal isn't shown in any view.</span>
+ window<span class="token punctuation">.</span>cth<span class="token punctuation">.</span><span class="token function">onPtyData</span><span class="token punctuation">(</span>ptyId<span class="token punctuation">,</span> <span class="token punctuation">(</span>chunk<span class="token punctuation">)</span> <span class="token operator">=></span> term<span class="token punctuation">.</span><span class="token function">write</span><span class="token punctuation">(</span>chunk<span class="token punctuation">)</span><span class="token punctuation">)</span><span class="token punctuation">;</span>
+ term<span class="token punctuation">.</span><span class="token function">onData</span><span class="token punctuation">(</span><span class="token punctuation">(</span>data<span class="token punctuation">)</span> <span class="token operator">=></span> window<span class="token punctuation">.</span>cth<span class="token punctuation">.</span><span class="token function">writePty</span><span class="token punctuation">(</span>ptyId<span class="token punctuation">,</span> data<span class="token punctuation">)</span><span class="token punctuation">)</span><span class="token punctuation">;</span>
+
+ <span class="token keyword">const</span> entry <span class="token operator">=</span> <span class="token punctuation">{</span> term<span class="token punctuation">,</span> fit<span class="token punctuation">,</span> host<span class="token punctuation">,</span> opened<span class="token operator">:</span> <span class="token boolean">false</span> <span class="token punctuation">}</span><span class="token punctuation">;</span>
+ pool<span class="token punctuation">.</span><span class="token function">set</span><span class="token punctuation">(</span>ptyId<span class="token punctuation">,</span> entry<span class="token punctuation">)</span><span class="token punctuation">;</span>
+ <span class="token keyword">return</span> entry<span class="token punctuation">;</span> <span class="token comment">// note: not open()ed yet</span>
+<span class="token punctuation">}</span></code></pre>
+<p>The two ideas that make this work:</p>
+<ul>
+<li><strong>Subscribe to the stream once, for the terminal’s whole life.</strong> Output flows into the buffer
+whether or not the terminal is currently mounted in a view. When you re-show it, the content is
+already there.</li>
+<li><strong>Re-parent the host element instead of recreating the terminal.</strong> A view simply moves the existing
+<code>host</code> <code>&lt;div&gt;</code> into itself on mount and lets it go on unmount. The rendered content moves with the
+element — instant, no repaint required.</li>
+</ul>
+<pre class="language-ts"><code class="language-ts"><span class="token keyword">function</span> <span class="token function">attachTerminal</span><span class="token punctuation">(</span>entry<span class="token operator">:</span> TerminalEntry<span class="token punctuation">,</span> container<span class="token operator">:</span> HTMLElement<span class="token punctuation">)</span> <span class="token punctuation">{</span>
+ container<span class="token punctuation">.</span><span class="token function">appendChild</span><span class="token punctuation">(</span>entry<span class="token punctuation">.</span>host<span class="token punctuation">)</span><span class="token punctuation">;</span>
+ <span class="token keyword">if</span> <span class="token punctuation">(</span><span class="token operator">!</span>entry<span class="token punctuation">.</span>opened<span class="token punctuation">)</span> <span class="token punctuation">{</span> <span class="token comment">// open lazily, on first real attach</span>
+ entry<span class="token punctuation">.</span>term<span class="token punctuation">.</span><span class="token function">open</span><span class="token punctuation">(</span>entry<span class="token punctuation">.</span>host<span class="token punctuation">)</span><span class="token punctuation">;</span> <span class="token comment">// now the host is in the document → measures correctly</span>
+ entry<span class="token punctuation">.</span>opened <span class="token operator">=</span> <span class="token boolean">true</span><span class="token punctuation">;</span>
+ <span class="token punctuation">}</span>
+<span class="token punctuation">}</span></code></pre>
+<p>Switching agents becomes a DOM move, not a teardown. The terminal is always populated and always
+visible immediately — which is what you need when a user is flicking between a dozen live sessions.</p>
+<h2 id="performance-notes-for-dozens-of-terminals" tabindex="-1">Performance notes for dozens of terminals <a class="anchor" href="#performance-notes-for-dozens-of-terminals" aria-hidden="true">#</a></h2>
+<p>A pool keeps correctness; a few habits keep it fast:</p>
+<ul>
+<li><strong>Don’t render what’s off-screen.</strong> Only the visible terminal needs to be in the DOM and laid out.
+The pool’s buffers keep filling in the background, but you’re only painting one (or a few) at a time.</li>
+<li><strong>Pick a sane scrollback.</strong> xterm holds scrollback in memory per terminal. 10,000 lines is generous;
+multiply by many terminals and it adds up — tune it to your needs.</li>
+<li><strong>Dispose for real when a session is gone.</strong> When an agent is truly finished, tear its entry down:
+unsubscribe from the stream, <code>term.dispose()</code>, and drop it from the pool. The pool is for <em>live</em>
+sessions, not a leak.</li>
+</ul>
+<p>The deeper performance story — rendering backends, batching writes, and keeping CPU flat with many
+streaming PTYs — is its own topic, but the pool is the structural decision everything else builds on.</p>
+<h2 id="why-a-harness-needs-all-of-this" tabindex="-1">Why a harness needs all of this <a class="anchor" href="#why-a-harness-needs-all-of-this" aria-hidden="true">#</a></h2>
+<p>An agent harness shows you many live terminals — one per agent — and lets you switch, zoom, and watch
+them stream simultaneously. Every detail above is load-bearing for that: real shells from
+<a href="/blog/node-pty-electron-real-terminals/">node-pty</a>, a persistent pool so switching agents is instant,
+and correct resize so each agent’s TUI renders right. It’s the visible half of a
+<a href="https://munderdiffl.in/#what">multi-agent harness</a> — the part that makes “a hive of agents” something
+you can actually watch instead of a black box. And keeping those agents’ shared state safe under all
+that concurrency is the job of <a href="/blog/single-committer-git-pattern/">the single-committer git pattern</a>.</p>
+<h2 id="faq" tabindex="-1">FAQ <a class="anchor" href="#faq" aria-hidden="true">#</a></h2>
+<p><strong>Should I use the canvas or WebGL renderer?</strong> xterm’s DOM renderer is fine for a few terminals; for
+many high-throughput ones, an accelerated renderer addon reduces CPU. Measure with your real workload
+before reaching for it.</p>
+<p><strong>Do I need to handle ANSI parsing myself?</strong> No — that’s exactly what xterm.js does. You feed it raw
+bytes from the PTY and it handles colors, cursor movement, and the alternate screen buffer.</p>
+<hr>
+<p>Munder Difflin renders a whole floor of live Claude Code terminals with xterm.js — one persistent,
+pooled terminal per agent, switchable instantly. <a href="https://munderdiffl.in/#install">Download Munder Difflin</a>
+to watch many real terminals at once; it’s free and open source.</p>
+
+
+
+ <section class="faq" aria-label="Frequently asked questions">
+ <h2 id="faq">FAQ</h2>
+
+ <div class="qa">
+ <p class="q">What is xterm.js?</p>
+ <p class="a">xterm.js is a terminal emulator for the browser. It renders a terminal grid in the DOM (or on a canvas/WebGL), parses ANSI escape sequences, and exposes write() for output and onData() for keystrokes — so you can pair it with a backend like node-pty to build a real, interactive terminal in a web UI.</p>
+ </div>
+
+ <div class="qa">
+ <p class="q">How do xterm.js and node-pty fit together?</p>
+ <p class="a">node-pty runs the real shell and produces bytes; xterm.js displays them and captures input. You forward node-pty&#39;s output into xterm&#39;s write(), and send xterm&#39;s onData() keystrokes back to node-pty. The two halves are connected by your IPC layer.</p>
+ </div>
+
+ <div class="qa">
+ <p class="q">Why does my xterm.js terminal go blank when I switch tabs?</p>
+ <p class="a">Because node-pty keeps no scrollback — if you destroy and recreate the xterm instance, the new one starts empty until the program repaints. Keep one persistent terminal per session and re-parent its element instead of recreating it.</p>
+ </div>
+
+ </section>
+
+
+
+ <hr />
+ <div class="share">
+ <span class="lbl">Tags</span>
+ <a class="tag" href="/blog/tags/internals/">Internals</a><a class="tag" href="/blog/tags/xtermjs/">xterm.js</a><a class="tag" href="/blog/tags/terminals/">Terminals</a><a class="tag" href="/blog/tags/electron/">Electron</a>
+ </div>
+
+ </div>
+
+
+ <aside class="toc-rail" aria-label="Table of contents">
+ <div class="tt">On this page</div>
+ <ol>
+ <li class="lvl-2"><a href="#the-two-halves">The two halves</a></li><li class="lvl-2"><a href="#step-1-create-the-terminal">Step 1 — Create the terminal</a></li><li class="lvl-2"><a href="#step-2-stream-output-in">Step 2 — Stream output in</a></li><li class="lvl-2"><a href="#step-3-send-keystrokes-back">Step 3 — Send keystrokes back</a></li><li class="lvl-2"><a href="#step-4-handle-resize-properly">Step 4 — Handle resize properly</a></li><li class="lvl-2"><a href="#step-5-the-hard-part-many-terminals-at-once">Step 5 — The hard part: many terminals at once</a></li><li class="lvl-2"><a href="#performance-notes-for-dozens-of-terminals">Performance notes for dozens of terminals</a></li><li class="lvl-2"><a href="#why-a-harness-needs-all-of-this">Why a harness needs all of this</a></li><li class="lvl-2"><a href="#faq">FAQ</a></li>
+ </ol>
+ </aside>
+
+ </div>
+
+ <footer class="post-foot wrap"><div class="prevnext">
+ <a class="pn prev" href="/blog/claude-code-hooks-explained/"><span class="k">← Older</span><span class="t">Claude Code Hooks, Explained (PreToolUse, PostToolUse, Stop)</span></a>
+ <a class="pn next" href="/blog/claude-squad-vs-munder-difflin/"><span class="k">Newer →</span><span class="t">Claude Squad vs Munder Difflin: Which Should You Use?</span></a>
+ </div>
+ <section class="related">
+ <h2>Related in Internals</h2>
+ <div class="post-grid">
+ <article class="card">
+ <a class="thumb t-internals" href="/blog/claude-code-hooks-explained/" aria-hidden="true" tabindex="-1">
+ <span>INTERNALS</span>
+ </a>
+ <div class="body">
+ <div class="meta">
+ <time datetime="2026-06-03">Jun 3, 2026</time>
+ <span class="dot" aria-hidden="true"></span>
+ <span>6 min</span>
+ </div>
+ <h3><a href="/blog/claude-code-hooks-explained/">Claude Code Hooks, Explained (PreToolUse, PostToolUse, Stop)</a></h3>
+ <p class="dek">A practical tour of Claude Code hooks — the PreToolUse, PostToolUse, and Stop lifecycle — and how a Unix-socket hook shim drives a live office floor.</p>
+ <div class="foot">
+ <span class="tag kind">Internals</span>
+ <a class="more" href="/blog/claude-code-hooks-explained/" aria-label="Read: Claude Code Hooks, Explained (PreToolUse, PostToolUse, Stop)">Read →</a>
+ </div>
+ </div>
+</article>
+<article class="card">
+ <a class="thumb t-internals" href="/blog/node-pty-electron-real-terminals/" aria-hidden="true" tabindex="-1">
+ <span>INTERNALS</span>
+ </a>
+ <div class="body">
+ <div class="meta">
+ <time datetime="2026-06-03">Jun 3, 2026</time>
+ <span class="dot" aria-hidden="true"></span>
+ <span>7 min</span>
+ </div>
+ <h3><a href="/blog/node-pty-electron-real-terminals/">Real Terminals in Electron with node-pty</a></h3>
+ <p class="dek">How to run byte-for-byte authentic shells inside Electron with node-pty: the native-rebuild gotcha, the macOS PATH trap, and streaming PTY output over IPC.</p>
+ <div class="foot">
+ <span class="tag kind">Internals</span>
+ <a class="more" href="/blog/node-pty-electron-real-terminals/" aria-label="Read: Real Terminals in Electron with node-pty">Read →</a>
+ </div>
+ </div>
+</article>
+<article class="card">
+ <a class="thumb t-internals" href="/blog/single-committer-git-pattern/" aria-hidden="true" tabindex="-1">
+ <span>INTERNALS</span>
+ </a>
+ <div class="body">
+ <div class="meta">
+ <time datetime="2026-06-02">Jun 2, 2026</time>
+ <span class="dot" aria-hidden="true"></span>
+ <span>5 min</span>
+ </div>
+ <h3><a href="/blog/single-committer-git-pattern/">The Single-Committer Pattern: Multi-Agent Git Without Corruption</a></h3>
+ <p class="dek">Parallel agents corrupt a repo with index.lock races. The single-committer pattern — agents write, one process commits — fixes concurrent git writes.</p>
+ <div class="foot">
+ <span class="tag kind">Internals</span>
+ <a class="more" href="/blog/single-committer-git-pattern/" aria-label="Read: The Single-Committer Pattern: Multi-Agent Git Without Corruption">Read →</a>
+ </div>
+ </div>
+</article>
+
+ </div>
+ </section>
+
+ </footer>
+</article>
+
+</main>
+<footer>
+ <div class="wrap">
+ <div class="foot-top">
+ <a class="foot-brand brand" href="/blog/">
+ <span class="brand-mark">MD</span>
+ <span class="brand-word">MUNDER DIFFLIN<span class="sep">/</span><span class="blog">BLOG</span></span>
+ </a>
+ <div class="foot-links">
+ <a href="/blog/">Latest</a>
+ <a href="/blog/topics/">Topics</a>
+ <a href="/blog/about/">About</a>
+ <a href="https://munderdiffl.in/blog/feed.xml">RSS</a>
+ <a href="https://github.com/chaitanyagiri/munder-difflin">GitHub</a>
+ <a href="https://munderdiffl.in">munderdiffl.in ↗</a>
+ </div>
+ </div>
+ <div class="foot-meta">
+ © 2026 Munder Difflin · Local-first · MIT-licensed ·
+ Built on <a href="https://munderdiffl.in">Electron, React, Pixi.js, xterm.js &amp; node-pty</a>.
+ Run an office of agents while you sleep.
+ </div>
+ </div>
+</footer>
+
+<script>
+ // sticky-nav border on scroll
+ (function () {
+ var nav = document.getElementById('nav');
+ if (!nav) return;
+ var onScroll = function () { nav.classList.toggle('scrolled', window.scrollY > 8); };
+ onScroll(); window.addEventListener('scroll', onScroll, { passive: true });
+ })();
+</script>
+
+</body>
+</html>
diff --git a/docs/blog/claude-code-automation-while-you-sleep/index.html b/docs/blog/claude-code-automation-while-you-sleep/index.html
new file mode 100644
index 00000000..48614b34
--- /dev/null
+++ b/docs/blog/claude-code-automation-while-you-sleep/index.html
@@ -0,0 +1,383 @@
+<!doctype html>
+<html lang="en">
+<head>
+<meta charset="UTF-8" />
+<meta name="viewport" content="width=device-width, initial-scale=1.0" />
+<title>Claude Code Automation: Let Agents Build While You Sleep — Munder Difflin Blog</title>
+<meta name="description" content="Claude Code automation that runs overnight: an autonomous Stop-hook loop, safe permission bypass, and guardrails so you wake up to progress, not chaos." />
+<link rel="canonical" href="https://munderdiffl.in/blog/claude-code-automation-while-you-sleep/" />
+
+<link rel="icon" type="image/png" href="https://munderdiffl.in/logo.png" />
+<link rel="apple-touch-icon" href="https://munderdiffl.in/logo.png" />
+<meta name="theme-color" content="#F5F2E8" />
+
+<!-- Open Graph -->
+<meta property="og:site_name" content="Munder Difflin Blog" />
+<meta property="og:type" content="article" />
+<meta property="og:title" content="Claude Code Automation: Let Agents Build While You Sleep — Munder Difflin Blog" />
+<meta property="og:description" content="Claude Code automation that runs overnight: an autonomous Stop-hook loop, safe permission bypass, and guardrails so you wake up to progress, not chaos." />
+<meta property="og:url" content="https://munderdiffl.in/blog/claude-code-automation-while-you-sleep/" />
+<meta property="og:image" content="https://munderdiffl.in/media/og.png" />
+<meta property="og:locale" content="en_US" />
+<meta property="article:published_time" content="2026-06-04T00:00:00.000Z" />
+<meta property="article:author" content="Chaitanya Giri" />
+<meta property="article:tag" content="Guides" />
+<meta property="article:tag" content="Automation" />
+<meta property="article:tag" content="Autonomous" />
+<meta property="article:tag" content="Claude Code" />
+
+
+<!-- Twitter -->
+<meta name="twitter:card" content="summary_large_image" />
+<meta name="twitter:title" content="Claude Code Automation: Let Agents Build While You Sleep — Munder Difflin Blog" />
+<meta name="twitter:description" content="Claude Code automation that runs overnight: an autonomous Stop-hook loop, safe permission bypass, and guardrails so you wake up to progress, not chaos." />
+<meta name="twitter:image" content="https://munderdiffl.in/media/og.png" />
+
+<link rel="alternate" type="application/atom+xml" title="Munder Difflin Blog" href="https://munderdiffl.in/blog/feed.xml" />
+<link rel="preconnect" href="https://fonts.googleapis.com" />
+<link rel="preconnect" href="https://fonts.gstatic.com" crossorigin />
+<link href="https://fonts.googleapis.com/css2?family=Geist:wght@400;500;600&family=JetBrains+Mono:wght@400;500;600;700&display=swap" rel="stylesheet" />
+<link rel="stylesheet" href="/blog/assets/blog.css" />
+
+<script type="application/ld+json">
+{
+ "@context": "https://schema.org",
+ "@type": "BlogPosting",
+ "headline": "Claude Code Automation: Let Agents Build While You Sleep",
+ "description": "Claude Code automation that runs overnight: an autonomous Stop-hook loop, safe permission bypass, and guardrails so you wake up to progress, not chaos.",
+ "image": ["https://munderdiffl.in/media/og.png"],
+ "datePublished": "2026-06-04T00:00:00.000Z",
+ "dateModified": "2026-06-04T00:00:00.000Z",
+ "author": { "@type": "Person", "name": "Chaitanya Giri" },
+ "publisher": {
+ "@type": "Organization",
+ "name": "Munder Difflin",
+ "logo": { "@type": "ImageObject", "url": "https://munderdiffl.in/logo.png" }
+ },
+ "mainEntityOfPage": { "@type": "WebPage", "@id": "https://munderdiffl.in/blog/claude-code-automation-while-you-sleep/" },
+ "keywords": "claude code automation, overnight ai coding, autonomous agents, run claude code while you sleep",
+ "articleSection": "Guides",
+ "inLanguage": "en-US",
+ "url": "https://munderdiffl.in/blog/claude-code-automation-while-you-sleep/"
+}
+</script>
+<script type="application/ld+json">
+{
+ "@context": "https://schema.org",
+ "@type": "BreadcrumbList",
+ "itemListElement": [
+ { "@type": "ListItem", "position": 1, "name": "Home", "item": "https://munderdiffl.in/" },
+ { "@type": "ListItem", "position": 2, "name": "Blog", "item": "https://munderdiffl.in/blog/" },
+ { "@type": "ListItem", "position": 3, "name": "Claude Code Automation: Let Agents Build While You Sleep", "item": "https://munderdiffl.in/blog/claude-code-automation-while-you-sleep/" }
+ ]
+}
+</script>
+
+<script type="application/ld+json">
+{
+ "@context": "https://schema.org",
+ "@type": "FAQPage",
+ "mainEntity": [
+ { "@type": "Question", "name": "How do I make Claude Code keep working without me approving every step?", "acceptedAnswer": { "@type": "Answer", "text": "Run it with a permission mode that bypasses approval prompts for routine actions, and pair that with an autonomous loop so the agent picks up the next task on its own. The safety comes from scoping what it can do and escalating the genuinely risky calls, not from approving each keystroke." } },
+ { "@type": "Question", "name": "Is it safe to run AI coding agents unattended overnight?", "acceptedAnswer": { "@type": "Answer", "text": "It's safe in proportion to your guardrails. Autonomy without guardrails is how you wake up to a mess. With a clear escalation policy (destructive ops, spend, scope changes go to a human queue), bounded scope, and a full audit log, unattended runs become low-risk and productive." } },
+ { "@type": "Question", "name": "What does an agent do when it runs out of work overnight?", "acceptedAnswer": { "@type": "Answer", "text": "In a well-built loop it simply stops. The autonomous loop only continues an agent while it has unread tasks in its inbox; when the queue is empty, the Stop hook lets it finish instead of spinning." } }
+
+ ]
+}
+</script>
+
+
+</head>
+<body>
+<a class="skip-link" href="#main">Skip to content</a>
+<nav id="nav">
+ <a class="brand" href="/blog/" aria-label="Munder Difflin Blog home">
+ <span class="brand-mark">MD</span>
+ <span class="brand-word">MUNDER DIFFLIN<span class="sep">/</span><span class="blog">BLOG</span></span>
+ </a>
+ <span class="spacer"></span>
+ <div class="links">
+ <a href="/blog/">Latest</a>
+ <a href="/blog/topics/">Topics</a>
+ <a href="/blog/about/">About</a>
+ <a href="https://munderdiffl.in">↗ Product</a>
+ </div>
+ <div class="nav-actions">
+ <a class="btn sm" href="https://munderdiffl.in/blog/feed.xml" aria-label="RSS feed">⤵ RSS</a>
+ <a class="btn sm primary" href="https://munderdiffl.in/#install">⤓ Download</a>
+ </div>
+</nav>
+
+<main id="main">
+
+<article>
+ <header class="post-head wrap">
+ <nav class="crumbs" aria-label="Breadcrumb">
+ <a href="/blog/">Blog</a>
+ <span>/</span>
+ <a href="/blog/topics/guides/">Guides</a>
+ </nav>
+ <h1>Claude Code Automation: Let Agents Build While You Sleep</h1>
+ <p class="dek">Claude Code automation that runs overnight: an autonomous Stop-hook loop, safe permission bypass, and guardrails so you wake up to progress, not chaos.</p>
+ <div class="byline">
+ <span class="av" aria-hidden="true">CG</span>
+ <strong>Chaitanya Giri</strong>
+ <span class="dot" aria-hidden="true">·</span>
+ <time datetime="2026-06-04">Jun 4, 2026</time>
+ <span class="dot" aria-hidden="true">·</span>
+ <span>5 min read</span>
+ <span class="tag kind">Guides</span>
+ </div>
+ </header>
+
+ <div class="post-wrap wrap">
+ <div class="prose">
+ <div class="callout tldr"><span class="ic">TL;DR</span><p><strong>Claude Code automation</strong> that
+runs overnight needs three things: an <strong>autonomous loop</strong> so agents pick up the next task
+themselves (built on the <code>Stop</code> hook), a <strong>permission mode that skips routine
+approvals</strong> so they don't stall waiting for you, and <strong>guardrails</strong> — a clear
+escalation policy plus an audit log — so you wake up to progress, not chaos. Autonomy and guardrails
+are the same project, not opposites.</p></div>
+<p>The dream is simple: describe what you want, close the laptop, and find it built in the morning. The
+reality is achievable — but only if you build the <em>guardrails</em> with the same care as the <em>autonomy</em>. An
+agent that never stops to ask is powerful; an agent that never stops to ask <em>and</em> has no boundaries is
+a liability. This guide shows how to set up overnight Claude Code automation that’s actually safe to
+leave running.</p>
+<h2 id="the-two-ingredients-of-autonomy" tabindex="-1">The two ingredients of autonomy <a class="anchor" href="#the-two-ingredients-of-autonomy" aria-hidden="true">#</a></h2>
+<p>For an agent to work unattended, it has to clear two hurdles that normally require you:</p>
+<ol>
+<li><strong>It can’t stop to ask permission for every action.</strong> By default an agent pauses for approval before
+many operations. Multiply that by a night of work and it’ll be stalled on the first prompt while you
+sleep.</li>
+<li><strong>It can’t stop when a task ends.</strong> Finishing one task and going idle is the opposite of overnight
+progress. The agent needs to reach for the next piece of work on its own.</li>
+</ol>
+<p>Solve both and you have automation. Solve them <em>carelessly</em> and you have a runaway. The art is solving
+them with the brakes already installed.</p>
+<h2 id="ingredient-1-skip-routine-approvals-deliberately" tabindex="-1">Ingredient 1 — Skip routine approvals (deliberately) <a class="anchor" href="#ingredient-1-skip-routine-approvals-deliberately" aria-hidden="true">#</a></h2>
+<p>Claude Code can run in a permission mode that bypasses the approval prompt for routine actions —
+effectively “don’t ask me before each edit or command.” For an unattended run that’s not optional;
+it’s the difference between an agent that works and one that waits.</p>
+<p>In Munder Difflin this is the <strong>auto mode</strong> toggle: when it’s on, agents are launched with
+<code>--permission-mode bypassPermissions</code> so they proceed without pausing on every step. You’ll see the
+exact command in the spawn dialog, so there’s no mystery about what’s being run.</p>
+<p>The important word is <strong>deliberately.</strong> Bypassing approvals is a real grant of authority, so you pair
+it with the boundaries below. Turn it off when you want to confirm each action; turn it on when you’ve
+scoped the work and you trust the guardrails.</p>
+<h2 id="ingredient-2-the-autonomous-loop" tabindex="-1">Ingredient 2 — The autonomous loop <a class="anchor" href="#ingredient-2-the-autonomous-loop" aria-hidden="true">#</a></h2>
+<p>The second ingredient is the loop that keeps an agent moving from one task to the next without you
+handing it each one. The elegant way to build it is on Claude Code’s <strong>Stop hook</strong> — the hook that
+fires when an agent is about to finish a turn.</p>
+<p>The mechanism, in plain terms: when an agent tries to stop, a hook checks whether it has any unread
+work waiting in its inbox. If it does, the hook returns <em>“don’t stop — here’s what’s next,”</em> and the
+agent keeps going. If the inbox is empty, the hook lets it finish. Two safeguards keep this from
+becoming an infinite loop: a flag that prevents blocking a stop twice in a row, and a per-agent cursor
+so each task is surfaced exactly once. The full mechanics are in
+<a href="/blog/claude-code-hooks-explained/">Claude Code hooks, explained</a>.</p>
+<p>The crucial property for overnight work: the loop is <strong>driven by a queue, not a timer.</strong> An agent
+continues only while it has tasks; when the work runs out, it stops cleanly instead of spinning or
+inventing busywork. You’re not setting a duration — you’re filling a queue and letting the team drain
+it.</p>
+<h2 id="ingredient-3-guardrails-the-part-that-makes-it-safe" tabindex="-1">Ingredient 3 — Guardrails (the part that makes it safe) <a class="anchor" href="#ingredient-3-guardrails-the-part-that-makes-it-safe" aria-hidden="true">#</a></h2>
+<p>This is where most “let it run overnight” experiments go wrong. Autonomy is easy; <em>bounded</em> autonomy is
+the work. Four guardrails turn an unattended run from reckless to routine.</p>
+<h3 id="an-explicit-escalation-policy" tabindex="-1">An explicit escalation policy <a class="anchor" href="#an-explicit-escalation-policy" aria-hidden="true">#</a></h3>
+<p>Decide, in writing, what the agents are <strong>not</strong> allowed to do on their own — and have those things
+escalate to a human queue instead of executing. A good default critical list:</p>
+<ul>
+<li><strong>destructive operations</strong> (anything hard to undo),</li>
+<li><strong>spending real money</strong>,</li>
+<li><strong>scope changes</strong> (work drifting from what you asked), and</li>
+<li><strong>conflicts</strong> the team can’t resolve.</li>
+</ul>
+<p>In a hive, the <a href="/blog/how-the-god-orchestrator-works/">orchestrator</a> enforces this: routine decisions
+it makes itself, critical ones it routes to an approvals queue. You come back in the morning to a short
+list of “I needed your call on these,” not a pile of irreversible actions.</p>
+<h3 id="bounded-scope" tabindex="-1">Bounded scope <a class="anchor" href="#bounded-scope" aria-hidden="true">#</a></h3>
+<p>Don’t point an unattended team at “improve the codebase.” Give it a concrete, finishable goal: “add
+validation to these three forms, with tests.” Bounded scope means the queue drains to empty — which,
+remember, is what makes the agents stop. Unbounded scope is how you get motion without progress.</p>
+<h3 id="a-full-audit-log" tabindex="-1">A full audit log <a class="anchor" href="#a-full-audit-log" aria-hidden="true">#</a></h3>
+<p>Every action and message should be recorded so you can reconstruct the night. A single-committer git
+repo doubles as that log: each coordination step is a commit you can read back in order. When you wake
+up, “what happened while I was out?” has a precise answer, not a guess.</p>
+<h3 id="start-small-then-extend-the-leash" tabindex="-1">Start small, then extend the leash <a class="anchor" href="#start-small-then-extend-the-leash" aria-hidden="true">#</a></h3>
+<p>Run a 30-minute unattended session before you run an 8-hour one. Watch what the agents do with the
+autonomy you’ve granted, tighten the escalation policy where they overstepped, and only then extend the
+duration. Trust is earned by observation, not assumed.</p>
+<h2 id="a-realistic-overnight-setup" tabindex="-1">A realistic overnight setup <a class="anchor" href="#a-realistic-overnight-setup" aria-hidden="true">#</a></h2>
+<p>Putting it together, a sane overnight automation looks like this:</p>
+<ol>
+<li><strong>Scope a finishable goal</strong> and break it into tasks.</li>
+<li><strong>Turn on auto mode</strong> so agents don’t stall on approvals.</li>
+<li><strong>Let the orchestrator route</strong> the tasks into agents’ inboxes; the autonomous loop keeps them
+working through the queue.</li>
+<li><strong>Keep the escalation policy tight</strong> so anything risky lands in the approvals queue instead of
+happening.</li>
+<li><strong>Close the laptop.</strong> Agents drain the queue, escalate the few things that need you, and stop when
+the work is done.</li>
+<li><strong>Review the audit log</strong> in the morning — and the short approvals list.</li>
+</ol>
+<p>That’s automation you can actually sleep through, because the system is built to <em>stop and ask</em> exactly
+when it should. It’s the practical version of running a coordinated team while you’re away, the same
+muscle as <a href="/blog/how-to-run-multiple-claude-code-agents/">running multiple Claude Code agents</a> — just
+with you out of the room.</p>
+<h2 id="whats-still-not-realistic" tabindex="-1">What’s still not realistic <a class="anchor" href="#whats-still-not-realistic" aria-hidden="true">#</a></h2>
+<p>Honesty matters here. Unattended agents are great at well-specified, bounded work and at grinding
+through a queue. They’re <em>not</em> a substitute for your judgment on ambiguous design calls, and they
+shouldn’t be handed open-ended mandates with money or production access. The right mental model is a
+diligent overnight shift with a clear ticket list and a manager who escalates — not a genie. Keep the
+goals concrete and the guardrails tight, and the overnight shift earns its keep.</p>
+<hr>
+<p>Munder Difflin gives you the whole kit: an autonomous Stop-hook loop, an auto mode that skips routine
+approvals, an orchestrator that escalates only the critical few, and a git audit log of the night.
+<a href="https://munderdiffl.in/#install">Download Munder Difflin</a> to let a hive of Claude Code agents build
+while you sleep; it’s free and open source.</p>
+
+
+
+ <section class="faq" aria-label="Frequently asked questions">
+ <h2 id="faq">FAQ</h2>
+
+ <div class="qa">
+ <p class="q">How do I make Claude Code keep working without me approving every step?</p>
+ <p class="a">Run it with a permission mode that bypasses approval prompts for routine actions, and pair that with an autonomous loop so the agent picks up the next task on its own. The safety comes from scoping what it can do and escalating the genuinely risky calls, not from approving each keystroke.</p>
+ </div>
+
+ <div class="qa">
+ <p class="q">Is it safe to run AI coding agents unattended overnight?</p>
+ <p class="a">It&#39;s safe in proportion to your guardrails. Autonomy without guardrails is how you wake up to a mess. With a clear escalation policy (destructive ops, spend, scope changes go to a human queue), bounded scope, and a full audit log, unattended runs become low-risk and productive.</p>
+ </div>
+
+ <div class="qa">
+ <p class="q">What does an agent do when it runs out of work overnight?</p>
+ <p class="a">In a well-built loop it simply stops. The autonomous loop only continues an agent while it has unread tasks in its inbox; when the queue is empty, the Stop hook lets it finish instead of spinning.</p>
+ </div>
+
+ </section>
+
+
+
+ <hr />
+ <div class="share">
+ <span class="lbl">Tags</span>
+ <a class="tag" href="/blog/tags/guides/">Guides</a><a class="tag" href="/blog/tags/automation/">Automation</a><a class="tag" href="/blog/tags/autonomous/">Autonomous</a><a class="tag" href="/blog/tags/claude-code/">Claude Code</a>
+ </div>
+
+ </div>
+
+
+ <aside class="toc-rail" aria-label="Table of contents">
+ <div class="tt">On this page</div>
+ <ol>
+ <li class="lvl-2"><a href="#the-two-ingredients-of-autonomy">The two ingredients of autonomy</a></li><li class="lvl-2"><a href="#ingredient-1-skip-routine-approvals-deliberately">Ingredient 1 — Skip routine approvals (deliberately)</a></li><li class="lvl-2"><a href="#ingredient-2-the-autonomous-loop">Ingredient 2 — The autonomous loop</a></li><li class="lvl-2"><a href="#ingredient-3-guardrails-the-part-that-makes-it-safe">Ingredient 3 — Guardrails (the part that makes it safe)</a></li><li class="lvl-3"><a href="#an-explicit-escalation-policy">An explicit escalation policy</a></li><li class="lvl-3"><a href="#bounded-scope">Bounded scope</a></li><li class="lvl-3"><a href="#a-full-audit-log">A full audit log</a></li><li class="lvl-3"><a href="#start-small-then-extend-the-leash">Start small, then extend the leash</a></li><li class="lvl-2"><a href="#a-realistic-overnight-setup">A realistic overnight setup</a></li><li class="lvl-2"><a href="#whats-still-not-realistic">What’s still not realistic</a></li>
+ </ol>
+ </aside>
+
+ </div>
+
+ <footer class="post-foot wrap"><div class="prevnext">
+ <a class="pn prev" href="/blog/claude-code-git-worktrees-vs-hive/"><span class="k">← Older</span><span class="t">Git Worktrees vs a Hive: Two Ways to Parallelize Claude Code</span></a>
+ <a class="pn next" href="/blog/best-claude-code-multi-agent-tools/"><span class="k">Newer →</span><span class="t">The Best Tools to Run Multiple Claude Code Agents (2026)</span></a>
+ </div>
+ <section class="related">
+ <h2>Related in Guides</h2>
+ <div class="post-grid">
+ <article class="card">
+ <a class="thumb t-guides" href="/blog/mcp-and-skills-in-a-hive/" aria-hidden="true" tabindex="-1">
+ <span>GUIDES</span>
+ </a>
+ <div class="body">
+ <div class="meta">
+ <time datetime="2026-06-03">Jun 3, 2026</time>
+ <span class="dot" aria-hidden="true"></span>
+ <span>6 min</span>
+ </div>
+ <h3><a href="/blog/mcp-and-skills-in-a-hive/">Bringing Your MCP Servers and Skills Into a Hive of Agents</a></h3>
+ <p class="dek">How agents in a hive inherit your existing Claude Code MCP servers, skills, and tools — and how to scope which agent gets which capability.</p>
+ <div class="foot">
+ <span class="tag kind">Guides</span>
+ <a class="more" href="/blog/mcp-and-skills-in-a-hive/" aria-label="Read: Bringing Your MCP Servers and Skills Into a Hive of Agents">Read →</a>
+ </div>
+ </div>
+</article>
+<article class="card">
+ <a class="thumb t-guides" href="/blog/how-to-run-multiple-claude-code-agents/" aria-hidden="true" tabindex="-1">
+ <span>GUIDES</span>
+ </a>
+ <div class="body">
+ <div class="meta">
+ <time datetime="2026-06-01">Jun 1, 2026</time>
+ <span class="dot" aria-hidden="true"></span>
+ <span>3 min</span>
+ </div>
+ <h3><a href="/blog/how-to-run-multiple-claude-code-agents/">How to Run Multiple Claude Code Agents (Without Losing Track)</a></h3>
+ <p class="dek">Run several Claude Code agents in parallel without the chaos: give each a role, let them coordinate, and stop alt-tabbing between terminal windows.</p>
+ <div class="foot">
+ <span class="tag kind">Guides</span>
+ <a class="more" href="/blog/how-to-run-multiple-claude-code-agents/" aria-label="Read: How to Run Multiple Claude Code Agents (Without Losing Track)">Read →</a>
+ </div>
+ </div>
+</article>
+<article class="card">
+ <a class="thumb t-guides" href="/blog/manage-multiple-claude-code-sessions/" aria-hidden="true" tabindex="-1">
+ <span>GUIDES</span>
+ </a>
+ <div class="body">
+ <div class="meta">
+ <time datetime="2026-05-25">May 25, 2026</time>
+ <span class="dot" aria-hidden="true"></span>
+ <span>4 min</span>
+ </div>
+ <h3><a href="/blog/manage-multiple-claude-code-sessions/">How to Manage Multiple Claude Code Sessions Like a Pro</a></h3>
+ <p class="dek">Tactics to manage multiple Claude Code sessions without losing track: naming, roles, context isolation, and when a harness beats juggling terminal tabs.</p>
+ <div class="foot">
+ <span class="tag kind">Guides</span>
+ <a class="more" href="/blog/manage-multiple-claude-code-sessions/" aria-label="Read: How to Manage Multiple Claude Code Sessions Like a Pro">Read →</a>
+ </div>
+ </div>
+</article>
+
+ </div>
+ </section>
+
+ </footer>
+</article>
+
+</main>
+<footer>
+ <div class="wrap">
+ <div class="foot-top">
+ <a class="foot-brand brand" href="/blog/">
+ <span class="brand-mark">MD</span>
+ <span class="brand-word">MUNDER DIFFLIN<span class="sep">/</span><span class="blog">BLOG</span></span>
+ </a>
+ <div class="foot-links">
+ <a href="/blog/">Latest</a>
+ <a href="/blog/topics/">Topics</a>
+ <a href="/blog/about/">About</a>
+ <a href="https://munderdiffl.in/blog/feed.xml">RSS</a>
+ <a href="https://github.com/chaitanyagiri/munder-difflin">GitHub</a>
+ <a href="https://munderdiffl.in">munderdiffl.in ↗</a>
+ </div>
+ </div>
+ <div class="foot-meta">
+ © 2026 Munder Difflin · Local-first · MIT-licensed ·
+ Built on <a href="https://munderdiffl.in">Electron, React, Pixi.js, xterm.js &amp; node-pty</a>.
+ Run an office of agents while you sleep.
+ </div>
+ </div>
+</footer>
+
+<script>
+ // sticky-nav border on scroll
+ (function () {
+ var nav = document.getElementById('nav');
+ if (!nav) return;
+ var onScroll = function () { nav.classList.toggle('scrolled', window.scrollY > 8); };
+ onScroll(); window.addEventListener('scroll', onScroll, { passive: true });
+ })();
+</script>
+
+</body>
+</html>
diff --git a/docs/blog/claude-code-git-worktrees-vs-hive/index.html b/docs/blog/claude-code-git-worktrees-vs-hive/index.html
new file mode 100644
index 00000000..15211d2e
--- /dev/null
+++ b/docs/blog/claude-code-git-worktrees-vs-hive/index.html
@@ -0,0 +1,388 @@
+<!doctype html>
+<html lang="en">
+<head>
+<meta charset="UTF-8" />
+<meta name="viewport" content="width=device-width, initial-scale=1.0" />
+<title>Git Worktrees vs a Hive: Two Ways to Parallelize Claude Code — Munder Difflin Blog</title>
+<meta name="description" content="Claude Code git worktrees vs a hive: when isolated worktrees suffice for parallel agents, and when you need memory, messaging, and an orchestrator on top." />
+<link rel="canonical" href="https://munderdiffl.in/blog/claude-code-git-worktrees-vs-hive/" />
+
+<link rel="icon" type="image/png" href="https://munderdiffl.in/logo.png" />
+<link rel="apple-touch-icon" href="https://munderdiffl.in/logo.png" />
+<meta name="theme-color" content="#F5F2E8" />
+
+<!-- Open Graph -->
+<meta property="og:site_name" content="Munder Difflin Blog" />
+<meta property="og:type" content="article" />
+<meta property="og:title" content="Git Worktrees vs a Hive: Two Ways to Parallelize Claude Code — Munder Difflin Blog" />
+<meta property="og:description" content="Claude Code git worktrees vs a hive: when isolated worktrees suffice for parallel agents, and when you need memory, messaging, and an orchestrator on top." />
+<meta property="og:url" content="https://munderdiffl.in/blog/claude-code-git-worktrees-vs-hive/" />
+<meta property="og:image" content="https://munderdiffl.in/media/og.png" />
+<meta property="og:locale" content="en_US" />
+<meta property="article:published_time" content="2026-06-04T00:00:00.000Z" />
+<meta property="article:author" content="Chaitanya Giri" />
+<meta property="article:tag" content="Orchestration" />
+<meta property="article:tag" content="Git" />
+<meta property="article:tag" content="Multi-Agent" />
+<meta property="article:tag" content="Claude Code" />
+
+
+<!-- Twitter -->
+<meta name="twitter:card" content="summary_large_image" />
+<meta name="twitter:title" content="Git Worktrees vs a Hive: Two Ways to Parallelize Claude Code — Munder Difflin Blog" />
+<meta name="twitter:description" content="Claude Code git worktrees vs a hive: when isolated worktrees suffice for parallel agents, and when you need memory, messaging, and an orchestrator on top." />
+<meta name="twitter:image" content="https://munderdiffl.in/media/og.png" />
+
+<link rel="alternate" type="application/atom+xml" title="Munder Difflin Blog" href="https://munderdiffl.in/blog/feed.xml" />
+<link rel="preconnect" href="https://fonts.googleapis.com" />
+<link rel="preconnect" href="https://fonts.gstatic.com" crossorigin />
+<link href="https://fonts.googleapis.com/css2?family=Geist:wght@400;500;600&family=JetBrains+Mono:wght@400;500;600;700&display=swap" rel="stylesheet" />
+<link rel="stylesheet" href="/blog/assets/blog.css" />
+
+<script type="application/ld+json">
+{
+ "@context": "https://schema.org",
+ "@type": "BlogPosting",
+ "headline": "Git Worktrees vs a Hive: Two Ways to Parallelize Claude Code",
+ "description": "Claude Code git worktrees vs a hive: when isolated worktrees suffice for parallel agents, and when you need memory, messaging, and an orchestrator on top.",
+ "image": ["https://munderdiffl.in/media/og.png"],
+ "datePublished": "2026-06-04T00:00:00.000Z",
+ "dateModified": "2026-06-04T00:00:00.000Z",
+ "author": { "@type": "Person", "name": "Chaitanya Giri" },
+ "publisher": {
+ "@type": "Organization",
+ "name": "Munder Difflin",
+ "logo": { "@type": "ImageObject", "url": "https://munderdiffl.in/logo.png" }
+ },
+ "mainEntityOfPage": { "@type": "WebPage", "@id": "https://munderdiffl.in/blog/claude-code-git-worktrees-vs-hive/" },
+ "keywords": "claude code git worktrees, git worktrees, claude code parallel, isolated agent workspaces",
+ "articleSection": "Orchestration",
+ "inLanguage": "en-US",
+ "url": "https://munderdiffl.in/blog/claude-code-git-worktrees-vs-hive/"
+}
+</script>
+<script type="application/ld+json">
+{
+ "@context": "https://schema.org",
+ "@type": "BreadcrumbList",
+ "itemListElement": [
+ { "@type": "ListItem", "position": 1, "name": "Home", "item": "https://munderdiffl.in/" },
+ { "@type": "ListItem", "position": 2, "name": "Blog", "item": "https://munderdiffl.in/blog/" },
+ { "@type": "ListItem", "position": 3, "name": "Git Worktrees vs a Hive: Two Ways to Parallelize Claude Code", "item": "https://munderdiffl.in/blog/claude-code-git-worktrees-vs-hive/" }
+ ]
+}
+</script>
+
+<script type="application/ld+json">
+{
+ "@context": "https://schema.org",
+ "@type": "FAQPage",
+ "mainEntity": [
+ { "@type": "Question", "name": "What is a git worktree?", "acceptedAnswer": { "@type": "Answer", "text": "A git worktree is an additional working directory attached to one repository. Each worktree has its own checked-out branch and its own index, but they share the same object store and refs — so you can have several branches checked out at once without cloning the repo multiple times." } },
+ { "@type": "Question", "name": "Are git worktrees enough to run parallel Claude Code agents?", "acceptedAnswer": { "@type": "Answer", "text": "For independent tasks on separate branches, often yes — worktrees give each agent its own files so they don't collide. What worktrees don't provide is coordination: shared memory, messaging between agents, or an orchestrator that divides one goal across the team." } },
+ { "@type": "Question", "name": "Can I use worktrees and a hive together?", "acceptedAnswer": { "@type": "Answer", "text": "Yes. Worktrees solve workspace isolation; a hive solves coordination. You can run a coordinated hive where each agent works in its own worktree, getting both isolation and shared memory plus messaging." } }
+
+ ]
+}
+</script>
+
+
+</head>
+<body>
+<a class="skip-link" href="#main">Skip to content</a>
+<nav id="nav">
+ <a class="brand" href="/blog/" aria-label="Munder Difflin Blog home">
+ <span class="brand-mark">MD</span>
+ <span class="brand-word">MUNDER DIFFLIN<span class="sep">/</span><span class="blog">BLOG</span></span>
+ </a>
+ <span class="spacer"></span>
+ <div class="links">
+ <a href="/blog/">Latest</a>
+ <a href="/blog/topics/">Topics</a>
+ <a href="/blog/about/">About</a>
+ <a href="https://munderdiffl.in">↗ Product</a>
+ </div>
+ <div class="nav-actions">
+ <a class="btn sm" href="https://munderdiffl.in/blog/feed.xml" aria-label="RSS feed">⤵ RSS</a>
+ <a class="btn sm primary" href="https://munderdiffl.in/#install">⤓ Download</a>
+ </div>
+</nav>
+
+<main id="main">
+
+<article>
+ <header class="post-head wrap">
+ <nav class="crumbs" aria-label="Breadcrumb">
+ <a href="/blog/">Blog</a>
+ <span>/</span>
+ <a href="/blog/topics/orchestration/">Orchestration</a>
+ </nav>
+ <h1>Git Worktrees vs a Hive: Two Ways to Parallelize Claude Code</h1>
+ <p class="dek">Claude Code git worktrees vs a hive: when isolated worktrees suffice for parallel agents, and when you need memory, messaging, and an orchestrator on top.</p>
+ <div class="byline">
+ <span class="av" aria-hidden="true">CG</span>
+ <strong>Chaitanya Giri</strong>
+ <span class="dot" aria-hidden="true">·</span>
+ <time datetime="2026-06-04">Jun 4, 2026</time>
+ <span class="dot" aria-hidden="true">·</span>
+ <span>5 min read</span>
+ <span class="tag kind">Orchestration</span>
+ </div>
+ </header>
+
+ <div class="post-wrap wrap">
+ <div class="prose">
+ <div class="callout tldr"><span class="ic">TL;DR</span><p><strong>Git worktrees</strong> give each
+Claude Code agent its own working directory and branch, so parallel agents don't collide on files —
+perfect for <em>independent</em> tasks. A <strong>hive</strong> adds what worktrees don't: shared
+memory, agent-to-agent messaging, and an orchestrator that splits one goal across the team. They solve
+different problems — isolation vs. coordination — and compose: run a hive whose agents each live in a
+worktree.</p></div>
+<p>There are two genuinely good answers to “how do I run Claude Code agents in parallel,” and they’re
+often pitched as rivals. They aren’t. Git worktrees and a coordinating hive solve different halves of
+the problem, and the right choice — or the right <em>combination</em> — depends on whether your parallel work
+is independent or interdependent. Here’s the honest comparison.</p>
+<h2 id="what-git-worktrees-give-you" tabindex="-1">What git worktrees give you <a class="anchor" href="#what-git-worktrees-give-you" aria-hidden="true">#</a></h2>
+<p>A <strong>worktree</strong> is an extra working directory attached to a single repository. Normally a repo has one
+checkout; <code>git worktree add ../feature-x feature-x</code> gives you a <em>second</em> directory with the <code>feature-x</code>
+branch checked out, sharing the same underlying repo.</p>
+<pre class="language-bash"><code class="language-bash"><span class="token function">git</span> worktree <span class="token function">add</span> <span class="token punctuation">..</span>/agent-a <span class="token parameter variable">-b</span> agent-a
+<span class="token function">git</span> worktree <span class="token function">add</span> <span class="token punctuation">..</span>/agent-b <span class="token parameter variable">-b</span> agent-b
+<span class="token comment"># now agent A and agent B each have their own directory + branch</span></code></pre>
+<p>The key properties:</p>
+<ul>
+<li><strong>Separate working directories.</strong> Each agent edits files in its own folder. They physically cannot
+step on each other’s uncommitted changes.</li>
+<li><strong>Separate indexes.</strong> Each worktree has its own staging area, so an agent staging and committing in
+one doesn’t fight another’s index. (This sidesteps a lot of the
+<a href="/blog/single-committer-git-pattern/"><code>index.lock</code> pain</a> you get when many processes share one
+index.)</li>
+<li><strong>Shared history.</strong> They share the same object store and refs, so branches and commits are visible
+across all of them — no duplicate clones, no re-fetching.</li>
+</ul>
+<p>For <strong>independent</strong> parallel work, this is often all you need. Three agents, three feature branches,
+three worktrees: they run side by side, each on its own task, and you merge the branches when they’re
+done. Clean and native.</p>
+<h2 id="where-worktrees-stop" tabindex="-1">Where worktrees stop <a class="anchor" href="#where-worktrees-stop" aria-hidden="true">#</a></h2>
+<p>Worktrees isolate <em>workspaces</em>. They do nothing about <em>coordination</em>. The moment your parallel agents
+aren’t fully independent, the gaps show:</p>
+<ul>
+<li><strong>No shared memory.</strong> Agent A figures out a quirk in the build; agent B, in a different worktree, has
+no idea. Each is its own island. Nothing carries knowledge between them or across sessions.</li>
+<li><strong>No messaging.</strong> If agent B needs something from agent A — a decision, an interface, a “don’t touch
+this module” — there’s no channel. You become the relay, copy-pasting between directories.</li>
+<li><strong>No orchestration.</strong> Worktrees don’t divide a <em>goal</em> into tasks or assign them. You still decide, by
+hand, who works on what. There’s no coordinator reading “ship feature X with tests and docs” and
+routing the pieces.</li>
+<li><strong>No shared plan or visibility.</strong> Three worktrees are three black boxes. There’s no shared board, no
+roster, no single place to see what the team is collectively doing.</li>
+</ul>
+<p>In other words, worktrees make parallel agents <em>safe to run</em>, not <em>able to cooperate</em>. That’s a real
+and useful guarantee — it’s just not the same as a team.</p>
+<h2 id="what-a-hive-gives-you" tabindex="-1">What a hive gives you <a class="anchor" href="#what-a-hive-gives-you" aria-hidden="true">#</a></h2>
+<p>A <strong>hive</strong> is the coordination layer worktrees lack. It wraps several long-lived agents and adds:</p>
+<ul>
+<li><strong>Shared, durable memory.</strong> Each agent’s notes persist and become recall-able by the whole team, so
+knowledge flows between agents and across sessions — <a href="/blog/semantic-memory-for-ai-agents/">semantic memory for agents</a>,
+not isolated context.</li>
+<li><strong>Direct messaging.</strong> Agents send messages to each other through a router; no human relay. (“I own
+the auth module” actually reaches everyone.)</li>
+<li><strong>An orchestrator.</strong> A coordinator decomposes your goal, routes work to the right agent, adjudicates
+the routine back-and-forth, and escalates only the critical calls — see
+<a href="/blog/claude-code-orchestration-guide/">orchestrating Claude Code agents</a>.</li>
+<li><strong>A shared plan and a live view.</strong> One board, one roster, one office floor you can watch.</li>
+</ul>
+<p>What a hive does <em>not</em> inherently solve is file isolation — if its agents share a single working
+directory, you need a discipline (single-writer files, single-committer git) to keep them from
+colliding. Which is exactly where worktrees come back in.</p>
+<h2 id="they-compose" tabindex="-1">They compose <a class="anchor" href="#they-compose" aria-hidden="true">#</a></h2>
+<p>Here’s the punchline the “vs.” framing hides: <strong>use both.</strong> Worktrees handle isolation; the hive
+handles coordination. Run a hive whose agents each operate in their own worktree, and you get the best
+of both — agents that can’t clobber each other’s files <em>and</em> can share memory, message each other, and
+take direction from an orchestrator.</p>
+<pre class="language-text"><code class="language-text"> ┌─ worktree: agent-a (branch agent-a) ─┐
+hive ───────┼─ worktree: agent-b (branch agent-b) ─┼── shared memory + messaging
+(coordination) └─ worktree: agent-c (branch agent-c) ┘ + orchestrator + board</code></pre>
+<p>The layers don’t conflict; they stack. Worktrees are a git feature for workspace isolation. A hive is a
+coordination feature for teamwork. Asking which to use is like asking whether to use seatbelts or a
+steering wheel.</p>
+<h2 id="a-decision-guide" tabindex="-1">A decision guide <a class="anchor" href="#a-decision-guide" aria-hidden="true">#</a></h2>
+<p>Pick based on how <em>interdependent</em> your parallel work is:</p>
+<p><strong>Just worktrees</strong> are enough when:</p>
+<ul>
+<li>the tasks are <strong>independent</strong> (separate features, separate branches),</li>
+<li>agents don’t need to know what the others learned, and</li>
+<li>you’re happy to assign work and merge results by hand.</li>
+</ul>
+<p><strong>A hive</strong> (optionally over worktrees) is worth it when:</p>
+<ul>
+<li>the work is <strong>one goal</strong> that needs dividing and recombining,</li>
+<li>agents must <strong>share knowledge</strong> or <strong>message</strong> each other, or</li>
+<li>you want to state intent once and have a <strong>coordinated team</strong> execute — the leap described in
+<a href="/blog/how-to-run-multiple-claude-code-agents/">how to run multiple Claude Code agents</a>.</li>
+</ul>
+<p>If you’ve ever wondered whether built-in mechanisms are enough versus an external coordination layer,
+the same question shows up for <a href="/blog/claude-code-subagents-vs-multi-agent-harness/">subagents vs a harness</a> —
+and the answer rhymes: native primitives handle the small scale; a coordination layer handles the team
+scale.</p>
+<h2 id="faq" tabindex="-1">FAQ <a class="anchor" href="#faq" aria-hidden="true">#</a></h2>
+<p><strong>Do worktrees prevent all git conflicts?</strong> They prevent index and working-directory collisions, which
+are the common ones. Shared refs and the object store are still common, so concurrent operations that
+touch refs still want care — which is one reason a hive uses a single committer for its <em>coordination</em>
+repo even when agents work in separate worktrees.</p>
+<p><strong>Is a hive heavier than worktrees?</strong> It’s more capable, so it’s more machinery. If your tasks are
+truly independent, worktrees alone are the lighter, correct choice. Add the hive when coordination —
+not just isolation — is the thing you’re missing.</p>
+<hr>
+<p>Munder Difflin is the coordination layer: shared memory, messaging, and a GOD orchestrator for a hive
+of Claude Code agents — and it plays nicely with the git workflow you already use.
+<a href="https://munderdiffl.in/#install">Download Munder Difflin</a> when isolation isn’t enough and you need a
+team; it’s free and open source.</p>
+
+
+
+ <section class="faq" aria-label="Frequently asked questions">
+ <h2 id="faq">FAQ</h2>
+
+ <div class="qa">
+ <p class="q">What is a git worktree?</p>
+ <p class="a">A git worktree is an additional working directory attached to one repository. Each worktree has its own checked-out branch and its own index, but they share the same object store and refs — so you can have several branches checked out at once without cloning the repo multiple times.</p>
+ </div>
+
+ <div class="qa">
+ <p class="q">Are git worktrees enough to run parallel Claude Code agents?</p>
+ <p class="a">For independent tasks on separate branches, often yes — worktrees give each agent its own files so they don&#39;t collide. What worktrees don&#39;t provide is coordination: shared memory, messaging between agents, or an orchestrator that divides one goal across the team.</p>
+ </div>
+
+ <div class="qa">
+ <p class="q">Can I use worktrees and a hive together?</p>
+ <p class="a">Yes. Worktrees solve workspace isolation; a hive solves coordination. You can run a coordinated hive where each agent works in its own worktree, getting both isolation and shared memory plus messaging.</p>
+ </div>
+
+ </section>
+
+
+
+ <hr />
+ <div class="share">
+ <span class="lbl">Tags</span>
+ <a class="tag" href="/blog/tags/orchestration/">Orchestration</a><a class="tag" href="/blog/tags/git/">Git</a><a class="tag" href="/blog/tags/multi-agent/">Multi-Agent</a><a class="tag" href="/blog/tags/claude-code/">Claude Code</a>
+ </div>
+
+ </div>
+
+
+ <aside class="toc-rail" aria-label="Table of contents">
+ <div class="tt">On this page</div>
+ <ol>
+ <li class="lvl-2"><a href="#what-git-worktrees-give-you">What git worktrees give you</a></li><li class="lvl-2"><a href="#where-worktrees-stop">Where worktrees stop</a></li><li class="lvl-2"><a href="#what-a-hive-gives-you">What a hive gives you</a></li><li class="lvl-2"><a href="#they-compose">They compose</a></li><li class="lvl-2"><a href="#a-decision-guide">A decision guide</a></li><li class="lvl-2"><a href="#faq">FAQ</a></li>
+ </ol>
+ </aside>
+
+ </div>
+
+ <footer class="post-foot wrap"><div class="prevnext">
+ <a class="pn prev" href="/blog/claude-code-orchestration-tools-compared/"><span class="k">← Older</span><span class="t">Claude Code Orchestration Tools, Compared</span></a>
+ <a class="pn next" href="/blog/claude-code-automation-while-you-sleep/"><span class="k">Newer →</span><span class="t">Claude Code Automation: Let Agents Build While You Sleep</span></a>
+ </div>
+ <section class="related">
+ <h2>Related in Orchestration</h2>
+ <div class="post-grid">
+ <article class="card">
+ <a class="thumb t-orchestration" href="/blog/how-the-god-orchestrator-works/" aria-hidden="true" tabindex="-1">
+ <span>ORCHESTRATION</span>
+ </a>
+ <div class="body">
+ <div class="meta">
+ <time datetime="2026-05-30">May 30, 2026</time>
+ <span class="dot" aria-hidden="true"></span>
+ <span>6 min</span>
+ </div>
+ <h3><a href="/blog/how-the-god-orchestrator-works/">Inside the GOD Orchestrator: Routing, Adjudication, Escalation</a></h3>
+ <p class="dek">A deep dive into the Claude Code orchestrator: how a GOD agent reads requests, routes work, adjudicates routine traffic, and escalates the critical few.</p>
+ <div class="foot">
+ <span class="tag kind">Orchestration</span>
+ <a class="more" href="/blog/how-the-god-orchestrator-works/" aria-label="Read: Inside the GOD Orchestrator: Routing, Adjudication, Escalation">Read →</a>
+ </div>
+ </div>
+</article>
+<article class="card">
+ <a class="thumb t-orchestration" href="/blog/coordinating-ai-coding-agents/" aria-hidden="true" tabindex="-1">
+ <span>ORCHESTRATION</span>
+ </a>
+ <div class="body">
+ <div class="meta">
+ <time datetime="2026-05-29">May 29, 2026</time>
+ <span class="dot" aria-hidden="true"></span>
+ <span>5 min</span>
+ </div>
+ <h3><a href="/blog/coordinating-ai-coding-agents/">The Best Way to Coordinate AI Coding Agents</a></h3>
+ <p class="dek">The best way to coordinate AI coding agents: single-writer files, a message router, a one-scribe plan, and an orchestrator — cooperate, not clobber.</p>
+ <div class="foot">
+ <span class="tag kind">Orchestration</span>
+ <a class="more" href="/blog/coordinating-ai-coding-agents/" aria-label="Read: The Best Way to Coordinate AI Coding Agents">Read →</a>
+ </div>
+ </div>
+</article>
+<article class="card">
+ <a class="thumb t-orchestration" href="/blog/claude-code-orchestration-guide/" aria-hidden="true" tabindex="-1">
+ <span>ORCHESTRATION</span>
+ </a>
+ <div class="body">
+ <div class="meta">
+ <time datetime="2026-05-28">May 28, 2026</time>
+ <span class="dot" aria-hidden="true"></span>
+ <span>5 min</span>
+ </div>
+ <h3><a href="/blog/claude-code-orchestration-guide/">Orchestrating Claude Code Agents: A Practical Guide</a></h3>
+ <p class="dek">How to orchestrate Claude Code agents in practice: what orchestration means, how a GOD orchestrator routes and escalates work, and how to wire it up.</p>
+ <div class="foot">
+ <span class="tag kind">Orchestration</span>
+ <a class="more" href="/blog/claude-code-orchestration-guide/" aria-label="Read: Orchestrating Claude Code Agents: A Practical Guide">Read →</a>
+ </div>
+ </div>
+</article>
+
+ </div>
+ </section>
+
+ </footer>
+</article>
+
+</main>
+<footer>
+ <div class="wrap">
+ <div class="foot-top">
+ <a class="foot-brand brand" href="/blog/">
+ <span class="brand-mark">MD</span>
+ <span class="brand-word">MUNDER DIFFLIN<span class="sep">/</span><span class="blog">BLOG</span></span>
+ </a>
+ <div class="foot-links">
+ <a href="/blog/">Latest</a>
+ <a href="/blog/topics/">Topics</a>
+ <a href="/blog/about/">About</a>
+ <a href="https://munderdiffl.in/blog/feed.xml">RSS</a>
+ <a href="https://github.com/chaitanyagiri/munder-difflin">GitHub</a>
+ <a href="https://munderdiffl.in">munderdiffl.in ↗</a>
+ </div>
+ </div>
+ <div class="foot-meta">
+ © 2026 Munder Difflin · Local-first · MIT-licensed ·
+ Built on <a href="https://munderdiffl.in">Electron, React, Pixi.js, xterm.js &amp; node-pty</a>.
+ Run an office of agents while you sleep.
+ </div>
+ </div>
+</footer>
+
+<script>
+ // sticky-nav border on scroll
+ (function () {
+ var nav = document.getElementById('nav');
+ if (!nav) return;
+ var onScroll = function () { nav.classList.toggle('scrolled', window.scrollY > 8); };
+ onScroll(); window.addEventListener('scroll', onScroll, { passive: true });
+ })();
+</script>
+
+</body>
+</html>
diff --git a/docs/blog/claude-code-hooks-explained/index.html b/docs/blog/claude-code-hooks-explained/index.html
new file mode 100644
index 00000000..202fc04f
--- /dev/null
+++ b/docs/blog/claude-code-hooks-explained/index.html
@@ -0,0 +1,401 @@
+<!doctype html>
+<html lang="en">
+<head>
+<meta charset="UTF-8" />
+<meta name="viewport" content="width=device-width, initial-scale=1.0" />
+<title>Claude Code Hooks, Explained (PreToolUse, PostToolUse, Stop) — Munder Difflin Blog</title>
+<meta name="description" content="A practical tour of Claude Code hooks — the PreToolUse, PostToolUse, and Stop lifecycle — and how a Unix-socket hook shim drives a live office floor." />
+<link rel="canonical" href="https://munderdiffl.in/blog/claude-code-hooks-explained/" />
+
+<link rel="icon" type="image/png" href="https://munderdiffl.in/logo.png" />
+<link rel="apple-touch-icon" href="https://munderdiffl.in/logo.png" />
+<meta name="theme-color" content="#F5F2E8" />
+
+<!-- Open Graph -->
+<meta property="og:site_name" content="Munder Difflin Blog" />
+<meta property="og:type" content="article" />
+<meta property="og:title" content="Claude Code Hooks, Explained (PreToolUse, PostToolUse, Stop) — Munder Difflin Blog" />
+<meta property="og:description" content="A practical tour of Claude Code hooks — the PreToolUse, PostToolUse, and Stop lifecycle — and how a Unix-socket hook shim drives a live office floor." />
+<meta property="og:url" content="https://munderdiffl.in/blog/claude-code-hooks-explained/" />
+<meta property="og:image" content="https://munderdiffl.in/media/og.png" />
+<meta property="og:locale" content="en_US" />
+<meta property="article:published_time" content="2026-06-03T00:00:00.000Z" />
+<meta property="article:author" content="Chaitanya Giri" />
+<meta property="article:tag" content="Internals" />
+<meta property="article:tag" content="Hooks" />
+<meta property="article:tag" content="Claude Code" />
+<meta property="article:tag" content="Automation" />
+
+
+<!-- Twitter -->
+<meta name="twitter:card" content="summary_large_image" />
+<meta name="twitter:title" content="Claude Code Hooks, Explained (PreToolUse, PostToolUse, Stop) — Munder Difflin Blog" />
+<meta name="twitter:description" content="A practical tour of Claude Code hooks — the PreToolUse, PostToolUse, and Stop lifecycle — and how a Unix-socket hook shim drives a live office floor." />
+<meta name="twitter:image" content="https://munderdiffl.in/media/og.png" />
+
+<link rel="alternate" type="application/atom+xml" title="Munder Difflin Blog" href="https://munderdiffl.in/blog/feed.xml" />
+<link rel="preconnect" href="https://fonts.googleapis.com" />
+<link rel="preconnect" href="https://fonts.gstatic.com" crossorigin />
+<link href="https://fonts.googleapis.com/css2?family=Geist:wght@400;500;600&family=JetBrains+Mono:wght@400;500;600;700&display=swap" rel="stylesheet" />
+<link rel="stylesheet" href="/blog/assets/blog.css" />
+
+<script type="application/ld+json">
+{
+ "@context": "https://schema.org",
+ "@type": "BlogPosting",
+ "headline": "Claude Code Hooks, Explained (PreToolUse, PostToolUse, Stop)",
+ "description": "A practical tour of Claude Code hooks — the PreToolUse, PostToolUse, and Stop lifecycle — and how a Unix-socket hook shim drives a live office floor.",
+ "image": ["https://munderdiffl.in/media/og.png"],
+ "datePublished": "2026-06-03T00:00:00.000Z",
+ "dateModified": "2026-06-03T00:00:00.000Z",
+ "author": { "@type": "Person", "name": "Chaitanya Giri" },
+ "publisher": {
+ "@type": "Organization",
+ "name": "Munder Difflin",
+ "logo": { "@type": "ImageObject", "url": "https://munderdiffl.in/logo.png" }
+ },
+ "mainEntityOfPage": { "@type": "WebPage", "@id": "https://munderdiffl.in/blog/claude-code-hooks-explained/" },
+ "keywords": "claude code hooks, pretooluse posttooluse, stop hook, claude code lifecycle",
+ "articleSection": "Internals",
+ "inLanguage": "en-US",
+ "url": "https://munderdiffl.in/blog/claude-code-hooks-explained/"
+}
+</script>
+<script type="application/ld+json">
+{
+ "@context": "https://schema.org",
+ "@type": "BreadcrumbList",
+ "itemListElement": [
+ { "@type": "ListItem", "position": 1, "name": "Home", "item": "https://munderdiffl.in/" },
+ { "@type": "ListItem", "position": 2, "name": "Blog", "item": "https://munderdiffl.in/blog/" },
+ { "@type": "ListItem", "position": 3, "name": "Claude Code Hooks, Explained (PreToolUse, PostToolUse, Stop)", "item": "https://munderdiffl.in/blog/claude-code-hooks-explained/" }
+ ]
+}
+</script>
+
+<script type="application/ld+json">
+{
+ "@context": "https://schema.org",
+ "@type": "FAQPage",
+ "mainEntity": [
+ { "@type": "Question", "name": "What are Claude Code hooks?", "acceptedAnswer": { "@type": "Answer", "text": "Hooks are commands Claude Code runs at points in its lifecycle — before and after a tool call, when it's about to stop, on a notification, and more. Each hook receives a JSON payload on stdin and can return JSON to influence what Claude does next." } },
+ { "@type": "Question", "name": "What does the Stop hook do?", "acceptedAnswer": { "@type": "Answer", "text": "The Stop hook fires when Claude is about to finish a turn. If it returns {\"decision\":\"block\",\"reason\":...}, Claude keeps working with that reason as new instructions — which is how you build an autonomous loop. A stop_hook_active flag prevents it from looping forever." } },
+ { "@type": "Question", "name": "Do hooks modify my repository?", "acceptedAnswer": { "@type": "Answer", "text": "They don't have to. Claude Code accepts a --settings file, so you can attach hooks from a settings file outside your project instead of editing files in the repo itself." } }
+
+ ]
+}
+</script>
+
+
+</head>
+<body>
+<a class="skip-link" href="#main">Skip to content</a>
+<nav id="nav">
+ <a class="brand" href="/blog/" aria-label="Munder Difflin Blog home">
+ <span class="brand-mark">MD</span>
+ <span class="brand-word">MUNDER DIFFLIN<span class="sep">/</span><span class="blog">BLOG</span></span>
+ </a>
+ <span class="spacer"></span>
+ <div class="links">
+ <a href="/blog/">Latest</a>
+ <a href="/blog/topics/">Topics</a>
+ <a href="/blog/about/">About</a>
+ <a href="https://munderdiffl.in">↗ Product</a>
+ </div>
+ <div class="nav-actions">
+ <a class="btn sm" href="https://munderdiffl.in/blog/feed.xml" aria-label="RSS feed">⤵ RSS</a>
+ <a class="btn sm primary" href="https://munderdiffl.in/#install">⤓ Download</a>
+ </div>
+</nav>
+
+<main id="main">
+
+<article>
+ <header class="post-head wrap">
+ <nav class="crumbs" aria-label="Breadcrumb">
+ <a href="/blog/">Blog</a>
+ <span>/</span>
+ <a href="/blog/topics/internals/">Internals</a>
+ </nav>
+ <h1>Claude Code Hooks, Explained (PreToolUse, PostToolUse, Stop)</h1>
+ <p class="dek">A practical tour of Claude Code hooks — the PreToolUse, PostToolUse, and Stop lifecycle — and how a Unix-socket hook shim drives a live office floor.</p>
+ <div class="byline">
+ <span class="av" aria-hidden="true">CG</span>
+ <strong>Chaitanya Giri</strong>
+ <span class="dot" aria-hidden="true">·</span>
+ <time datetime="2026-06-03">Jun 3, 2026</time>
+ <span class="dot" aria-hidden="true">·</span>
+ <span>6 min read</span>
+ <span class="tag kind">Internals</span>
+ </div>
+ </header>
+
+ <div class="post-wrap wrap">
+ <div class="prose">
+ <div class="callout tldr"><span class="ic">TL;DR</span><p><strong>Claude Code hooks</strong> are
+commands that run at lifecycle points — <code>PreToolUse</code>, <code>PostToolUse</code>,
+<code>Stop</code>, <code>Notification</code>, and more. Each gets a JSON payload on stdin and can
+return JSON to steer Claude. Munder Difflin attaches a tiny <strong>hook shim</strong> via
+<code>--settings</code> that forwards every event to the harness over a Unix socket — driving live
+avatars from <code>PreToolUse</code>/<code>PostToolUse</code>, and building an <strong>autonomous
+loop</strong> out of the <code>Stop</code> hook.</p></div>
+<p>Hooks are the most underrated part of Claude Code. They’re the official extension point for “do
+something when Claude does something” — and once you understand them, a lot of agent tooling that
+looks like magic turns out to be a well-placed hook. This post walks the lifecycle, then shows exactly
+how Munder Difflin uses hooks to animate a multi-agent office floor and keep agents working
+autonomously.</p>
+<h2 id="what-a-hook-is" tabindex="-1">What a hook is <a class="anchor" href="#what-a-hook-is" aria-hidden="true">#</a></h2>
+<p>A hook is a command Claude Code runs at a defined moment in its lifecycle. When the moment arrives,
+Claude executes your command and pipes it a <strong>JSON payload on stdin</strong> describing what’s happening. Your
+command can do whatever it likes, and — for some events — return <strong>JSON on stdout</strong> that influences
+Claude’s next move.</p>
+<p>You configure hooks in settings, mapping each event to one or more commands:</p>
+<pre class="language-jsonc"><code class="language-jsonc">{
+ "hooks": {
+ "PreToolUse": [{ "matcher": "*", "hooks": [{ "type": "command", "command": "node my-hook.js" }] }],
+ "PostToolUse": [{ "matcher": "*", "hooks": [{ "type": "command", "command": "node my-hook.js" }] }],
+ "Stop": [{ "hooks": [{ "type": "command", "command": "node my-hook.js" }] }]
+ }
+}</code></pre>
+<p>The <code>matcher</code> (for tool events) lets you scope a hook to specific tools — <code>*</code> means “every tool.” Tool
+events carry that matcher; lifecycle events like <code>Stop</code> don’t need one.</p>
+<h2 id="the-lifecycle-events-that-matter" tabindex="-1">The lifecycle events that matter <a class="anchor" href="#the-lifecycle-events-that-matter" aria-hidden="true">#</a></h2>
+<p>There are several hook events; these are the ones you’ll reach for most.</p>
+<h3 id="pretooluse" tabindex="-1">PreToolUse <a class="anchor" href="#pretooluse" aria-hidden="true">#</a></h3>
+<p>Fires <strong>before</strong> Claude runs a tool. The payload includes the <code>tool_name</code> (e.g. <code>Edit</code>, <code>Bash</code>) and
+the <code>tool_input</code>. This is your “Claude is about to do X” signal. You can use it for observability, or —
+because PreToolUse can return a decision — to gate or block a tool call before it runs.</p>
+<h3 id="posttooluse" tabindex="-1">PostToolUse <a class="anchor" href="#posttooluse" aria-hidden="true">#</a></h3>
+<p>Fires <strong>after</strong> a tool completes. Same shape, now with the result available. PostToolUse is the natural
+place to react to what just happened: log it, update a UI, trigger a follow-up.</p>
+<p>Together, PreToolUse and PostToolUse bracket every action Claude takes. If you want a faithful,
+real-time picture of what an agent is doing, these two events are it — you’re not scraping terminal
+output or guessing, you’re getting structured “about to / just did” events straight from Claude.</p>
+<h3 id="stop-and-subagentstop" tabindex="-1">Stop (and SubagentStop) <a class="anchor" href="#stop-and-subagentstop" aria-hidden="true">#</a></h3>
+<p>Fires when Claude is about to <strong>finish a turn</strong> — it’s done and ready to hand control back. This is the
+most powerful hook, because of what it can return:</p>
+<pre class="language-json"><code class="language-json"><span class="token punctuation">{</span> <span class="token property">"decision"</span><span class="token operator">:</span> <span class="token string">"block"</span><span class="token punctuation">,</span> <span class="token property">"reason"</span><span class="token operator">:</span> <span class="token string">"Here's what to do next…"</span> <span class="token punctuation">}</span></code></pre>
+<p>Returning <code>block</code> tells Claude <em>not</em> to stop — to keep going, treating <code>reason</code> as fresh instructions.
+That’s the entire basis of an <strong>autonomous loop</strong>: every time the agent tries to finish, a Stop hook
+can hand it more work. <code>SubagentStop</code> is the same event for a spawned subagent.</p>
+<p>The obvious danger is an infinite loop, so the payload carries a <code>stop_hook_active</code> flag: it’s true
+when a previous Stop hook already blocked this turn. Check it, and you can guarantee you never block
+twice in a row — the loop always has an exit.</p>
+<h3 id="notification-userpromptsubmit-sessionstart" tabindex="-1">Notification, UserPromptSubmit, SessionStart <a class="anchor" href="#notification-userpromptsubmit-sessionstart" aria-hidden="true">#</a></h3>
+<ul>
+<li><strong>Notification</strong> fires when Claude surfaces a message — including when it’s idle and waiting for
+input, or asking permission. The payload’s text lets you tell “needs you” apart from “just done.”</li>
+<li><strong>UserPromptSubmit</strong> fires when a prompt is submitted — a clean “the agent started working” signal.</li>
+<li><strong>SessionStart</strong> fires when a session begins — handy for setup or registration.</li>
+</ul>
+<h2 id="how-munder-difflin-uses-hooks" tabindex="-1">How Munder Difflin uses hooks <a class="anchor" href="#how-munder-difflin-uses-hooks" aria-hidden="true">#</a></h2>
+<p>Munder Difflin runs many <code>claude</code> agents at once and needs two things from each: a live view of what
+it’s doing, and a way to keep it working through a queue. Both come from hooks.</p>
+<h3 id="a-hook-shim-over-a-unix-socket" tabindex="-1">A hook shim over a Unix socket <a class="anchor" href="#a-hook-shim-over-a-unix-socket" aria-hidden="true">#</a></h3>
+<p>The harness can’t run heavy logic inside each hook invocation — hooks fire constantly and must be fast.
+So each agent is launched with a <strong>hook shim</strong>: a tiny script wired to every relevant event. The shim
+does almost nothing. It reads the hook payload on stdin, tags it with the agent’s id (from an
+environment variable), forwards it to the harness over a <strong>Unix domain socket</strong>, and relays the
+response back to Claude. All the real logic lives in the harness’s main process, which listens on that
+socket.</p>
+<pre class="language-text"><code class="language-text">claude ──hook fires──▶ shim ──UDS──▶ harness (main process)
+ ▲ │
+ └──── response ◀───────┘</code></pre>
+<p>The shim is deliberately dumb and crash-proof: if the socket isn’t there or anything errors, it exits
+cleanly and never blocks the agent. Newline-delimited JSON over the socket keeps the protocol trivial.</p>
+<h3 id="attached-without-touching-your-repo" tabindex="-1">Attached without touching your repo <a class="anchor" href="#attached-without-touching-your-repo" aria-hidden="true">#</a></h3>
+<p>A key detail: the hooks are attached with Claude Code’s <code>--settings</code> flag, pointing at a settings file
+the harness writes <strong>outside</strong> your project. Your repository is never modified to add hooks — no stray
+<code>.claude/settings.json</code> diff, nothing to gitignore. The agent is hive-aware purely through launch
+flags and environment variables.</p>
+<h3 id="pretooluseposttooluse-live-avatars" tabindex="-1">PreToolUse/PostToolUse → live avatars <a class="anchor" href="#pretooluseposttooluse-live-avatars" aria-hidden="true">#</a></h3>
+<p>Every tool event the harness receives is forwarded to the UI. That’s what drives the office floor: when
+an agent calls a file tool, its avatar walks to the right station; when it runs a command, it moves to
+a terminal. Because the events are structured and come straight from Claude, the visualization reflects
+<em>real</em> activity rather than a scripted animation or fragile log-scraping.</p>
+<h3 id="stop-the-autonomous-loop" tabindex="-1">Stop → the autonomous loop <a class="anchor" href="#stop-the-autonomous-loop" aria-hidden="true">#</a></h3>
+<p>This is where hooks earn their keep. When an agent’s <code>Stop</code> hook fires, the harness checks that agent’s
+inbox for unread messages. If there are any, it returns <code>{&quot;decision&quot;:&quot;block&quot;,&quot;reason&quot;: &lt;the messages&gt;}</code> — so instead of stopping, the agent reads its new messages and keeps working. If the inbox
+is empty, it returns nothing and the agent is allowed to finish.</p>
+<p>Two guards keep this safe:</p>
+<ul>
+<li><strong><code>stop_hook_active</code></strong> — if a previous Stop already blocked this turn, the harness lets it stop, so
+it can never block twice back-to-back.</li>
+<li><strong>A per-agent cursor</strong> — the harness tracks the last message id it surfaced, so each message is fed
+to the agent exactly once. No message is re-delivered, and the loop can’t spin on stale mail.</li>
+</ul>
+<p>The result is an agent that drains its work queue on its own and only goes quiet when there’s genuinely
+nothing left — the foundation of <a href="/blog/claude-code-automation-while-you-sleep/">letting agents build while you sleep</a>.
+It’s also how the <a href="/blog/how-the-god-orchestrator-works/">GOD orchestrator</a> keeps the whole floor
+moving: route a task into an agent’s inbox, and its next Stop hook picks it up automatically.</p>
+<h2 id="writing-your-own-hooks-practical-tips" tabindex="-1">Writing your own hooks: practical tips <a class="anchor" href="#writing-your-own-hooks-practical-tips" aria-hidden="true">#</a></h2>
+<p>If you’re building with hooks directly, a few lessons that save pain:</p>
+<ul>
+<li><strong>Keep them fast.</strong> Hooks run synchronously in Claude’s path. Do the minimum and offload anything
+heavy (a socket forward, a queued job) rather than blocking.</li>
+<li><strong>Fail open.</strong> A hook that errors shouldn’t wedge the agent. Catch everything and exit cleanly.</li>
+<li><strong>Respect <code>stop_hook_active</code>.</strong> Any Stop hook that can block must check this flag, or you’ll build an
+infinite loop.</li>
+<li><strong>Use <code>--settings</code> for portability.</strong> Attaching hooks via a settings file outside the repo keeps your
+project clean and lets you apply the same hooks to many sessions.</li>
+</ul>
+<h2 id="faq" tabindex="-1">FAQ <a class="anchor" href="#faq" aria-hidden="true">#</a></h2>
+<p><strong>Can a hook block a dangerous tool call?</strong> Yes — PreToolUse can return a decision that prevents a tool
+from running, which is useful for guardrails. Munder Difflin leans on its orchestrator and approval
+queue for that judgment, but the hook-level gate is available.</p>
+<p><strong>Do hooks slow Claude down?</strong> Only as much as your hook command does. A shim that just forwards a
+payload over a local socket adds negligible overhead, which is exactly why the heavy logic lives
+elsewhere.</p>
+<hr>
+<p>Munder Difflin turns Claude Code’s hook lifecycle into a live, autonomous office: real-time avatars
+from tool events and a self-draining work loop from the Stop hook — all without editing your repo.
+<a href="https://munderdiffl.in/#install">Download Munder Difflin</a> to see hooks driving a hive of agents; it’s
+free and open source.</p>
+
+
+
+ <section class="faq" aria-label="Frequently asked questions">
+ <h2 id="faq">FAQ</h2>
+
+ <div class="qa">
+ <p class="q">What are Claude Code hooks?</p>
+ <p class="a">Hooks are commands Claude Code runs at points in its lifecycle — before and after a tool call, when it&#39;s about to stop, on a notification, and more. Each hook receives a JSON payload on stdin and can return JSON to influence what Claude does next.</p>
+ </div>
+
+ <div class="qa">
+ <p class="q">What does the Stop hook do?</p>
+ <p class="a">The Stop hook fires when Claude is about to finish a turn. If it returns {&quot;decision&quot;:&quot;block&quot;,&quot;reason&quot;:...}, Claude keeps working with that reason as new instructions — which is how you build an autonomous loop. A stop_hook_active flag prevents it from looping forever.</p>
+ </div>
+
+ <div class="qa">
+ <p class="q">Do hooks modify my repository?</p>
+ <p class="a">They don&#39;t have to. Claude Code accepts a --settings file, so you can attach hooks from a settings file outside your project instead of editing files in the repo itself.</p>
+ </div>
+
+ </section>
+
+
+
+ <hr />
+ <div class="share">
+ <span class="lbl">Tags</span>
+ <a class="tag" href="/blog/tags/internals/">Internals</a><a class="tag" href="/blog/tags/hooks/">Hooks</a><a class="tag" href="/blog/tags/claude-code/">Claude Code</a><a class="tag" href="/blog/tags/automation/">Automation</a>
+ </div>
+
+ </div>
+
+
+ <aside class="toc-rail" aria-label="Table of contents">
+ <div class="tt">On this page</div>
+ <ol>
+ <li class="lvl-2"><a href="#what-a-hook-is">What a hook is</a></li><li class="lvl-2"><a href="#the-lifecycle-events-that-matter">The lifecycle events that matter</a></li><li class="lvl-3"><a href="#pretooluse">PreToolUse</a></li><li class="lvl-3"><a href="#posttooluse">PostToolUse</a></li><li class="lvl-3"><a href="#stop-and-subagentstop">Stop (and SubagentStop)</a></li><li class="lvl-3"><a href="#notification-userpromptsubmit-sessionstart">Notification, UserPromptSubmit, SessionStart</a></li><li class="lvl-2"><a href="#how-munder-difflin-uses-hooks">How Munder Difflin uses hooks</a></li><li class="lvl-3"><a href="#a-hook-shim-over-a-unix-socket">A hook shim over a Unix socket</a></li><li class="lvl-3"><a href="#attached-without-touching-your-repo">Attached without touching your repo</a></li><li class="lvl-3"><a href="#pretooluseposttooluse-live-avatars">PreToolUse/PostToolUse → live avatars</a></li><li class="lvl-3"><a href="#stop-the-autonomous-loop">Stop → the autonomous loop</a></li><li class="lvl-2"><a href="#writing-your-own-hooks-practical-tips">Writing your own hooks: practical tips</a></li><li class="lvl-2"><a href="#faq">FAQ</a></li>
+ </ol>
+ </aside>
+
+ </div>
+
+ <footer class="post-foot wrap"><div class="prevnext">
+ <a class="pn prev" href="/blog/claude-squad-alternative/"><span class="k">← Older</span><span class="t">Looking for a Claude Squad Alternative?</span></a>
+ <a class="pn next" href="/blog/building-a-terminal-ui-xterm-node-pty/"><span class="k">Newer →</span><span class="t">Building a Terminal UI with xterm.js and node-pty</span></a>
+ </div>
+ <section class="related">
+ <h2>Related in Internals</h2>
+ <div class="post-grid">
+ <article class="card">
+ <a class="thumb t-internals" href="/blog/building-a-terminal-ui-xterm-node-pty/" aria-hidden="true" tabindex="-1">
+ <span>INTERNALS</span>
+ </a>
+ <div class="body">
+ <div class="meta">
+ <time datetime="2026-06-03">Jun 3, 2026</time>
+ <span class="dot" aria-hidden="true"></span>
+ <span>8 min</span>
+ </div>
+ <h3><a href="/blog/building-a-terminal-ui-xterm-node-pty/">Building a Terminal UI with xterm.js and node-pty</a></h3>
+ <p class="dek">Wire xterm.js to a node-pty backend: stream output, write keystrokes back, handle resize, and keep many live terminals fast with a terminal pool.</p>
+ <div class="foot">
+ <span class="tag kind">Internals</span>
+ <a class="more" href="/blog/building-a-terminal-ui-xterm-node-pty/" aria-label="Read: Building a Terminal UI with xterm.js and node-pty">Read →</a>
+ </div>
+ </div>
+</article>
+<article class="card">
+ <a class="thumb t-internals" href="/blog/node-pty-electron-real-terminals/" aria-hidden="true" tabindex="-1">
+ <span>INTERNALS</span>
+ </a>
+ <div class="body">
+ <div class="meta">
+ <time datetime="2026-06-03">Jun 3, 2026</time>
+ <span class="dot" aria-hidden="true"></span>
+ <span>7 min</span>
+ </div>
+ <h3><a href="/blog/node-pty-electron-real-terminals/">Real Terminals in Electron with node-pty</a></h3>
+ <p class="dek">How to run byte-for-byte authentic shells inside Electron with node-pty: the native-rebuild gotcha, the macOS PATH trap, and streaming PTY output over IPC.</p>
+ <div class="foot">
+ <span class="tag kind">Internals</span>
+ <a class="more" href="/blog/node-pty-electron-real-terminals/" aria-label="Read: Real Terminals in Electron with node-pty">Read →</a>
+ </div>
+ </div>
+</article>
+<article class="card">
+ <a class="thumb t-internals" href="/blog/single-committer-git-pattern/" aria-hidden="true" tabindex="-1">
+ <span>INTERNALS</span>
+ </a>
+ <div class="body">
+ <div class="meta">
+ <time datetime="2026-06-02">Jun 2, 2026</time>
+ <span class="dot" aria-hidden="true"></span>
+ <span>5 min</span>
+ </div>
+ <h3><a href="/blog/single-committer-git-pattern/">The Single-Committer Pattern: Multi-Agent Git Without Corruption</a></h3>
+ <p class="dek">Parallel agents corrupt a repo with index.lock races. The single-committer pattern — agents write, one process commits — fixes concurrent git writes.</p>
+ <div class="foot">
+ <span class="tag kind">Internals</span>
+ <a class="more" href="/blog/single-committer-git-pattern/" aria-label="Read: The Single-Committer Pattern: Multi-Agent Git Without Corruption">Read →</a>
+ </div>
+ </div>
+</article>
+
+ </div>
+ </section>
+
+ </footer>
+</article>
+
+</main>
+<footer>
+ <div class="wrap">
+ <div class="foot-top">
+ <a class="foot-brand brand" href="/blog/">
+ <span class="brand-mark">MD</span>
+ <span class="brand-word">MUNDER DIFFLIN<span class="sep">/</span><span class="blog">BLOG</span></span>
+ </a>
+ <div class="foot-links">
+ <a href="/blog/">Latest</a>
+ <a href="/blog/topics/">Topics</a>
+ <a href="/blog/about/">About</a>
+ <a href="https://munderdiffl.in/blog/feed.xml">RSS</a>
+ <a href="https://github.com/chaitanyagiri/munder-difflin">GitHub</a>
+ <a href="https://munderdiffl.in">munderdiffl.in ↗</a>
+ </div>
+ </div>
+ <div class="foot-meta">
+ © 2026 Munder Difflin · Local-first · MIT-licensed ·
+ Built on <a href="https://munderdiffl.in">Electron, React, Pixi.js, xterm.js &amp; node-pty</a>.
+ Run an office of agents while you sleep.
+ </div>
+ </div>
+</footer>
+
+<script>
+ // sticky-nav border on scroll
+ (function () {
+ var nav = document.getElementById('nav');
+ if (!nav) return;
+ var onScroll = function () { nav.classList.toggle('scrolled', window.scrollY > 8); };
+ onScroll(); window.addEventListener('scroll', onScroll, { passive: true });
+ })();
+</script>
+
+</body>
+</html>
diff --git a/docs/blog/claude-code-multi-agent-setup-tutorial/index.html b/docs/blog/claude-code-multi-agent-setup-tutorial/index.html
new file mode 100644
index 00000000..d1bf33fc
--- /dev/null
+++ b/docs/blog/claude-code-multi-agent-setup-tutorial/index.html
@@ -0,0 +1,379 @@
+<!doctype html>
+<html lang="en">
+<head>
+<meta charset="UTF-8" />
+<meta name="viewport" content="width=device-width, initial-scale=1.0" />
+<title>Set Up a Claude Code Multi-Agent Workflow in 10 Minutes — Munder Difflin Blog</title>
+<meta name="description" content="A from-zero Claude Code multi-agent setup: install Munder Difflin, onboard, spawn a few agents, and watch the GOD orchestrator route your first task." />
+<link rel="canonical" href="https://munderdiffl.in/blog/claude-code-multi-agent-setup-tutorial/" />
+
+<link rel="icon" type="image/png" href="https://munderdiffl.in/logo.png" />
+<link rel="apple-touch-icon" href="https://munderdiffl.in/logo.png" />
+<meta name="theme-color" content="#F5F2E8" />
+
+<!-- Open Graph -->
+<meta property="og:site_name" content="Munder Difflin Blog" />
+<meta property="og:type" content="article" />
+<meta property="og:title" content="Set Up a Claude Code Multi-Agent Workflow in 10 Minutes — Munder Difflin Blog" />
+<meta property="og:description" content="A from-zero Claude Code multi-agent setup: install Munder Difflin, onboard, spawn a few agents, and watch the GOD orchestrator route your first task." />
+<meta property="og:url" content="https://munderdiffl.in/blog/claude-code-multi-agent-setup-tutorial/" />
+<meta property="og:image" content="https://munderdiffl.in/media/og.png" />
+<meta property="og:locale" content="en_US" />
+<meta property="article:published_time" content="2026-05-24T00:00:00.000Z" />
+<meta property="article:author" content="Chaitanya Giri" />
+<meta property="article:tag" content="Getting Started" />
+<meta property="article:tag" content="Guides" />
+<meta property="article:tag" content="Multi-Agent" />
+<meta property="article:tag" content="Claude Code" />
+
+
+<!-- Twitter -->
+<meta name="twitter:card" content="summary_large_image" />
+<meta name="twitter:title" content="Set Up a Claude Code Multi-Agent Workflow in 10 Minutes — Munder Difflin Blog" />
+<meta name="twitter:description" content="A from-zero Claude Code multi-agent setup: install Munder Difflin, onboard, spawn a few agents, and watch the GOD orchestrator route your first task." />
+<meta name="twitter:image" content="https://munderdiffl.in/media/og.png" />
+
+<link rel="alternate" type="application/atom+xml" title="Munder Difflin Blog" href="https://munderdiffl.in/blog/feed.xml" />
+<link rel="preconnect" href="https://fonts.googleapis.com" />
+<link rel="preconnect" href="https://fonts.gstatic.com" crossorigin />
+<link href="https://fonts.googleapis.com/css2?family=Geist:wght@400;500;600&family=JetBrains+Mono:wght@400;500;600;700&display=swap" rel="stylesheet" />
+<link rel="stylesheet" href="/blog/assets/blog.css" />
+
+<script type="application/ld+json">
+{
+ "@context": "https://schema.org",
+ "@type": "BlogPosting",
+ "headline": "Set Up a Claude Code Multi-Agent Workflow in 10 Minutes",
+ "description": "A from-zero Claude Code multi-agent setup: install Munder Difflin, onboard, spawn a few agents, and watch the GOD orchestrator route your first task.",
+ "image": ["https://munderdiffl.in/media/og.png"],
+ "datePublished": "2026-05-24T00:00:00.000Z",
+ "dateModified": "2026-05-24T00:00:00.000Z",
+ "author": { "@type": "Person", "name": "Chaitanya Giri" },
+ "publisher": {
+ "@type": "Organization",
+ "name": "Munder Difflin",
+ "logo": { "@type": "ImageObject", "url": "https://munderdiffl.in/logo.png" }
+ },
+ "mainEntityOfPage": { "@type": "WebPage", "@id": "https://munderdiffl.in/blog/claude-code-multi-agent-setup-tutorial/" },
+ "keywords": "claude code multi-agent setup, claude code parallel agents, getting started, multi-agent workflow",
+ "articleSection": "Guides",
+ "inLanguage": "en-US",
+ "url": "https://munderdiffl.in/blog/claude-code-multi-agent-setup-tutorial/"
+}
+</script>
+<script type="application/ld+json">
+{
+ "@context": "https://schema.org",
+ "@type": "BreadcrumbList",
+ "itemListElement": [
+ { "@type": "ListItem", "position": 1, "name": "Home", "item": "https://munderdiffl.in/" },
+ { "@type": "ListItem", "position": 2, "name": "Blog", "item": "https://munderdiffl.in/blog/" },
+ { "@type": "ListItem", "position": 3, "name": "Set Up a Claude Code Multi-Agent Workflow in 10 Minutes", "item": "https://munderdiffl.in/blog/claude-code-multi-agent-setup-tutorial/" }
+ ]
+}
+</script>
+
+<script type="application/ld+json">
+{
+ "@context": "https://schema.org",
+ "@type": "FAQPage",
+ "mainEntity": [
+ { "@type": "Question", "name": "Do I need anything besides Claude Code to set up a multi-agent workflow?", "acceptedAnswer": { "@type": "Answer", "text": "You need Claude Code installed and on your PATH, plus the Munder Difflin app. The harness spawns real `claude` sessions for you, so your existing Claude plan, MCP servers, and skills come along automatically." } },
+ { "@type": "Question", "name": "How many Claude Code agents can I run at once?", "acceptedAnswer": { "@type": "Answer", "text": "Start with two or three so you can follow the work, then add more. Each agent is a real terminal process, so the practical limit is your machine's RAM and your Claude rate limits — not the harness." } },
+ { "@type": "Question", "name": "Is the multi-agent setup local or cloud?", "acceptedAnswer": { "@type": "Answer", "text": "Local. The harness, the agents, and their shared memory all run on your own machine — nothing is sent to a coordination server in the cloud." } }
+
+ ]
+}
+</script>
+
+
+</head>
+<body>
+<a class="skip-link" href="#main">Skip to content</a>
+<nav id="nav">
+ <a class="brand" href="/blog/" aria-label="Munder Difflin Blog home">
+ <span class="brand-mark">MD</span>
+ <span class="brand-word">MUNDER DIFFLIN<span class="sep">/</span><span class="blog">BLOG</span></span>
+ </a>
+ <span class="spacer"></span>
+ <div class="links">
+ <a href="/blog/">Latest</a>
+ <a href="/blog/topics/">Topics</a>
+ <a href="/blog/about/">About</a>
+ <a href="https://munderdiffl.in">↗ Product</a>
+ </div>
+ <div class="nav-actions">
+ <a class="btn sm" href="https://munderdiffl.in/blog/feed.xml" aria-label="RSS feed">⤵ RSS</a>
+ <a class="btn sm primary" href="https://munderdiffl.in/#install">⤓ Download</a>
+ </div>
+</nav>
+
+<main id="main">
+
+<article>
+ <header class="post-head wrap">
+ <nav class="crumbs" aria-label="Breadcrumb">
+ <a href="/blog/">Blog</a>
+ <span>/</span>
+ <a href="/blog/topics/guides/">Guides</a>
+ </nav>
+ <h1>Set Up a Claude Code Multi-Agent Workflow in 10 Minutes</h1>
+ <p class="dek">A from-zero Claude Code multi-agent setup: install Munder Difflin, onboard, spawn a few agents, and watch the GOD orchestrator route your first task.</p>
+ <div class="byline">
+ <span class="av" aria-hidden="true">CG</span>
+ <strong>Chaitanya Giri</strong>
+ <span class="dot" aria-hidden="true">·</span>
+ <time datetime="2026-05-24">May 24, 2026</time>
+ <span class="dot" aria-hidden="true">·</span>
+ <span>5 min read</span>
+ <span class="tag kind">Guides</span>
+ </div>
+ </header>
+
+ <div class="post-wrap wrap">
+ <div class="prose">
+ <div class="callout tldr"><span class="ic">TL;DR</span><p>A working
+<strong>Claude Code multi-agent setup</strong> takes about ten minutes: install Munder Difflin,
+point onboarding at a repo, let it auto-spawn a <strong>GOD orchestrator</strong>, add a couple of
+worker agents, and describe one task in plain language. The harness handles identity, messaging,
+memory, and git so the agents act like a team instead of a pile of terminal tabs.</p></div>
+<p>You can run several Claude Code sessions by hand, but the coordination — who does what, who knows
+what, who’s allowed to commit — is the part that eats your afternoon. This guide gets you from zero
+to a coordinated team in about ten minutes, using <a href="https://munderdiffl.in/#install">Munder Difflin</a>
+as the harness that does the wiring.</p>
+<h2 id="before-you-start-2-minutes" tabindex="-1">Before you start (2 minutes) <a class="anchor" href="#before-you-start-2-minutes" aria-hidden="true">#</a></h2>
+<p>You need two things:</p>
+<ol>
+<li><strong>Claude Code</strong>, installed and runnable as <code>claude</code> in your terminal. Munder Difflin resolves the
+binary against your interactive shell’s <code>PATH</code> (and common install spots like
+<code>~/.claude/local/</code>), so if <code>claude</code> works in a normal terminal, the harness will find it.</li>
+<li><strong>The Munder Difflin app</strong> — <a href="https://munderdiffl.in/#install">download it</a> for macOS, Windows,
+or Linux. It’s free and open source.</li>
+</ol>
+<p>That’s the whole prerequisite list. You don’t install a framework, a database, or a server. Every
+agent the harness spawns is a <em>real</em> <code>claude</code> process, so your existing Claude plan and rate limits
+are exactly what you already have.</p>
+<h2 id="step-1-finish-onboarding-2-minutes" tabindex="-1">Step 1 — Finish onboarding (2 minutes) <a class="anchor" href="#step-1-finish-onboarding-2-minutes" aria-hidden="true">#</a></h2>
+<p>On first launch the app runs a short onboarding wizard. Two choices matter:</p>
+<ul>
+<li><strong>Pick a folder.</strong> This is the working directory your agents operate in — usually a code repo. The
+harness checks that it exists before spawning anything, so point it at a real project.</li>
+<li><strong>Auto mode.</strong> When auto mode is on, new agents are launched with
+<code>--permission-mode bypassPermissions</code> so they don’t stop to ask you to approve every file write.
+It’s the right default for a watch-it-work demo; turn it off if you want to confirm each action.
+(You can read the exact spawn command the wizard will use right in the dialog.)</li>
+</ul>
+<p>Onboarding also sets a <strong>harness home</strong> — a folder where the harness keeps its own state: the hive
+git repo, each agent’s memory, and the shared semantic memory palace. You never edit it by hand; it’s
+just where coordination lives.</p>
+<h2 id="step-2-meet-the-god-orchestrator-1-minute" tabindex="-1">Step 2 — Meet the GOD orchestrator (1 minute) <a class="anchor" href="#step-2-meet-the-god-orchestrator-1-minute" aria-hidden="true">#</a></h2>
+<p>When the hive comes up, one agent is already there: the <strong>GOD orchestrator</strong>, seated in the corner
+office. It’s an ordinary <code>claude</code> process with one extra job — it runs the floor. You talk to <em>it</em> in
+plain language, and it routes work to the other agents, answers their clarifying questions, and only
+interrupts you for genuinely critical calls (spending real money, destructive operations, scope
+changes).</p>
+<p>If you want the full mental model of what the orchestrator does under the hood, see
+<a href="/blog/how-the-god-orchestrator-works/">inside the GOD orchestrator</a>. For now, just know: it’s the
+one agent you address, and it manages the rest.</p>
+<h2 id="step-3-spawn-a-couple-of-worker-agents-2-minutes" tabindex="-1">Step 3 — Spawn a couple of worker agents (2 minutes) <a class="anchor" href="#step-3-spawn-a-couple-of-worker-agents-2-minutes" aria-hidden="true">#</a></h2>
+<p>Add two or three agents and give each a <strong>role</strong> — a name and a short description of its job:</p>
+<ul>
+<li><code>test-writer</code> — writes and runs tests</li>
+<li><code>refactorer</code> — cleans up code without changing behavior</li>
+<li><code>docs</code> — keeps the README and comments in sync</li>
+</ul>
+<p>Roles aren’t cosmetic. When the harness spawns each agent, it injects an identity and the hive
+protocol into the session’s system prompt, plus environment variables (<code>AGENT_ID</code>, <code>AGENT_NAME</code>,
+<code>HIVE_ROOT</code>, <code>AGENT_DIR</code>). The agent reads its own <code>memory.md</code> and inbox at the start of every task
+and writes durable facts back as it learns. A clear role keeps each agent in its lane and makes “who
+should handle this?” obvious to the orchestrator.</p>
+<p>Start small. Two or three agents is enough to <em>see</em> coordination happening without losing the thread.
+For the habits that keep a bigger team legible, read
+<a href="/blog/manage-multiple-claude-code-sessions/">how to manage multiple Claude Code sessions</a>.</p>
+<h2 id="step-4-describe-one-task-and-watch-it-route-3-minutes" tabindex="-1">Step 4 — Describe one task and watch it route (3 minutes) <a class="anchor" href="#step-4-describe-one-task-and-watch-it-route-3-minutes" aria-hidden="true">#</a></h2>
+<p>Now the payoff. Don’t hand-assign work — describe intent once to the orchestrator, for example:</p>
+<blockquote>
+<p>“Add input validation to the signup form, write tests for it, and update the docs.”</p>
+</blockquote>
+<p>Here’s what happens, and what you’ll see on the floor:</p>
+<ol>
+<li>The orchestrator decomposes the request and <strong>routes</strong> sub-tasks to the right agents — validation
+to one, tests to <code>test-writer</code>, docs to <code>docs</code>.</li>
+<li>Each agent works in its own session. When one needs something from another, it <strong>sends a message</strong>
+(the harness delivers it; agents never write into each other’s folders).</li>
+<li>Avatars move around the office as the work happens — a real-time view driven by the agents’
+actual tool calls, not a simulation. Envelopes fly desk-to-desk when messages route.</li>
+<li>The harness <strong>commits</strong> the coordination state to its own git repo as it goes, so there’s an
+audit trail of who said what.</li>
+</ol>
+<p>You’ve gone from a blank app to a coordinated team acting on one sentence. That’s the setup.</p>
+<h2 id="what-you-just-avoided" tabindex="-1">What you just avoided <a class="anchor" href="#what-you-just-avoided" aria-hidden="true">#</a></h2>
+<p>Doing this by hand means you become the message bus: copy-pasting findings between windows, manually
+deciding who edits which file, and resolving <code>index.lock</code> errors when two agents commit at once. The
+harness removes all three — roles, messaging, and a single-committer git design — which is the
+difference between “several Claude Code sessions” and a
+<a href="/blog/how-to-run-multiple-claude-code-agents/">multi-agent workflow</a> that actually saves you time.</p>
+<h2 id="faq" tabindex="-1">FAQ <a class="anchor" href="#faq" aria-hidden="true">#</a></h2>
+<p><strong>Do I need to configure MCP servers or skills separately for each agent?</strong> No. Because each agent is
+a real <code>claude</code> session in your project directory, it inherits the MCP servers and skills you already
+use. The harness adds coordination on top without touching that config.</p>
+<p><strong>What if <code>mempalace</code> (semantic memory) isn’t installed?</strong> Everything still works. Memory degrades
+gracefully to plain markdown files; the semantic recall layer is an optional upgrade.</p>
+<h2 id="next-steps" tabindex="-1">Next steps <a class="anchor" href="#next-steps" aria-hidden="true">#</a></h2>
+<ul>
+<li><a href="/blog/how-to-run-multiple-claude-code-agents/">How to run multiple Claude Code agents</a> — the
+habits behind a healthy multi-agent workflow.</li>
+<li><a href="/blog/manage-multiple-claude-code-sessions/">How to manage multiple Claude Code sessions</a> — naming,
+roles, and context isolation as you scale up.</li>
+</ul>
+<hr>
+<p>Ready to try it? <a href="https://munderdiffl.in/#install">Download Munder Difflin</a> and run your first
+coordinated team of Claude Code agents — it’s free, local, and open source.</p>
+
+
+
+ <section class="faq" aria-label="Frequently asked questions">
+ <h2 id="faq">FAQ</h2>
+
+ <div class="qa">
+ <p class="q">Do I need anything besides Claude Code to set up a multi-agent workflow?</p>
+ <p class="a">You need Claude Code installed and on your PATH, plus the Munder Difflin app. The harness spawns real `claude` sessions for you, so your existing Claude plan, MCP servers, and skills come along automatically.</p>
+ </div>
+
+ <div class="qa">
+ <p class="q">How many Claude Code agents can I run at once?</p>
+ <p class="a">Start with two or three so you can follow the work, then add more. Each agent is a real terminal process, so the practical limit is your machine&#39;s RAM and your Claude rate limits — not the harness.</p>
+ </div>
+
+ <div class="qa">
+ <p class="q">Is the multi-agent setup local or cloud?</p>
+ <p class="a">Local. The harness, the agents, and their shared memory all run on your own machine — nothing is sent to a coordination server in the cloud.</p>
+ </div>
+
+ </section>
+
+
+
+ <hr />
+ <div class="share">
+ <span class="lbl">Tags</span>
+ <a class="tag" href="/blog/tags/getting-started/">Getting Started</a><a class="tag" href="/blog/tags/guides/">Guides</a><a class="tag" href="/blog/tags/multi-agent/">Multi-Agent</a><a class="tag" href="/blog/tags/claude-code/">Claude Code</a>
+ </div>
+
+ </div>
+
+
+ <aside class="toc-rail" aria-label="Table of contents">
+ <div class="tt">On this page</div>
+ <ol>
+ <li class="lvl-2"><a href="#before-you-start-2-minutes">Before you start (2 minutes)</a></li><li class="lvl-2"><a href="#step-1-finish-onboarding-2-minutes">Step 1 — Finish onboarding (2 minutes)</a></li><li class="lvl-2"><a href="#step-2-meet-the-god-orchestrator-1-minute">Step 2 — Meet the GOD orchestrator (1 minute)</a></li><li class="lvl-2"><a href="#step-3-spawn-a-couple-of-worker-agents-2-minutes">Step 3 — Spawn a couple of worker agents (2 minutes)</a></li><li class="lvl-2"><a href="#step-4-describe-one-task-and-watch-it-route-3-minutes">Step 4 — Describe one task and watch it route (3 minutes)</a></li><li class="lvl-2"><a href="#what-you-just-avoided">What you just avoided</a></li><li class="lvl-2"><a href="#faq">FAQ</a></li><li class="lvl-2"><a href="#next-steps">Next steps</a></li>
+ </ol>
+ </aside>
+
+ </div>
+
+ <footer class="post-foot wrap"><div class="prevnext">
+ <a class="pn prev" href="/blog/claude-code-subagents-vs-multi-agent-harness/"><span class="k">← Older</span><span class="t">Claude Code Subagents vs a Multi-Agent Harness</span></a>
+ <a class="pn next" href="/blog/manage-multiple-claude-code-sessions/"><span class="k">Newer →</span><span class="t">How to Manage Multiple Claude Code Sessions Like a Pro</span></a>
+ </div>
+ <section class="related">
+ <h2>Related in Guides</h2>
+ <div class="post-grid">
+ <article class="card">
+ <a class="thumb t-guides" href="/blog/claude-code-automation-while-you-sleep/" aria-hidden="true" tabindex="-1">
+ <span>GUIDES</span>
+ </a>
+ <div class="body">
+ <div class="meta">
+ <time datetime="2026-06-04">Jun 4, 2026</time>
+ <span class="dot" aria-hidden="true"></span>
+ <span>5 min</span>
+ </div>
+ <h3><a href="/blog/claude-code-automation-while-you-sleep/">Claude Code Automation: Let Agents Build While You Sleep</a></h3>
+ <p class="dek">Claude Code automation that runs overnight: an autonomous Stop-hook loop, safe permission bypass, and guardrails so you wake up to progress, not chaos.</p>
+ <div class="foot">
+ <span class="tag kind">Guides</span>
+ <a class="more" href="/blog/claude-code-automation-while-you-sleep/" aria-label="Read: Claude Code Automation: Let Agents Build While You Sleep">Read →</a>
+ </div>
+ </div>
+</article>
+<article class="card">
+ <a class="thumb t-guides" href="/blog/mcp-and-skills-in-a-hive/" aria-hidden="true" tabindex="-1">
+ <span>GUIDES</span>
+ </a>
+ <div class="body">
+ <div class="meta">
+ <time datetime="2026-06-03">Jun 3, 2026</time>
+ <span class="dot" aria-hidden="true"></span>
+ <span>6 min</span>
+ </div>
+ <h3><a href="/blog/mcp-and-skills-in-a-hive/">Bringing Your MCP Servers and Skills Into a Hive of Agents</a></h3>
+ <p class="dek">How agents in a hive inherit your existing Claude Code MCP servers, skills, and tools — and how to scope which agent gets which capability.</p>
+ <div class="foot">
+ <span class="tag kind">Guides</span>
+ <a class="more" href="/blog/mcp-and-skills-in-a-hive/" aria-label="Read: Bringing Your MCP Servers and Skills Into a Hive of Agents">Read →</a>
+ </div>
+ </div>
+</article>
+<article class="card">
+ <a class="thumb t-guides" href="/blog/how-to-run-multiple-claude-code-agents/" aria-hidden="true" tabindex="-1">
+ <span>GUIDES</span>
+ </a>
+ <div class="body">
+ <div class="meta">
+ <time datetime="2026-06-01">Jun 1, 2026</time>
+ <span class="dot" aria-hidden="true"></span>
+ <span>3 min</span>
+ </div>
+ <h3><a href="/blog/how-to-run-multiple-claude-code-agents/">How to Run Multiple Claude Code Agents (Without Losing Track)</a></h3>
+ <p class="dek">Run several Claude Code agents in parallel without the chaos: give each a role, let them coordinate, and stop alt-tabbing between terminal windows.</p>
+ <div class="foot">
+ <span class="tag kind">Guides</span>
+ <a class="more" href="/blog/how-to-run-multiple-claude-code-agents/" aria-label="Read: How to Run Multiple Claude Code Agents (Without Losing Track)">Read →</a>
+ </div>
+ </div>
+</article>
+
+ </div>
+ </section>
+
+ </footer>
+</article>
+
+</main>
+<footer>
+ <div class="wrap">
+ <div class="foot-top">
+ <a class="foot-brand brand" href="/blog/">
+ <span class="brand-mark">MD</span>
+ <span class="brand-word">MUNDER DIFFLIN<span class="sep">/</span><span class="blog">BLOG</span></span>
+ </a>
+ <div class="foot-links">
+ <a href="/blog/">Latest</a>
+ <a href="/blog/topics/">Topics</a>
+ <a href="/blog/about/">About</a>
+ <a href="https://munderdiffl.in/blog/feed.xml">RSS</a>
+ <a href="https://github.com/chaitanyagiri/munder-difflin">GitHub</a>
+ <a href="https://munderdiffl.in">munderdiffl.in ↗</a>
+ </div>
+ </div>
+ <div class="foot-meta">
+ © 2026 Munder Difflin · Local-first · MIT-licensed ·
+ Built on <a href="https://munderdiffl.in">Electron, React, Pixi.js, xterm.js &amp; node-pty</a>.
+ Run an office of agents while you sleep.
+ </div>
+ </div>
+</footer>
+
+<script>
+ // sticky-nav border on scroll
+ (function () {
+ var nav = document.getElementById('nav');
+ if (!nav) return;
+ var onScroll = function () { nav.classList.toggle('scrolled', window.scrollY > 8); };
+ onScroll(); window.addEventListener('scroll', onScroll, { passive: true });
+ })();
+</script>
+
+</body>
+</html>
diff --git a/docs/blog/claude-code-orchestration-guide/index.html b/docs/blog/claude-code-orchestration-guide/index.html
new file mode 100644
index 00000000..12e8a353
--- /dev/null
+++ b/docs/blog/claude-code-orchestration-guide/index.html
@@ -0,0 +1,388 @@
+<!doctype html>
+<html lang="en">
+<head>
+<meta charset="UTF-8" />
+<meta name="viewport" content="width=device-width, initial-scale=1.0" />
+<title>Orchestrating Claude Code Agents: A Practical Guide — Munder Difflin Blog</title>
+<meta name="description" content="How to orchestrate Claude Code agents in practice: what orchestration means, how a GOD orchestrator routes and escalates work, and how to wire it up." />
+<link rel="canonical" href="https://munderdiffl.in/blog/claude-code-orchestration-guide/" />
+
+<link rel="icon" type="image/png" href="https://munderdiffl.in/logo.png" />
+<link rel="apple-touch-icon" href="https://munderdiffl.in/logo.png" />
+<meta name="theme-color" content="#F5F2E8" />
+
+<!-- Open Graph -->
+<meta property="og:site_name" content="Munder Difflin Blog" />
+<meta property="og:type" content="article" />
+<meta property="og:title" content="Orchestrating Claude Code Agents: A Practical Guide — Munder Difflin Blog" />
+<meta property="og:description" content="How to orchestrate Claude Code agents in practice: what orchestration means, how a GOD orchestrator routes and escalates work, and how to wire it up." />
+<meta property="og:url" content="https://munderdiffl.in/blog/claude-code-orchestration-guide/" />
+<meta property="og:image" content="https://munderdiffl.in/media/og.png" />
+<meta property="og:locale" content="en_US" />
+<meta property="article:published_time" content="2026-05-28T00:00:00.000Z" />
+<meta property="article:author" content="Chaitanya Giri" />
+<meta property="article:tag" content="Orchestration" />
+<meta property="article:tag" content="Multi-Agent" />
+<meta property="article:tag" content="Claude Code" />
+<meta property="article:tag" content="GOD" />
+
+
+<!-- Twitter -->
+<meta name="twitter:card" content="summary_large_image" />
+<meta name="twitter:title" content="Orchestrating Claude Code Agents: A Practical Guide — Munder Difflin Blog" />
+<meta name="twitter:description" content="How to orchestrate Claude Code agents in practice: what orchestration means, how a GOD orchestrator routes and escalates work, and how to wire it up." />
+<meta name="twitter:image" content="https://munderdiffl.in/media/og.png" />
+
+<link rel="alternate" type="application/atom+xml" title="Munder Difflin Blog" href="https://munderdiffl.in/blog/feed.xml" />
+<link rel="preconnect" href="https://fonts.googleapis.com" />
+<link rel="preconnect" href="https://fonts.gstatic.com" crossorigin />
+<link href="https://fonts.googleapis.com/css2?family=Geist:wght@400;500;600&family=JetBrains+Mono:wght@400;500;600;700&display=swap" rel="stylesheet" />
+<link rel="stylesheet" href="/blog/assets/blog.css" />
+
+<script type="application/ld+json">
+{
+ "@context": "https://schema.org",
+ "@type": "BlogPosting",
+ "headline": "Orchestrating Claude Code Agents: A Practical Guide",
+ "description": "How to orchestrate Claude Code agents in practice: what orchestration means, how a GOD orchestrator routes and escalates work, and how to wire it up.",
+ "image": ["https://munderdiffl.in/media/og.png"],
+ "datePublished": "2026-05-28T00:00:00.000Z",
+ "dateModified": "2026-05-28T00:00:00.000Z",
+ "author": { "@type": "Person", "name": "Chaitanya Giri" },
+ "publisher": {
+ "@type": "Organization",
+ "name": "Munder Difflin",
+ "logo": { "@type": "ImageObject", "url": "https://munderdiffl.in/logo.png" }
+ },
+ "mainEntityOfPage": { "@type": "WebPage", "@id": "https://munderdiffl.in/blog/claude-code-orchestration-guide/" },
+ "keywords": "how to orchestrate claude code agents, claude code orchestration, claude code orchestrator, ai agent orchestration",
+ "articleSection": "Orchestration",
+ "inLanguage": "en-US",
+ "url": "https://munderdiffl.in/blog/claude-code-orchestration-guide/"
+}
+</script>
+<script type="application/ld+json">
+{
+ "@context": "https://schema.org",
+ "@type": "BreadcrumbList",
+ "itemListElement": [
+ { "@type": "ListItem", "position": 1, "name": "Home", "item": "https://munderdiffl.in/" },
+ { "@type": "ListItem", "position": 2, "name": "Blog", "item": "https://munderdiffl.in/blog/" },
+ { "@type": "ListItem", "position": 3, "name": "Orchestrating Claude Code Agents: A Practical Guide", "item": "https://munderdiffl.in/blog/claude-code-orchestration-guide/" }
+ ]
+}
+</script>
+
+<script type="application/ld+json">
+{
+ "@context": "https://schema.org",
+ "@type": "FAQPage",
+ "mainEntity": [
+ { "@type": "Question", "name": "What does it mean to orchestrate Claude Code agents?", "acceptedAnswer": { "@type": "Answer", "text": "Orchestration is the layer that decides which agent does what: it reads your intent, decomposes it into tasks, routes each to the right agent, resolves routine questions between agents, and escalates only the decisions that genuinely need a human." } },
+ { "@type": "Question", "name": "Do I write the orchestration logic myself?", "acceptedAnswer": { "@type": "Answer", "text": "You can, but you don't have to. In Munder Difflin the orchestrator is itself a Claude agent — the GOD agent — so the routing intelligence is a prompt you tune, not code you maintain. The harness provides the mechanism (messaging, git, escalation queue); the agent provides the judgment." } },
+ { "@type": "Question", "name": "How is an orchestrator different from a task queue?", "acceptedAnswer": { "@type": "Answer", "text": "A queue hands out work in order; it doesn't reason about it. An orchestrator reads each request, decides who's best suited, writes a self-contained task spec, and adapts when an agent gets blocked or two agents conflict." } }
+
+ ]
+}
+</script>
+
+
+</head>
+<body>
+<a class="skip-link" href="#main">Skip to content</a>
+<nav id="nav">
+ <a class="brand" href="/blog/" aria-label="Munder Difflin Blog home">
+ <span class="brand-mark">MD</span>
+ <span class="brand-word">MUNDER DIFFLIN<span class="sep">/</span><span class="blog">BLOG</span></span>
+ </a>
+ <span class="spacer"></span>
+ <div class="links">
+ <a href="/blog/">Latest</a>
+ <a href="/blog/topics/">Topics</a>
+ <a href="/blog/about/">About</a>
+ <a href="https://munderdiffl.in">↗ Product</a>
+ </div>
+ <div class="nav-actions">
+ <a class="btn sm" href="https://munderdiffl.in/blog/feed.xml" aria-label="RSS feed">⤵ RSS</a>
+ <a class="btn sm primary" href="https://munderdiffl.in/#install">⤓ Download</a>
+ </div>
+</nav>
+
+<main id="main">
+
+<article>
+ <header class="post-head wrap">
+ <nav class="crumbs" aria-label="Breadcrumb">
+ <a href="/blog/">Blog</a>
+ <span>/</span>
+ <a href="/blog/topics/orchestration/">Orchestration</a>
+ </nav>
+ <h1>Orchestrating Claude Code Agents: A Practical Guide</h1>
+ <p class="dek">How to orchestrate Claude Code agents in practice: what orchestration means, how a GOD orchestrator routes and escalates work, and how to wire it up.</p>
+ <div class="byline">
+ <span class="av" aria-hidden="true">CG</span>
+ <strong>Chaitanya Giri</strong>
+ <span class="dot" aria-hidden="true">·</span>
+ <time datetime="2026-05-28">May 28, 2026</time>
+ <span class="dot" aria-hidden="true">·</span>
+ <span>5 min read</span>
+ <span class="tag kind">Orchestration</span>
+ </div>
+ </header>
+
+ <div class="post-wrap wrap">
+ <div class="prose">
+ <div class="callout tldr"><span class="ic">TL;DR</span><p><strong>Orchestration</strong> is the layer
+that turns "a few Claude Code agents" into "a team that finishes a goal." It reads your intent,
+<strong>decomposes</strong> it, <strong>routes</strong> each piece to the right agent, <strong>adjudicates</strong>
+the routine back-and-forth between agents, and <strong>escalates</strong> only the critical calls to
+you. In Munder Difflin that role is played by a GOD orchestrator — a Claude agent whose only job is to
+run the floor.</p></div>
+<p>Most “multi-agent” setups are really just multiple agents — several sessions running side by side
+with you in the middle, deciding who does what. The thing that makes them a <em>team</em> is orchestration.
+This guide explains what orchestration actually does for coding agents, and how to wire it so it runs
+without you in the loop for every decision.</p>
+<h2 id="what-orchestration-means-for-coding-agents" tabindex="-1">What “orchestration” means for coding agents <a class="anchor" href="#what-orchestration-means-for-coding-agents" aria-hidden="true">#</a></h2>
+<p>Strip away the buzzword and orchestration is five concrete jobs:</p>
+<ol>
+<li><strong>Read intent.</strong> Take a plain-language goal (“ship input validation with tests and docs”) instead
+of pre-chopped tasks.</li>
+<li><strong>Decompose.</strong> Break the goal into units small enough for one agent to own.</li>
+<li><strong>Route.</strong> Assign each unit to the agent best suited for it, with a self-contained task spec so the
+agent doesn’t have to ask what you meant.</li>
+<li><strong>Adjudicate.</strong> Handle the questions agents raise <em>for each other</em> — clarifications, data asks,
+small plan changes — so the team keeps moving without bouncing everything back to you.</li>
+<li><strong>Escalate.</strong> Recognize the few decisions that genuinely need a human (spending money, destructive
+operations, scope changes, conflicts nobody can resolve) and stop there.</li>
+</ol>
+<p>A task queue does #3 and nothing else. Orchestration is the other four — the <em>judgment</em> — which is
+why, in a well-designed harness, the orchestrator is itself an intelligent agent rather than a switch
+statement.</p>
+<h2 id="the-mechanism-vs-the-intelligence" tabindex="-1">The mechanism vs. the intelligence <a class="anchor" href="#the-mechanism-vs-the-intelligence" aria-hidden="true">#</a></h2>
+<p>The cleanest way to build this is to split it in two:</p>
+<ul>
+<li><strong>The mechanism</strong> is plumbing: deliver messages, commit state, hold a queue of items waiting on a
+human. It has no opinions. It must be reliable, not smart.</li>
+<li><strong>The intelligence</strong> is an agent — the orchestrator — that reads requests and decides. It must be
+smart, and it’s allowed to be imperfect, because the mechanism keeps the system safe.</li>
+</ul>
+<p>In Munder Difflin the mechanism is the harness’s main process (it runs git, the message router, and
+the approvals queue) and the intelligence is the <strong>GOD agent</strong> — an ordinary <code>claude</code> process flagged
+as the orchestrator, seated in the corner office. Because the orchestrator is a prompt, not a
+codebase, you tune <em>how</em> it routes and <em>what</em> it considers critical by editing its instructions, not
+by redeploying. That’s the practical heart of
+<a href="/blog/how-the-god-orchestrator-works/">how the GOD orchestrator works</a>.</p>
+<h2 id="how-a-request-flows-through-the-orchestrator" tabindex="-1">How a request flows through the orchestrator <a class="anchor" href="#how-a-request-flows-through-the-orchestrator" aria-hidden="true">#</a></h2>
+<p>Here’s the path a single instruction takes, end to end:</p>
+<h3 id="1-you-describe-a-goal-to-the-orchestrator" tabindex="-1">1. You describe a goal to the orchestrator <a class="anchor" href="#1-you-describe-a-goal-to-the-orchestrator" aria-hidden="true">#</a></h3>
+<p>You talk to one agent — the orchestrator — in plain language. You don’t address the workers directly
+and you don’t pre-assign tasks. This is the whole ergonomic win: one conversation instead of N.</p>
+<h3 id="2-it-decomposes-and-routes" tabindex="-1">2. It decomposes and routes <a class="anchor" href="#2-it-decomposes-and-routes" aria-hidden="true">#</a></h3>
+<p>The orchestrator reads its roster (who exists, their roles and capabilities) and assigns each piece of
+work, writing a task spec that’s self-contained enough for the receiving agent to act without a
+follow-up. Routing to the <em>right</em> agent is where roles earn their keep — a <code>test-writer</code> gets the
+tests, not the migration.</p>
+<h3 id="3-agents-work-and-message-each-other" tabindex="-1">3. Agents work, and message each other <a class="anchor" href="#3-agents-work-and-message-each-other" aria-hidden="true">#</a></h3>
+<p>Each worker is its own session with isolated context. When one needs something from another, it sends
+a message rather than going through you. Crucially, agents never write into each other’s files — they
+drop a message in their own outbox and the harness delivers it. That single-writer discipline is what
+keeps the whole thing from corrupting itself; the mechanics are in
+<a href="/blog/atomic-file-mailboxes-for-agents/">atomic file mailboxes</a>.</p>
+<h3 id="4-the-orchestrator-adjudicates-the-routine-stuff" tabindex="-1">4. The orchestrator adjudicates the routine stuff <a class="anchor" href="#4-the-orchestrator-adjudicates-the-routine-stuff" aria-hidden="true">#</a></h3>
+<p>Most inter-agent traffic is mundane: “which schema do I validate against?” “is the staging URL still
+X?” The orchestrator answers these itself and keeps the floor autonomous. Anti-loop rules matter
+here — only requests, queries, and proposals obligate a reply, and a hop counter caps how long any
+exchange can ping-pong before the orchestrator steps in. Without those rules, two polite agents will
+thank each other forever.</p>
+<h3 id="5-it-escalates-only-the-critical-few" tabindex="-1">5. It escalates only the critical few <a class="anchor" href="#5-it-escalates-only-the-critical-few" aria-hidden="true">#</a></h3>
+<p>When something crosses a line — real spend, a destructive operation, a scope change, a conflict it
+can’t resolve — the orchestrator escalates to <em>you</em> instead of deciding. That item lands in a
+human-approval queue; your answer (with an optional note like “yes, but cap it at $5”) is relayed back
+to the agent that asked. Everything else stays autonomous. This selective escalation is the difference
+between an agent team that needs constant supervision and one that only taps you on the shoulder when
+it should.</p>
+<h2 id="designing-good-orchestration" tabindex="-1">Designing good orchestration <a class="anchor" href="#designing-good-orchestration" aria-hidden="true">#</a></h2>
+<p>If you’re building or tuning an orchestrator, a few principles separate the ones that work from the
+ones that thrash:</p>
+<ul>
+<li><strong>Make the escalation policy explicit.</strong> “Critical” should be a written list (spend, destructive
+ops, scope, unresolvable conflict), not a vibe. It’s the single most important control surface —
+too loose and the team does scary things; too tight and you become the bottleneck again.</li>
+<li><strong>Give the orchestrator a real roster.</strong> It can only route well if it knows who exists and what
+they’re good at. Roles and capabilities aren’t decoration; they’re the routing table.</li>
+<li><strong>Keep the orchestrator out of the work.</strong> Its job is to route and adjudicate, not to write the
+code itself. An orchestrator that starts doing the tasks is a bottleneck wearing a manager’s hat.</li>
+<li><strong>Make coordination auditable.</strong> Every routed message and every escalation should be logged, so
+when the team goes sideways you can replay what happened. For the broader patterns here, see
+<a href="/blog/coordinating-ai-coding-agents/">the best way to coordinate AI coding agents</a>.</li>
+</ul>
+<h2 id="when-you-actually-need-an-orchestrator" tabindex="-1">When you actually need an orchestrator <a class="anchor" href="#when-you-actually-need-an-orchestrator" aria-hidden="true">#</a></h2>
+<p>You don’t need orchestration for one agent, or even for two or three independent tasks you’re happy to
+assign by hand. You need it when:</p>
+<ul>
+<li>you’re describing the <em>same</em> context to multiple agents over and over,</li>
+<li>you find yourself relaying messages between agents, or</li>
+<li>you want to state a goal once and have the team figure out the division of labor.</li>
+</ul>
+<p>That’s the threshold where <a href="/blog/how-to-run-multiple-claude-code-agents/">running multiple Claude Code agents</a>
+turns from a chore into something that genuinely compounds.</p>
+<h2 id="faq" tabindex="-1">FAQ <a class="anchor" href="#faq" aria-hidden="true">#</a></h2>
+<p><strong>Can the orchestrator route to the wrong agent?</strong> Yes — it’s a model, so it can misjudge. The
+mechanism contains the damage: misrouted work still goes through messaging and the single-committer
+git layer, so a bad routing decision is recoverable, not corrupting. And because the policy is a
+prompt, you correct the pattern by editing instructions.</p>
+<p><strong>Does orchestration add latency?</strong> A little — there’s a routing hop before work starts. In exchange
+you stop being the router yourself, which is almost always the bigger time sink.</p>
+<hr>
+<p>Munder Difflin ships this orchestration model out of the box: a GOD agent you talk to, a reliable
+message router, and a human-approval queue for the critical few — all running locally.
+<a href="https://munderdiffl.in/#install">Download Munder Difflin</a> to orchestrate your own team of Claude Code
+agents; it’s free and open source.</p>
+
+
+
+ <section class="faq" aria-label="Frequently asked questions">
+ <h2 id="faq">FAQ</h2>
+
+ <div class="qa">
+ <p class="q">What does it mean to orchestrate Claude Code agents?</p>
+ <p class="a">Orchestration is the layer that decides which agent does what: it reads your intent, decomposes it into tasks, routes each to the right agent, resolves routine questions between agents, and escalates only the decisions that genuinely need a human.</p>
+ </div>
+
+ <div class="qa">
+ <p class="q">Do I write the orchestration logic myself?</p>
+ <p class="a">You can, but you don&#39;t have to. In Munder Difflin the orchestrator is itself a Claude agent — the GOD agent — so the routing intelligence is a prompt you tune, not code you maintain. The harness provides the mechanism (messaging, git, escalation queue); the agent provides the judgment.</p>
+ </div>
+
+ <div class="qa">
+ <p class="q">How is an orchestrator different from a task queue?</p>
+ <p class="a">A queue hands out work in order; it doesn&#39;t reason about it. An orchestrator reads each request, decides who&#39;s best suited, writes a self-contained task spec, and adapts when an agent gets blocked or two agents conflict.</p>
+ </div>
+
+ </section>
+
+
+
+ <hr />
+ <div class="share">
+ <span class="lbl">Tags</span>
+ <a class="tag" href="/blog/tags/orchestration/">Orchestration</a><a class="tag" href="/blog/tags/multi-agent/">Multi-Agent</a><a class="tag" href="/blog/tags/claude-code/">Claude Code</a><a class="tag" href="/blog/tags/god/">GOD</a>
+ </div>
+
+ </div>
+
+
+ <aside class="toc-rail" aria-label="Table of contents">
+ <div class="tt">On this page</div>
+ <ol>
+ <li class="lvl-2"><a href="#what-orchestration-means-for-coding-agents">What “orchestration” means for coding agents</a></li><li class="lvl-2"><a href="#the-mechanism-vs-the-intelligence">The mechanism vs. the intelligence</a></li><li class="lvl-2"><a href="#how-a-request-flows-through-the-orchestrator">How a request flows through the orchestrator</a></li><li class="lvl-3"><a href="#1-you-describe-a-goal-to-the-orchestrator">1. You describe a goal to the orchestrator</a></li><li class="lvl-3"><a href="#2-it-decomposes-and-routes">2. It decomposes and routes</a></li><li class="lvl-3"><a href="#3-agents-work-and-message-each-other">3. Agents work, and message each other</a></li><li class="lvl-3"><a href="#4-the-orchestrator-adjudicates-the-routine-stuff">4. The orchestrator adjudicates the routine stuff</a></li><li class="lvl-3"><a href="#5-it-escalates-only-the-critical-few">5. It escalates only the critical few</a></li><li class="lvl-2"><a href="#designing-good-orchestration">Designing good orchestration</a></li><li class="lvl-2"><a href="#when-you-actually-need-an-orchestrator">When you actually need an orchestrator</a></li><li class="lvl-2"><a href="#faq">FAQ</a></li>
+ </ol>
+ </aside>
+
+ </div>
+
+ <footer class="post-foot wrap"><div class="prevnext">
+ <a class="pn prev" href="/blog/give-claude-code-long-term-memory/"><span class="k">← Older</span><span class="t">How to Give Claude Code Long-Term Memory</span></a>
+ <a class="pn next" href="/blog/coordinating-ai-coding-agents/"><span class="k">Newer →</span><span class="t">The Best Way to Coordinate AI Coding Agents</span></a>
+ </div>
+ <section class="related">
+ <h2>Related in Orchestration</h2>
+ <div class="post-grid">
+ <article class="card">
+ <a class="thumb t-orchestration" href="/blog/claude-code-git-worktrees-vs-hive/" aria-hidden="true" tabindex="-1">
+ <span>ORCHESTRATION</span>
+ </a>
+ <div class="body">
+ <div class="meta">
+ <time datetime="2026-06-04">Jun 4, 2026</time>
+ <span class="dot" aria-hidden="true"></span>
+ <span>5 min</span>
+ </div>
+ <h3><a href="/blog/claude-code-git-worktrees-vs-hive/">Git Worktrees vs a Hive: Two Ways to Parallelize Claude Code</a></h3>
+ <p class="dek">Claude Code git worktrees vs a hive: when isolated worktrees suffice for parallel agents, and when you need memory, messaging, and an orchestrator on top.</p>
+ <div class="foot">
+ <span class="tag kind">Orchestration</span>
+ <a class="more" href="/blog/claude-code-git-worktrees-vs-hive/" aria-label="Read: Git Worktrees vs a Hive: Two Ways to Parallelize Claude Code">Read →</a>
+ </div>
+ </div>
+</article>
+<article class="card">
+ <a class="thumb t-orchestration" href="/blog/how-the-god-orchestrator-works/" aria-hidden="true" tabindex="-1">
+ <span>ORCHESTRATION</span>
+ </a>
+ <div class="body">
+ <div class="meta">
+ <time datetime="2026-05-30">May 30, 2026</time>
+ <span class="dot" aria-hidden="true"></span>
+ <span>6 min</span>
+ </div>
+ <h3><a href="/blog/how-the-god-orchestrator-works/">Inside the GOD Orchestrator: Routing, Adjudication, Escalation</a></h3>
+ <p class="dek">A deep dive into the Claude Code orchestrator: how a GOD agent reads requests, routes work, adjudicates routine traffic, and escalates the critical few.</p>
+ <div class="foot">
+ <span class="tag kind">Orchestration</span>
+ <a class="more" href="/blog/how-the-god-orchestrator-works/" aria-label="Read: Inside the GOD Orchestrator: Routing, Adjudication, Escalation">Read →</a>
+ </div>
+ </div>
+</article>
+<article class="card">
+ <a class="thumb t-orchestration" href="/blog/coordinating-ai-coding-agents/" aria-hidden="true" tabindex="-1">
+ <span>ORCHESTRATION</span>
+ </a>
+ <div class="body">
+ <div class="meta">
+ <time datetime="2026-05-29">May 29, 2026</time>
+ <span class="dot" aria-hidden="true"></span>
+ <span>5 min</span>
+ </div>
+ <h3><a href="/blog/coordinating-ai-coding-agents/">The Best Way to Coordinate AI Coding Agents</a></h3>
+ <p class="dek">The best way to coordinate AI coding agents: single-writer files, a message router, a one-scribe plan, and an orchestrator — cooperate, not clobber.</p>
+ <div class="foot">
+ <span class="tag kind">Orchestration</span>
+ <a class="more" href="/blog/coordinating-ai-coding-agents/" aria-label="Read: The Best Way to Coordinate AI Coding Agents">Read →</a>
+ </div>
+ </div>
+</article>
+
+ </div>
+ </section>
+
+ </footer>
+</article>
+
+</main>
+<footer>
+ <div class="wrap">
+ <div class="foot-top">
+ <a class="foot-brand brand" href="/blog/">
+ <span class="brand-mark">MD</span>
+ <span class="brand-word">MUNDER DIFFLIN<span class="sep">/</span><span class="blog">BLOG</span></span>
+ </a>
+ <div class="foot-links">
+ <a href="/blog/">Latest</a>
+ <a href="/blog/topics/">Topics</a>
+ <a href="/blog/about/">About</a>
+ <a href="https://munderdiffl.in/blog/feed.xml">RSS</a>
+ <a href="https://github.com/chaitanyagiri/munder-difflin">GitHub</a>
+ <a href="https://munderdiffl.in">munderdiffl.in ↗</a>
+ </div>
+ </div>
+ <div class="foot-meta">
+ © 2026 Munder Difflin · Local-first · MIT-licensed ·
+ Built on <a href="https://munderdiffl.in">Electron, React, Pixi.js, xterm.js &amp; node-pty</a>.
+ Run an office of agents while you sleep.
+ </div>
+ </div>
+</footer>
+
+<script>
+ // sticky-nav border on scroll
+ (function () {
+ var nav = document.getElementById('nav');
+ if (!nav) return;
+ var onScroll = function () { nav.classList.toggle('scrolled', window.scrollY > 8); };
+ onScroll(); window.addEventListener('scroll', onScroll, { passive: true });
+ })();
+</script>
+
+</body>
+</html>
diff --git a/docs/blog/claude-code-orchestration-tools-compared/index.html b/docs/blog/claude-code-orchestration-tools-compared/index.html
new file mode 100644
index 00000000..fec70a75
--- /dev/null
+++ b/docs/blog/claude-code-orchestration-tools-compared/index.html
@@ -0,0 +1,376 @@
+<!doctype html>
+<html lang="en">
+<head>
+<meta charset="UTF-8" />
+<meta name="viewport" content="width=device-width, initial-scale=1.0" />
+<title>Claude Code Orchestration Tools, Compared — Munder Difflin Blog</title>
+<meta name="description" content="Claude Code orchestration tools compared on memory, messaging, visibility, control, and local-first — across Claude Squad, Conductor, Crystal, and more." />
+<link rel="canonical" href="https://munderdiffl.in/blog/claude-code-orchestration-tools-compared/" />
+
+<link rel="icon" type="image/png" href="https://munderdiffl.in/logo.png" />
+<link rel="apple-touch-icon" href="https://munderdiffl.in/logo.png" />
+<meta name="theme-color" content="#F5F2E8" />
+
+<!-- Open Graph -->
+<meta property="og:site_name" content="Munder Difflin Blog" />
+<meta property="og:type" content="article" />
+<meta property="og:title" content="Claude Code Orchestration Tools, Compared — Munder Difflin Blog" />
+<meta property="og:description" content="Claude Code orchestration tools compared on memory, messaging, visibility, control, and local-first — across Claude Squad, Conductor, Crystal, and more." />
+<meta property="og:url" content="https://munderdiffl.in/blog/claude-code-orchestration-tools-compared/" />
+<meta property="og:image" content="https://munderdiffl.in/media/og.png" />
+<meta property="og:locale" content="en_US" />
+<meta property="article:published_time" content="2026-06-04T00:00:00.000Z" />
+<meta property="article:author" content="Chaitanya Giri" />
+<meta property="article:tag" content="Comparisons" />
+<meta property="article:tag" content="Orchestration" />
+<meta property="article:tag" content="Claude Code" />
+<meta property="article:tag" content="Tools" />
+
+
+<!-- Twitter -->
+<meta name="twitter:card" content="summary_large_image" />
+<meta name="twitter:title" content="Claude Code Orchestration Tools, Compared — Munder Difflin Blog" />
+<meta name="twitter:description" content="Claude Code orchestration tools compared on memory, messaging, visibility, control, and local-first — across Claude Squad, Conductor, Crystal, and more." />
+<meta name="twitter:image" content="https://munderdiffl.in/media/og.png" />
+
+<link rel="alternate" type="application/atom+xml" title="Munder Difflin Blog" href="https://munderdiffl.in/blog/feed.xml" />
+<link rel="preconnect" href="https://fonts.googleapis.com" />
+<link rel="preconnect" href="https://fonts.gstatic.com" crossorigin />
+<link href="https://fonts.googleapis.com/css2?family=Geist:wght@400;500;600&family=JetBrains+Mono:wght@400;500;600;700&display=swap" rel="stylesheet" />
+<link rel="stylesheet" href="/blog/assets/blog.css" />
+
+<script type="application/ld+json">
+{
+ "@context": "https://schema.org",
+ "@type": "BlogPosting",
+ "headline": "Claude Code Orchestration Tools, Compared",
+ "description": "Claude Code orchestration tools compared on memory, messaging, visibility, control, and local-first — across Claude Squad, Conductor, Crystal, and more.",
+ "image": ["https://munderdiffl.in/media/og.png"],
+ "datePublished": "2026-06-04T00:00:00.000Z",
+ "dateModified": "2026-06-04T00:00:00.000Z",
+ "author": { "@type": "Person", "name": "Chaitanya Giri" },
+ "publisher": {
+ "@type": "Organization",
+ "name": "Munder Difflin",
+ "logo": { "@type": "ImageObject", "url": "https://munderdiffl.in/logo.png" }
+ },
+ "mainEntityOfPage": { "@type": "WebPage", "@id": "https://munderdiffl.in/blog/claude-code-orchestration-tools-compared/" },
+ "keywords": "claude code orchestration tools compared, claude code orchestration tools compared, best claude code multi-agent tools, claude code orchestration",
+ "articleSection": "Comparisons",
+ "inLanguage": "en-US",
+ "url": "https://munderdiffl.in/blog/claude-code-orchestration-tools-compared/"
+}
+</script>
+<script type="application/ld+json">
+{
+ "@context": "https://schema.org",
+ "@type": "BreadcrumbList",
+ "itemListElement": [
+ { "@type": "ListItem", "position": 1, "name": "Home", "item": "https://munderdiffl.in/" },
+ { "@type": "ListItem", "position": 2, "name": "Blog", "item": "https://munderdiffl.in/blog/" },
+ { "@type": "ListItem", "position": 3, "name": "Claude Code Orchestration Tools, Compared", "item": "https://munderdiffl.in/blog/claude-code-orchestration-tools-compared/" }
+ ]
+}
+</script>
+
+
+</head>
+<body>
+<a class="skip-link" href="#main">Skip to content</a>
+<nav id="nav">
+ <a class="brand" href="/blog/" aria-label="Munder Difflin Blog home">
+ <span class="brand-mark">MD</span>
+ <span class="brand-word">MUNDER DIFFLIN<span class="sep">/</span><span class="blog">BLOG</span></span>
+ </a>
+ <span class="spacer"></span>
+ <div class="links">
+ <a href="/blog/">Latest</a>
+ <a href="/blog/topics/">Topics</a>
+ <a href="/blog/about/">About</a>
+ <a href="https://munderdiffl.in">↗ Product</a>
+ </div>
+ <div class="nav-actions">
+ <a class="btn sm" href="https://munderdiffl.in/blog/feed.xml" aria-label="RSS feed">⤵ RSS</a>
+ <a class="btn sm primary" href="https://munderdiffl.in/#install">⤓ Download</a>
+ </div>
+</nav>
+
+<main id="main">
+
+<article>
+ <header class="post-head wrap">
+ <nav class="crumbs" aria-label="Breadcrumb">
+ <a href="/blog/">Blog</a>
+ <span>/</span>
+ <a href="/blog/topics/comparisons/">Comparisons</a>
+ </nav>
+ <h1>Claude Code Orchestration Tools, Compared</h1>
+ <p class="dek">Claude Code orchestration tools compared on memory, messaging, visibility, control, and local-first — across Claude Squad, Conductor, Crystal, and more.</p>
+ <div class="byline">
+ <span class="av" aria-hidden="true">CG</span>
+ <strong>Chaitanya Giri</strong>
+ <span class="dot" aria-hidden="true">·</span>
+ <time datetime="2026-06-04">Jun 4, 2026</time>
+ <span class="dot" aria-hidden="true">·</span>
+ <span>3 min read</span>
+ <span class="tag kind">Comparisons</span>
+ </div>
+ </header>
+
+ <div class="post-wrap wrap">
+ <div class="prose">
+ <div class="callout tldr"><span class="ic">TL;DR</span><p>Compare <strong>Claude Code orchestration
+tools</strong> on five criteria that actually change your day: <strong>shared memory</strong>,
+<strong>inter-agent messaging</strong>, <strong>visibility</strong>, <strong>control</strong>, and
+<strong>local-first</strong>. Session managers and worktree apps score high on control and simplicity;
+a coordinated hive scores high on memory, messaging, and visibility. Score the tools against <em>your</em>
+priorities, not a generic "best."</p></div>
+<p>“Orchestration” gets used loosely. To compare tools meaningfully, you need criteria that map to real
+outcomes — not feature checklists. Here are the five that matter for <a href="/#how">orchestrating Claude Code
+agents</a>, and how the main tools stack up against each.</p>
+<h2 id="the-five-criteria-that-matter" tabindex="-1">The five criteria that matter <a class="anchor" href="#the-five-criteria-that-matter" aria-hidden="true">#</a></h2>
+<ol>
+<li><strong>Shared memory</strong> — do agents pool what they learn into a durable, cross-session
+<a href="/blog/give-claude-code-long-term-memory/">long-term memory</a>, or does each start cold?</li>
+<li><strong>Inter-agent messaging</strong> — can agents hand work and findings to each other directly, or do you
+relay everything?</li>
+<li><strong>Visibility</strong> — can you <em>see</em> what the team is doing, or is it a black box of terminal tabs?</li>
+<li><strong>Control</strong> — how much do you steer vs. delegate? Manual assignment is more control; an
+orchestrator is more leverage.</li>
+<li><strong>Local-first</strong> — does everything run on your machine (privacy, cost, offline), or in the cloud?</li>
+</ol>
+<p>A sixth practical factor — <strong>footprint</strong> — decides whether a tool is overkill for your workload.
+We’ll fold it into the verdict.</p>
+<h2 id="the-comparison" tabindex="-1">The comparison <a class="anchor" href="#the-comparison" aria-hidden="true">#</a></h2>
+<p>Scored as ●●● strong · ●●○ partial · ●○○ minimal, to the best of our knowledge at the time of writing.
+Tools evolve — verify against each project’s current docs.</p>
+<table>
+<thead>
+<tr>
+<th>Criterion</th>
+<th>Claude Squad</th>
+<th>Conductor</th>
+<th>Crystal</th>
+<th>vibe-kanban</th>
+<th>Munder Difflin</th>
+</tr>
+</thead>
+<tbody>
+<tr>
+<td>Shared memory</td>
+<td>●○○</td>
+<td>●○○</td>
+<td>●○○</td>
+<td>●○○</td>
+<td>●●●</td>
+</tr>
+<tr>
+<td>Inter-agent messaging</td>
+<td>●○○</td>
+<td>●○○</td>
+<td>●○○</td>
+<td>●●○</td>
+<td>●●●</td>
+</tr>
+<tr>
+<td>Visibility</td>
+<td>●●○</td>
+<td>●●●</td>
+<td>●●○</td>
+<td>●●●</td>
+<td>●●●</td>
+</tr>
+<tr>
+<td>Control (manual ↔ delegated)</td>
+<td>manual</td>
+<td>manual</td>
+<td>manual</td>
+<td>board</td>
+<td>delegated + escalation</td>
+</tr>
+<tr>
+<td>Local-first</td>
+<td>●●●</td>
+<td>●●●</td>
+<td>●●●</td>
+<td>●●○</td>
+<td>●●●</td>
+</tr>
+<tr>
+<td>Footprint</td>
+<td>tiny</td>
+<td>medium</td>
+<td>medium</td>
+<td>medium</td>
+<td>larger</td>
+</tr>
+</tbody>
+</table>
+<p>Read the table as a fit, not a scoreboard. The tools clustered on the left optimize for <strong>control and
+simplicity</strong>; Munder Difflin optimizes for <strong>coordination</strong> (memory + messaging + a routing
+orchestrator). Both are legitimate.</p>
+<h2 id="how-to-read-each-criterion" tabindex="-1">How to read each criterion <a class="anchor" href="#how-to-read-each-criterion" aria-hidden="true">#</a></h2>
+<h3 id="shared-memory-is-the-real-divider" tabindex="-1">Shared memory is the real divider <a class="anchor" href="#shared-memory-is-the-real-divider" aria-hidden="true">#</a></h3>
+<p>This is where the field genuinely splits. Session managers and worktree apps (Claude Squad, Conductor,
+Crystal) keep each agent’s context isolated — great for clean parallel attempts, but the team forgets
+between runs. vibe-kanban’s cards hold task state, not a shared brain. A hive with a <a href="/#how">semantic memory
+layer</a> is the outlier: every agent reads and writes MemPalace, so knowledge compounds.</p>
+<h3 id="messaging-vs-you-as-the-bus" tabindex="-1">Messaging vs. you-as-the-bus <a class="anchor" href="#messaging-vs-you-as-the-bus" aria-hidden="true">#</a></h3>
+<p>Most tools route coordination through you. vibe-kanban gives the board a coordinating role; a hive
+goes further with agent-to-agent mailboxes so findings flow without a human courier.</p>
+<h3 id="visibility-takes-different-forms" tabindex="-1">Visibility takes different forms <a class="anchor" href="#visibility-takes-different-forms" aria-hidden="true">#</a></h3>
+<p>A TUI list (Claude Squad), a diff-review GUI (Conductor, Crystal), a board (vibe-kanban), or a live
+office floor (Munder Difflin) — all “visible,” but they answer different questions. A floor answers
+“what’s everyone doing <em>right now</em>?”; a board answers “what’s the state of the backlog?”</p>
+<h3 id="control-is-a-preference-not-a-ranking" tabindex="-1">Control is a preference, not a ranking <a class="anchor" href="#control-is-a-preference-not-a-ranking" aria-hidden="true">#</a></h3>
+<p>More manual control (assign every task) suits small, deliberate workloads. More delegation (an
+orchestrator that routes, escalating only the critical) suits larger, fluid ones. Neither is “better”
+— it’s about how much you want to drive.</p>
+<h3 id="local-first-is-increasingly-a-deciding-factor" tabindex="-1">Local-first is increasingly a deciding factor <a class="anchor" href="#local-first-is-increasingly-a-deciding-factor" aria-hidden="true">#</a></h3>
+<p>Running the harness, agents, and memory <a href="/blog/why-local-first-matters-for-ai-agents/">on your own machine</a>
+buys privacy, predictable cost, and offline capability. Most of these tools are local; confirm where
+each one runs before you assume.</p>
+<h2 id="matching-tools-to-priorities" tabindex="-1">Matching tools to priorities <a class="anchor" href="#matching-tools-to-priorities" aria-hidden="true">#</a></h2>
+<ul>
+<li><strong>Prioritize simplicity + control</strong> → Claude Squad.</li>
+<li><strong>Prioritize Mac-native parallel review</strong> → Conductor.</li>
+<li><strong>Prioritize open-source parallel experiments</strong> → Crystal.</li>
+<li><strong>Prioritize a task-board workflow</strong> → vibe-kanban.</li>
+<li><strong>Prioritize memory + messaging + delegated routing</strong> → Munder Difflin.</li>
+</ul>
+<p>If you want a structured way to apply this to your own situation, the <a href="/blog/how-to-choose-a-multi-agent-tool/">buyer’s
+checklist</a> turns these criteria into a scoring rubric, and a
+<a href="/blog/conductor-claude-code-alternative/">Conductor alternative</a> digs into what “orchestration”
+should mean.</p>
+<hr>
+<p>If memory, messaging, and delegated orchestration top your list, the fastest way to judge is to run
+one: <a href="/#install">download Munder Difflin</a> — free, open source, and local-first on macOS, Windows, and
+Linux.</p>
+
+
+
+
+
+ <hr />
+ <div class="share">
+ <span class="lbl">Tags</span>
+ <a class="tag" href="/blog/tags/comparisons/">Comparisons</a><a class="tag" href="/blog/tags/orchestration/">Orchestration</a><a class="tag" href="/blog/tags/claude-code/">Claude Code</a><a class="tag" href="/blog/tags/tools/">Tools</a>
+ </div>
+
+ </div>
+
+
+ <aside class="toc-rail" aria-label="Table of contents">
+ <div class="tt">On this page</div>
+ <ol>
+ <li class="lvl-2"><a href="#the-five-criteria-that-matter">The five criteria that matter</a></li><li class="lvl-2"><a href="#the-comparison">The comparison</a></li><li class="lvl-2"><a href="#how-to-read-each-criterion">How to read each criterion</a></li><li class="lvl-3"><a href="#shared-memory-is-the-real-divider">Shared memory is the real divider</a></li><li class="lvl-3"><a href="#messaging-vs-you-as-the-bus">Messaging vs. you-as-the-bus</a></li><li class="lvl-3"><a href="#visibility-takes-different-forms">Visibility takes different forms</a></li><li class="lvl-3"><a href="#control-is-a-preference-not-a-ranking">Control is a preference, not a ranking</a></li><li class="lvl-3"><a href="#local-first-is-increasingly-a-deciding-factor">Local-first is increasingly a deciding factor</a></li><li class="lvl-2"><a href="#matching-tools-to-priorities">Matching tools to priorities</a></li>
+ </ol>
+ </aside>
+
+ </div>
+
+ <footer class="post-foot wrap"><div class="prevnext">
+ <a class="pn prev" href="/blog/claude-squad-vs-munder-difflin/"><span class="k">← Older</span><span class="t">Claude Squad vs Munder Difflin: Which Should You Use?</span></a>
+ <a class="pn next" href="/blog/claude-code-git-worktrees-vs-hive/"><span class="k">Newer →</span><span class="t">Git Worktrees vs a Hive: Two Ways to Parallelize Claude Code</span></a>
+ </div>
+ <section class="related">
+ <h2>Related in Comparisons</h2>
+ <div class="post-grid">
+ <article class="card">
+ <a class="thumb t-comparisons" href="/blog/best-claude-code-multi-agent-tools/" aria-hidden="true" tabindex="-1">
+ <span>COMPARISONS</span>
+ </a>
+ <div class="body">
+ <div class="meta">
+ <time datetime="2026-06-04">Jun 4, 2026</time>
+ <span class="dot" aria-hidden="true"></span>
+ <span>6 min</span>
+ </div>
+ <h3><a href="/blog/best-claude-code-multi-agent-tools/">The Best Tools to Run Multiple Claude Code Agents (2026)</a></h3>
+ <p class="dek">An honest 2026 roundup of tools to run multiple Claude Code agents — Claude Squad, Conductor, Crystal, vibe-kanban, and Munder Difflin — compared.</p>
+ <div class="foot">
+ <span class="tag kind">Comparisons</span>
+ <a class="more" href="/blog/best-claude-code-multi-agent-tools/" aria-label="Read: The Best Tools to Run Multiple Claude Code Agents (2026)">Read →</a>
+ </div>
+ </div>
+</article>
+<article class="card">
+ <a class="thumb t-comparisons" href="/blog/claude-squad-vs-munder-difflin/" aria-hidden="true" tabindex="-1">
+ <span>COMPARISONS</span>
+ </a>
+ <div class="body">
+ <div class="meta">
+ <time datetime="2026-06-04">Jun 4, 2026</time>
+ <span class="dot" aria-hidden="true"></span>
+ <span>3 min</span>
+ </div>
+ <h3><a href="/blog/claude-squad-vs-munder-difflin/">Claude Squad vs Munder Difflin: Which Should You Use?</a></h3>
+ <p class="dek">Claude Squad vs Munder Difflin: a lean terminal session manager against a memory-backed, orchestrated, visual hive. Feature table and an honest verdict.</p>
+ <div class="foot">
+ <span class="tag kind">Comparisons</span>
+ <a class="more" href="/blog/claude-squad-vs-munder-difflin/" aria-label="Read: Claude Squad vs Munder Difflin: Which Should You Use?">Read →</a>
+ </div>
+ </div>
+</article>
+<article class="card">
+ <a class="thumb t-comparisons" href="/blog/claude-squad-alternative/" aria-hidden="true" tabindex="-1">
+ <span>COMPARISONS</span>
+ </a>
+ <div class="body">
+ <div class="meta">
+ <time datetime="2026-06-03">Jun 3, 2026</time>
+ <span class="dot" aria-hidden="true"></span>
+ <span>3 min</span>
+ </div>
+ <h3><a href="/blog/claude-squad-alternative/">Looking for a Claude Squad Alternative?</a></h3>
+ <p class="dek">What Claude Squad does well, where it stops, and why a memory-backed, orchestrated hive may be the Claude Squad alternative you&#39;re after.</p>
+ <div class="foot">
+ <span class="tag kind">Comparisons</span>
+ <a class="more" href="/blog/claude-squad-alternative/" aria-label="Read: Looking for a Claude Squad Alternative?">Read →</a>
+ </div>
+ </div>
+</article>
+
+ </div>
+ </section>
+
+ </footer>
+</article>
+
+</main>
+<footer>
+ <div class="wrap">
+ <div class="foot-top">
+ <a class="foot-brand brand" href="/blog/">
+ <span class="brand-mark">MD</span>
+ <span class="brand-word">MUNDER DIFFLIN<span class="sep">/</span><span class="blog">BLOG</span></span>
+ </a>
+ <div class="foot-links">
+ <a href="/blog/">Latest</a>
+ <a href="/blog/topics/">Topics</a>
+ <a href="/blog/about/">About</a>
+ <a href="https://munderdiffl.in/blog/feed.xml">RSS</a>
+ <a href="https://github.com/chaitanyagiri/munder-difflin">GitHub</a>
+ <a href="https://munderdiffl.in">munderdiffl.in ↗</a>
+ </div>
+ </div>
+ <div class="foot-meta">
+ © 2026 Munder Difflin · Local-first · MIT-licensed ·
+ Built on <a href="https://munderdiffl.in">Electron, React, Pixi.js, xterm.js &amp; node-pty</a>.
+ Run an office of agents while you sleep.
+ </div>
+ </div>
+</footer>
+
+<script>
+ // sticky-nav border on scroll
+ (function () {
+ var nav = document.getElementById('nav');
+ if (!nav) return;
+ var onScroll = function () { nav.classList.toggle('scrolled', window.scrollY > 8); };
+ onScroll(); window.addEventListener('scroll', onScroll, { passive: true });
+ })();
+</script>
+
+</body>
+</html>
diff --git a/docs/blog/claude-code-subagents-vs-multi-agent-harness/index.html b/docs/blog/claude-code-subagents-vs-multi-agent-harness/index.html
new file mode 100644
index 00000000..674cfaa0
--- /dev/null
+++ b/docs/blog/claude-code-subagents-vs-multi-agent-harness/index.html
@@ -0,0 +1,418 @@
+<!doctype html>
+<html lang="en">
+<head>
+<meta charset="UTF-8" />
+<meta name="viewport" content="width=device-width, initial-scale=1.0" />
+<title>Claude Code Subagents vs a Multi-Agent Harness — Munder Difflin Blog</title>
+<meta name="description" content="Claude Code subagents vs a multi-agent harness: where subagents stop and a harness with shared memory, messaging, and an orchestrator takes over." />
+<link rel="canonical" href="https://munderdiffl.in/blog/claude-code-subagents-vs-multi-agent-harness/" />
+
+<link rel="icon" type="image/png" href="https://munderdiffl.in/logo.png" />
+<link rel="apple-touch-icon" href="https://munderdiffl.in/logo.png" />
+<meta name="theme-color" content="#F5F2E8" />
+
+<!-- Open Graph -->
+<meta property="og:site_name" content="Munder Difflin Blog" />
+<meta property="og:type" content="article" />
+<meta property="og:title" content="Claude Code Subagents vs a Multi-Agent Harness — Munder Difflin Blog" />
+<meta property="og:description" content="Claude Code subagents vs a multi-agent harness: where subagents stop and a harness with shared memory, messaging, and an orchestrator takes over." />
+<meta property="og:url" content="https://munderdiffl.in/blog/claude-code-subagents-vs-multi-agent-harness/" />
+<meta property="og:image" content="https://munderdiffl.in/media/og.png" />
+<meta property="og:locale" content="en_US" />
+<meta property="article:published_time" content="2026-05-23T00:00:00.000Z" />
+<meta property="article:author" content="Chaitanya Giri" />
+<meta property="article:tag" content="Guides" />
+<meta property="article:tag" content="Subagents" />
+<meta property="article:tag" content="Multi-Agent" />
+<meta property="article:tag" content="Claude Code" />
+
+
+<!-- Twitter -->
+<meta name="twitter:card" content="summary_large_image" />
+<meta name="twitter:title" content="Claude Code Subagents vs a Multi-Agent Harness — Munder Difflin Blog" />
+<meta name="twitter:description" content="Claude Code subagents vs a multi-agent harness: where subagents stop and a harness with shared memory, messaging, and an orchestrator takes over." />
+<meta name="twitter:image" content="https://munderdiffl.in/media/og.png" />
+
+<link rel="alternate" type="application/atom+xml" title="Munder Difflin Blog" href="https://munderdiffl.in/blog/feed.xml" />
+<link rel="preconnect" href="https://fonts.googleapis.com" />
+<link rel="preconnect" href="https://fonts.gstatic.com" crossorigin />
+<link href="https://fonts.googleapis.com/css2?family=Geist:wght@400;500;600&family=JetBrains+Mono:wght@400;500;600;700&display=swap" rel="stylesheet" />
+<link rel="stylesheet" href="/blog/assets/blog.css" />
+
+<script type="application/ld+json">
+{
+ "@context": "https://schema.org",
+ "@type": "BlogPosting",
+ "headline": "Claude Code Subagents vs a Multi-Agent Harness",
+ "description": "Claude Code subagents vs a multi-agent harness: where subagents stop and a harness with shared memory, messaging, and an orchestrator takes over.",
+ "image": ["https://munderdiffl.in/media/og.png"],
+ "datePublished": "2026-05-23T00:00:00.000Z",
+ "dateModified": "2026-05-23T00:00:00.000Z",
+ "author": { "@type": "Person", "name": "Chaitanya Giri" },
+ "publisher": {
+ "@type": "Organization",
+ "name": "Munder Difflin",
+ "logo": { "@type": "ImageObject", "url": "https://munderdiffl.in/logo.png" }
+ },
+ "mainEntityOfPage": { "@type": "WebPage", "@id": "https://munderdiffl.in/blog/claude-code-subagents-vs-multi-agent-harness/" },
+ "keywords": "claude code subagents, multi-agent harness, subagent limits, claude code agents",
+ "articleSection": "Guides",
+ "inLanguage": "en-US",
+ "url": "https://munderdiffl.in/blog/claude-code-subagents-vs-multi-agent-harness/"
+}
+</script>
+<script type="application/ld+json">
+{
+ "@context": "https://schema.org",
+ "@type": "BreadcrumbList",
+ "itemListElement": [
+ { "@type": "ListItem", "position": 1, "name": "Home", "item": "https://munderdiffl.in/" },
+ { "@type": "ListItem", "position": 2, "name": "Blog", "item": "https://munderdiffl.in/blog/" },
+ { "@type": "ListItem", "position": 3, "name": "Claude Code Subagents vs a Multi-Agent Harness", "item": "https://munderdiffl.in/blog/claude-code-subagents-vs-multi-agent-harness/" }
+ ]
+}
+</script>
+
+<script type="application/ld+json">
+{
+ "@context": "https://schema.org",
+ "@type": "FAQPage",
+ "mainEntity": [
+ { "@type": "Question", "name": "What are Claude Code subagents?", "acceptedAnswer": { "@type": "Answer", "text": "Subagents are helpers a Claude Code session spawns inside its own run to handle a scoped piece of work — often parallel, read-heavy tasks. Each runs in its own context window and returns a result to the parent, then goes away. They're a fan-out tool, not a persistent team." } },
+ { "@type": "Question", "name": "When do subagents stop being enough?", "acceptedAnswer": { "@type": "Answer", "text": "When you need work to persist across sessions, agents to remember what they learned, agents to message each other directly rather than only through a parent, or a coordinator that routes a whole goal. Those are harness features, not subagent features." } },
+ { "@type": "Question", "name": "Can I use subagents and a harness together?", "acceptedAnswer": { "@type": "Answer", "text": "Yes, and you often should. Use subagents for fan-out inside a single agent's task; use a harness to coordinate multiple long-lived agents with shared memory and messaging across the whole workflow." } }
+
+ ]
+}
+</script>
+
+
+</head>
+<body>
+<a class="skip-link" href="#main">Skip to content</a>
+<nav id="nav">
+ <a class="brand" href="/blog/" aria-label="Munder Difflin Blog home">
+ <span class="brand-mark">MD</span>
+ <span class="brand-word">MUNDER DIFFLIN<span class="sep">/</span><span class="blog">BLOG</span></span>
+ </a>
+ <span class="spacer"></span>
+ <div class="links">
+ <a href="/blog/">Latest</a>
+ <a href="/blog/topics/">Topics</a>
+ <a href="/blog/about/">About</a>
+ <a href="https://munderdiffl.in">↗ Product</a>
+ </div>
+ <div class="nav-actions">
+ <a class="btn sm" href="https://munderdiffl.in/blog/feed.xml" aria-label="RSS feed">⤵ RSS</a>
+ <a class="btn sm primary" href="https://munderdiffl.in/#install">⤓ Download</a>
+ </div>
+</nav>
+
+<main id="main">
+
+<article>
+ <header class="post-head wrap">
+ <nav class="crumbs" aria-label="Breadcrumb">
+ <a href="/blog/">Blog</a>
+ <span>/</span>
+ <a href="/blog/topics/guides/">Guides</a>
+ </nav>
+ <h1>Claude Code Subagents vs a Multi-Agent Harness</h1>
+ <p class="dek">Claude Code subagents vs a multi-agent harness: where subagents stop and a harness with shared memory, messaging, and an orchestrator takes over.</p>
+ <div class="byline">
+ <span class="av" aria-hidden="true">CG</span>
+ <strong>Chaitanya Giri</strong>
+ <span class="dot" aria-hidden="true">·</span>
+ <time datetime="2026-05-23">May 23, 2026</time>
+ <span class="dot" aria-hidden="true">·</span>
+ <span>5 min read</span>
+ <span class="tag kind">Guides</span>
+ </div>
+ </header>
+
+ <div class="post-wrap wrap">
+ <div class="prose">
+ <div class="callout tldr"><span class="ic">TL;DR</span><p><strong>Claude Code subagents</strong> are
+short-lived helpers one session spawns to fan out scoped work — great for parallel reads, scoped to a
+single parent, gone when done. A <strong>multi-agent harness</strong> wraps several long-lived agents
+and adds what subagents don't have: <strong>persistent identities, shared memory, direct messaging
+between agents, an orchestrator, and visibility</strong>. They're complementary — subagents work
+<em>inside</em> an agent; a harness coordinates <em>across</em> agents.</p></div>
+<p>“Claude Code already has subagents — why would I need a harness?” It’s a fair question, and the answer
+isn’t “subagents are bad.” Subagents are excellent at what they do. They just do a different job than a
+harness. This post draws the line precisely so you know which one a given problem calls for.</p>
+<h2 id="what-subagents-are" tabindex="-1">What subagents are <a class="anchor" href="#what-subagents-are" aria-hidden="true">#</a></h2>
+<p>A subagent is a helper a Claude Code session spawns <em>inside its own run</em>. The main agent delegates a
+scoped task — “search these directories,” “draft this section” — to a subagent that runs in its <strong>own
+context window</strong>, does the work, and <strong>returns a result</strong> to the parent. Then it’s gone.</p>
+<p>Their sweet spot is <strong>fan-out</strong>, especially read-heavy work:</p>
+<ul>
+<li>searching a large codebase several ways at once,</li>
+<li>gathering context from many files in parallel,</li>
+<li>exploring independent options and reporting back.</li>
+</ul>
+<p>Because each subagent has a fresh context window, the parent stays uncluttered — it gets conclusions,
+not the raw dump. For a single agent tackling one big task, that’s a real superpower.</p>
+<h2 id="what-subagents-are-not" tabindex="-1">What subagents are not <a class="anchor" href="#what-subagents-are-not" aria-hidden="true">#</a></h2>
+<p>The limits all stem from one fact: a subagent is <strong>scoped to its parent’s run</strong>.</p>
+<ul>
+<li><strong>They’re ephemeral.</strong> A subagent exists for one task and disappears. Nothing it learned persists to
+the next session — there’s no durable memory of its own.</li>
+<li><strong>Coordination is hub-and-spoke.</strong> Subagents talk to the <em>parent</em>, not to each other. Two subagents
+can’t message directly, share state, or negotiate. The parent is the only hub, and it’s a bottleneck
+by design.</li>
+<li><strong>No shared long-term memory.</strong> A subagent’s findings live in the parent’s context until that
+context is gone. There’s no store the <em>whole workflow</em> reads from across sessions.</li>
+<li><strong>No standing roster.</strong> You don’t have a <code>reviewer</code> and a <code>migration</code> agent that persist as
+teammates across tasks; you have helpers conjured for one job.</li>
+</ul>
+<p>None of this is a flaw — it’s the scope. Subagents are an <em>intra-agent</em> concurrency primitive. They
+were never meant to be a standing team.</p>
+<h2 id="what-a-harness-adds" tabindex="-1">What a harness adds <a class="anchor" href="#what-a-harness-adds" aria-hidden="true">#</a></h2>
+<p>A <a href="https://munderdiffl.in/#what">multi-agent harness</a> wraps agents you already run — full Claude Code
+sessions — and adds the layer subagents structurally can’t provide:</p>
+<ul>
+<li><strong>Persistent identities.</strong> Each agent has a role, a name, and its own workspace that lives across
+tasks. Your <code>test-writer</code> is the same teammate next session.</li>
+<li><strong>Durable, shared memory.</strong> Agents write notes that persist and become recall-able by the <em>whole</em>
+team — so agent B uses what agent A learned, even sessions later. That’s
+<a href="/blog/semantic-memory-for-ai-agents/">semantic memory for agents</a>, not a context window that
+vanishes.</li>
+<li><strong>Direct messaging.</strong> Agents send messages to <em>each other</em>, not only up to a parent. A router
+delivers them safely, so coordination is a mesh, not a single hub.</li>
+<li><strong>An orchestrator.</strong> A coordinator reads your goal, decomposes it, and routes work across the team —
+and escalates only the critical calls to you. The parent-as-bottleneck problem goes away.</li>
+<li><strong>Visibility.</strong> You can watch the whole team work, rather than peering into one agent’s run.</li>
+</ul>
+<p>Put simply: subagents give one agent <em>helpers</em>; a harness gives you a <em>team</em>.</p>
+<h2 id="a-side-by-side" tabindex="-1">A side-by-side <a class="anchor" href="#a-side-by-side" aria-hidden="true">#</a></h2>
+<table>
+<thead>
+<tr>
+<th></th>
+<th>Claude Code subagents</th>
+<th>Multi-agent harness</th>
+</tr>
+</thead>
+<tbody>
+<tr>
+<td><strong>Lifespan</strong></td>
+<td>One task, then gone</td>
+<td>Persistent across sessions</td>
+</tr>
+<tr>
+<td><strong>Memory</strong></td>
+<td>Parent’s context only</td>
+<td>Durable + shared across the team</td>
+</tr>
+<tr>
+<td><strong>Communication</strong></td>
+<td>To the parent (hub-and-spoke)</td>
+<td>Agent-to-agent (mesh) via a router</td>
+</tr>
+<tr>
+<td><strong>Coordination</strong></td>
+<td>The parent decides</td>
+<td>An orchestrator routes + escalates</td>
+</tr>
+<tr>
+<td><strong>Identity / roles</strong></td>
+<td>Ephemeral helpers</td>
+<td>Standing roster with roles</td>
+</tr>
+<tr>
+<td><strong>Best for</strong></td>
+<td>Fan-out within one task</td>
+<td>Coordinating long-lived work</td>
+</tr>
+</tbody>
+</table>
+<p>The table isn’t a scoreboard — it’s a map. Each column wins its own territory.</p>
+<h2 id="theyre-better-together" tabindex="-1">They’re better together <a class="anchor" href="#theyre-better-together" aria-hidden="true">#</a></h2>
+<p>The framing that trips people up is “subagents <em>or</em> a harness.” In practice it’s both:</p>
+<ul>
+<li><strong>Inside</strong> a single agent’s task, subagents fan out the read-heavy parts and keep that agent’s
+context clean.</li>
+<li><strong>Across</strong> agents, the harness coordinates the standing team — shared memory, messaging, orchestration.</li>
+</ul>
+<p>A harness-managed agent can absolutely use subagents for its own work. The harness operates one level
+up, at the team scale; subagents operate one level down, at the task scale. Nothing about running a
+coordinated team stops an individual agent from spawning helpers — and nothing about spawning helpers
+gives you a coordinated team.</p>
+<h2 id="which-do-you-need" tabindex="-1">Which do you need? <a class="anchor" href="#which-do-you-need" aria-hidden="true">#</a></h2>
+<p>Use <strong>subagents</strong> (and nothing more) when:</p>
+<ul>
+<li>you’re working with <strong>one</strong> primary agent on a task,</li>
+<li>the parallelism you want is <em>within</em> that task (search, gather, explore), and</li>
+<li>you don’t need anything to persist past the run.</li>
+</ul>
+<p>Reach for a <strong>harness</strong> when:</p>
+<ul>
+<li>you’re running <strong>several</strong> agents and losing track of who’s doing what,</li>
+<li>you keep <strong>re-explaining</strong> context because each session forgets,</li>
+<li>agents need to <strong>hand work to each other</strong> without you relaying it, or</li>
+<li>you want to state a goal once and have a <strong>team</strong> divide and conquer.</li>
+</ul>
+<p>That threshold — one agent’s task vs. a coordinated team — is the whole decision. If you’re hitting it,
+the next read is <a href="/blog/how-to-run-multiple-claude-code-agents/">how to run multiple Claude Code agents</a>,
+and the concept underneath it is <a href="/blog/what-is-a-multi-agent-harness/">what a multi-agent harness is</a>.</p>
+<h2 id="faq" tabindex="-1">FAQ <a class="anchor" href="#faq" aria-hidden="true">#</a></h2>
+<p><strong>Is a harness just “subagents that don’t expire”?</strong> Not quite. Persistence is part of it, but the
+bigger additions are <em>shared memory</em> and <em>direct inter-agent messaging</em> — a subagent that merely lived
+longer still couldn’t message a sibling or recall another agent’s notes.</p>
+<p><strong>Do I lose subagents if I adopt a harness?</strong> No. Your agents are still full Claude Code sessions, so
+they keep every native capability, subagents included. The harness adds coordination around them; it
+doesn’t take anything away.</p>
+<hr>
+<p>Munder Difflin is the harness layer: persistent agents, shared memory, direct messaging, and a GOD
+orchestrator — wrapped around the Claude Code sessions (and subagents) you already use.
+<a href="https://munderdiffl.in/#install">Download Munder Difflin</a> to turn helpers into a team; it’s free and
+open source.</p>
+
+
+
+ <section class="faq" aria-label="Frequently asked questions">
+ <h2 id="faq">FAQ</h2>
+
+ <div class="qa">
+ <p class="q">What are Claude Code subagents?</p>
+ <p class="a">Subagents are helpers a Claude Code session spawns inside its own run to handle a scoped piece of work — often parallel, read-heavy tasks. Each runs in its own context window and returns a result to the parent, then goes away. They&#39;re a fan-out tool, not a persistent team.</p>
+ </div>
+
+ <div class="qa">
+ <p class="q">When do subagents stop being enough?</p>
+ <p class="a">When you need work to persist across sessions, agents to remember what they learned, agents to message each other directly rather than only through a parent, or a coordinator that routes a whole goal. Those are harness features, not subagent features.</p>
+ </div>
+
+ <div class="qa">
+ <p class="q">Can I use subagents and a harness together?</p>
+ <p class="a">Yes, and you often should. Use subagents for fan-out inside a single agent&#39;s task; use a harness to coordinate multiple long-lived agents with shared memory and messaging across the whole workflow.</p>
+ </div>
+
+ </section>
+
+
+
+ <hr />
+ <div class="share">
+ <span class="lbl">Tags</span>
+ <a class="tag" href="/blog/tags/guides/">Guides</a><a class="tag" href="/blog/tags/subagents/">Subagents</a><a class="tag" href="/blog/tags/multi-agent/">Multi-Agent</a><a class="tag" href="/blog/tags/claude-code/">Claude Code</a>
+ </div>
+
+ </div>
+
+
+ <aside class="toc-rail" aria-label="Table of contents">
+ <div class="tt">On this page</div>
+ <ol>
+ <li class="lvl-2"><a href="#what-subagents-are">What subagents are</a></li><li class="lvl-2"><a href="#what-subagents-are-not">What subagents are not</a></li><li class="lvl-2"><a href="#what-a-harness-adds">What a harness adds</a></li><li class="lvl-2"><a href="#a-side-by-side">A side-by-side</a></li><li class="lvl-2"><a href="#theyre-better-together">They’re better together</a></li><li class="lvl-2"><a href="#which-do-you-need">Which do you need?</a></li><li class="lvl-2"><a href="#faq">FAQ</a></li>
+ </ol>
+ </aside>
+
+ </div>
+
+ <footer class="post-foot wrap"><div class="prevnext">
+ <a class="pn prev" href="/blog/what-is-a-multi-agent-harness/"><span class="k">← Older</span><span class="t">What Is a Multi-Agent Harness? (Plain-English Guide)</span></a>
+ <a class="pn next" href="/blog/claude-code-multi-agent-setup-tutorial/"><span class="k">Newer →</span><span class="t">Set Up a Claude Code Multi-Agent Workflow in 10 Minutes</span></a>
+ </div>
+ <section class="related">
+ <h2>Related in Guides</h2>
+ <div class="post-grid">
+ <article class="card">
+ <a class="thumb t-guides" href="/blog/claude-code-automation-while-you-sleep/" aria-hidden="true" tabindex="-1">
+ <span>GUIDES</span>
+ </a>
+ <div class="body">
+ <div class="meta">
+ <time datetime="2026-06-04">Jun 4, 2026</time>
+ <span class="dot" aria-hidden="true"></span>
+ <span>5 min</span>
+ </div>
+ <h3><a href="/blog/claude-code-automation-while-you-sleep/">Claude Code Automation: Let Agents Build While You Sleep</a></h3>
+ <p class="dek">Claude Code automation that runs overnight: an autonomous Stop-hook loop, safe permission bypass, and guardrails so you wake up to progress, not chaos.</p>
+ <div class="foot">
+ <span class="tag kind">Guides</span>
+ <a class="more" href="/blog/claude-code-automation-while-you-sleep/" aria-label="Read: Claude Code Automation: Let Agents Build While You Sleep">Read →</a>
+ </div>
+ </div>
+</article>
+<article class="card">
+ <a class="thumb t-guides" href="/blog/mcp-and-skills-in-a-hive/" aria-hidden="true" tabindex="-1">
+ <span>GUIDES</span>
+ </a>
+ <div class="body">
+ <div class="meta">
+ <time datetime="2026-06-03">Jun 3, 2026</time>
+ <span class="dot" aria-hidden="true"></span>
+ <span>6 min</span>
+ </div>
+ <h3><a href="/blog/mcp-and-skills-in-a-hive/">Bringing Your MCP Servers and Skills Into a Hive of Agents</a></h3>
+ <p class="dek">How agents in a hive inherit your existing Claude Code MCP servers, skills, and tools — and how to scope which agent gets which capability.</p>
+ <div class="foot">
+ <span class="tag kind">Guides</span>
+ <a class="more" href="/blog/mcp-and-skills-in-a-hive/" aria-label="Read: Bringing Your MCP Servers and Skills Into a Hive of Agents">Read →</a>
+ </div>
+ </div>
+</article>
+<article class="card">
+ <a class="thumb t-guides" href="/blog/how-to-run-multiple-claude-code-agents/" aria-hidden="true" tabindex="-1">
+ <span>GUIDES</span>
+ </a>
+ <div class="body">
+ <div class="meta">
+ <time datetime="2026-06-01">Jun 1, 2026</time>
+ <span class="dot" aria-hidden="true"></span>
+ <span>3 min</span>
+ </div>
+ <h3><a href="/blog/how-to-run-multiple-claude-code-agents/">How to Run Multiple Claude Code Agents (Without Losing Track)</a></h3>
+ <p class="dek">Run several Claude Code agents in parallel without the chaos: give each a role, let them coordinate, and stop alt-tabbing between terminal windows.</p>
+ <div class="foot">
+ <span class="tag kind">Guides</span>
+ <a class="more" href="/blog/how-to-run-multiple-claude-code-agents/" aria-label="Read: How to Run Multiple Claude Code Agents (Without Losing Track)">Read →</a>
+ </div>
+ </div>
+</article>
+
+ </div>
+ </section>
+
+ </footer>
+</article>
+
+</main>
+<footer>
+ <div class="wrap">
+ <div class="foot-top">
+ <a class="foot-brand brand" href="/blog/">
+ <span class="brand-mark">MD</span>
+ <span class="brand-word">MUNDER DIFFLIN<span class="sep">/</span><span class="blog">BLOG</span></span>
+ </a>
+ <div class="foot-links">
+ <a href="/blog/">Latest</a>
+ <a href="/blog/topics/">Topics</a>
+ <a href="/blog/about/">About</a>
+ <a href="https://munderdiffl.in/blog/feed.xml">RSS</a>
+ <a href="https://github.com/chaitanyagiri/munder-difflin">GitHub</a>
+ <a href="https://munderdiffl.in">munderdiffl.in ↗</a>
+ </div>
+ </div>
+ <div class="foot-meta">
+ © 2026 Munder Difflin · Local-first · MIT-licensed ·
+ Built on <a href="https://munderdiffl.in">Electron, React, Pixi.js, xterm.js &amp; node-pty</a>.
+ Run an office of agents while you sleep.
+ </div>
+ </div>
+</footer>
+
+<script>
+ // sticky-nav border on scroll
+ (function () {
+ var nav = document.getElementById('nav');
+ if (!nav) return;
+ var onScroll = function () { nav.classList.toggle('scrolled', window.scrollY > 8); };
+ onScroll(); window.addEventListener('scroll', onScroll, { passive: true });
+ })();
+</script>
+
+</body>
+</html>
diff --git a/docs/blog/claude-squad-alternative/index.html b/docs/blog/claude-squad-alternative/index.html
new file mode 100644
index 00000000..a64f3cd4
--- /dev/null
+++ b/docs/blog/claude-squad-alternative/index.html
@@ -0,0 +1,314 @@
+<!doctype html>
+<html lang="en">
+<head>
+<meta charset="UTF-8" />
+<meta name="viewport" content="width=device-width, initial-scale=1.0" />
+<title>Looking for a Claude Squad Alternative? — Munder Difflin Blog</title>
+<meta name="description" content="What Claude Squad does well, where it stops, and why a memory-backed, orchestrated hive may be the Claude Squad alternative you&#39;re after." />
+<link rel="canonical" href="https://munderdiffl.in/blog/claude-squad-alternative/" />
+
+<link rel="icon" type="image/png" href="https://munderdiffl.in/logo.png" />
+<link rel="apple-touch-icon" href="https://munderdiffl.in/logo.png" />
+<meta name="theme-color" content="#F5F2E8" />
+
+<!-- Open Graph -->
+<meta property="og:site_name" content="Munder Difflin Blog" />
+<meta property="og:type" content="article" />
+<meta property="og:title" content="Looking for a Claude Squad Alternative? — Munder Difflin Blog" />
+<meta property="og:description" content="What Claude Squad does well, where it stops, and why a memory-backed, orchestrated hive may be the Claude Squad alternative you&#39;re after." />
+<meta property="og:url" content="https://munderdiffl.in/blog/claude-squad-alternative/" />
+<meta property="og:image" content="https://munderdiffl.in/media/og.png" />
+<meta property="og:locale" content="en_US" />
+<meta property="article:published_time" content="2026-06-03T00:00:00.000Z" />
+<meta property="article:author" content="Chaitanya Giri" />
+<meta property="article:tag" content="Comparisons" />
+<meta property="article:tag" content="Multi-Agent" />
+<meta property="article:tag" content="Claude Code" />
+<meta property="article:tag" content="Tools" />
+
+
+<!-- Twitter -->
+<meta name="twitter:card" content="summary_large_image" />
+<meta name="twitter:title" content="Looking for a Claude Squad Alternative? — Munder Difflin Blog" />
+<meta name="twitter:description" content="What Claude Squad does well, where it stops, and why a memory-backed, orchestrated hive may be the Claude Squad alternative you&#39;re after." />
+<meta name="twitter:image" content="https://munderdiffl.in/media/og.png" />
+
+<link rel="alternate" type="application/atom+xml" title="Munder Difflin Blog" href="https://munderdiffl.in/blog/feed.xml" />
+<link rel="preconnect" href="https://fonts.googleapis.com" />
+<link rel="preconnect" href="https://fonts.gstatic.com" crossorigin />
+<link href="https://fonts.googleapis.com/css2?family=Geist:wght@400;500;600&family=JetBrains+Mono:wght@400;500;600;700&display=swap" rel="stylesheet" />
+<link rel="stylesheet" href="/blog/assets/blog.css" />
+
+<script type="application/ld+json">
+{
+ "@context": "https://schema.org",
+ "@type": "BlogPosting",
+ "headline": "Looking for a Claude Squad Alternative?",
+ "description": "What Claude Squad does well, where it stops, and why a memory-backed, orchestrated hive may be the Claude Squad alternative you're after.",
+ "image": ["https://munderdiffl.in/media/og.png"],
+ "datePublished": "2026-06-03T00:00:00.000Z",
+ "dateModified": "2026-06-03T00:00:00.000Z",
+ "author": { "@type": "Person", "name": "Chaitanya Giri" },
+ "publisher": {
+ "@type": "Organization",
+ "name": "Munder Difflin",
+ "logo": { "@type": "ImageObject", "url": "https://munderdiffl.in/logo.png" }
+ },
+ "mainEntityOfPage": { "@type": "WebPage", "@id": "https://munderdiffl.in/blog/claude-squad-alternative/" },
+ "keywords": "claude squad alternative, claude code multi-agent tool, claude squad vs munder difflin, claude squad alternative",
+ "articleSection": "Comparisons",
+ "inLanguage": "en-US",
+ "url": "https://munderdiffl.in/blog/claude-squad-alternative/"
+}
+</script>
+<script type="application/ld+json">
+{
+ "@context": "https://schema.org",
+ "@type": "BreadcrumbList",
+ "itemListElement": [
+ { "@type": "ListItem", "position": 1, "name": "Home", "item": "https://munderdiffl.in/" },
+ { "@type": "ListItem", "position": 2, "name": "Blog", "item": "https://munderdiffl.in/blog/" },
+ { "@type": "ListItem", "position": 3, "name": "Looking for a Claude Squad Alternative?", "item": "https://munderdiffl.in/blog/claude-squad-alternative/" }
+ ]
+}
+</script>
+
+
+</head>
+<body>
+<a class="skip-link" href="#main">Skip to content</a>
+<nav id="nav">
+ <a class="brand" href="/blog/" aria-label="Munder Difflin Blog home">
+ <span class="brand-mark">MD</span>
+ <span class="brand-word">MUNDER DIFFLIN<span class="sep">/</span><span class="blog">BLOG</span></span>
+ </a>
+ <span class="spacer"></span>
+ <div class="links">
+ <a href="/blog/">Latest</a>
+ <a href="/blog/topics/">Topics</a>
+ <a href="/blog/about/">About</a>
+ <a href="https://munderdiffl.in">↗ Product</a>
+ </div>
+ <div class="nav-actions">
+ <a class="btn sm" href="https://munderdiffl.in/blog/feed.xml" aria-label="RSS feed">⤵ RSS</a>
+ <a class="btn sm primary" href="https://munderdiffl.in/#install">⤓ Download</a>
+ </div>
+</nav>
+
+<main id="main">
+
+<article>
+ <header class="post-head wrap">
+ <nav class="crumbs" aria-label="Breadcrumb">
+ <a href="/blog/">Blog</a>
+ <span>/</span>
+ <a href="/blog/topics/comparisons/">Comparisons</a>
+ </nav>
+ <h1>Looking for a Claude Squad Alternative?</h1>
+ <p class="dek">What Claude Squad does well, where it stops, and why a memory-backed, orchestrated hive may be the Claude Squad alternative you&#39;re after.</p>
+ <div class="byline">
+ <span class="av" aria-hidden="true">CG</span>
+ <strong>Chaitanya Giri</strong>
+ <span class="dot" aria-hidden="true">·</span>
+ <time datetime="2026-06-03">Jun 3, 2026</time>
+ <span class="dot" aria-hidden="true">·</span>
+ <span>3 min read</span>
+ <span class="tag kind">Comparisons</span>
+ </div>
+ </header>
+
+ <div class="post-wrap wrap">
+ <div class="prose">
+ <div class="callout tldr"><span class="ic">TL;DR</span><p><strong>Claude Squad</strong> is an
+excellent lean, terminal-based way to run several Claude Code agents in parallel using tmux and git
+worktrees. If you're looking for a <strong>Claude Squad alternative</strong>, it's usually because
+you want what a session manager doesn't do: agents that <strong>share memory</strong>, <strong>message
+each other</strong>, and are <strong>routed by an orchestrator</strong> — plus a way to actually see
+the work. That's the gap a coordinated hive fills.</p></div>
+<p><a href="https://github.com/smtg-ai/claude-squad">Claude Squad</a> is a genuinely good tool. Before we talk
+alternatives, let’s be fair about what it gets right — because the reason to switch is specific.</p>
+<h2 id="what-claude-squad-does-well" tabindex="-1">What Claude Squad does well <a class="anchor" href="#what-claude-squad-does-well" aria-hidden="true">#</a></h2>
+<p>Claude Squad is a terminal UI that manages multiple AI coding agents — Claude Code included — each in
+its own tmux session, with git worktrees isolating their changes. From one keyboard-driven interface
+you launch agents, switch between them, background long-running ones, and review their work.</p>
+<ul>
+<li><strong>It’s featherweight.</strong> No GUI, no Electron, minimal setup. It starts fast and stays out of the way.</li>
+<li><strong>It’s terminal-native and SSH-friendly.</strong> Run it on a remote box and drive a fleet of agents over
+a single connection.</li>
+<li><strong>Worktree isolation is built in.</strong> Each agent works in its own <a href="/blog/how-to-run-multiple-claude-code-agents/">git
+worktree</a>, so parallel agents don’t clobber each
+other’s files.</li>
+</ul>
+<p>If your need is “run a few independent Claude Code tasks in parallel from the terminal,” Claude Squad
+may be all you ever want. Switching costs you simplicity — so switch only for a real reason.</p>
+<h2 id="where-a-session-manager-stops" tabindex="-1">Where a session manager stops <a class="anchor" href="#where-a-session-manager-stops" aria-hidden="true">#</a></h2>
+<p>A session manager parallelizes agents; it doesn’t <em>coordinate</em> them. Three things stay your job:</p>
+<h3 id="1-agents-dont-share-what-they-learn" tabindex="-1">1. Agents don’t share what they learn <a class="anchor" href="#1-agents-dont-share-what-they-learn" aria-hidden="true">#</a></h3>
+<p>Each session has its own context. What agent A discovered, agent B can’t use — unless you copy it
+across yourself. There’s no shared, durable <a href="/blog/give-claude-code-long-term-memory/">long-term
+memory</a>, so the team forgets between (and across) runs.</p>
+<h3 id="2-agents-cant-talk-to-each-other" tabindex="-1">2. Agents can’t talk to each other <a class="anchor" href="#2-agents-cant-talk-to-each-other" aria-hidden="true">#</a></h3>
+<p>Coordination flows through <em>you</em>. There’s no mailbox for agent A to hand a result to agent B; you’re
+the message bus, relaying findings between sessions.</p>
+<h3 id="3-nothing-routes-the-work" tabindex="-1">3. Nothing routes the work <a class="anchor" href="#3-nothing-routes-the-work" aria-hidden="true">#</a></h3>
+<p>You assign every task by hand. For three agents that’s fine; for a dozen, deciding who does what
+becomes the bottleneck — and there’s no orchestrator to take it off your plate.</p>
+<p>None of these are bugs — they’re simply outside a session manager’s scope. They’re also exactly the
+things people go looking for an alternative to solve.</p>
+<h2 id="what-a-coordinated-hive-adds" tabindex="-1">What a coordinated hive adds <a class="anchor" href="#what-a-coordinated-hive-adds" aria-hidden="true">#</a></h2>
+<p>The alternative isn’t “a fancier terminal.” It’s a different <em>shape</em>: a <a href="/#what">multi-agent harness</a>
+that wraps the agents you already run and adds the coordination layer on top.</p>
+<ul>
+<li><strong>Shared memory.</strong> A semantic memory store (MemPalace) every agent reads and writes, so knowledge
+compounds instead of evaporating at the end of each session.</li>
+<li><strong>Inter-agent messaging.</strong> Each agent has a mailbox; a router delivers messages between them, so
+agent A hands work to agent B directly — no human courier.</li>
+<li><strong>An orchestrator.</strong> A <a href="/#how">GOD agent</a> you talk to in plain language decomposes your intent and
+routes work across the team, so you stop hand-assigning everything.</li>
+<li><strong>Visibility.</strong> The whole floor is rendered as avatars at their desks, so “what’s everyone doing?”
+has an answer at a glance.</li>
+</ul>
+<p>That’s <a href="/#what">Munder Difflin</a>: a local, open-source alternative built around coordination rather
+than just parallelism. It’s the same Claude Code you already run — just wired into a team.</p>
+<h2 id="which-should-you-pick" tabindex="-1">Which should you pick? <a class="anchor" href="#which-should-you-pick" aria-hidden="true">#</a></h2>
+<ul>
+<li><strong>Stay with Claude Squad</strong> if you value minimalism, live in the terminal, and your tasks are
+genuinely independent. It’s the right tool for that job.</li>
+<li><strong>Move to a hive</strong> if your agents need to share context, hand work to each other, or be routed for
+you — and if seeing the work matters.</li>
+</ul>
+<p>For a head-to-head on exactly this, read <a href="/blog/claude-squad-vs-munder-difflin/">Claude Squad vs Munder
+Difflin</a>, and for the wider field see <a href="/blog/best-claude-code-multi-agent-tools/">the best tools to run
+multiple Claude Code agents</a>.</p>
+<hr>
+<p>If “agents that remember and coordinate” is the alternative you’re after, the quickest way to feel
+the difference is to try it: <a href="/#install">download Munder Difflin</a> — free, open source, and local-first
+on macOS, Windows, and Linux.</p>
+
+
+
+
+
+ <hr />
+ <div class="share">
+ <span class="lbl">Tags</span>
+ <a class="tag" href="/blog/tags/comparisons/">Comparisons</a><a class="tag" href="/blog/tags/multi-agent/">Multi-Agent</a><a class="tag" href="/blog/tags/claude-code/">Claude Code</a><a class="tag" href="/blog/tags/tools/">Tools</a>
+ </div>
+
+ </div>
+
+
+ <aside class="toc-rail" aria-label="Table of contents">
+ <div class="tt">On this page</div>
+ <ol>
+ <li class="lvl-2"><a href="#what-claude-squad-does-well">What Claude Squad does well</a></li><li class="lvl-2"><a href="#where-a-session-manager-stops">Where a session manager stops</a></li><li class="lvl-3"><a href="#1-agents-dont-share-what-they-learn">1. Agents don’t share what they learn</a></li><li class="lvl-3"><a href="#2-agents-cant-talk-to-each-other">2. Agents can’t talk to each other</a></li><li class="lvl-3"><a href="#3-nothing-routes-the-work">3. Nothing routes the work</a></li><li class="lvl-2"><a href="#what-a-coordinated-hive-adds">What a coordinated hive adds</a></li><li class="lvl-2"><a href="#which-should-you-pick">Which should you pick?</a></li>
+ </ol>
+ </aside>
+
+ </div>
+
+ <footer class="post-foot wrap"><div class="prevnext">
+ <a class="pn prev" href="/blog/conductor-claude-code-alternative/"><span class="k">← Older</span><span class="t">A Conductor Alternative for Orchestrating Claude Code</span></a>
+ <a class="pn next" href="/blog/claude-code-hooks-explained/"><span class="k">Newer →</span><span class="t">Claude Code Hooks, Explained (PreToolUse, PostToolUse, Stop)</span></a>
+ </div>
+ <section class="related">
+ <h2>Related in Comparisons</h2>
+ <div class="post-grid">
+ <article class="card">
+ <a class="thumb t-comparisons" href="/blog/best-claude-code-multi-agent-tools/" aria-hidden="true" tabindex="-1">
+ <span>COMPARISONS</span>
+ </a>
+ <div class="body">
+ <div class="meta">
+ <time datetime="2026-06-04">Jun 4, 2026</time>
+ <span class="dot" aria-hidden="true"></span>
+ <span>6 min</span>
+ </div>
+ <h3><a href="/blog/best-claude-code-multi-agent-tools/">The Best Tools to Run Multiple Claude Code Agents (2026)</a></h3>
+ <p class="dek">An honest 2026 roundup of tools to run multiple Claude Code agents — Claude Squad, Conductor, Crystal, vibe-kanban, and Munder Difflin — compared.</p>
+ <div class="foot">
+ <span class="tag kind">Comparisons</span>
+ <a class="more" href="/blog/best-claude-code-multi-agent-tools/" aria-label="Read: The Best Tools to Run Multiple Claude Code Agents (2026)">Read →</a>
+ </div>
+ </div>
+</article>
+<article class="card">
+ <a class="thumb t-comparisons" href="/blog/claude-code-orchestration-tools-compared/" aria-hidden="true" tabindex="-1">
+ <span>COMPARISONS</span>
+ </a>
+ <div class="body">
+ <div class="meta">
+ <time datetime="2026-06-04">Jun 4, 2026</time>
+ <span class="dot" aria-hidden="true"></span>
+ <span>3 min</span>
+ </div>
+ <h3><a href="/blog/claude-code-orchestration-tools-compared/">Claude Code Orchestration Tools, Compared</a></h3>
+ <p class="dek">Claude Code orchestration tools compared on memory, messaging, visibility, control, and local-first — across Claude Squad, Conductor, Crystal, and more.</p>
+ <div class="foot">
+ <span class="tag kind">Comparisons</span>
+ <a class="more" href="/blog/claude-code-orchestration-tools-compared/" aria-label="Read: Claude Code Orchestration Tools, Compared">Read →</a>
+ </div>
+ </div>
+</article>
+<article class="card">
+ <a class="thumb t-comparisons" href="/blog/claude-squad-vs-munder-difflin/" aria-hidden="true" tabindex="-1">
+ <span>COMPARISONS</span>
+ </a>
+ <div class="body">
+ <div class="meta">
+ <time datetime="2026-06-04">Jun 4, 2026</time>
+ <span class="dot" aria-hidden="true"></span>
+ <span>3 min</span>
+ </div>
+ <h3><a href="/blog/claude-squad-vs-munder-difflin/">Claude Squad vs Munder Difflin: Which Should You Use?</a></h3>
+ <p class="dek">Claude Squad vs Munder Difflin: a lean terminal session manager against a memory-backed, orchestrated, visual hive. Feature table and an honest verdict.</p>
+ <div class="foot">
+ <span class="tag kind">Comparisons</span>
+ <a class="more" href="/blog/claude-squad-vs-munder-difflin/" aria-label="Read: Claude Squad vs Munder Difflin: Which Should You Use?">Read →</a>
+ </div>
+ </div>
+</article>
+
+ </div>
+ </section>
+
+ </footer>
+</article>
+
+</main>
+<footer>
+ <div class="wrap">
+ <div class="foot-top">
+ <a class="foot-brand brand" href="/blog/">
+ <span class="brand-mark">MD</span>
+ <span class="brand-word">MUNDER DIFFLIN<span class="sep">/</span><span class="blog">BLOG</span></span>
+ </a>
+ <div class="foot-links">
+ <a href="/blog/">Latest</a>
+ <a href="/blog/topics/">Topics</a>
+ <a href="/blog/about/">About</a>
+ <a href="https://munderdiffl.in/blog/feed.xml">RSS</a>
+ <a href="https://github.com/chaitanyagiri/munder-difflin">GitHub</a>
+ <a href="https://munderdiffl.in">munderdiffl.in ↗</a>
+ </div>
+ </div>
+ <div class="foot-meta">
+ © 2026 Munder Difflin · Local-first · MIT-licensed ·
+ Built on <a href="https://munderdiffl.in">Electron, React, Pixi.js, xterm.js &amp; node-pty</a>.
+ Run an office of agents while you sleep.
+ </div>
+ </div>
+</footer>
+
+<script>
+ // sticky-nav border on scroll
+ (function () {
+ var nav = document.getElementById('nav');
+ if (!nav) return;
+ var onScroll = function () { nav.classList.toggle('scrolled', window.scrollY > 8); };
+ onScroll(); window.addEventListener('scroll', onScroll, { passive: true });
+ })();
+</script>
+
+</body>
+</html>
diff --git a/docs/blog/claude-squad-vs-munder-difflin/index.html b/docs/blog/claude-squad-vs-munder-difflin/index.html
new file mode 100644
index 00000000..a3780339
--- /dev/null
+++ b/docs/blog/claude-squad-vs-munder-difflin/index.html
@@ -0,0 +1,401 @@
+<!doctype html>
+<html lang="en">
+<head>
+<meta charset="UTF-8" />
+<meta name="viewport" content="width=device-width, initial-scale=1.0" />
+<title>Claude Squad vs Munder Difflin: Which Should You Use? — Munder Difflin Blog</title>
+<meta name="description" content="Claude Squad vs Munder Difflin: a lean terminal session manager against a memory-backed, orchestrated, visual hive. Feature table and an honest verdict." />
+<link rel="canonical" href="https://munderdiffl.in/blog/claude-squad-vs-munder-difflin/" />
+
+<link rel="icon" type="image/png" href="https://munderdiffl.in/logo.png" />
+<link rel="apple-touch-icon" href="https://munderdiffl.in/logo.png" />
+<meta name="theme-color" content="#F5F2E8" />
+
+<!-- Open Graph -->
+<meta property="og:site_name" content="Munder Difflin Blog" />
+<meta property="og:type" content="article" />
+<meta property="og:title" content="Claude Squad vs Munder Difflin: Which Should You Use? — Munder Difflin Blog" />
+<meta property="og:description" content="Claude Squad vs Munder Difflin: a lean terminal session manager against a memory-backed, orchestrated, visual hive. Feature table and an honest verdict." />
+<meta property="og:url" content="https://munderdiffl.in/blog/claude-squad-vs-munder-difflin/" />
+<meta property="og:image" content="https://munderdiffl.in/media/og.png" />
+<meta property="og:locale" content="en_US" />
+<meta property="article:published_time" content="2026-06-04T00:00:00.000Z" />
+<meta property="article:author" content="Chaitanya Giri" />
+<meta property="article:tag" content="Comparisons" />
+<meta property="article:tag" content="Multi-Agent" />
+<meta property="article:tag" content="Claude Code" />
+<meta property="article:tag" content="Tools" />
+
+
+<!-- Twitter -->
+<meta name="twitter:card" content="summary_large_image" />
+<meta name="twitter:title" content="Claude Squad vs Munder Difflin: Which Should You Use? — Munder Difflin Blog" />
+<meta name="twitter:description" content="Claude Squad vs Munder Difflin: a lean terminal session manager against a memory-backed, orchestrated, visual hive. Feature table and an honest verdict." />
+<meta name="twitter:image" content="https://munderdiffl.in/media/og.png" />
+
+<link rel="alternate" type="application/atom+xml" title="Munder Difflin Blog" href="https://munderdiffl.in/blog/feed.xml" />
+<link rel="preconnect" href="https://fonts.googleapis.com" />
+<link rel="preconnect" href="https://fonts.gstatic.com" crossorigin />
+<link href="https://fonts.googleapis.com/css2?family=Geist:wght@400;500;600&family=JetBrains+Mono:wght@400;500;600;700&display=swap" rel="stylesheet" />
+<link rel="stylesheet" href="/blog/assets/blog.css" />
+
+<script type="application/ld+json">
+{
+ "@context": "https://schema.org",
+ "@type": "BlogPosting",
+ "headline": "Claude Squad vs Munder Difflin: Which Should You Use?",
+ "description": "Claude Squad vs Munder Difflin: a lean terminal session manager against a memory-backed, orchestrated, visual hive. Feature table and an honest verdict.",
+ "image": ["https://munderdiffl.in/media/og.png"],
+ "datePublished": "2026-06-04T00:00:00.000Z",
+ "dateModified": "2026-06-04T00:00:00.000Z",
+ "author": { "@type": "Person", "name": "Chaitanya Giri" },
+ "publisher": {
+ "@type": "Organization",
+ "name": "Munder Difflin",
+ "logo": { "@type": "ImageObject", "url": "https://munderdiffl.in/logo.png" }
+ },
+ "mainEntityOfPage": { "@type": "WebPage", "@id": "https://munderdiffl.in/blog/claude-squad-vs-munder-difflin/" },
+ "keywords": "claude squad vs munder difflin, claude squad vs munder difflin, claude code multi-agent tool, claude squad alternative",
+ "articleSection": "Comparisons",
+ "inLanguage": "en-US",
+ "url": "https://munderdiffl.in/blog/claude-squad-vs-munder-difflin/"
+}
+</script>
+<script type="application/ld+json">
+{
+ "@context": "https://schema.org",
+ "@type": "BreadcrumbList",
+ "itemListElement": [
+ { "@type": "ListItem", "position": 1, "name": "Home", "item": "https://munderdiffl.in/" },
+ { "@type": "ListItem", "position": 2, "name": "Blog", "item": "https://munderdiffl.in/blog/" },
+ { "@type": "ListItem", "position": 3, "name": "Claude Squad vs Munder Difflin: Which Should You Use?", "item": "https://munderdiffl.in/blog/claude-squad-vs-munder-difflin/" }
+ ]
+}
+</script>
+
+<script type="application/ld+json">
+{
+ "@context": "https://schema.org",
+ "@type": "FAQPage",
+ "mainEntity": [
+ { "@type": "Question", "name": "What's the main difference between Claude Squad and Munder Difflin?", "acceptedAnswer": { "@type": "Answer", "text": "Claude Squad is a lightweight terminal session manager that runs agents in parallel using tmux and git worktrees. Munder Difflin is a coordinated hive that adds shared long-term memory, inter-agent messaging, a GOD orchestrator, and a visual office floor — so the agents act as one team, not just parallel sessions." } },
+ { "@type": "Question", "name": "Is Munder Difflin heavier than Claude Squad?", "acceptedAnswer": { "@type": "Answer", "text": "Yes. Claude Squad is a minimal terminal tool; Munder Difflin is a desktop app with a visual floor and a coordination layer. For one or two quick parallel tasks, Claude Squad is less to think about. For a real team of agents that need to coordinate, Munder Difflin's extra weight earns its keep." } },
+ { "@type": "Question", "name": "Are both free and open source?", "acceptedAnswer": { "@type": "Answer", "text": "Yes — both are open source. Munder Difflin is MIT-licensed and runs on macOS, Windows, and Linux. Always check each project's current license before you rely on it." } }
+
+ ]
+}
+</script>
+
+
+</head>
+<body>
+<a class="skip-link" href="#main">Skip to content</a>
+<nav id="nav">
+ <a class="brand" href="/blog/" aria-label="Munder Difflin Blog home">
+ <span class="brand-mark">MD</span>
+ <span class="brand-word">MUNDER DIFFLIN<span class="sep">/</span><span class="blog">BLOG</span></span>
+ </a>
+ <span class="spacer"></span>
+ <div class="links">
+ <a href="/blog/">Latest</a>
+ <a href="/blog/topics/">Topics</a>
+ <a href="/blog/about/">About</a>
+ <a href="https://munderdiffl.in">↗ Product</a>
+ </div>
+ <div class="nav-actions">
+ <a class="btn sm" href="https://munderdiffl.in/blog/feed.xml" aria-label="RSS feed">⤵ RSS</a>
+ <a class="btn sm primary" href="https://munderdiffl.in/#install">⤓ Download</a>
+ </div>
+</nav>
+
+<main id="main">
+
+<article>
+ <header class="post-head wrap">
+ <nav class="crumbs" aria-label="Breadcrumb">
+ <a href="/blog/">Blog</a>
+ <span>/</span>
+ <a href="/blog/topics/comparisons/">Comparisons</a>
+ </nav>
+ <h1>Claude Squad vs Munder Difflin: Which Should You Use?</h1>
+ <p class="dek">Claude Squad vs Munder Difflin: a lean terminal session manager against a memory-backed, orchestrated, visual hive. Feature table and an honest verdict.</p>
+ <div class="byline">
+ <span class="av" aria-hidden="true">CG</span>
+ <strong>Chaitanya Giri</strong>
+ <span class="dot" aria-hidden="true">·</span>
+ <time datetime="2026-06-04">Jun 4, 2026</time>
+ <span class="dot" aria-hidden="true">·</span>
+ <span>3 min read</span>
+ <span class="tag kind">Comparisons</span>
+ </div>
+ </header>
+
+ <div class="post-wrap wrap">
+ <div class="prose">
+ <div class="callout tldr"><span class="ic">TL;DR</span><p><strong>Claude Squad</strong> wins on
+minimalism — a fast, terminal-native way to run parallel Claude Code agents. <strong>Munder
+Difflin</strong> wins on coordination — shared memory, inter-agent messaging, an orchestrator, and a
+visual floor. Choose Claude Squad for a few independent tasks in the terminal; choose Munder Difflin
+when coordination, not just parallelism, is the problem.</p></div>
+<p>These two tools are often compared, but they’re solving different problems. This is the honest
+head-to-head: where each is genuinely better, and how to decide.</p>
+<h2 id="the-one-line-difference" tabindex="-1">The one-line difference <a class="anchor" href="#the-one-line-difference" aria-hidden="true">#</a></h2>
+<ul>
+<li><strong>Claude Squad</strong> runs agents <em>in parallel</em>. It’s a terminal session manager.</li>
+<li><strong>Munder Difflin</strong> runs agents <em>as a team</em>. It’s a <a href="/#what">multi-agent harness</a>.</li>
+</ul>
+<p>Everything below is detail on that distinction.</p>
+<h2 id="feature-comparison" tabindex="-1">Feature comparison <a class="anchor" href="#feature-comparison" aria-hidden="true">#</a></h2>
+<table>
+<thead>
+<tr>
+<th></th>
+<th>Claude Squad</th>
+<th>Munder Difflin</th>
+</tr>
+</thead>
+<tbody>
+<tr>
+<td>Form factor</td>
+<td>Terminal UI (TUI)</td>
+<td>Desktop app (Electron)</td>
+</tr>
+<tr>
+<td>Parallelism</td>
+<td>tmux sessions + git worktrees</td>
+<td>Roles + mailboxes + orchestrator</td>
+</tr>
+<tr>
+<td>Shared long-term memory</td>
+<td>No</td>
+<td>Yes — semantic MemPalace</td>
+</tr>
+<tr>
+<td>Inter-agent messaging</td>
+<td>No</td>
+<td>Yes — mailboxes + router</td>
+</tr>
+<tr>
+<td>Orchestrator</td>
+<td>No (you assign)</td>
+<td>Yes — GOD agent you talk to</td>
+</tr>
+<tr>
+<td>Visibility</td>
+<td>TUI session list</td>
+<td>Live office floor (avatars)</td>
+</tr>
+<tr>
+<td>Footprint</td>
+<td>Featherweight</td>
+<td>Heavier (GUI + viz)</td>
+</tr>
+<tr>
+<td>SSH / remote</td>
+<td>Excellent</td>
+<td>Local desktop app</td>
+</tr>
+<tr>
+<td>Platforms</td>
+<td>Terminal (cross-platform)</td>
+<td>macOS, Windows, Linux</td>
+</tr>
+<tr>
+<td>License</td>
+<td>Open source</td>
+<td>Open source (MIT)</td>
+</tr>
+</tbody>
+</table>
+<p>No row makes one “win” outright — they reflect two philosophies. Claude Squad optimizes for <em>less</em>;
+Munder Difflin optimizes for <em>coordination</em>.</p>
+<h2 id="where-claude-squad-is-the-better-pick" tabindex="-1">Where Claude Squad is the better pick <a class="anchor" href="#where-claude-squad-is-the-better-pick" aria-hidden="true">#</a></h2>
+<ul>
+<li><strong>You live in the terminal.</strong> No GUI, no Electron — it’s fast and it stays out of the way.</li>
+<li><strong>You work over SSH.</strong> Driving a fleet of agents on a remote box from one connection is Claude
+Squad’s home turf.</li>
+<li><strong>Your tasks are independent.</strong> Three unrelated jobs in three worktrees don’t need a memory layer
+or an orchestrator — they need isolation, which Claude Squad gives you cleanly.</li>
+<li><strong>You want minimal moving parts.</strong> Fewer features can be a feature.</li>
+</ul>
+<p>If that’s you, Claude Squad is the right tool and the visual floor would just be overhead. Be honest
+about your workload before you reach for more.</p>
+<h2 id="where-munder-difflin-is-the-better-pick" tabindex="-1">Where Munder Difflin is the better pick <a class="anchor" href="#where-munder-difflin-is-the-better-pick" aria-hidden="true">#</a></h2>
+<ul>
+<li><strong>Your agents need to share what they learn.</strong> <a href="/blog/give-claude-code-long-term-memory/">Long-term
+memory</a> (MemPalace) means knowledge compounds instead of
+resetting every session.</li>
+<li><strong>Agents need to hand work to each other.</strong> Mailboxes + a router let agent A pass a result to agent
+B without you relaying it.</li>
+<li><strong>You don’t want to assign every task.</strong> A <a href="/#how">GOD orchestrator</a> you talk to in plain language
+decomposes intent and routes work for you.</li>
+<li><strong>Seeing the work matters.</strong> A live office floor turns “what’s everyone doing?” into a glance —
+useful for trust and for catching problems early.</li>
+</ul>
+<p>In short: when <em>coordination</em> is the cost, the coordination layer pays for itself.</p>
+<h2 id="the-verdict" tabindex="-1">The verdict <a class="anchor" href="#the-verdict" aria-hidden="true">#</a></h2>
+<p>There’s no universal winner — there’s a right tool for your workload:</p>
+<ul>
+<li><strong>A few independent tasks, terminal-first, minimal:</strong> Claude Squad.</li>
+<li><strong>A coordinated team that remembers, messages, and routes:</strong> Munder Difflin.</li>
+</ul>
+<p>Many people start on Claude Squad and move to a hive exactly when they hit the coordination wall —
+the same arc as <a href="/blog/from-one-terminal-to-a-team/">going from one terminal to a team</a>. If you’re
+still scoping the field, read <a href="/blog/best-claude-code-multi-agent-tools/">the best tools to run multiple Claude Code
+agents</a>, or if you’ve already outgrown a session manager,
+<a href="/blog/claude-squad-alternative/">looking for a Claude Squad alternative</a> goes deeper on the gap.</p>
+<hr>
+<blockquote>
+<p>Both tools evolve quickly — check each project’s repo for current details. Munder Difflin is our own
+tool; we’ve tried to give Claude Squad a fair shake.</p>
+</blockquote>
+<p>Curious how a coordinated hive feels? <a href="/#install">Download Munder Difflin</a> — free, open source, and
+local-first.</p>
+
+
+
+ <section class="faq" aria-label="Frequently asked questions">
+ <h2 id="faq">FAQ</h2>
+
+ <div class="qa">
+ <p class="q">What&#39;s the main difference between Claude Squad and Munder Difflin?</p>
+ <p class="a">Claude Squad is a lightweight terminal session manager that runs agents in parallel using tmux and git worktrees. Munder Difflin is a coordinated hive that adds shared long-term memory, inter-agent messaging, a GOD orchestrator, and a visual office floor — so the agents act as one team, not just parallel sessions.</p>
+ </div>
+
+ <div class="qa">
+ <p class="q">Is Munder Difflin heavier than Claude Squad?</p>
+ <p class="a">Yes. Claude Squad is a minimal terminal tool; Munder Difflin is a desktop app with a visual floor and a coordination layer. For one or two quick parallel tasks, Claude Squad is less to think about. For a real team of agents that need to coordinate, Munder Difflin&#39;s extra weight earns its keep.</p>
+ </div>
+
+ <div class="qa">
+ <p class="q">Are both free and open source?</p>
+ <p class="a">Yes — both are open source. Munder Difflin is MIT-licensed and runs on macOS, Windows, and Linux. Always check each project&#39;s current license before you rely on it.</p>
+ </div>
+
+ </section>
+
+
+
+ <hr />
+ <div class="share">
+ <span class="lbl">Tags</span>
+ <a class="tag" href="/blog/tags/comparisons/">Comparisons</a><a class="tag" href="/blog/tags/multi-agent/">Multi-Agent</a><a class="tag" href="/blog/tags/claude-code/">Claude Code</a><a class="tag" href="/blog/tags/tools/">Tools</a>
+ </div>
+
+ </div>
+
+
+ <aside class="toc-rail" aria-label="Table of contents">
+ <div class="tt">On this page</div>
+ <ol>
+ <li class="lvl-2"><a href="#the-one-line-difference">The one-line difference</a></li><li class="lvl-2"><a href="#feature-comparison">Feature comparison</a></li><li class="lvl-2"><a href="#where-claude-squad-is-the-better-pick">Where Claude Squad is the better pick</a></li><li class="lvl-2"><a href="#where-munder-difflin-is-the-better-pick">Where Munder Difflin is the better pick</a></li><li class="lvl-2"><a href="#the-verdict">The verdict</a></li>
+ </ol>
+ </aside>
+
+ </div>
+
+ <footer class="post-foot wrap"><div class="prevnext">
+ <a class="pn prev" href="/blog/building-a-terminal-ui-xterm-node-pty/"><span class="k">← Older</span><span class="t">Building a Terminal UI with xterm.js and node-pty</span></a>
+ <a class="pn next" href="/blog/claude-code-orchestration-tools-compared/"><span class="k">Newer →</span><span class="t">Claude Code Orchestration Tools, Compared</span></a>
+ </div>
+ <section class="related">
+ <h2>Related in Comparisons</h2>
+ <div class="post-grid">
+ <article class="card">
+ <a class="thumb t-comparisons" href="/blog/best-claude-code-multi-agent-tools/" aria-hidden="true" tabindex="-1">
+ <span>COMPARISONS</span>
+ </a>
+ <div class="body">
+ <div class="meta">
+ <time datetime="2026-06-04">Jun 4, 2026</time>
+ <span class="dot" aria-hidden="true"></span>
+ <span>6 min</span>
+ </div>
+ <h3><a href="/blog/best-claude-code-multi-agent-tools/">The Best Tools to Run Multiple Claude Code Agents (2026)</a></h3>
+ <p class="dek">An honest 2026 roundup of tools to run multiple Claude Code agents — Claude Squad, Conductor, Crystal, vibe-kanban, and Munder Difflin — compared.</p>
+ <div class="foot">
+ <span class="tag kind">Comparisons</span>
+ <a class="more" href="/blog/best-claude-code-multi-agent-tools/" aria-label="Read: The Best Tools to Run Multiple Claude Code Agents (2026)">Read →</a>
+ </div>
+ </div>
+</article>
+<article class="card">
+ <a class="thumb t-comparisons" href="/blog/claude-code-orchestration-tools-compared/" aria-hidden="true" tabindex="-1">
+ <span>COMPARISONS</span>
+ </a>
+ <div class="body">
+ <div class="meta">
+ <time datetime="2026-06-04">Jun 4, 2026</time>
+ <span class="dot" aria-hidden="true"></span>
+ <span>3 min</span>
+ </div>
+ <h3><a href="/blog/claude-code-orchestration-tools-compared/">Claude Code Orchestration Tools, Compared</a></h3>
+ <p class="dek">Claude Code orchestration tools compared on memory, messaging, visibility, control, and local-first — across Claude Squad, Conductor, Crystal, and more.</p>
+ <div class="foot">
+ <span class="tag kind">Comparisons</span>
+ <a class="more" href="/blog/claude-code-orchestration-tools-compared/" aria-label="Read: Claude Code Orchestration Tools, Compared">Read →</a>
+ </div>
+ </div>
+</article>
+<article class="card">
+ <a class="thumb t-comparisons" href="/blog/claude-squad-alternative/" aria-hidden="true" tabindex="-1">
+ <span>COMPARISONS</span>
+ </a>
+ <div class="body">
+ <div class="meta">
+ <time datetime="2026-06-03">Jun 3, 2026</time>
+ <span class="dot" aria-hidden="true"></span>
+ <span>3 min</span>
+ </div>
+ <h3><a href="/blog/claude-squad-alternative/">Looking for a Claude Squad Alternative?</a></h3>
+ <p class="dek">What Claude Squad does well, where it stops, and why a memory-backed, orchestrated hive may be the Claude Squad alternative you&#39;re after.</p>
+ <div class="foot">
+ <span class="tag kind">Comparisons</span>
+ <a class="more" href="/blog/claude-squad-alternative/" aria-label="Read: Looking for a Claude Squad Alternative?">Read →</a>
+ </div>
+ </div>
+</article>
+
+ </div>
+ </section>
+
+ </footer>
+</article>
+
+</main>
+<footer>
+ <div class="wrap">
+ <div class="foot-top">
+ <a class="foot-brand brand" href="/blog/">
+ <span class="brand-mark">MD</span>
+ <span class="brand-word">MUNDER DIFFLIN<span class="sep">/</span><span class="blog">BLOG</span></span>
+ </a>
+ <div class="foot-links">
+ <a href="/blog/">Latest</a>
+ <a href="/blog/topics/">Topics</a>
+ <a href="/blog/about/">About</a>
+ <a href="https://munderdiffl.in/blog/feed.xml">RSS</a>
+ <a href="https://github.com/chaitanyagiri/munder-difflin">GitHub</a>
+ <a href="https://munderdiffl.in">munderdiffl.in ↗</a>
+ </div>
+ </div>
+ <div class="foot-meta">
+ © 2026 Munder Difflin · Local-first · MIT-licensed ·
+ Built on <a href="https://munderdiffl.in">Electron, React, Pixi.js, xterm.js &amp; node-pty</a>.
+ Run an office of agents while you sleep.
+ </div>
+ </div>
+</footer>
+
+<script>
+ // sticky-nav border on scroll
+ (function () {
+ var nav = document.getElementById('nav');
+ if (!nav) return;
+ var onScroll = function () { nav.classList.toggle('scrolled', window.scrollY > 8); };
+ onScroll(); window.addEventListener('scroll', onScroll, { passive: true });
+ })();
+</script>
+
+</body>
+</html>
diff --git a/docs/blog/conductor-claude-code-alternative/index.html b/docs/blog/conductor-claude-code-alternative/index.html
new file mode 100644
index 00000000..4c0b2cd2
--- /dev/null
+++ b/docs/blog/conductor-claude-code-alternative/index.html
@@ -0,0 +1,315 @@
+<!doctype html>
+<html lang="en">
+<head>
+<meta charset="UTF-8" />
+<meta name="viewport" content="width=device-width, initial-scale=1.0" />
+<title>A Conductor Alternative for Orchestrating Claude Code — Munder Difflin Blog</title>
+<meta name="description" content="Conductor is a polished macOS app for parallel Claude Code worktrees. When to pick a cross-platform, orchestrated hive as your Conductor alternative." />
+<link rel="canonical" href="https://munderdiffl.in/blog/conductor-claude-code-alternative/" />
+
+<link rel="icon" type="image/png" href="https://munderdiffl.in/logo.png" />
+<link rel="apple-touch-icon" href="https://munderdiffl.in/logo.png" />
+<meta name="theme-color" content="#F5F2E8" />
+
+<!-- Open Graph -->
+<meta property="og:site_name" content="Munder Difflin Blog" />
+<meta property="og:type" content="article" />
+<meta property="og:title" content="A Conductor Alternative for Orchestrating Claude Code — Munder Difflin Blog" />
+<meta property="og:description" content="Conductor is a polished macOS app for parallel Claude Code worktrees. When to pick a cross-platform, orchestrated hive as your Conductor alternative." />
+<meta property="og:url" content="https://munderdiffl.in/blog/conductor-claude-code-alternative/" />
+<meta property="og:image" content="https://munderdiffl.in/media/og.png" />
+<meta property="og:locale" content="en_US" />
+<meta property="article:published_time" content="2026-06-03T00:00:00.000Z" />
+<meta property="article:author" content="Chaitanya Giri" />
+<meta property="article:tag" content="Comparisons" />
+<meta property="article:tag" content="Orchestration" />
+<meta property="article:tag" content="Claude Code" />
+<meta property="article:tag" content="Tools" />
+
+
+<!-- Twitter -->
+<meta name="twitter:card" content="summary_large_image" />
+<meta name="twitter:title" content="A Conductor Alternative for Orchestrating Claude Code — Munder Difflin Blog" />
+<meta name="twitter:description" content="Conductor is a polished macOS app for parallel Claude Code worktrees. When to pick a cross-platform, orchestrated hive as your Conductor alternative." />
+<meta name="twitter:image" content="https://munderdiffl.in/media/og.png" />
+
+<link rel="alternate" type="application/atom+xml" title="Munder Difflin Blog" href="https://munderdiffl.in/blog/feed.xml" />
+<link rel="preconnect" href="https://fonts.googleapis.com" />
+<link rel="preconnect" href="https://fonts.gstatic.com" crossorigin />
+<link href="https://fonts.googleapis.com/css2?family=Geist:wght@400;500;600&family=JetBrains+Mono:wght@400;500;600;700&display=swap" rel="stylesheet" />
+<link rel="stylesheet" href="/blog/assets/blog.css" />
+
+<script type="application/ld+json">
+{
+ "@context": "https://schema.org",
+ "@type": "BlogPosting",
+ "headline": "A Conductor Alternative for Orchestrating Claude Code",
+ "description": "Conductor is a polished macOS app for parallel Claude Code worktrees. When to pick a cross-platform, orchestrated hive as your Conductor alternative.",
+ "image": ["https://munderdiffl.in/media/og.png"],
+ "datePublished": "2026-06-03T00:00:00.000Z",
+ "dateModified": "2026-06-03T00:00:00.000Z",
+ "author": { "@type": "Person", "name": "Chaitanya Giri" },
+ "publisher": {
+ "@type": "Organization",
+ "name": "Munder Difflin",
+ "logo": { "@type": "ImageObject", "url": "https://munderdiffl.in/logo.png" }
+ },
+ "mainEntityOfPage": { "@type": "WebPage", "@id": "https://munderdiffl.in/blog/conductor-claude-code-alternative/" },
+ "keywords": "conductor claude code alternative, conductor claude code alternative, claude code orchestration tools, claude code multi-agent tool",
+ "articleSection": "Comparisons",
+ "inLanguage": "en-US",
+ "url": "https://munderdiffl.in/blog/conductor-claude-code-alternative/"
+}
+</script>
+<script type="application/ld+json">
+{
+ "@context": "https://schema.org",
+ "@type": "BreadcrumbList",
+ "itemListElement": [
+ { "@type": "ListItem", "position": 1, "name": "Home", "item": "https://munderdiffl.in/" },
+ { "@type": "ListItem", "position": 2, "name": "Blog", "item": "https://munderdiffl.in/blog/" },
+ { "@type": "ListItem", "position": 3, "name": "A Conductor Alternative for Orchestrating Claude Code", "item": "https://munderdiffl.in/blog/conductor-claude-code-alternative/" }
+ ]
+}
+</script>
+
+
+</head>
+<body>
+<a class="skip-link" href="#main">Skip to content</a>
+<nav id="nav">
+ <a class="brand" href="/blog/" aria-label="Munder Difflin Blog home">
+ <span class="brand-mark">MD</span>
+ <span class="brand-word">MUNDER DIFFLIN<span class="sep">/</span><span class="blog">BLOG</span></span>
+ </a>
+ <span class="spacer"></span>
+ <div class="links">
+ <a href="/blog/">Latest</a>
+ <a href="/blog/topics/">Topics</a>
+ <a href="/blog/about/">About</a>
+ <a href="https://munderdiffl.in">↗ Product</a>
+ </div>
+ <div class="nav-actions">
+ <a class="btn sm" href="https://munderdiffl.in/blog/feed.xml" aria-label="RSS feed">⤵ RSS</a>
+ <a class="btn sm primary" href="https://munderdiffl.in/#install">⤓ Download</a>
+ </div>
+</nav>
+
+<main id="main">
+
+<article>
+ <header class="post-head wrap">
+ <nav class="crumbs" aria-label="Breadcrumb">
+ <a href="/blog/">Blog</a>
+ <span>/</span>
+ <a href="/blog/topics/comparisons/">Comparisons</a>
+ </nav>
+ <h1>A Conductor Alternative for Orchestrating Claude Code</h1>
+ <p class="dek">Conductor is a polished macOS app for parallel Claude Code worktrees. When to pick a cross-platform, orchestrated hive as your Conductor alternative.</p>
+ <div class="byline">
+ <span class="av" aria-hidden="true">CG</span>
+ <strong>Chaitanya Giri</strong>
+ <span class="dot" aria-hidden="true">·</span>
+ <time datetime="2026-06-03">Jun 3, 2026</time>
+ <span class="dot" aria-hidden="true">·</span>
+ <span>3 min read</span>
+ <span class="tag kind">Comparisons</span>
+ </div>
+ </header>
+
+ <div class="post-wrap wrap">
+ <div class="prose">
+ <div class="callout tldr"><span class="ic">TL;DR</span><p><strong>Conductor</strong> is a polished,
+native macOS app for running Claude Code agents in parallel git worktrees with clean diff review. You
+might want a <strong>Conductor alternative</strong> if you're not on a Mac, want open source, or need
+real <strong>orchestration</strong> — agents that share memory, message each other, and are routed by
+a coordinator — rather than parallel isolated workspaces.</p></div>
+<p><a href="https://conductor.build">Conductor</a> earned its reputation honestly: it’s one of the nicest ways to
+run parallel Claude Code on a Mac. So this isn’t a takedown — it’s a map of when its model fits and
+when you’d reach for something else.</p>
+<h2 id="what-conductor-does-well" tabindex="-1">What Conductor does well <a class="anchor" href="#what-conductor-does-well" aria-hidden="true">#</a></h2>
+<p>Conductor is a native macOS app that runs Claude Code agents in parallel, each in its own isolated
+git worktree, with a refined GUI for launching tasks and reviewing the diffs they produce.</p>
+<ul>
+<li><strong>The UX is genuinely good.</strong> It feels like a Mac app, not a wrapped web page.</li>
+<li><strong>Parallel worktrees are first-class.</strong> Kick off several agents on the same repo without them
+stepping on each other’s files.</li>
+<li><strong>Diff review is fast.</strong> Seeing what each agent changed, side by side, is the core loop and it’s
+smooth.</li>
+</ul>
+<p>If you’re a Mac user whose workflow is “spin up N parallel attempts and review the diffs,” Conductor
+is a strong fit. The reasons to look elsewhere are specific.</p>
+<h2 id="where-youd-want-an-alternative" tabindex="-1">Where you’d want an alternative <a class="anchor" href="#where-youd-want-an-alternative" aria-hidden="true">#</a></h2>
+<h3 id="its-macos-only" tabindex="-1">It’s macOS-only <a class="anchor" href="#its-macos-only" aria-hidden="true">#</a></h3>
+<p>If you’re on Windows or Linux — or you bounce between machines — a Mac-only app is a hard stop. A
+<a href="/blog/why-local-first-matters-for-ai-agents/">local-first</a> cross-platform tool keeps your workflow
+consistent everywhere.</p>
+<h3 id="its-parallelism-not-orchestration" tabindex="-1">It’s parallelism, not orchestration <a class="anchor" href="#its-parallelism-not-orchestration" aria-hidden="true">#</a></h3>
+<p>Conductor runs agents <em>beside</em> each other in isolated worktrees. What it doesn’t do is <em>coordinate</em>
+them: there’s no shared long-term memory between agents, no agent-to-agent messaging, and no
+orchestrator that decomposes your intent and routes work. You’re still the one assigning tasks and
+ferrying context between worktrees.</p>
+<h3 id="its-closed-source" tabindex="-1">It’s closed-source <a class="anchor" href="#its-closed-source" aria-hidden="true">#</a></h3>
+<p>You can’t read the internals, self-host changes, or extend it. For some teams that’s fine; for others
+— especially open-source-minded ones — it’s a dealbreaker.</p>
+<h2 id="what-orchestration-actually-means" tabindex="-1">What “orchestration” actually means <a class="anchor" href="#what-orchestration-actually-means" aria-hidden="true">#</a></h2>
+<p>The word <em>conductor</em> implies coordination, so it’s worth being precise about what full
+<a href="/#how">orchestration</a> looks like for coding agents:</p>
+<ul>
+<li><strong>A coordinator that routes.</strong> You describe intent once; an orchestrator decomposes it and assigns
+the pieces — instead of you hand-launching each agent.</li>
+<li><strong>A shared brain.</strong> A <a href="/blog/give-claude-code-long-term-memory/">long-term memory</a> layer every
+agent reads and writes, so the team’s knowledge compounds.</li>
+<li><strong>Direct messaging.</strong> Agents hand work and findings to each other through mailboxes, not through
+you.</li>
+<li><strong>Adjudication + escalation.</strong> The coordinator resolves the routine and escalates only the
+genuinely critical (spend, destructive ops, scope) for your sign-off.</li>
+</ul>
+<p>That’s the model behind <a href="/#what">Munder Difflin</a>: a <a href="/#how">GOD orchestrator</a> you talk to in plain
+language, shared MemPalace memory, inter-agent messaging, and a watchable office floor — open source
+(MIT) and running on macOS, Windows, and Linux.</p>
+<h2 id="conductor-vs-an-orchestrated-hive" tabindex="-1">Conductor vs an orchestrated hive <a class="anchor" href="#conductor-vs-an-orchestrated-hive" aria-hidden="true">#</a></h2>
+<ul>
+<li><strong>Conductor</strong> is the better choice if you’re on a Mac and your loop is parallel worktrees + diff
+review, and you don’t need agents to coordinate.</li>
+<li><strong>An orchestrated hive</strong> is the better choice if you want cross-platform, open source, shared
+memory, messaging, and a coordinator that routes work for you.</li>
+</ul>
+<p>For the broader field, see <a href="/blog/best-claude-code-multi-agent-tools/">the best tools to run multiple Claude Code
+agents</a> and a criteria-based <a href="/blog/claude-code-orchestration-tools-compared/">orchestration tools
+comparison</a>.</p>
+<hr>
+<blockquote>
+<p>Features and platforms change — check Conductor’s site for current details. Munder Difflin is our
+own tool; we’ve described Conductor on its own terms.</p>
+</blockquote>
+<p>If real orchestration is what you’re missing, <a href="/#install">download Munder Difflin</a> and run a
+coordinated team locally — it’s free and open source.</p>
+
+
+
+
+
+ <hr />
+ <div class="share">
+ <span class="lbl">Tags</span>
+ <a class="tag" href="/blog/tags/comparisons/">Comparisons</a><a class="tag" href="/blog/tags/orchestration/">Orchestration</a><a class="tag" href="/blog/tags/claude-code/">Claude Code</a><a class="tag" href="/blog/tags/tools/">Tools</a>
+ </div>
+
+ </div>
+
+
+ <aside class="toc-rail" aria-label="Table of contents">
+ <div class="tt">On this page</div>
+ <ol>
+ <li class="lvl-2"><a href="#what-conductor-does-well">What Conductor does well</a></li><li class="lvl-2"><a href="#where-youd-want-an-alternative">Where you’d want an alternative</a></li><li class="lvl-3"><a href="#its-macos-only">It’s macOS-only</a></li><li class="lvl-3"><a href="#its-parallelism-not-orchestration">It’s parallelism, not orchestration</a></li><li class="lvl-3"><a href="#its-closed-source">It’s closed-source</a></li><li class="lvl-2"><a href="#what-orchestration-actually-means">What “orchestration” actually means</a></li><li class="lvl-2"><a href="#conductor-vs-an-orchestrated-hive">Conductor vs an orchestrated hive</a></li>
+ </ol>
+ </aside>
+
+ </div>
+
+ <footer class="post-foot wrap"><div class="prevnext">
+ <a class="pn prev" href="/blog/crystal-claude-code-alternative/"><span class="k">← Older</span><span class="t">A Crystal Alternative: Multi-Agent Claude Code with Memory</span></a>
+ <a class="pn next" href="/blog/claude-squad-alternative/"><span class="k">Newer →</span><span class="t">Looking for a Claude Squad Alternative?</span></a>
+ </div>
+ <section class="related">
+ <h2>Related in Comparisons</h2>
+ <div class="post-grid">
+ <article class="card">
+ <a class="thumb t-comparisons" href="/blog/best-claude-code-multi-agent-tools/" aria-hidden="true" tabindex="-1">
+ <span>COMPARISONS</span>
+ </a>
+ <div class="body">
+ <div class="meta">
+ <time datetime="2026-06-04">Jun 4, 2026</time>
+ <span class="dot" aria-hidden="true"></span>
+ <span>6 min</span>
+ </div>
+ <h3><a href="/blog/best-claude-code-multi-agent-tools/">The Best Tools to Run Multiple Claude Code Agents (2026)</a></h3>
+ <p class="dek">An honest 2026 roundup of tools to run multiple Claude Code agents — Claude Squad, Conductor, Crystal, vibe-kanban, and Munder Difflin — compared.</p>
+ <div class="foot">
+ <span class="tag kind">Comparisons</span>
+ <a class="more" href="/blog/best-claude-code-multi-agent-tools/" aria-label="Read: The Best Tools to Run Multiple Claude Code Agents (2026)">Read →</a>
+ </div>
+ </div>
+</article>
+<article class="card">
+ <a class="thumb t-comparisons" href="/blog/claude-code-orchestration-tools-compared/" aria-hidden="true" tabindex="-1">
+ <span>COMPARISONS</span>
+ </a>
+ <div class="body">
+ <div class="meta">
+ <time datetime="2026-06-04">Jun 4, 2026</time>
+ <span class="dot" aria-hidden="true"></span>
+ <span>3 min</span>
+ </div>
+ <h3><a href="/blog/claude-code-orchestration-tools-compared/">Claude Code Orchestration Tools, Compared</a></h3>
+ <p class="dek">Claude Code orchestration tools compared on memory, messaging, visibility, control, and local-first — across Claude Squad, Conductor, Crystal, and more.</p>
+ <div class="foot">
+ <span class="tag kind">Comparisons</span>
+ <a class="more" href="/blog/claude-code-orchestration-tools-compared/" aria-label="Read: Claude Code Orchestration Tools, Compared">Read →</a>
+ </div>
+ </div>
+</article>
+<article class="card">
+ <a class="thumb t-comparisons" href="/blog/claude-squad-vs-munder-difflin/" aria-hidden="true" tabindex="-1">
+ <span>COMPARISONS</span>
+ </a>
+ <div class="body">
+ <div class="meta">
+ <time datetime="2026-06-04">Jun 4, 2026</time>
+ <span class="dot" aria-hidden="true"></span>
+ <span>3 min</span>
+ </div>
+ <h3><a href="/blog/claude-squad-vs-munder-difflin/">Claude Squad vs Munder Difflin: Which Should You Use?</a></h3>
+ <p class="dek">Claude Squad vs Munder Difflin: a lean terminal session manager against a memory-backed, orchestrated, visual hive. Feature table and an honest verdict.</p>
+ <div class="foot">
+ <span class="tag kind">Comparisons</span>
+ <a class="more" href="/blog/claude-squad-vs-munder-difflin/" aria-label="Read: Claude Squad vs Munder Difflin: Which Should You Use?">Read →</a>
+ </div>
+ </div>
+</article>
+
+ </div>
+ </section>
+
+ </footer>
+</article>
+
+</main>
+<footer>
+ <div class="wrap">
+ <div class="foot-top">
+ <a class="foot-brand brand" href="/blog/">
+ <span class="brand-mark">MD</span>
+ <span class="brand-word">MUNDER DIFFLIN<span class="sep">/</span><span class="blog">BLOG</span></span>
+ </a>
+ <div class="foot-links">
+ <a href="/blog/">Latest</a>
+ <a href="/blog/topics/">Topics</a>
+ <a href="/blog/about/">About</a>
+ <a href="https://munderdiffl.in/blog/feed.xml">RSS</a>
+ <a href="https://github.com/chaitanyagiri/munder-difflin">GitHub</a>
+ <a href="https://munderdiffl.in">munderdiffl.in ↗</a>
+ </div>
+ </div>
+ <div class="foot-meta">
+ © 2026 Munder Difflin · Local-first · MIT-licensed ·
+ Built on <a href="https://munderdiffl.in">Electron, React, Pixi.js, xterm.js &amp; node-pty</a>.
+ Run an office of agents while you sleep.
+ </div>
+ </div>
+</footer>
+
+<script>
+ // sticky-nav border on scroll
+ (function () {
+ var nav = document.getElementById('nav');
+ if (!nav) return;
+ var onScroll = function () { nav.classList.toggle('scrolled', window.scrollY > 8); };
+ onScroll(); window.addEventListener('scroll', onScroll, { passive: true });
+ })();
+</script>
+
+</body>
+</html>
diff --git a/docs/blog/coordinating-ai-coding-agents/index.html b/docs/blog/coordinating-ai-coding-agents/index.html
new file mode 100644
index 00000000..6f37bfc3
--- /dev/null
+++ b/docs/blog/coordinating-ai-coding-agents/index.html
@@ -0,0 +1,375 @@
+<!doctype html>
+<html lang="en">
+<head>
+<meta charset="UTF-8" />
+<meta name="viewport" content="width=device-width, initial-scale=1.0" />
+<title>The Best Way to Coordinate AI Coding Agents — Munder Difflin Blog</title>
+<meta name="description" content="The best way to coordinate AI coding agents: single-writer files, a message router, a one-scribe plan, and an orchestrator — cooperate, not clobber." />
+<link rel="canonical" href="https://munderdiffl.in/blog/coordinating-ai-coding-agents/" />
+
+<link rel="icon" type="image/png" href="https://munderdiffl.in/logo.png" />
+<link rel="apple-touch-icon" href="https://munderdiffl.in/logo.png" />
+<meta name="theme-color" content="#F5F2E8" />
+
+<!-- Open Graph -->
+<meta property="og:site_name" content="Munder Difflin Blog" />
+<meta property="og:type" content="article" />
+<meta property="og:title" content="The Best Way to Coordinate AI Coding Agents — Munder Difflin Blog" />
+<meta property="og:description" content="The best way to coordinate AI coding agents: single-writer files, a message router, a one-scribe plan, and an orchestrator — cooperate, not clobber." />
+<meta property="og:url" content="https://munderdiffl.in/blog/coordinating-ai-coding-agents/" />
+<meta property="og:image" content="https://munderdiffl.in/media/og.png" />
+<meta property="og:locale" content="en_US" />
+<meta property="article:published_time" content="2026-05-29T00:00:00.000Z" />
+<meta property="article:author" content="Chaitanya Giri" />
+<meta property="article:tag" content="Orchestration" />
+<meta property="article:tag" content="Multi-Agent" />
+<meta property="article:tag" content="Coordination" />
+<meta property="article:tag" content="Claude Code" />
+
+
+<!-- Twitter -->
+<meta name="twitter:card" content="summary_large_image" />
+<meta name="twitter:title" content="The Best Way to Coordinate AI Coding Agents — Munder Difflin Blog" />
+<meta name="twitter:description" content="The best way to coordinate AI coding agents: single-writer files, a message router, a one-scribe plan, and an orchestrator — cooperate, not clobber." />
+<meta name="twitter:image" content="https://munderdiffl.in/media/og.png" />
+
+<link rel="alternate" type="application/atom+xml" title="Munder Difflin Blog" href="https://munderdiffl.in/blog/feed.xml" />
+<link rel="preconnect" href="https://fonts.googleapis.com" />
+<link rel="preconnect" href="https://fonts.gstatic.com" crossorigin />
+<link href="https://fonts.googleapis.com/css2?family=Geist:wght@400;500;600&family=JetBrains+Mono:wght@400;500;600;700&display=swap" rel="stylesheet" />
+<link rel="stylesheet" href="/blog/assets/blog.css" />
+
+<script type="application/ld+json">
+{
+ "@context": "https://schema.org",
+ "@type": "BlogPosting",
+ "headline": "The Best Way to Coordinate AI Coding Agents",
+ "description": "The best way to coordinate AI coding agents: single-writer files, a message router, a one-scribe plan, and an orchestrator — cooperate, not clobber.",
+ "image": ["https://munderdiffl.in/media/og.png"],
+ "datePublished": "2026-05-29T00:00:00.000Z",
+ "dateModified": "2026-05-29T00:00:00.000Z",
+ "author": { "@type": "Person", "name": "Chaitanya Giri" },
+ "publisher": {
+ "@type": "Organization",
+ "name": "Munder Difflin",
+ "logo": { "@type": "ImageObject", "url": "https://munderdiffl.in/logo.png" }
+ },
+ "mainEntityOfPage": { "@type": "WebPage", "@id": "https://munderdiffl.in/blog/coordinating-ai-coding-agents/" },
+ "keywords": "best way to coordinate ai coding agents, coordinate ai agents, ai coding agent teams, agent collaboration",
+ "articleSection": "Orchestration",
+ "inLanguage": "en-US",
+ "url": "https://munderdiffl.in/blog/coordinating-ai-coding-agents/"
+}
+</script>
+<script type="application/ld+json">
+{
+ "@context": "https://schema.org",
+ "@type": "BreadcrumbList",
+ "itemListElement": [
+ { "@type": "ListItem", "position": 1, "name": "Home", "item": "https://munderdiffl.in/" },
+ { "@type": "ListItem", "position": 2, "name": "Blog", "item": "https://munderdiffl.in/blog/" },
+ { "@type": "ListItem", "position": 3, "name": "The Best Way to Coordinate AI Coding Agents", "item": "https://munderdiffl.in/blog/coordinating-ai-coding-agents/" }
+ ]
+}
+</script>
+
+<script type="application/ld+json">
+{
+ "@context": "https://schema.org",
+ "@type": "FAQPage",
+ "mainEntity": [
+ { "@type": "Question", "name": "What's the most common way multi-agent coding setups fail?", "acceptedAnswer": { "@type": "Answer", "text": "Two agents writing the same thing at the same time — the same file, or the same git index — which produces half-applied changes and lock errors. Almost every coordination design is really an answer to 'who is allowed to write what.'" } },
+ { "@type": "Question", "name": "Do AI coding agents need a message bus to coordinate?", "acceptedAnswer": { "@type": "Answer", "text": "They need a way to pass information without going through you, and a rule that stops them from looping forever. That can be as simple as files plus a router: each agent writes to its own outbox, and one process delivers messages to recipients' inboxes." } },
+ { "@type": "Question", "name": "Should every agent be able to edit the shared plan?", "acceptedAnswer": { "@type": "Answer", "text": "No. A plan that everyone edits is the one file guaranteed to conflict. Route changes through a single scribe — usually the orchestrator — so the shared plan has exactly one writer." } }
+
+ ]
+}
+</script>
+
+
+</head>
+<body>
+<a class="skip-link" href="#main">Skip to content</a>
+<nav id="nav">
+ <a class="brand" href="/blog/" aria-label="Munder Difflin Blog home">
+ <span class="brand-mark">MD</span>
+ <span class="brand-word">MUNDER DIFFLIN<span class="sep">/</span><span class="blog">BLOG</span></span>
+ </a>
+ <span class="spacer"></span>
+ <div class="links">
+ <a href="/blog/">Latest</a>
+ <a href="/blog/topics/">Topics</a>
+ <a href="/blog/about/">About</a>
+ <a href="https://munderdiffl.in">↗ Product</a>
+ </div>
+ <div class="nav-actions">
+ <a class="btn sm" href="https://munderdiffl.in/blog/feed.xml" aria-label="RSS feed">⤵ RSS</a>
+ <a class="btn sm primary" href="https://munderdiffl.in/#install">⤓ Download</a>
+ </div>
+</nav>
+
+<main id="main">
+
+<article>
+ <header class="post-head wrap">
+ <nav class="crumbs" aria-label="Breadcrumb">
+ <a href="/blog/">Blog</a>
+ <span>/</span>
+ <a href="/blog/topics/orchestration/">Orchestration</a>
+ </nav>
+ <h1>The Best Way to Coordinate AI Coding Agents</h1>
+ <p class="dek">The best way to coordinate AI coding agents: single-writer files, a message router, a one-scribe plan, and an orchestrator — cooperate, not clobber.</p>
+ <div class="byline">
+ <span class="av" aria-hidden="true">CG</span>
+ <strong>Chaitanya Giri</strong>
+ <span class="dot" aria-hidden="true">·</span>
+ <time datetime="2026-05-29">May 29, 2026</time>
+ <span class="dot" aria-hidden="true">·</span>
+ <span>5 min read</span>
+ <span class="tag kind">Orchestration</span>
+ </div>
+ </header>
+
+ <div class="post-wrap wrap">
+ <div class="prose">
+ <div class="callout tldr"><span class="ic">TL;DR</span><p>The best way to
+<strong>coordinate AI coding agents</strong> is to make collisions structurally impossible:
+<strong>one writer per file</strong>, message-passing through a router instead of shared edits, a
+<strong>single committer</strong> for git, a shared plan with <strong>one scribe</strong>, and an
+orchestrator that routes work and breaks ties. Get those five right and agents cooperate instead of
+clobbering each other.</p></div>
+<p>Coordinating AI coding agents sounds like a prompting problem — “just tell them to be careful.” It
+isn’t. The moment two agents share a filesystem and a git repo, “be careful” is a race condition
+waiting to happen. The reliable approach is to design the coordination so the bad outcomes <em>can’t</em>
+occur, not to hope the agents avoid them. Here are the five rules that do that.</p>
+<h2 id="rule-1-one-writer-per-file" tabindex="-1">Rule 1 — One writer per file <a class="anchor" href="#rule-1-one-writer-per-file" aria-hidden="true">#</a></h2>
+<p>The root cause of almost every multi-agent coding mess is two processes writing the same thing at
+once. So the first rule is the strictest: <strong>every file has exactly one writer.</strong></p>
+<p>In practice that means each agent gets its own private workspace — its own memory file, its own inbox,
+its own outbox — and never reaches into another agent’s directory. If agent A needs agent B to do
+something, A does not edit B’s files; A sends a message. No file is ever touched by two processes, so
+there’s nothing to race over.</p>
+<p>This sounds restrictive until you realize it’s what makes everything else safe. Single-writer is the
+foundation the other four rules sit on.</p>
+<h2 id="rule-2-pass-messages-through-a-router-not-through-shared-edits" tabindex="-1">Rule 2 — Pass messages through a router, not through shared edits <a class="anchor" href="#rule-2-pass-messages-through-a-router-not-through-shared-edits" aria-hidden="true">#</a></h2>
+<p>If agents can’t write into each other’s space, they need another channel. The clean one is a
+<strong>mailbox</strong> with a router in the middle:</p>
+<ul>
+<li>Each agent has an <code>outbox/</code> it writes to and an <code>inbox/</code> it reads from.</li>
+<li>A router (a single coordinating process) drains every outbox and delivers each message into the
+recipient’s inbox.</li>
+<li>Messages are written as individual files via an atomic rename — write to a temp name, then rename
+into place — so a reader never sees a half-written message.</li>
+</ul>
+<p>One file per message, delivered atomically, is dramatically more robust than a shared “chat log” file
+that every agent appends to (that file is just a multi-writer conflict by another name). The full
+design — speech acts, hop caps to prevent ping-pong, idempotent delivery — is in
+<a href="/blog/atomic-file-mailboxes-for-agents/">atomic file mailboxes for agents</a>.</p>
+<h2 id="rule-3-one-committer-for-git" tabindex="-1">Rule 3 — One committer for git <a class="anchor" href="#rule-3-one-committer-for-git" aria-hidden="true">#</a></h2>
+<p>Here’s the rule people learn the hard way. Git is not safe to drive from many processes at once. The
+moment two agents run <code>git add</code>/<code>git commit</code> concurrently, they race on <code>.git/index.lock</code> and you get
+errors and half-staged commits.</p>
+<p>The fix is the same shape as Rule 1: <strong>one committer.</strong> Agents never call git at all — they only write
+plain files. A single process owns every commit, serializes them, and recovers from a stale lock if a
+previous run died mid-write. That turns git from a liability into the team’s audit log: every
+coordination step is a commit you can read back. The mechanics, including the retry-and-backoff that
+makes it bulletproof, are in
+<a href="/blog/single-committer-git-pattern/">the single-committer pattern</a>.</p>
+<h2 id="rule-4-a-shared-plan-with-a-single-scribe" tabindex="-1">Rule 4 — A shared plan with a single scribe <a class="anchor" href="#rule-4-a-shared-plan-with-a-single-scribe" aria-hidden="true">#</a></h2>
+<p>Teams need a shared picture of the plan — what’s being built, in what order, by whom. But a shared
+plan document is the <em>one</em> file you most want everyone to edit and the one that will conflict the most
+if they do.</p>
+<p>Resolve the tension by separating reading from writing: everyone can <strong>read</strong> the plan; only one agent
+<strong>writes</strong> it. Other agents <em>propose</em> changes; the scribe — typically the orchestrator — incorporates
+them. The plan stays coherent because it has one author, and it stays current because everyone can
+suggest edits. Same single-writer principle, applied to the one genuinely co-owned artifact.</p>
+<h2 id="rule-5-an-orchestrator-to-route-and-break-ties" tabindex="-1">Rule 5 — An orchestrator to route and break ties <a class="anchor" href="#rule-5-an-orchestrator-to-route-and-break-ties" aria-hidden="true">#</a></h2>
+<p>The first four rules make collisions impossible. The fifth makes the team <em>productive</em>: someone has to
+decide who does what and settle disputes.</p>
+<p>That’s the orchestrator. It reads your goal, decomposes it, routes each piece to the right agent, and
+adjudicates the routine questions agents raise for each other — escalating only the genuinely critical
+calls to you. Without it, you’re back to hand-assigning work and relaying messages, which is the chore
+coordination was supposed to remove. For the full picture of routing and escalation, see
+<a href="/blog/claude-code-orchestration-guide/">orchestrating Claude Code agents</a> and
+<a href="/blog/how-the-god-orchestrator-works/">inside the GOD orchestrator</a>.</p>
+<h2 id="why-just-prompt-them-to-cooperate-fails" tabindex="-1">Why “just prompt them to cooperate” fails <a class="anchor" href="#why-just-prompt-them-to-cooperate-fails" aria-hidden="true">#</a></h2>
+<p>It’s worth being concrete about why the prompt-only approach breaks, because it’s tempting:</p>
+<ul>
+<li><strong>Prompts are advisory; races are physical.</strong> You can ask two agents not to commit simultaneously,
+but if both finish a task at the same second, both will try. Only serialization in the mechanism
+prevents it.</li>
+<li><strong>Context windows forget.</strong> An agent that “agreed” to own a file in one turn doesn’t remember that
+agreement in the next session. Ownership has to live in structure, not in a conversation.</li>
+<li><strong>Politeness loops.</strong> Two agents instructed to “coordinate” will message back and forth — “thanks!”
+“no, thank you!” — until something caps it. You need hop limits and a rule that only certain message
+types obligate a reply.</li>
+</ul>
+<p>The pattern across all three: put the guarantee in the mechanism, and let the agents be smart on top
+of a floor that’s already safe.</p>
+<h2 id="putting-it-together" tabindex="-1">Putting it together <a class="anchor" href="#putting-it-together" aria-hidden="true">#</a></h2>
+<p>A well-coordinated team of coding agents looks like this in motion:</p>
+<ol>
+<li>You state a goal to the orchestrator.</li>
+<li>It decomposes and routes work to agents in their private workspaces.</li>
+<li>Agents do the work, messaging each other through the router when they need to — never editing each
+other’s files.</li>
+<li>One process commits the coordination state to git, serialized and auditable.</li>
+<li>The shared plan stays coherent because the orchestrator is its only scribe.</li>
+<li>You’re consulted only for the critical few decisions.</li>
+</ol>
+<p>No collisions, no lock errors, no human message bus. That’s the difference between
+<a href="/blog/how-to-run-multiple-claude-code-agents/">running multiple Claude Code agents</a> and merely
+running multiple agents.</p>
+<hr>
+<p>Munder Difflin implements all five rules so you don’t have to: single-writer workspaces, an atomic
+message router, a single-committer git layer, a single-scribe shared board, and a GOD orchestrator —
+all local and open source. <a href="https://munderdiffl.in/#install">Download Munder Difflin</a> to coordinate
+your own team of Claude Code agents.</p>
+
+
+
+ <section class="faq" aria-label="Frequently asked questions">
+ <h2 id="faq">FAQ</h2>
+
+ <div class="qa">
+ <p class="q">What&#39;s the most common way multi-agent coding setups fail?</p>
+ <p class="a">Two agents writing the same thing at the same time — the same file, or the same git index — which produces half-applied changes and lock errors. Almost every coordination design is really an answer to &#39;who is allowed to write what.&#39;</p>
+ </div>
+
+ <div class="qa">
+ <p class="q">Do AI coding agents need a message bus to coordinate?</p>
+ <p class="a">They need a way to pass information without going through you, and a rule that stops them from looping forever. That can be as simple as files plus a router: each agent writes to its own outbox, and one process delivers messages to recipients&#39; inboxes.</p>
+ </div>
+
+ <div class="qa">
+ <p class="q">Should every agent be able to edit the shared plan?</p>
+ <p class="a">No. A plan that everyone edits is the one file guaranteed to conflict. Route changes through a single scribe — usually the orchestrator — so the shared plan has exactly one writer.</p>
+ </div>
+
+ </section>
+
+
+
+ <hr />
+ <div class="share">
+ <span class="lbl">Tags</span>
+ <a class="tag" href="/blog/tags/orchestration/">Orchestration</a><a class="tag" href="/blog/tags/multi-agent/">Multi-Agent</a><a class="tag" href="/blog/tags/coordination/">Coordination</a><a class="tag" href="/blog/tags/claude-code/">Claude Code</a>
+ </div>
+
+ </div>
+
+
+ <aside class="toc-rail" aria-label="Table of contents">
+ <div class="tt">On this page</div>
+ <ol>
+ <li class="lvl-2"><a href="#rule-1-one-writer-per-file">Rule 1 — One writer per file</a></li><li class="lvl-2"><a href="#rule-2-pass-messages-through-a-router-not-through-shared-edits">Rule 2 — Pass messages through a router, not through shared edits</a></li><li class="lvl-2"><a href="#rule-3-one-committer-for-git">Rule 3 — One committer for git</a></li><li class="lvl-2"><a href="#rule-4-a-shared-plan-with-a-single-scribe">Rule 4 — A shared plan with a single scribe</a></li><li class="lvl-2"><a href="#rule-5-an-orchestrator-to-route-and-break-ties">Rule 5 — An orchestrator to route and break ties</a></li><li class="lvl-2"><a href="#why-just-prompt-them-to-cooperate-fails">Why “just prompt them to cooperate” fails</a></li><li class="lvl-2"><a href="#putting-it-together">Putting it together</a></li>
+ </ol>
+ </aside>
+
+ </div>
+
+ <footer class="post-foot wrap"><div class="prevnext">
+ <a class="pn prev" href="/blog/claude-code-orchestration-guide/"><span class="k">← Older</span><span class="t">Orchestrating Claude Code Agents: A Practical Guide</span></a>
+ <a class="pn next" href="/blog/how-the-god-orchestrator-works/"><span class="k">Newer →</span><span class="t">Inside the GOD Orchestrator: Routing, Adjudication, Escalation</span></a>
+ </div>
+ <section class="related">
+ <h2>Related in Orchestration</h2>
+ <div class="post-grid">
+ <article class="card">
+ <a class="thumb t-orchestration" href="/blog/claude-code-git-worktrees-vs-hive/" aria-hidden="true" tabindex="-1">
+ <span>ORCHESTRATION</span>
+ </a>
+ <div class="body">
+ <div class="meta">
+ <time datetime="2026-06-04">Jun 4, 2026</time>
+ <span class="dot" aria-hidden="true"></span>
+ <span>5 min</span>
+ </div>
+ <h3><a href="/blog/claude-code-git-worktrees-vs-hive/">Git Worktrees vs a Hive: Two Ways to Parallelize Claude Code</a></h3>
+ <p class="dek">Claude Code git worktrees vs a hive: when isolated worktrees suffice for parallel agents, and when you need memory, messaging, and an orchestrator on top.</p>
+ <div class="foot">
+ <span class="tag kind">Orchestration</span>
+ <a class="more" href="/blog/claude-code-git-worktrees-vs-hive/" aria-label="Read: Git Worktrees vs a Hive: Two Ways to Parallelize Claude Code">Read →</a>
+ </div>
+ </div>
+</article>
+<article class="card">
+ <a class="thumb t-orchestration" href="/blog/how-the-god-orchestrator-works/" aria-hidden="true" tabindex="-1">
+ <span>ORCHESTRATION</span>
+ </a>
+ <div class="body">
+ <div class="meta">
+ <time datetime="2026-05-30">May 30, 2026</time>
+ <span class="dot" aria-hidden="true"></span>
+ <span>6 min</span>
+ </div>
+ <h3><a href="/blog/how-the-god-orchestrator-works/">Inside the GOD Orchestrator: Routing, Adjudication, Escalation</a></h3>
+ <p class="dek">A deep dive into the Claude Code orchestrator: how a GOD agent reads requests, routes work, adjudicates routine traffic, and escalates the critical few.</p>
+ <div class="foot">
+ <span class="tag kind">Orchestration</span>
+ <a class="more" href="/blog/how-the-god-orchestrator-works/" aria-label="Read: Inside the GOD Orchestrator: Routing, Adjudication, Escalation">Read →</a>
+ </div>
+ </div>
+</article>
+<article class="card">
+ <a class="thumb t-orchestration" href="/blog/claude-code-orchestration-guide/" aria-hidden="true" tabindex="-1">
+ <span>ORCHESTRATION</span>
+ </a>
+ <div class="body">
+ <div class="meta">
+ <time datetime="2026-05-28">May 28, 2026</time>
+ <span class="dot" aria-hidden="true"></span>
+ <span>5 min</span>
+ </div>
+ <h3><a href="/blog/claude-code-orchestration-guide/">Orchestrating Claude Code Agents: A Practical Guide</a></h3>
+ <p class="dek">How to orchestrate Claude Code agents in practice: what orchestration means, how a GOD orchestrator routes and escalates work, and how to wire it up.</p>
+ <div class="foot">
+ <span class="tag kind">Orchestration</span>
+ <a class="more" href="/blog/claude-code-orchestration-guide/" aria-label="Read: Orchestrating Claude Code Agents: A Practical Guide">Read →</a>
+ </div>
+ </div>
+</article>
+
+ </div>
+ </section>
+
+ </footer>
+</article>
+
+</main>
+<footer>
+ <div class="wrap">
+ <div class="foot-top">
+ <a class="foot-brand brand" href="/blog/">
+ <span class="brand-mark">MD</span>
+ <span class="brand-word">MUNDER DIFFLIN<span class="sep">/</span><span class="blog">BLOG</span></span>
+ </a>
+ <div class="foot-links">
+ <a href="/blog/">Latest</a>
+ <a href="/blog/topics/">Topics</a>
+ <a href="/blog/about/">About</a>
+ <a href="https://munderdiffl.in/blog/feed.xml">RSS</a>
+ <a href="https://github.com/chaitanyagiri/munder-difflin">GitHub</a>
+ <a href="https://munderdiffl.in">munderdiffl.in ↗</a>
+ </div>
+ </div>
+ <div class="foot-meta">
+ © 2026 Munder Difflin · Local-first · MIT-licensed ·
+ Built on <a href="https://munderdiffl.in">Electron, React, Pixi.js, xterm.js &amp; node-pty</a>.
+ Run an office of agents while you sleep.
+ </div>
+ </div>
+</footer>
+
+<script>
+ // sticky-nav border on scroll
+ (function () {
+ var nav = document.getElementById('nav');
+ if (!nav) return;
+ var onScroll = function () { nav.classList.toggle('scrolled', window.scrollY > 8); };
+ onScroll(); window.addEventListener('scroll', onScroll, { passive: true });
+ })();
+</script>
+
+</body>
+</html>
diff --git a/docs/blog/crystal-claude-code-alternative/index.html b/docs/blog/crystal-claude-code-alternative/index.html
new file mode 100644
index 00000000..e12226d1
--- /dev/null
+++ b/docs/blog/crystal-claude-code-alternative/index.html
@@ -0,0 +1,312 @@
+<!doctype html>
+<html lang="en">
+<head>
+<meta charset="UTF-8" />
+<meta name="viewport" content="width=device-width, initial-scale=1.0" />
+<title>A Crystal Alternative: Multi-Agent Claude Code with Memory — Munder Difflin Blog</title>
+<meta name="description" content="Crystal runs parallel Claude Code worktrees well. Where a memory-backed, orchestrated hive changes the workflow — and when to stick with Crystal." />
+<link rel="canonical" href="https://munderdiffl.in/blog/crystal-claude-code-alternative/" />
+
+<link rel="icon" type="image/png" href="https://munderdiffl.in/logo.png" />
+<link rel="apple-touch-icon" href="https://munderdiffl.in/logo.png" />
+<meta name="theme-color" content="#F5F2E8" />
+
+<!-- Open Graph -->
+<meta property="og:site_name" content="Munder Difflin Blog" />
+<meta property="og:type" content="article" />
+<meta property="og:title" content="A Crystal Alternative: Multi-Agent Claude Code with Memory — Munder Difflin Blog" />
+<meta property="og:description" content="Crystal runs parallel Claude Code worktrees well. Where a memory-backed, orchestrated hive changes the workflow — and when to stick with Crystal." />
+<meta property="og:url" content="https://munderdiffl.in/blog/crystal-claude-code-alternative/" />
+<meta property="og:image" content="https://munderdiffl.in/media/og.png" />
+<meta property="og:locale" content="en_US" />
+<meta property="article:published_time" content="2026-06-03T00:00:00.000Z" />
+<meta property="article:author" content="Chaitanya Giri" />
+<meta property="article:tag" content="Comparisons" />
+<meta property="article:tag" content="Memory" />
+<meta property="article:tag" content="Claude Code" />
+<meta property="article:tag" content="Tools" />
+
+
+<!-- Twitter -->
+<meta name="twitter:card" content="summary_large_image" />
+<meta name="twitter:title" content="A Crystal Alternative: Multi-Agent Claude Code with Memory — Munder Difflin Blog" />
+<meta name="twitter:description" content="Crystal runs parallel Claude Code worktrees well. Where a memory-backed, orchestrated hive changes the workflow — and when to stick with Crystal." />
+<meta name="twitter:image" content="https://munderdiffl.in/media/og.png" />
+
+<link rel="alternate" type="application/atom+xml" title="Munder Difflin Blog" href="https://munderdiffl.in/blog/feed.xml" />
+<link rel="preconnect" href="https://fonts.googleapis.com" />
+<link rel="preconnect" href="https://fonts.gstatic.com" crossorigin />
+<link href="https://fonts.googleapis.com/css2?family=Geist:wght@400;500;600&family=JetBrains+Mono:wght@400;500;600;700&display=swap" rel="stylesheet" />
+<link rel="stylesheet" href="/blog/assets/blog.css" />
+
+<script type="application/ld+json">
+{
+ "@context": "https://schema.org",
+ "@type": "BlogPosting",
+ "headline": "A Crystal Alternative: Multi-Agent Claude Code with Memory",
+ "description": "Crystal runs parallel Claude Code worktrees well. Where a memory-backed, orchestrated hive changes the workflow — and when to stick with Crystal.",
+ "image": ["https://munderdiffl.in/media/og.png"],
+ "datePublished": "2026-06-03T00:00:00.000Z",
+ "dateModified": "2026-06-03T00:00:00.000Z",
+ "author": { "@type": "Person", "name": "Chaitanya Giri" },
+ "publisher": {
+ "@type": "Organization",
+ "name": "Munder Difflin",
+ "logo": { "@type": "ImageObject", "url": "https://munderdiffl.in/logo.png" }
+ },
+ "mainEntityOfPage": { "@type": "WebPage", "@id": "https://munderdiffl.in/blog/crystal-claude-code-alternative/" },
+ "keywords": "crystal claude code alternative, crystal claude code alternative, claude code multi-agent tool, multi-agent claude code with memory",
+ "articleSection": "Comparisons",
+ "inLanguage": "en-US",
+ "url": "https://munderdiffl.in/blog/crystal-claude-code-alternative/"
+}
+</script>
+<script type="application/ld+json">
+{
+ "@context": "https://schema.org",
+ "@type": "BreadcrumbList",
+ "itemListElement": [
+ { "@type": "ListItem", "position": 1, "name": "Home", "item": "https://munderdiffl.in/" },
+ { "@type": "ListItem", "position": 2, "name": "Blog", "item": "https://munderdiffl.in/blog/" },
+ { "@type": "ListItem", "position": 3, "name": "A Crystal Alternative: Multi-Agent Claude Code with Memory", "item": "https://munderdiffl.in/blog/crystal-claude-code-alternative/" }
+ ]
+}
+</script>
+
+
+</head>
+<body>
+<a class="skip-link" href="#main">Skip to content</a>
+<nav id="nav">
+ <a class="brand" href="/blog/" aria-label="Munder Difflin Blog home">
+ <span class="brand-mark">MD</span>
+ <span class="brand-word">MUNDER DIFFLIN<span class="sep">/</span><span class="blog">BLOG</span></span>
+ </a>
+ <span class="spacer"></span>
+ <div class="links">
+ <a href="/blog/">Latest</a>
+ <a href="/blog/topics/">Topics</a>
+ <a href="/blog/about/">About</a>
+ <a href="https://munderdiffl.in">↗ Product</a>
+ </div>
+ <div class="nav-actions">
+ <a class="btn sm" href="https://munderdiffl.in/blog/feed.xml" aria-label="RSS feed">⤵ RSS</a>
+ <a class="btn sm primary" href="https://munderdiffl.in/#install">⤓ Download</a>
+ </div>
+</nav>
+
+<main id="main">
+
+<article>
+ <header class="post-head wrap">
+ <nav class="crumbs" aria-label="Breadcrumb">
+ <a href="/blog/">Blog</a>
+ <span>/</span>
+ <a href="/blog/topics/comparisons/">Comparisons</a>
+ </nav>
+ <h1>A Crystal Alternative: Multi-Agent Claude Code with Memory</h1>
+ <p class="dek">Crystal runs parallel Claude Code worktrees well. Where a memory-backed, orchestrated hive changes the workflow — and when to stick with Crystal.</p>
+ <div class="byline">
+ <span class="av" aria-hidden="true">CG</span>
+ <strong>Chaitanya Giri</strong>
+ <span class="dot" aria-hidden="true">·</span>
+ <time datetime="2026-06-03">Jun 3, 2026</time>
+ <span class="dot" aria-hidden="true">·</span>
+ <span>3 min read</span>
+ <span class="tag kind">Comparisons</span>
+ </div>
+ </header>
+
+ <div class="post-wrap wrap">
+ <div class="prose">
+ <div class="callout tldr"><span class="ic">TL;DR</span><p><strong>Crystal</strong> is a tidy,
+open-source desktop app for running multiple Claude Code sessions in parallel, each in its own git
+worktree, with diff and test review. A <strong>Crystal alternative</strong> makes sense when you want
+the agents to do more than run side by side — to <strong>share long-term memory</strong>, message
+each other, and be routed by an orchestrator. That's the difference between parallel sessions and a
+coordinated team.</p></div>
+<p><a href="https://github.com/stravu/crystal">Crystal</a> is a likeable tool: open source, a real GUI, and a clean
+model for running parallel Claude Code experiments. If you’re weighing an alternative, start by being
+clear about what Crystal already nails.</p>
+<h2 id="what-crystal-does-well" tabindex="-1">What Crystal does well <a class="anchor" href="#what-crystal-does-well" aria-hidden="true">#</a></h2>
+<p>Crystal is an open-source desktop app that spins up multiple Claude Code sessions from prompts, runs
+them concurrently in isolated git worktrees, and lets you review diffs and test results across them in
+one window.</p>
+<ul>
+<li><strong>It’s open source.</strong> You can read it, file issues, and contribute.</li>
+<li><strong>Parallel experimentation is the sweet spot.</strong> Try several approaches to the same problem at once,
+then compare outcomes.</li>
+<li><strong>Worktree isolation + diff review</strong> keep parallel work safe and reviewable without terminal
+juggling.</li>
+</ul>
+<p>For “run a few variations in parallel and pick the best diff,” Crystal is a good answer. The reason to
+look further is usually one word: <em>memory</em>.</p>
+<h2 id="where-parallel-sessions-hit-a-ceiling" tabindex="-1">Where parallel sessions hit a ceiling <a class="anchor" href="#where-parallel-sessions-hit-a-ceiling" aria-hidden="true">#</a></h2>
+<p>Crystal, like other parallel-worktree apps, runs agents <em>beside</em> each other. What it doesn’t add is a
+coordination layer:</p>
+<h3 id="sessions-dont-share-knowledge" tabindex="-1">Sessions don’t share knowledge <a class="anchor" href="#sessions-dont-share-knowledge" aria-hidden="true">#</a></h3>
+<p>Each session is its own island of context. When one agent figures out a convention or a gotcha, the
+others don’t inherit it. Without <a href="/blog/give-claude-code-long-term-memory/">shared long-term
+memory</a>, the team re-learns the same things and you re-explain
+the same context.</p>
+<h3 id="agents-dont-message-each-other" tabindex="-1">Agents don’t message each other <a class="anchor" href="#agents-dont-message-each-other" aria-hidden="true">#</a></h3>
+<p>There’s no mailbox for one agent to hand a result to another. Coordination routes through you.</p>
+<h3 id="theres-no-orchestrator" tabindex="-1">There’s no orchestrator <a class="anchor" href="#theres-no-orchestrator" aria-hidden="true">#</a></h3>
+<p>You launch and assign each session. Nothing decomposes a goal and routes the pieces across the team
+for you.</p>
+<h2 id="what-memory-changes-day-to-day" tabindex="-1">What memory changes, day to day <a class="anchor" href="#what-memory-changes-day-to-day" aria-hidden="true">#</a></h2>
+<p>Adding a shared brain to a team of agents is a bigger shift than it sounds:</p>
+<ul>
+<li><strong>Context stops resetting.</strong> Decisions, conventions, and gotchas live in a <a href="/#how">semantic memory
+layer</a> (MemPalace) every agent reads on startup and writes to as it learns.</li>
+<li><strong>Briefs get shorter.</strong> You stop re-explaining the project because the team already remembers it.</li>
+<li><strong>Work compounds.</strong> Agent B builds on what agent A learned an hour — or a week — ago.</li>
+</ul>
+<p>Layer messaging and an orchestrator on top of that memory and you’ve crossed from “parallel sessions”
+to a <a href="/#what">multi-agent harness</a>: agents with roles and mailboxes, a <a href="/#how">GOD orchestrator</a> that
+routes work, and a visual office floor. That’s <a href="/#what">Munder Difflin</a> — open source (MIT), local-first,
+on macOS, Windows, and Linux.</p>
+<h2 id="crystal-vs-a-memory-backed-hive" tabindex="-1">Crystal vs a memory-backed hive <a class="anchor" href="#crystal-vs-a-memory-backed-hive" aria-hidden="true">#</a></h2>
+<ul>
+<li><strong>Stay with Crystal</strong> if your loop is parallel experiments + diff review and you don’t need agents
+to coordinate or remember across sessions.</li>
+<li><strong>Move to a hive</strong> if you want shared memory, inter-agent messaging, and an orchestrator — agents
+that act as one team instead of parallel strangers.</li>
+</ul>
+<p>See also: a head-to-head <a href="/blog/claude-squad-vs-munder-difflin/">Claude Squad vs Munder Difflin</a> and
+the full <a href="/blog/best-claude-code-multi-agent-tools/">roundup of multi-agent Claude Code tools</a>.</p>
+<hr>
+<blockquote>
+<p>The tooling landscape moves fast — check Crystal’s repo for current features. We’ve described it on
+its own terms; Munder Difflin is our own project.</p>
+</blockquote>
+<p>If shared memory is the missing piece, <a href="/#install">download Munder Difflin</a> and let your agents
+actually remember — free and open source.</p>
+
+
+
+
+
+ <hr />
+ <div class="share">
+ <span class="lbl">Tags</span>
+ <a class="tag" href="/blog/tags/comparisons/">Comparisons</a><a class="tag" href="/blog/tags/memory/">Memory</a><a class="tag" href="/blog/tags/claude-code/">Claude Code</a><a class="tag" href="/blog/tags/tools/">Tools</a>
+ </div>
+
+ </div>
+
+
+ <aside class="toc-rail" aria-label="Table of contents">
+ <div class="tt">On this page</div>
+ <ol>
+ <li class="lvl-2"><a href="#what-crystal-does-well">What Crystal does well</a></li><li class="lvl-2"><a href="#where-parallel-sessions-hit-a-ceiling">Where parallel sessions hit a ceiling</a></li><li class="lvl-3"><a href="#sessions-dont-share-knowledge">Sessions don’t share knowledge</a></li><li class="lvl-3"><a href="#agents-dont-message-each-other">Agents don’t message each other</a></li><li class="lvl-3"><a href="#theres-no-orchestrator">There’s no orchestrator</a></li><li class="lvl-2"><a href="#what-memory-changes-day-to-day">What memory changes, day to day</a></li><li class="lvl-2"><a href="#crystal-vs-a-memory-backed-hive">Crystal vs a memory-backed hive</a></li>
+ </ol>
+ </aside>
+
+ </div>
+
+ <footer class="post-foot wrap"><div class="prevnext">
+ <a class="pn prev" href="/blog/mcp-and-skills-in-a-hive/"><span class="k">← Older</span><span class="t">Bringing Your MCP Servers and Skills Into a Hive of Agents</span></a>
+ <a class="pn next" href="/blog/conductor-claude-code-alternative/"><span class="k">Newer →</span><span class="t">A Conductor Alternative for Orchestrating Claude Code</span></a>
+ </div>
+ <section class="related">
+ <h2>Related in Comparisons</h2>
+ <div class="post-grid">
+ <article class="card">
+ <a class="thumb t-comparisons" href="/blog/best-claude-code-multi-agent-tools/" aria-hidden="true" tabindex="-1">
+ <span>COMPARISONS</span>
+ </a>
+ <div class="body">
+ <div class="meta">
+ <time datetime="2026-06-04">Jun 4, 2026</time>
+ <span class="dot" aria-hidden="true"></span>
+ <span>6 min</span>
+ </div>
+ <h3><a href="/blog/best-claude-code-multi-agent-tools/">The Best Tools to Run Multiple Claude Code Agents (2026)</a></h3>
+ <p class="dek">An honest 2026 roundup of tools to run multiple Claude Code agents — Claude Squad, Conductor, Crystal, vibe-kanban, and Munder Difflin — compared.</p>
+ <div class="foot">
+ <span class="tag kind">Comparisons</span>
+ <a class="more" href="/blog/best-claude-code-multi-agent-tools/" aria-label="Read: The Best Tools to Run Multiple Claude Code Agents (2026)">Read →</a>
+ </div>
+ </div>
+</article>
+<article class="card">
+ <a class="thumb t-comparisons" href="/blog/claude-code-orchestration-tools-compared/" aria-hidden="true" tabindex="-1">
+ <span>COMPARISONS</span>
+ </a>
+ <div class="body">
+ <div class="meta">
+ <time datetime="2026-06-04">Jun 4, 2026</time>
+ <span class="dot" aria-hidden="true"></span>
+ <span>3 min</span>
+ </div>
+ <h3><a href="/blog/claude-code-orchestration-tools-compared/">Claude Code Orchestration Tools, Compared</a></h3>
+ <p class="dek">Claude Code orchestration tools compared on memory, messaging, visibility, control, and local-first — across Claude Squad, Conductor, Crystal, and more.</p>
+ <div class="foot">
+ <span class="tag kind">Comparisons</span>
+ <a class="more" href="/blog/claude-code-orchestration-tools-compared/" aria-label="Read: Claude Code Orchestration Tools, Compared">Read →</a>
+ </div>
+ </div>
+</article>
+<article class="card">
+ <a class="thumb t-comparisons" href="/blog/claude-squad-vs-munder-difflin/" aria-hidden="true" tabindex="-1">
+ <span>COMPARISONS</span>
+ </a>
+ <div class="body">
+ <div class="meta">
+ <time datetime="2026-06-04">Jun 4, 2026</time>
+ <span class="dot" aria-hidden="true"></span>
+ <span>3 min</span>
+ </div>
+ <h3><a href="/blog/claude-squad-vs-munder-difflin/">Claude Squad vs Munder Difflin: Which Should You Use?</a></h3>
+ <p class="dek">Claude Squad vs Munder Difflin: a lean terminal session manager against a memory-backed, orchestrated, visual hive. Feature table and an honest verdict.</p>
+ <div class="foot">
+ <span class="tag kind">Comparisons</span>
+ <a class="more" href="/blog/claude-squad-vs-munder-difflin/" aria-label="Read: Claude Squad vs Munder Difflin: Which Should You Use?">Read →</a>
+ </div>
+ </div>
+</article>
+
+ </div>
+ </section>
+
+ </footer>
+</article>
+
+</main>
+<footer>
+ <div class="wrap">
+ <div class="foot-top">
+ <a class="foot-brand brand" href="/blog/">
+ <span class="brand-mark">MD</span>
+ <span class="brand-word">MUNDER DIFFLIN<span class="sep">/</span><span class="blog">BLOG</span></span>
+ </a>
+ <div class="foot-links">
+ <a href="/blog/">Latest</a>
+ <a href="/blog/topics/">Topics</a>
+ <a href="/blog/about/">About</a>
+ <a href="https://munderdiffl.in/blog/feed.xml">RSS</a>
+ <a href="https://github.com/chaitanyagiri/munder-difflin">GitHub</a>
+ <a href="https://munderdiffl.in">munderdiffl.in ↗</a>
+ </div>
+ </div>
+ <div class="foot-meta">
+ © 2026 Munder Difflin · Local-first · MIT-licensed ·
+ Built on <a href="https://munderdiffl.in">Electron, React, Pixi.js, xterm.js &amp; node-pty</a>.
+ Run an office of agents while you sleep.
+ </div>
+ </div>
+</footer>
+
+<script>
+ // sticky-nav border on scroll
+ (function () {
+ var nav = document.getElementById('nav');
+ if (!nav) return;
+ var onScroll = function () { nav.classList.toggle('scrolled', window.scrollY > 8); };
+ onScroll(); window.addEventListener('scroll', onScroll, { passive: true });
+ })();
+</script>
+
+</body>
+</html>
diff --git a/docs/blog/feed.xml b/docs/blog/feed.xml
index ded7945a..1e151587 100644
--- a/docs/blog/feed.xml
+++ b/docs/blog/feed.xml
@@ -4,9 +4,185 @@
<subtitle>Guides, deep dives, and comparisons on running multi-agent Claude Code: orchestration, agent memory, automation, and the tooling landscape.</subtitle>
<link href="https://munderdiffl.in/blog/feed.xml" rel="self" />
<link href="https://munderdiffl.in/blog/" />
- <updated>2026-06-01T00:00:00.000Z</updated>
+ <updated>2026-06-04T00:00:00.000Z</updated>
<id>https://munderdiffl.in/blog/</id>
<author><name>Chaitanya Giri</name><uri>https://munderdiffl.in</uri></author>
+ <entry>
+ <title>The Best Tools to Run Multiple Claude Code Agents (2026)</title>
+ <link href="https://munderdiffl.in/blog/best-claude-code-multi-agent-tools/" />
+ <id>https://munderdiffl.in/blog/best-claude-code-multi-agent-tools/</id>
+ <published>2026-06-04T00:00:00.000Z</published>
+ <updated>2026-06-04T00:00:00.000Z</updated><category term="Comparisons" />
+ <summary>An honest 2026 roundup of tools to run multiple Claude Code agents — Claude Squad, Conductor, Crystal, vibe-kanban, and Munder Difflin — compared.</summary>
+ </entry>
+ <entry>
+ <title>Claude Code Automation: Let Agents Build While You Sleep</title>
+ <link href="https://munderdiffl.in/blog/claude-code-automation-while-you-sleep/" />
+ <id>https://munderdiffl.in/blog/claude-code-automation-while-you-sleep/</id>
+ <published>2026-06-04T00:00:00.000Z</published>
+ <updated>2026-06-04T00:00:00.000Z</updated><category term="Guides" />
+ <summary>Claude Code automation that runs overnight: an autonomous Stop-hook loop, safe permission bypass, and guardrails so you wake up to progress, not chaos.</summary>
+ </entry>
+ <entry>
+ <title>Git Worktrees vs a Hive: Two Ways to Parallelize Claude Code</title>
+ <link href="https://munderdiffl.in/blog/claude-code-git-worktrees-vs-hive/" />
+ <id>https://munderdiffl.in/blog/claude-code-git-worktrees-vs-hive/</id>
+ <published>2026-06-04T00:00:00.000Z</published>
+ <updated>2026-06-04T00:00:00.000Z</updated><category term="Orchestration" />
+ <summary>Claude Code git worktrees vs a hive: when isolated worktrees suffice for parallel agents, and when you need memory, messaging, and an orchestrator on top.</summary>
+ </entry>
+ <entry>
+ <title>Claude Code Orchestration Tools, Compared</title>
+ <link href="https://munderdiffl.in/blog/claude-code-orchestration-tools-compared/" />
+ <id>https://munderdiffl.in/blog/claude-code-orchestration-tools-compared/</id>
+ <published>2026-06-04T00:00:00.000Z</published>
+ <updated>2026-06-04T00:00:00.000Z</updated><category term="Comparisons" />
+ <summary>Claude Code orchestration tools compared on memory, messaging, visibility, control, and local-first — across Claude Squad, Conductor, Crystal, and more.</summary>
+ </entry>
+ <entry>
+ <title>Claude Squad vs Munder Difflin: Which Should You Use?</title>
+ <link href="https://munderdiffl.in/blog/claude-squad-vs-munder-difflin/" />
+ <id>https://munderdiffl.in/blog/claude-squad-vs-munder-difflin/</id>
+ <published>2026-06-04T00:00:00.000Z</published>
+ <updated>2026-06-04T00:00:00.000Z</updated><category term="Comparisons" />
+ <summary>Claude Squad vs Munder Difflin: a lean terminal session manager against a memory-backed, orchestrated, visual hive. Feature table and an honest verdict.</summary>
+ </entry>
+ <entry>
+ <title>Building a Terminal UI with xterm.js and node-pty</title>
+ <link href="https://munderdiffl.in/blog/building-a-terminal-ui-xterm-node-pty/" />
+ <id>https://munderdiffl.in/blog/building-a-terminal-ui-xterm-node-pty/</id>
+ <published>2026-06-03T00:00:00.000Z</published>
+ <updated>2026-06-03T00:00:00.000Z</updated><category term="Internals" />
+ <summary>Wire xterm.js to a node-pty backend: stream output, write keystrokes back, handle resize, and keep many live terminals fast with a terminal pool.</summary>
+ </entry>
+ <entry>
+ <title>Claude Code Hooks, Explained (PreToolUse, PostToolUse, Stop)</title>
+ <link href="https://munderdiffl.in/blog/claude-code-hooks-explained/" />
+ <id>https://munderdiffl.in/blog/claude-code-hooks-explained/</id>
+ <published>2026-06-03T00:00:00.000Z</published>
+ <updated>2026-06-03T00:00:00.000Z</updated><category term="Internals" />
+ <summary>A practical tour of Claude Code hooks — the PreToolUse, PostToolUse, and Stop lifecycle — and how a Unix-socket hook shim drives a live office floor.</summary>
+ </entry>
+ <entry>
+ <title>Looking for a Claude Squad Alternative?</title>
+ <link href="https://munderdiffl.in/blog/claude-squad-alternative/" />
+ <id>https://munderdiffl.in/blog/claude-squad-alternative/</id>
+ <published>2026-06-03T00:00:00.000Z</published>
+ <updated>2026-06-03T00:00:00.000Z</updated><category term="Comparisons" />
+ <summary>What Claude Squad does well, where it stops, and why a memory-backed, orchestrated hive may be the Claude Squad alternative you&#39;re after.</summary>
+ </entry>
+ <entry>
+ <title>A Conductor Alternative for Orchestrating Claude Code</title>
+ <link href="https://munderdiffl.in/blog/conductor-claude-code-alternative/" />
+ <id>https://munderdiffl.in/blog/conductor-claude-code-alternative/</id>
+ <published>2026-06-03T00:00:00.000Z</published>
+ <updated>2026-06-03T00:00:00.000Z</updated><category term="Comparisons" />
+ <summary>Conductor is a polished macOS app for parallel Claude Code worktrees. When to pick a cross-platform, orchestrated hive as your Conductor alternative.</summary>
+ </entry>
+ <entry>
+ <title>A Crystal Alternative: Multi-Agent Claude Code with Memory</title>
+ <link href="https://munderdiffl.in/blog/crystal-claude-code-alternative/" />
+ <id>https://munderdiffl.in/blog/crystal-claude-code-alternative/</id>
+ <published>2026-06-03T00:00:00.000Z</published>
+ <updated>2026-06-03T00:00:00.000Z</updated><category term="Comparisons" />
+ <summary>Crystal runs parallel Claude Code worktrees well. Where a memory-backed, orchestrated hive changes the workflow — and when to stick with Crystal.</summary>
+ </entry>
+ <entry>
+ <title>Bringing Your MCP Servers and Skills Into a Hive of Agents</title>
+ <link href="https://munderdiffl.in/blog/mcp-and-skills-in-a-hive/" />
+ <id>https://munderdiffl.in/blog/mcp-and-skills-in-a-hive/</id>
+ <published>2026-06-03T00:00:00.000Z</published>
+ <updated>2026-06-03T00:00:00.000Z</updated><category term="Guides" />
+ <summary>How agents in a hive inherit your existing Claude Code MCP servers, skills, and tools — and how to scope which agent gets which capability.</summary>
+ </entry>
+ <entry>
+ <title>Real Terminals in Electron with node-pty</title>
+ <link href="https://munderdiffl.in/blog/node-pty-electron-real-terminals/" />
+ <id>https://munderdiffl.in/blog/node-pty-electron-real-terminals/</id>
+ <published>2026-06-03T00:00:00.000Z</published>
+ <updated>2026-06-03T00:00:00.000Z</updated><category term="Internals" />
+ <summary>How to run byte-for-byte authentic shells inside Electron with node-pty: the native-rebuild gotcha, the macOS PATH trap, and streaming PTY output over IPC.</summary>
+ </entry>
+ <entry>
+ <title>A vibe-kanban Alternative for Coordinating AI Agents</title>
+ <link href="https://munderdiffl.in/blog/vibe-kanban-alternative/" />
+ <id>https://munderdiffl.in/blog/vibe-kanban-alternative/</id>
+ <published>2026-06-03T00:00:00.000Z</published>
+ <updated>2026-06-03T00:00:00.000Z</updated><category term="Comparisons" />
+ <summary>vibe-kanban gives you a board to assign tasks to coding agents. When a self-routing hive is the better vibe-kanban alternative — and when a board wins.</summary>
+ </entry>
+ <entry>
+ <title>The AI Coding Agent Glossary: Harness, Orchestrator, Hive, Subagent</title>
+ <link href="https://munderdiffl.in/blog/ai-agent-glossary/" />
+ <id>https://munderdiffl.in/blog/ai-agent-glossary/</id>
+ <published>2026-06-02T00:00:00.000Z</published>
+ <updated>2026-06-02T00:00:00.000Z</updated><category term="Concepts" />
+ <summary>Plain-English definitions of the AI coding agent terms everyone trips over — harness, orchestrator, hive, subagent, agent memory — each in one line.</summary>
+ </entry>
+ <entry>
+ <title>From One Terminal to a Team: Scaling Your Claude Code Workflow</title>
+ <link href="https://munderdiffl.in/blog/from-one-terminal-to-a-team/" />
+ <id>https://munderdiffl.in/blog/from-one-terminal-to-a-team/</id>
+ <published>2026-06-02T00:00:00.000Z</published>
+ <updated>2026-06-02T00:00:00.000Z</updated><category term="Use Cases" />
+ <summary>The workflow shift from a single Claude Code session to a coordinated team of agents — what changes, where it breaks, and the concrete before-and-after.</summary>
+ </entry>
+ <entry>
+ <title>How to Choose a Multi-Agent Coding Tool: A Buyer&#39;s Checklist</title>
+ <link href="https://munderdiffl.in/blog/how-to-choose-a-multi-agent-tool/" />
+ <id>https://munderdiffl.in/blog/how-to-choose-a-multi-agent-tool/</id>
+ <published>2026-06-02T00:00:00.000Z</published>
+ <updated>2026-06-02T00:00:00.000Z</updated><category term="Comparisons" />
+ <summary>A decision framework for choosing a multi-agent coding tool — memory, control, visibility, cost, local-first — with a simple scoring rubric you can run.</summary>
+ </entry>
+ <entry>
+ <title>Munder Difflin FAQ: Everything People Ask</title>
+ <link href="https://munderdiffl.in/blog/munder-difflin-faq/" />
+ <id>https://munderdiffl.in/blog/munder-difflin-faq/</id>
+ <published>2026-06-02T00:00:00.000Z</published>
+ <updated>2026-06-02T00:00:00.000Z</updated><category term="Concepts" />
+ <summary>Answers to the top Munder Difflin questions — what it is, is it free, does it run locally, which platforms, and how it differs from many terminals.</summary>
+ </entry>
+ <entry>
+ <title>Run an Office of AI Agents While You Sleep</title>
+ <link href="https://munderdiffl.in/blog/run-an-office-of-ai-agents/" />
+ <id>https://munderdiffl.in/blog/run-an-office-of-ai-agents/</id>
+ <published>2026-06-02T00:00:00.000Z</published>
+ <updated>2026-06-02T00:00:00.000Z</updated><category term="Use Cases" />
+ <summary>What it takes to run a self-coordinating office of AI coding agents that keeps shipping after you log off — and the guardrails that keep it sane.</summary>
+ </entry>
+ <entry>
+ <title>The Single-Committer Pattern: Multi-Agent Git Without Corruption</title>
+ <link href="https://munderdiffl.in/blog/single-committer-git-pattern/" />
+ <id>https://munderdiffl.in/blog/single-committer-git-pattern/</id>
+ <published>2026-06-02T00:00:00.000Z</published>
+ <updated>2026-06-02T00:00:00.000Z</updated><category term="Internals" />
+ <summary>Parallel agents corrupt a repo with index.lock races. The single-committer pattern — agents write, one process commits — fixes concurrent git writes.</summary>
+ </entry>
+ <entry>
+ <title>What Are Claude Code Agents? And How to Use Many at Once</title>
+ <link href="https://munderdiffl.in/blog/what-are-claude-code-agents/" />
+ <id>https://munderdiffl.in/blog/what-are-claude-code-agents/</id>
+ <published>2026-06-02T00:00:00.000Z</published>
+ <updated>2026-06-02T00:00:00.000Z</updated><category term="Concepts" />
+ <summary>Claude Code agents explained in plain English — what an agent actually is, how subagents differ, and the leap from one agent to a coordinated team.</summary>
+ </entry>
+ <entry>
+ <title>Why Local-First Matters for Your AI Agents</title>
+ <link href="https://munderdiffl.in/blog/why-local-first-matters-for-ai-agents/" />
+ <id>https://munderdiffl.in/blog/why-local-first-matters-for-ai-agents/</id>
+ <published>2026-06-02T00:00:00.000Z</published>
+ <updated>2026-06-02T00:00:00.000Z</updated><category term="Use Cases" />
+ <summary>The control, privacy, and cost case for keeping your AI agents and their memory on your own machine — and what cloud orchestration quietly costs.</summary>
+ </entry>
+ <entry>
+ <title>Why We Built Munder Difflin</title>
+ <link href="https://munderdiffl.in/blog/why-we-built-munder-difflin/" />
+ <id>https://munderdiffl.in/blog/why-we-built-munder-difflin/</id>
+ <published>2026-06-02T00:00:00.000Z</published>
+ <updated>2026-06-02T00:00:00.000Z</updated><category term="Story" />
+ <summary>The origin story of Munder Difflin — how the pain of juggling Claude Code terminals led to a coordinated, memory-backed hive of agents you can watch.</summary>
+ </entry>
<entry>
<title>How to Run Multiple Claude Code Agents (Without Losing Track)</title>
<link href="https://munderdiffl.in/blog/how-to-run-multiple-claude-code-agents/" />
@@ -15,6 +191,38 @@
<updated>2026-06-01T00:00:00.000Z</updated><category term="Guides" />
<summary>Run several Claude Code agents in parallel without the chaos: give each a role, let them coordinate, and stop alt-tabbing between terminal windows.</summary>
</entry>
+ <entry>
+ <title>Atomic File Mailboxes: How Agents Message Each Other</title>
+ <link href="https://munderdiffl.in/blog/atomic-file-mailboxes-for-agents/" />
+ <id>https://munderdiffl.in/blog/atomic-file-mailboxes-for-agents/</id>
+ <published>2026-05-31T00:00:00.000Z</published>
+ <updated>2026-05-31T00:00:00.000Z</updated><category term="Internals" />
+ <summary>Can Claude Code agents talk to each other? Yes — the outbox-router-inbox design that lets agents message safely using plain files and atomic renames.</summary>
+ </entry>
+ <entry>
+ <title>Inside the GOD Orchestrator: Routing, Adjudication, Escalation</title>
+ <link href="https://munderdiffl.in/blog/how-the-god-orchestrator-works/" />
+ <id>https://munderdiffl.in/blog/how-the-god-orchestrator-works/</id>
+ <published>2026-05-30T00:00:00.000Z</published>
+ <updated>2026-05-30T00:00:00.000Z</updated><category term="Orchestration" />
+ <summary>A deep dive into the Claude Code orchestrator: how a GOD agent reads requests, routes work, adjudicates routine traffic, and escalates the critical few.</summary>
+ </entry>
+ <entry>
+ <title>The Best Way to Coordinate AI Coding Agents</title>
+ <link href="https://munderdiffl.in/blog/coordinating-ai-coding-agents/" />
+ <id>https://munderdiffl.in/blog/coordinating-ai-coding-agents/</id>
+ <published>2026-05-29T00:00:00.000Z</published>
+ <updated>2026-05-29T00:00:00.000Z</updated><category term="Orchestration" />
+ <summary>The best way to coordinate AI coding agents: single-writer files, a message router, a one-scribe plan, and an orchestrator — cooperate, not clobber.</summary>
+ </entry>
+ <entry>
+ <title>Orchestrating Claude Code Agents: A Practical Guide</title>
+ <link href="https://munderdiffl.in/blog/claude-code-orchestration-guide/" />
+ <id>https://munderdiffl.in/blog/claude-code-orchestration-guide/</id>
+ <published>2026-05-28T00:00:00.000Z</published>
+ <updated>2026-05-28T00:00:00.000Z</updated><category term="Orchestration" />
+ <summary>How to orchestrate Claude Code agents in practice: what orchestration means, how a GOD orchestrator routes and escalates work, and how to wire it up.</summary>
+ </entry>
<entry>
<title>How to Give Claude Code Long-Term Memory</title>
<link href="https://munderdiffl.in/blog/give-claude-code-long-term-memory/" />
@@ -23,6 +231,38 @@
<updated>2026-05-27T00:00:00.000Z</updated><category term="Memory" />
<summary>Claude Code forgets between sessions. Here&#39;s how a markdown-first memory layer with semantic recall lets your agents remember across runs.</summary>
</entry>
+ <entry>
+ <title>Semantic Memory for AI Agents: Recall in Milliseconds</title>
+ <link href="https://munderdiffl.in/blog/semantic-memory-for-ai-agents/" />
+ <id>https://munderdiffl.in/blog/semantic-memory-for-ai-agents/</id>
+ <published>2026-05-26T00:00:00.000Z</published>
+ <updated>2026-05-26T00:00:00.000Z</updated><category term="Memory" />
+ <summary>What semantic memory for AI agents is, why a markdown-first store beats a heavy DB, and how a shared palace lets a hive recall a note by meaning, fast.</summary>
+ </entry>
+ <entry>
+ <title>How to Manage Multiple Claude Code Sessions Like a Pro</title>
+ <link href="https://munderdiffl.in/blog/manage-multiple-claude-code-sessions/" />
+ <id>https://munderdiffl.in/blog/manage-multiple-claude-code-sessions/</id>
+ <published>2026-05-25T00:00:00.000Z</published>
+ <updated>2026-05-25T00:00:00.000Z</updated><category term="Guides" />
+ <summary>Tactics to manage multiple Claude Code sessions without losing track: naming, roles, context isolation, and when a harness beats juggling terminal tabs.</summary>
+ </entry>
+ <entry>
+ <title>Set Up a Claude Code Multi-Agent Workflow in 10 Minutes</title>
+ <link href="https://munderdiffl.in/blog/claude-code-multi-agent-setup-tutorial/" />
+ <id>https://munderdiffl.in/blog/claude-code-multi-agent-setup-tutorial/</id>
+ <published>2026-05-24T00:00:00.000Z</published>
+ <updated>2026-05-24T00:00:00.000Z</updated><category term="Guides" />
+ <summary>A from-zero Claude Code multi-agent setup: install Munder Difflin, onboard, spawn a few agents, and watch the GOD orchestrator route your first task.</summary>
+ </entry>
+ <entry>
+ <title>Claude Code Subagents vs a Multi-Agent Harness</title>
+ <link href="https://munderdiffl.in/blog/claude-code-subagents-vs-multi-agent-harness/" />
+ <id>https://munderdiffl.in/blog/claude-code-subagents-vs-multi-agent-harness/</id>
+ <published>2026-05-23T00:00:00.000Z</published>
+ <updated>2026-05-23T00:00:00.000Z</updated><category term="Guides" />
+ <summary>Claude Code subagents vs a multi-agent harness: where subagents stop and a harness with shared memory, messaging, and an orchestrator takes over.</summary>
+ </entry>
<entry>
<title>What Is a Multi-Agent Harness? (Plain-English Guide)</title>
<link href="https://munderdiffl.in/blog/what-is-a-multi-agent-harness/" />
diff --git a/docs/blog/from-one-terminal-to-a-team/index.html b/docs/blog/from-one-terminal-to-a-team/index.html
new file mode 100644
index 00000000..b89776e8
--- /dev/null
+++ b/docs/blog/from-one-terminal-to-a-team/index.html
@@ -0,0 +1,330 @@
+<!doctype html>
+<html lang="en">
+<head>
+<meta charset="UTF-8" />
+<meta name="viewport" content="width=device-width, initial-scale=1.0" />
+<title>From One Terminal to a Team: Scaling Your Claude Code Workflow — Munder Difflin Blog</title>
+<meta name="description" content="The workflow shift from a single Claude Code session to a coordinated team of agents — what changes, where it breaks, and the concrete before-and-after." />
+<link rel="canonical" href="https://munderdiffl.in/blog/from-one-terminal-to-a-team/" />
+
+<link rel="icon" type="image/png" href="https://munderdiffl.in/logo.png" />
+<link rel="apple-touch-icon" href="https://munderdiffl.in/logo.png" />
+<meta name="theme-color" content="#F5F2E8" />
+
+<!-- Open Graph -->
+<meta property="og:site_name" content="Munder Difflin Blog" />
+<meta property="og:type" content="article" />
+<meta property="og:title" content="From One Terminal to a Team: Scaling Your Claude Code Workflow — Munder Difflin Blog" />
+<meta property="og:description" content="The workflow shift from a single Claude Code session to a coordinated team of agents — what changes, where it breaks, and the concrete before-and-after." />
+<meta property="og:url" content="https://munderdiffl.in/blog/from-one-terminal-to-a-team/" />
+<meta property="og:image" content="https://munderdiffl.in/media/og.png" />
+<meta property="og:locale" content="en_US" />
+<meta property="article:published_time" content="2026-06-02T00:00:00.000Z" />
+<meta property="article:author" content="Chaitanya Giri" />
+<meta property="article:tag" content="Use Cases" />
+<meta property="article:tag" content="Multi-Agent" />
+<meta property="article:tag" content="Claude Code" />
+<meta property="article:tag" content="Workflow" />
+
+
+<!-- Twitter -->
+<meta name="twitter:card" content="summary_large_image" />
+<meta name="twitter:title" content="From One Terminal to a Team: Scaling Your Claude Code Workflow — Munder Difflin Blog" />
+<meta name="twitter:description" content="The workflow shift from a single Claude Code session to a coordinated team of agents — what changes, where it breaks, and the concrete before-and-after." />
+<meta name="twitter:image" content="https://munderdiffl.in/media/og.png" />
+
+<link rel="alternate" type="application/atom+xml" title="Munder Difflin Blog" href="https://munderdiffl.in/blog/feed.xml" />
+<link rel="preconnect" href="https://fonts.googleapis.com" />
+<link rel="preconnect" href="https://fonts.gstatic.com" crossorigin />
+<link href="https://fonts.googleapis.com/css2?family=Geist:wght@400;500;600&family=JetBrains+Mono:wght@400;500;600;700&display=swap" rel="stylesheet" />
+<link rel="stylesheet" href="/blog/assets/blog.css" />
+
+<script type="application/ld+json">
+{
+ "@context": "https://schema.org",
+ "@type": "BlogPosting",
+ "headline": "From One Terminal to a Team: Scaling Your Claude Code Workflow",
+ "description": "The workflow shift from a single Claude Code session to a coordinated team of agents — what changes, where it breaks, and the concrete before-and-after.",
+ "image": ["https://munderdiffl.in/media/og.png"],
+ "datePublished": "2026-06-02T00:00:00.000Z",
+ "dateModified": "2026-06-02T00:00:00.000Z",
+ "author": { "@type": "Person", "name": "Chaitanya Giri" },
+ "publisher": {
+ "@type": "Organization",
+ "name": "Munder Difflin",
+ "logo": { "@type": "ImageObject", "url": "https://munderdiffl.in/logo.png" }
+ },
+ "mainEntityOfPage": { "@type": "WebPage", "@id": "https://munderdiffl.in/blog/from-one-terminal-to-a-team/" },
+ "keywords": "run multiple claude code agents, claude code workflow, scaling ai agents, ai coding agent teams",
+ "articleSection": "Use Cases",
+ "inLanguage": "en-US",
+ "url": "https://munderdiffl.in/blog/from-one-terminal-to-a-team/"
+}
+</script>
+<script type="application/ld+json">
+{
+ "@context": "https://schema.org",
+ "@type": "BreadcrumbList",
+ "itemListElement": [
+ { "@type": "ListItem", "position": 1, "name": "Home", "item": "https://munderdiffl.in/" },
+ { "@type": "ListItem", "position": 2, "name": "Blog", "item": "https://munderdiffl.in/blog/" },
+ { "@type": "ListItem", "position": 3, "name": "From One Terminal to a Team: Scaling Your Claude Code Workflow", "item": "https://munderdiffl.in/blog/from-one-terminal-to-a-team/" }
+ ]
+}
+</script>
+
+
+</head>
+<body>
+<a class="skip-link" href="#main">Skip to content</a>
+<nav id="nav">
+ <a class="brand" href="/blog/" aria-label="Munder Difflin Blog home">
+ <span class="brand-mark">MD</span>
+ <span class="brand-word">MUNDER DIFFLIN<span class="sep">/</span><span class="blog">BLOG</span></span>
+ </a>
+ <span class="spacer"></span>
+ <div class="links">
+ <a href="/blog/">Latest</a>
+ <a href="/blog/topics/">Topics</a>
+ <a href="/blog/about/">About</a>
+ <a href="https://munderdiffl.in">↗ Product</a>
+ </div>
+ <div class="nav-actions">
+ <a class="btn sm" href="https://munderdiffl.in/blog/feed.xml" aria-label="RSS feed">⤵ RSS</a>
+ <a class="btn sm primary" href="https://munderdiffl.in/#install">⤓ Download</a>
+ </div>
+</nav>
+
+<main id="main">
+
+<article>
+ <header class="post-head wrap">
+ <nav class="crumbs" aria-label="Breadcrumb">
+ <a href="/blog/">Blog</a>
+ <span>/</span>
+ <a href="/blog/topics/use-cases/">Use Cases</a>
+ </nav>
+ <h1>From One Terminal to a Team: Scaling Your Claude Code Workflow</h1>
+ <p class="dek">The workflow shift from a single Claude Code session to a coordinated team of agents — what changes, where it breaks, and the concrete before-and-after.</p>
+ <div class="byline">
+ <span class="av" aria-hidden="true">CG</span>
+ <strong>Chaitanya Giri</strong>
+ <span class="dot" aria-hidden="true">·</span>
+ <time datetime="2026-06-02">Jun 2, 2026</time>
+ <span class="dot" aria-hidden="true">·</span>
+ <span>3 min read</span>
+ <span class="tag kind">Use Cases</span>
+ </div>
+ </header>
+
+ <div class="post-wrap wrap">
+ <div class="prose">
+ <div class="callout tldr"><span class="ic">TL;DR</span><p>Scaling your Claude Code workflow goes
+through three stages: <strong>one session</strong> → <strong>a few manual terminals</strong> →
+<strong>a coordinated team</strong>. Each stage solves the previous one's pain and introduces a new
+one. The jump that actually changes your day is the last: giving agents <strong>shared memory,
+messaging, and an orchestrator</strong> so they stop colliding and forgetting.</p></div>
+<p>Most people don’t decide to “run a team of agents” — they back into it, one terminal at a time, until
+the workflow strains. Here’s the arc, what breaks at each step, and the concrete before-and-after of
+crossing to a real team.</p>
+<h2 id="stage-1-one-terminal" tabindex="-1">Stage 1: One terminal <a class="anchor" href="#stage-1-one-terminal" aria-hidden="true">#</a></h2>
+<p>You run a single <code>claude</code> session. It’s focused, it’s easy to follow, and for most tasks it’s all you
+need. The only ceiling is <em>throughput</em> — one agent does one thing at a time, and you’re the only
+parallelism in the room.</p>
+<p><strong>The pain that pushes you forward:</strong> you’re waiting on the agent while three other things you could
+parallelize sit idle.</p>
+<h2 id="stage-2-a-few-manual-terminals" tabindex="-1">Stage 2: A few manual terminals <a class="anchor" href="#stage-2-a-few-manual-terminals" aria-hidden="true">#</a></h2>
+<p>So you open more terminals — a <a href="/blog/how-to-run-multiple-claude-code-agents/">classic move</a>. One
+writes tests, one refactors, one updates docs. Throughput jumps. For two or three <em>independent</em> tasks,
+this genuinely works.</p>
+<p>Then they start to overlap, and three problems show up:</p>
+<ul>
+<li><strong>Collisions.</strong> Two agents edit the same file and race each other; in git you get <code>index.lock</code>
+errors and half-applied changes.</li>
+<li><strong>Amnesia.</strong> Each session has its own context. What agent A learned, agent B can’t use — so <em>you</em>
+become the courier, copy-pasting findings between windows.</li>
+<li><strong>Lost track.</strong> With six tabs open, “what is everyone doing right now?” has no answer.</li>
+</ul>
+<p><strong>The pain that pushes you forward:</strong> you’ve become the message bus, the conflict resolver, and the
+project’s only memory. The agents got faster; <em>you</em> became the bottleneck.</p>
+<h2 id="stage-3-a-coordinated-team" tabindex="-1">Stage 3: A coordinated team <a class="anchor" href="#stage-3-a-coordinated-team" aria-hidden="true">#</a></h2>
+<p>The fix isn’t more tabs — it’s a coordination layer. Three additions turn parallel sessions into a
+team:</p>
+<ul>
+<li><strong>Roles</strong> so each agent stays in its lane and “who does this?” is obvious.</li>
+<li><strong>Shared memory</strong> so the team reads from one <a href="/blog/give-claude-code-long-term-memory/">long-term
+memory</a> and stops re-learning the project.</li>
+<li><strong>Messaging + an orchestrator</strong> so agents hand work to each other and a coordinator routes it —
+instead of routing through you.</li>
+</ul>
+<p>That’s the leap from juggling <a href="/blog/what-are-claude-code-agents/">Claude Code agents</a> to running a
+<a href="/#what">multi-agent harness</a>. It’s the stage where adding agents stops adding <em>overhead</em>.</p>
+<h2 id="the-before-and-after" tabindex="-1">The before-and-after <a class="anchor" href="#the-before-and-after" aria-hidden="true">#</a></h2>
+<p>The same morning, two ways:</p>
+<table>
+<thead>
+<tr>
+<th></th>
+<th>Manual terminals</th>
+<th>Coordinated team</th>
+</tr>
+</thead>
+<tbody>
+<tr>
+<td>Assigning work</td>
+<td>You, tab by tab</td>
+<td>Describe intent; orchestrator routes</td>
+</tr>
+<tr>
+<td>Context sharing</td>
+<td>You copy-paste between windows</td>
+<td>Shared memory; agents read it</td>
+</tr>
+<tr>
+<td>Handing off</td>
+<td>You relay results</td>
+<td>Agents message each other</td>
+</tr>
+<tr>
+<td>File conflicts</td>
+<td><code>index.lock</code>, manual cleanup</td>
+<td>Coordination rules prevent it</td>
+</tr>
+<tr>
+<td>“What’s happening?”</td>
+<td>Alt-tab and guess</td>
+<td>A glance at the floor</td>
+</tr>
+<tr>
+<td>Your role</td>
+<td>Message bus</td>
+<td>Manager</td>
+</tr>
+</tbody>
+</table>
+<p>Nothing about the <em>agents</em> changed — they’re the same Claude Code sessions. What changed is the layer
+around them, and that’s what moves you from operator to manager.</p>
+<h2 id="knowing-when-to-make-the-jump" tabindex="-1">Knowing when to make the jump <a class="anchor" href="#knowing-when-to-make-the-jump" aria-hidden="true">#</a></h2>
+<p>You don’t need a team to use Claude Code. You want one when:</p>
+<ul>
+<li>you’re running <strong>three or more</strong> sessions and losing the thread,</li>
+<li>you keep <strong>re-explaining context</strong> because each session forgets, or</li>
+<li>agents <strong>collide</strong> on the same files.</li>
+</ul>
+<p>If that’s you, the next step is the coordination layer — and you can keep the whole thing
+<a href="/blog/why-local-first-matters-for-ai-agents/">local</a>. The natural destination is <a href="/blog/run-an-office-of-ai-agents/">an office of agents
+that keeps shipping</a> even after you log off.</p>
+<hr>
+<p>Munder Difflin is the coordination layer for the Claude Code agents you already run — roles, shared
+memory, messaging, and an orchestrator, all local. <a href="/#install">Download Munder Difflin</a> to make the
+jump; it’s free and open source.</p>
+
+
+
+
+
+ <hr />
+ <div class="share">
+ <span class="lbl">Tags</span>
+ <a class="tag" href="/blog/tags/use-cases/">Use Cases</a><a class="tag" href="/blog/tags/multi-agent/">Multi-Agent</a><a class="tag" href="/blog/tags/claude-code/">Claude Code</a><a class="tag" href="/blog/tags/workflow/">Workflow</a>
+ </div>
+
+ </div>
+
+
+ <aside class="toc-rail" aria-label="Table of contents">
+ <div class="tt">On this page</div>
+ <ol>
+ <li class="lvl-2"><a href="#stage-1-one-terminal">Stage 1: One terminal</a></li><li class="lvl-2"><a href="#stage-2-a-few-manual-terminals">Stage 2: A few manual terminals</a></li><li class="lvl-2"><a href="#stage-3-a-coordinated-team">Stage 3: A coordinated team</a></li><li class="lvl-2"><a href="#the-before-and-after">The before-and-after</a></li><li class="lvl-2"><a href="#knowing-when-to-make-the-jump">Knowing when to make the jump</a></li>
+ </ol>
+ </aside>
+
+ </div>
+
+ <footer class="post-foot wrap"><div class="prevnext">
+ <a class="pn prev" href="/blog/how-to-choose-a-multi-agent-tool/"><span class="k">← Older</span><span class="t">How to Choose a Multi-Agent Coding Tool: A Buyer&#39;s Checklist</span></a>
+ <a class="pn next" href="/blog/ai-agent-glossary/"><span class="k">Newer →</span><span class="t">The AI Coding Agent Glossary: Harness, Orchestrator, Hive, Subagent</span></a>
+ </div>
+ <section class="related">
+ <h2>Related in Use Cases</h2>
+ <div class="post-grid">
+ <article class="card">
+ <a class="thumb t-use-cases" href="/blog/run-an-office-of-ai-agents/" aria-hidden="true" tabindex="-1">
+ <span>USE CASES</span>
+ </a>
+ <div class="body">
+ <div class="meta">
+ <time datetime="2026-06-02">Jun 2, 2026</time>
+ <span class="dot" aria-hidden="true"></span>
+ <span>3 min</span>
+ </div>
+ <h3><a href="/blog/run-an-office-of-ai-agents/">Run an Office of AI Agents While You Sleep</a></h3>
+ <p class="dek">What it takes to run a self-coordinating office of AI coding agents that keeps shipping after you log off — and the guardrails that keep it sane.</p>
+ <div class="foot">
+ <span class="tag kind">Use Cases</span>
+ <a class="more" href="/blog/run-an-office-of-ai-agents/" aria-label="Read: Run an Office of AI Agents While You Sleep">Read →</a>
+ </div>
+ </div>
+</article>
+<article class="card">
+ <a class="thumb t-use-cases" href="/blog/why-local-first-matters-for-ai-agents/" aria-hidden="true" tabindex="-1">
+ <span>USE CASES</span>
+ </a>
+ <div class="body">
+ <div class="meta">
+ <time datetime="2026-06-02">Jun 2, 2026</time>
+ <span class="dot" aria-hidden="true"></span>
+ <span>3 min</span>
+ </div>
+ <h3><a href="/blog/why-local-first-matters-for-ai-agents/">Why Local-First Matters for Your AI Agents</a></h3>
+ <p class="dek">The control, privacy, and cost case for keeping your AI agents and their memory on your own machine — and what cloud orchestration quietly costs.</p>
+ <div class="foot">
+ <span class="tag kind">Use Cases</span>
+ <a class="more" href="/blog/why-local-first-matters-for-ai-agents/" aria-label="Read: Why Local-First Matters for Your AI Agents">Read →</a>
+ </div>
+ </div>
+</article>
+
+ </div>
+ </section>
+
+ </footer>
+</article>
+
+</main>
+<footer>
+ <div class="wrap">
+ <div class="foot-top">
+ <a class="foot-brand brand" href="/blog/">
+ <span class="brand-mark">MD</span>
+ <span class="brand-word">MUNDER DIFFLIN<span class="sep">/</span><span class="blog">BLOG</span></span>
+ </a>
+ <div class="foot-links">
+ <a href="/blog/">Latest</a>
+ <a href="/blog/topics/">Topics</a>
+ <a href="/blog/about/">About</a>
+ <a href="https://munderdiffl.in/blog/feed.xml">RSS</a>
+ <a href="https://github.com/chaitanyagiri/munder-difflin">GitHub</a>
+ <a href="https://munderdiffl.in">munderdiffl.in ↗</a>
+ </div>
+ </div>
+ <div class="foot-meta">
+ © 2026 Munder Difflin · Local-first · MIT-licensed ·
+ Built on <a href="https://munderdiffl.in">Electron, React, Pixi.js, xterm.js &amp; node-pty</a>.
+ Run an office of agents while you sleep.
+ </div>
+ </div>
+</footer>
+
+<script>
+ // sticky-nav border on scroll
+ (function () {
+ var nav = document.getElementById('nav');
+ if (!nav) return;
+ var onScroll = function () { nav.classList.toggle('scrolled', window.scrollY > 8); };
+ onScroll(); window.addEventListener('scroll', onScroll, { passive: true });
+ })();
+</script>
+
+</body>
+</html>
diff --git a/docs/blog/give-claude-code-long-term-memory/index.html b/docs/blog/give-claude-code-long-term-memory/index.html
index c1656f24..a3e1b77a 100644
--- a/docs/blog/give-claude-code-long-term-memory/index.html
+++ b/docs/blog/give-claude-code-long-term-memory/index.html
@@ -201,9 +201,34 @@ to try it; it’s free and open source.</p>
</div>
<footer class="post-foot wrap"><div class="prevnext">
- <a class="pn prev" href="/blog/what-is-a-multi-agent-harness/"><span class="k">← Older</span><span class="t">What Is a Multi-Agent Harness? (Plain-English Guide)</span></a>
- <a class="pn next" href="/blog/how-to-run-multiple-claude-code-agents/"><span class="k">Newer →</span><span class="t">How to Run Multiple Claude Code Agents (Without Losing Track)</span></a>
+ <a class="pn prev" href="/blog/semantic-memory-for-ai-agents/"><span class="k">← Older</span><span class="t">Semantic Memory for AI Agents: Recall in Milliseconds</span></a>
+ <a class="pn next" href="/blog/claude-code-orchestration-guide/"><span class="k">Newer →</span><span class="t">Orchestrating Claude Code Agents: A Practical Guide</span></a>
</div>
+ <section class="related">
+ <h2>Related in Memory</h2>
+ <div class="post-grid">
+ <article class="card">
+ <a class="thumb t-memory" href="/blog/semantic-memory-for-ai-agents/" aria-hidden="true" tabindex="-1">
+ <span>MEMORY</span>
+ </a>
+ <div class="body">
+ <div class="meta">
+ <time datetime="2026-05-26">May 26, 2026</time>
+ <span class="dot" aria-hidden="true"></span>
+ <span>6 min</span>
+ </div>
+ <h3><a href="/blog/semantic-memory-for-ai-agents/">Semantic Memory for AI Agents: Recall in Milliseconds</a></h3>
+ <p class="dek">What semantic memory for AI agents is, why a markdown-first store beats a heavy DB, and how a shared palace lets a hive recall a note by meaning, fast.</p>
+ <div class="foot">
+ <span class="tag kind">Memory</span>
+ <a class="more" href="/blog/semantic-memory-for-ai-agents/" aria-label="Read: Semantic Memory for AI Agents: Recall in Milliseconds">Read →</a>
+ </div>
+ </div>
+</article>
+
+ </div>
+ </section>
+
</footer>
</article>
diff --git a/docs/blog/how-the-god-orchestrator-works/index.html b/docs/blog/how-the-god-orchestrator-works/index.html
new file mode 100644
index 00000000..c06b50c8
--- /dev/null
+++ b/docs/blog/how-the-god-orchestrator-works/index.html
@@ -0,0 +1,409 @@
+<!doctype html>
+<html lang="en">
+<head>
+<meta charset="UTF-8" />
+<meta name="viewport" content="width=device-width, initial-scale=1.0" />
+<title>Inside the GOD Orchestrator: Routing, Adjudication, Escalation — Munder Difflin Blog</title>
+<meta name="description" content="A deep dive into the Claude Code orchestrator: how a GOD agent reads requests, routes work, adjudicates routine traffic, and escalates the critical few." />
+<link rel="canonical" href="https://munderdiffl.in/blog/how-the-god-orchestrator-works/" />
+
+<link rel="icon" type="image/png" href="https://munderdiffl.in/logo.png" />
+<link rel="apple-touch-icon" href="https://munderdiffl.in/logo.png" />
+<meta name="theme-color" content="#F5F2E8" />
+
+<!-- Open Graph -->
+<meta property="og:site_name" content="Munder Difflin Blog" />
+<meta property="og:type" content="article" />
+<meta property="og:title" content="Inside the GOD Orchestrator: Routing, Adjudication, Escalation — Munder Difflin Blog" />
+<meta property="og:description" content="A deep dive into the Claude Code orchestrator: how a GOD agent reads requests, routes work, adjudicates routine traffic, and escalates the critical few." />
+<meta property="og:url" content="https://munderdiffl.in/blog/how-the-god-orchestrator-works/" />
+<meta property="og:image" content="https://munderdiffl.in/media/og.png" />
+<meta property="og:locale" content="en_US" />
+<meta property="article:published_time" content="2026-05-30T00:00:00.000Z" />
+<meta property="article:author" content="Chaitanya Giri" />
+<meta property="article:tag" content="Orchestration" />
+<meta property="article:tag" content="GOD" />
+<meta property="article:tag" content="Multi-Agent" />
+<meta property="article:tag" content="Internals" />
+
+
+<!-- Twitter -->
+<meta name="twitter:card" content="summary_large_image" />
+<meta name="twitter:title" content="Inside the GOD Orchestrator: Routing, Adjudication, Escalation — Munder Difflin Blog" />
+<meta name="twitter:description" content="A deep dive into the Claude Code orchestrator: how a GOD agent reads requests, routes work, adjudicates routine traffic, and escalates the critical few." />
+<meta name="twitter:image" content="https://munderdiffl.in/media/og.png" />
+
+<link rel="alternate" type="application/atom+xml" title="Munder Difflin Blog" href="https://munderdiffl.in/blog/feed.xml" />
+<link rel="preconnect" href="https://fonts.googleapis.com" />
+<link rel="preconnect" href="https://fonts.gstatic.com" crossorigin />
+<link href="https://fonts.googleapis.com/css2?family=Geist:wght@400;500;600&family=JetBrains+Mono:wght@400;500;600;700&display=swap" rel="stylesheet" />
+<link rel="stylesheet" href="/blog/assets/blog.css" />
+
+<script type="application/ld+json">
+{
+ "@context": "https://schema.org",
+ "@type": "BlogPosting",
+ "headline": "Inside the GOD Orchestrator: Routing, Adjudication, Escalation",
+ "description": "A deep dive into the Claude Code orchestrator: how a GOD agent reads requests, routes work, adjudicates routine traffic, and escalates the critical few.",
+ "image": ["https://munderdiffl.in/media/og.png"],
+ "datePublished": "2026-05-30T00:00:00.000Z",
+ "dateModified": "2026-05-30T00:00:00.000Z",
+ "author": { "@type": "Person", "name": "Chaitanya Giri" },
+ "publisher": {
+ "@type": "Organization",
+ "name": "Munder Difflin",
+ "logo": { "@type": "ImageObject", "url": "https://munderdiffl.in/logo.png" }
+ },
+ "mainEntityOfPage": { "@type": "WebPage", "@id": "https://munderdiffl.in/blog/how-the-god-orchestrator-works/" },
+ "keywords": "claude code orchestrator, ai orchestrator, agent routing, supervisor agent",
+ "articleSection": "Orchestration",
+ "inLanguage": "en-US",
+ "url": "https://munderdiffl.in/blog/how-the-god-orchestrator-works/"
+}
+</script>
+<script type="application/ld+json">
+{
+ "@context": "https://schema.org",
+ "@type": "BreadcrumbList",
+ "itemListElement": [
+ { "@type": "ListItem", "position": 1, "name": "Home", "item": "https://munderdiffl.in/" },
+ { "@type": "ListItem", "position": 2, "name": "Blog", "item": "https://munderdiffl.in/blog/" },
+ { "@type": "ListItem", "position": 3, "name": "Inside the GOD Orchestrator: Routing, Adjudication, Escalation", "item": "https://munderdiffl.in/blog/how-the-god-orchestrator-works/" }
+ ]
+}
+</script>
+
+<script type="application/ld+json">
+{
+ "@context": "https://schema.org",
+ "@type": "FAQPage",
+ "mainEntity": [
+ { "@type": "Question", "name": "Is the GOD orchestrator a special kind of model?", "acceptedAnswer": { "@type": "Answer", "text": "No. It's an ordinary Claude Code process with a flag marking it as the orchestrator and a system prompt that defines its job. The intelligence is a normal agent; the harness around it provides the mechanism — routing, git, and the human-approval queue." } },
+ { "@type": "Question", "name": "What does the orchestrator escalate to a human?", "acceptedAnswer": { "@type": "Answer", "text": "Only genuinely critical items: destructive operations, spending real money, scope changes, and conflicts it can't resolve. Everything else — clarifications, data asks, small plan tweaks — it resolves itself so the team stays autonomous." } },
+ { "@type": "Question", "name": "How does the orchestrator avoid infinite loops between agents?", "acceptedAnswer": { "@type": "Answer", "text": "Messages carry a hop count that increments on each reply; past a cap the item is escalated instead of bouncing forever. Only requests, queries, and proposals obligate a reply — pure informational messages are terminal." } }
+
+ ]
+}
+</script>
+
+
+</head>
+<body>
+<a class="skip-link" href="#main">Skip to content</a>
+<nav id="nav">
+ <a class="brand" href="/blog/" aria-label="Munder Difflin Blog home">
+ <span class="brand-mark">MD</span>
+ <span class="brand-word">MUNDER DIFFLIN<span class="sep">/</span><span class="blog">BLOG</span></span>
+ </a>
+ <span class="spacer"></span>
+ <div class="links">
+ <a href="/blog/">Latest</a>
+ <a href="/blog/topics/">Topics</a>
+ <a href="/blog/about/">About</a>
+ <a href="https://munderdiffl.in">↗ Product</a>
+ </div>
+ <div class="nav-actions">
+ <a class="btn sm" href="https://munderdiffl.in/blog/feed.xml" aria-label="RSS feed">⤵ RSS</a>
+ <a class="btn sm primary" href="https://munderdiffl.in/#install">⤓ Download</a>
+ </div>
+</nav>
+
+<main id="main">
+
+<article>
+ <header class="post-head wrap">
+ <nav class="crumbs" aria-label="Breadcrumb">
+ <a href="/blog/">Blog</a>
+ <span>/</span>
+ <a href="/blog/topics/orchestration/">Orchestration</a>
+ </nav>
+ <h1>Inside the GOD Orchestrator: Routing, Adjudication, Escalation</h1>
+ <p class="dek">A deep dive into the Claude Code orchestrator: how a GOD agent reads requests, routes work, adjudicates routine traffic, and escalates the critical few.</p>
+ <div class="byline">
+ <span class="av" aria-hidden="true">CG</span>
+ <strong>Chaitanya Giri</strong>
+ <span class="dot" aria-hidden="true">·</span>
+ <time datetime="2026-05-30">May 30, 2026</time>
+ <span class="dot" aria-hidden="true">·</span>
+ <span>6 min read</span>
+ <span class="tag kind">Orchestration</span>
+ </div>
+ </header>
+
+ <div class="post-wrap wrap">
+ <div class="prose">
+ <div class="callout tldr"><span class="ic">TL;DR</span><p>The <strong>GOD orchestrator</strong> is the
+supervisor agent that runs a hive of Claude Code agents. It's a normal Claude process — the
+<em>intelligence</em> — wrapped by a harness that provides the <em>mechanism</em> (a message router,
+single-committer git, and a human-approval queue). Its four jobs: keep the <strong>roster</strong>,
+<strong>route</strong> work, <strong>adjudicate</strong> routine inter-agent traffic, and
+<strong>escalate</strong> only the critical few to you.</p></div>
+<p>Every multi-agent system eventually needs one agent in charge — not to do the work, but to decide who
+does. In Munder Difflin that’s the <strong>GOD orchestrator</strong>. This is a deep dive into how it actually
+works: the split between intelligence and mechanism, the four jobs it owns, and the rules that keep it
+from looping or going rogue.</p>
+<h2 id="intelligence-vs-mechanism" tabindex="-1">Intelligence vs. mechanism <a class="anchor" href="#intelligence-vs-mechanism" aria-hidden="true">#</a></h2>
+<p>The single most important design decision is what the orchestrator <em>is</em>. It would be tempting to write
+the routing logic as code — a big dispatcher that inspects each request and assigns it. That’s
+brittle: every new kind of task needs new code.</p>
+<p>Instead, the orchestrator is split in two:</p>
+<ul>
+<li><strong>The mechanism</strong> lives in the harness’s main process. It runs git (single committer), the message
+router that moves messages between agents, the append-only event log, and the approvals queue that
+holds items waiting on a human. The mechanism has no judgment. It’s reliable plumbing.</li>
+<li><strong>The intelligence</strong> is the GOD agent itself — an ordinary <code>claude</code> process, flagged as the
+orchestrator, that reads requests and decides what to do with them. Its routing and escalation
+<em>policy</em> live in its system prompt.</li>
+</ul>
+<p>The payoff: you change how the orchestrator behaves by editing a prompt, not by shipping code. Want it
+to escalate more aggressively, or to favor a particular specialist? Tune the instructions. The
+mechanism underneath stays the same and stays safe. (For the broader principle, see
+<a href="/blog/claude-code-orchestration-guide/">orchestrating Claude Code agents</a>.)</p>
+<h2 id="job-1-keep-the-roster" tabindex="-1">Job 1 — Keep the roster <a class="anchor" href="#job-1-keep-the-roster" aria-hidden="true">#</a></h2>
+<p>The orchestrator can only route well if it knows who’s on the floor. The harness maintains a
+<strong>registry</strong> — every agent’s id, name, role, capabilities, and current status (idle, working, blocked,
+gone). When an agent is spawned, it’s registered; the orchestrator reads the registry to know its
+options.</p>
+<p>This is the routing table. A request to “write tests for the new endpoint” goes to the agent whose
+role and capabilities say <em>tests</em>, not to whoever happens to be free. Roles aren’t cosmetic — they’re
+how the orchestrator makes a sensible assignment instead of a random one.</p>
+<h2 id="job-2-route-work" tabindex="-1">Job 2 — Route work <a class="anchor" href="#job-2-route-work" aria-hidden="true">#</a></h2>
+<p>When you describe a goal, the orchestrator decomposes it and routes each piece. The key detail is
+<em>how</em> it routes: it doesn’t reach into a worker’s files and tell it what to do. It sends a message — a
+self-contained task spec — into the worker’s inbox, via the same router every agent uses.</p>
+<p>That message is a structured object. Borrowing the one useful idea from agent-communication research —
+the <strong>speech act</strong> — each message declares its intent:</p>
+<pre class="language-jsonc"><code class="language-jsonc">{
+ "to": "agent.coder",
+ "act": "request", // request | inform | propose | query | agree | refuse | done
+ "subject": "Add validation to signup",
+ "body": "…self-contained task spec…",
+ "conversation": "conv-7f3" // groups a thread
+}</code></pre>
+<p>The harness fills in the id, sender, hop count, and timestamps. A good task spec means the worker can
+start without a follow-up question — which is the difference between routing that accelerates the team
+and routing that just adds a hop.</p>
+<h2 id="job-3-adjudicate-the-routine-traffic" tabindex="-1">Job 3 — Adjudicate the routine traffic <a class="anchor" href="#job-3-adjudicate-the-routine-traffic" aria-hidden="true">#</a></h2>
+<p>This is the job that makes autonomy real. As agents work, they raise questions <em>for each other</em>: which
+schema to validate against, whether a staging URL is current, a small change to the plan. If every one
+of those bounced back to you, the “team” would just be a slower version of you doing everything.</p>
+<p>So the orchestrator adjudicates. It drains its own inbox continually, answers the routine asks itself,
+and routes work to the right specialist with a clear spec. Most inter-agent traffic never reaches you
+because it shouldn’t have to.</p>
+<p>Two rules keep adjudication from turning into chaos:</p>
+<ul>
+<li><strong>Not every message obligates a reply.</strong> Only <code>request</code>, <code>query</code>, and <code>propose</code> expect an answer.
+<code>inform</code> and <code>done</code> are terminal — replying to them is how two agents loop forever, so the protocol
+forbids it.</li>
+<li><strong>Hops are capped.</strong> Every reply increments a hop counter. Past the cap, the item is escalated to a
+human instead of being allowed to ping-pong. It’s a livelock fuse.</li>
+</ul>
+<p>The shared plan is adjudicated too: the orchestrator is the <strong>single scribe</strong> of the board. Other
+agents propose changes; only the orchestrator writes them. That keeps the one genuinely co-owned
+document from conflicting. The messaging fabric beneath all of this is covered in
+<a href="/blog/atomic-file-mailboxes-for-agents/">atomic file mailboxes for agents</a>.</p>
+<h2 id="job-4-escalate-the-critical-few" tabindex="-1">Job 4 — Escalate the critical few <a class="anchor" href="#job-4-escalate-the-critical-few" aria-hidden="true">#</a></h2>
+<p>The orchestrator’s most important boundary is knowing what <em>not</em> to decide. Its escalation policy is a
+short, explicit list of what counts as critical:</p>
+<ul>
+<li><strong>Destructive operations</strong> — anything that deletes or overwrites in a way that’s hard to undo.</li>
+<li><strong>Spending real money</strong> — actions with a dollar cost.</li>
+<li><strong>Scope changes</strong> — work that drifts from what you actually asked for.</li>
+<li><strong>Unresolvable conflicts</strong> — two agents at an impasse the orchestrator can’t break.</li>
+</ul>
+<p>When an item matches, the orchestrator escalates instead of acting. Mechanically, it sends a message
+addressed to the human (or flags it as needing human attention), and the harness diverts it into an
+<strong>approvals queue</strong> surfaced in the UI. You approve or reject — optionally with a note, like “yes, but
+cap it at $5” — and that note is relayed back to the agent that asked, as a message from the human.
+The agent picks up where it left off with your guidance in hand.</p>
+<p>Everything not on the critical list stays autonomous. This selective escalation is the entire reason a
+hive can run for a long stretch without babysitting: it interrupts you precisely when it should, and
+never otherwise. It’s also the model’s primary safety rail — the policy is the control surface, so you
+tighten or loosen it by editing the prompt.</p>
+<h2 id="how-a-single-request-travels" tabindex="-1">How a single request travels <a class="anchor" href="#how-a-single-request-travels" aria-hidden="true">#</a></h2>
+<p>Putting the four jobs together, here’s the life of one instruction:</p>
+<ol>
+<li>You tell the orchestrator a goal in plain language.</li>
+<li>It reads the <strong>roster</strong>, decomposes the goal, and <strong>routes</strong> task specs to the right agents’
+inboxes.</li>
+<li>Agents work in isolated sessions. When one needs something, it messages another through its outbox;
+the router delivers it.</li>
+<li>The orchestrator <strong>adjudicates</strong> the routine questions, answering or re-routing, keeping the floor
+moving.</li>
+<li>If something critical comes up, it <strong>escalates</strong> to the approvals queue and waits for your call.</li>
+<li>Every step is committed to the hive’s git repo and written to an append-only log, so the whole
+episode is auditable and replayable.</li>
+</ol>
+<h2 id="what-makes-it-robust" tabindex="-1">What makes it robust <a class="anchor" href="#what-makes-it-robust" aria-hidden="true">#</a></h2>
+<p>A few properties keep the orchestrator from being a single point of failure:</p>
+<ul>
+<li><strong>The mechanism is dumb and reliable.</strong> Routing, commits, and the queue work even if the
+orchestrator makes a poor call — a bad route is recoverable because it still flows through
+single-writer files and serialized commits.</li>
+<li><strong>Idempotent message handling.</strong> Each agent tracks a cursor of what it has already processed, so a
+message is acted on exactly once. Re-seeing a handled message is a no-op.</li>
+<li><strong>Escalation is fail-safe.</strong> When in doubt — a hop cap hit, an addressing edge case — the system
+routes to the human rather than guessing. The default is “ask,” not “act.”</li>
+</ul>
+<p>If you want the design rationale behind these choices,
+<a href="/blog/coordinating-ai-coding-agents/">the best way to coordinate AI coding agents</a> lays out the
+single-writer and single-committer principles the orchestrator depends on.</p>
+<h2 id="faq" tabindex="-1">FAQ <a class="anchor" href="#faq" aria-hidden="true">#</a></h2>
+<p><strong>Can I run without an orchestrator?</strong> You can run agents without one, but then you’re the
+orchestrator — assigning work and relaying messages by hand. The GOD agent exists to take that role
+off your plate.</p>
+<p><strong>Where does the orchestrator “live”?</strong> It’s a fixed, always-on agent in the corner office (Michael’s
+room, naturally), with a reserved desk. It boots with the hive and runs alongside the workers as just
+another <code>claude</code> process — a special one.</p>
+<hr>
+<p>Munder Difflin’s GOD orchestrator routes, adjudicates, and escalates for a whole hive of Claude Code
+agents — on your own machine, with a full audit trail. <a href="https://munderdiffl.in/#install">Download Munder Difflin</a>
+to put one in charge of your floor; it’s free and open source.</p>
+
+
+
+ <section class="faq" aria-label="Frequently asked questions">
+ <h2 id="faq">FAQ</h2>
+
+ <div class="qa">
+ <p class="q">Is the GOD orchestrator a special kind of model?</p>
+ <p class="a">No. It&#39;s an ordinary Claude Code process with a flag marking it as the orchestrator and a system prompt that defines its job. The intelligence is a normal agent; the harness around it provides the mechanism — routing, git, and the human-approval queue.</p>
+ </div>
+
+ <div class="qa">
+ <p class="q">What does the orchestrator escalate to a human?</p>
+ <p class="a">Only genuinely critical items: destructive operations, spending real money, scope changes, and conflicts it can&#39;t resolve. Everything else — clarifications, data asks, small plan tweaks — it resolves itself so the team stays autonomous.</p>
+ </div>
+
+ <div class="qa">
+ <p class="q">How does the orchestrator avoid infinite loops between agents?</p>
+ <p class="a">Messages carry a hop count that increments on each reply; past a cap the item is escalated instead of bouncing forever. Only requests, queries, and proposals obligate a reply — pure informational messages are terminal.</p>
+ </div>
+
+ </section>
+
+
+
+ <hr />
+ <div class="share">
+ <span class="lbl">Tags</span>
+ <a class="tag" href="/blog/tags/orchestration/">Orchestration</a><a class="tag" href="/blog/tags/god/">GOD</a><a class="tag" href="/blog/tags/multi-agent/">Multi-Agent</a><a class="tag" href="/blog/tags/internals/">Internals</a>
+ </div>
+
+ </div>
+
+
+ <aside class="toc-rail" aria-label="Table of contents">
+ <div class="tt">On this page</div>
+ <ol>
+ <li class="lvl-2"><a href="#intelligence-vs-mechanism">Intelligence vs. mechanism</a></li><li class="lvl-2"><a href="#job-1-keep-the-roster">Job 1 — Keep the roster</a></li><li class="lvl-2"><a href="#job-2-route-work">Job 2 — Route work</a></li><li class="lvl-2"><a href="#job-3-adjudicate-the-routine-traffic">Job 3 — Adjudicate the routine traffic</a></li><li class="lvl-2"><a href="#job-4-escalate-the-critical-few">Job 4 — Escalate the critical few</a></li><li class="lvl-2"><a href="#how-a-single-request-travels">How a single request travels</a></li><li class="lvl-2"><a href="#what-makes-it-robust">What makes it robust</a></li><li class="lvl-2"><a href="#faq">FAQ</a></li>
+ </ol>
+ </aside>
+
+ </div>
+
+ <footer class="post-foot wrap"><div class="prevnext">
+ <a class="pn prev" href="/blog/coordinating-ai-coding-agents/"><span class="k">← Older</span><span class="t">The Best Way to Coordinate AI Coding Agents</span></a>
+ <a class="pn next" href="/blog/atomic-file-mailboxes-for-agents/"><span class="k">Newer →</span><span class="t">Atomic File Mailboxes: How Agents Message Each Other</span></a>
+ </div>
+ <section class="related">
+ <h2>Related in Orchestration</h2>
+ <div class="post-grid">
+ <article class="card">
+ <a class="thumb t-orchestration" href="/blog/claude-code-git-worktrees-vs-hive/" aria-hidden="true" tabindex="-1">
+ <span>ORCHESTRATION</span>
+ </a>
+ <div class="body">
+ <div class="meta">
+ <time datetime="2026-06-04">Jun 4, 2026</time>
+ <span class="dot" aria-hidden="true"></span>
+ <span>5 min</span>
+ </div>
+ <h3><a href="/blog/claude-code-git-worktrees-vs-hive/">Git Worktrees vs a Hive: Two Ways to Parallelize Claude Code</a></h3>
+ <p class="dek">Claude Code git worktrees vs a hive: when isolated worktrees suffice for parallel agents, and when you need memory, messaging, and an orchestrator on top.</p>
+ <div class="foot">
+ <span class="tag kind">Orchestration</span>
+ <a class="more" href="/blog/claude-code-git-worktrees-vs-hive/" aria-label="Read: Git Worktrees vs a Hive: Two Ways to Parallelize Claude Code">Read →</a>
+ </div>
+ </div>
+</article>
+<article class="card">
+ <a class="thumb t-orchestration" href="/blog/coordinating-ai-coding-agents/" aria-hidden="true" tabindex="-1">
+ <span>ORCHESTRATION</span>
+ </a>
+ <div class="body">
+ <div class="meta">
+ <time datetime="2026-05-29">May 29, 2026</time>
+ <span class="dot" aria-hidden="true"></span>
+ <span>5 min</span>
+ </div>
+ <h3><a href="/blog/coordinating-ai-coding-agents/">The Best Way to Coordinate AI Coding Agents</a></h3>
+ <p class="dek">The best way to coordinate AI coding agents: single-writer files, a message router, a one-scribe plan, and an orchestrator — cooperate, not clobber.</p>
+ <div class="foot">
+ <span class="tag kind">Orchestration</span>
+ <a class="more" href="/blog/coordinating-ai-coding-agents/" aria-label="Read: The Best Way to Coordinate AI Coding Agents">Read →</a>
+ </div>
+ </div>
+</article>
+<article class="card">
+ <a class="thumb t-orchestration" href="/blog/claude-code-orchestration-guide/" aria-hidden="true" tabindex="-1">
+ <span>ORCHESTRATION</span>
+ </a>
+ <div class="body">
+ <div class="meta">
+ <time datetime="2026-05-28">May 28, 2026</time>
+ <span class="dot" aria-hidden="true"></span>
+ <span>5 min</span>
+ </div>
+ <h3><a href="/blog/claude-code-orchestration-guide/">Orchestrating Claude Code Agents: A Practical Guide</a></h3>
+ <p class="dek">How to orchestrate Claude Code agents in practice: what orchestration means, how a GOD orchestrator routes and escalates work, and how to wire it up.</p>
+ <div class="foot">
+ <span class="tag kind">Orchestration</span>
+ <a class="more" href="/blog/claude-code-orchestration-guide/" aria-label="Read: Orchestrating Claude Code Agents: A Practical Guide">Read →</a>
+ </div>
+ </div>
+</article>
+
+ </div>
+ </section>
+
+ </footer>
+</article>
+
+</main>
+<footer>
+ <div class="wrap">
+ <div class="foot-top">
+ <a class="foot-brand brand" href="/blog/">
+ <span class="brand-mark">MD</span>
+ <span class="brand-word">MUNDER DIFFLIN<span class="sep">/</span><span class="blog">BLOG</span></span>
+ </a>
+ <div class="foot-links">
+ <a href="/blog/">Latest</a>
+ <a href="/blog/topics/">Topics</a>
+ <a href="/blog/about/">About</a>
+ <a href="https://munderdiffl.in/blog/feed.xml">RSS</a>
+ <a href="https://github.com/chaitanyagiri/munder-difflin">GitHub</a>
+ <a href="https://munderdiffl.in">munderdiffl.in ↗</a>
+ </div>
+ </div>
+ <div class="foot-meta">
+ © 2026 Munder Difflin · Local-first · MIT-licensed ·
+ Built on <a href="https://munderdiffl.in">Electron, React, Pixi.js, xterm.js &amp; node-pty</a>.
+ Run an office of agents while you sleep.
+ </div>
+ </div>
+</footer>
+
+<script>
+ // sticky-nav border on scroll
+ (function () {
+ var nav = document.getElementById('nav');
+ if (!nav) return;
+ var onScroll = function () { nav.classList.toggle('scrolled', window.scrollY > 8); };
+ onScroll(); window.addEventListener('scroll', onScroll, { passive: true });
+ })();
+</script>
+
+</body>
+</html>
diff --git a/docs/blog/how-to-choose-a-multi-agent-tool/index.html b/docs/blog/how-to-choose-a-multi-agent-tool/index.html
new file mode 100644
index 00000000..0f8dba9a
--- /dev/null
+++ b/docs/blog/how-to-choose-a-multi-agent-tool/index.html
@@ -0,0 +1,379 @@
+<!doctype html>
+<html lang="en">
+<head>
+<meta charset="UTF-8" />
+<meta name="viewport" content="width=device-width, initial-scale=1.0" />
+<title>How to Choose a Multi-Agent Coding Tool: A Buyer&#39;s Checklist — Munder Difflin Blog</title>
+<meta name="description" content="A decision framework for choosing a multi-agent coding tool — memory, control, visibility, cost, local-first — with a simple scoring rubric you can run." />
+<link rel="canonical" href="https://munderdiffl.in/blog/how-to-choose-a-multi-agent-tool/" />
+
+<link rel="icon" type="image/png" href="https://munderdiffl.in/logo.png" />
+<link rel="apple-touch-icon" href="https://munderdiffl.in/logo.png" />
+<meta name="theme-color" content="#F5F2E8" />
+
+<!-- Open Graph -->
+<meta property="og:site_name" content="Munder Difflin Blog" />
+<meta property="og:type" content="article" />
+<meta property="og:title" content="How to Choose a Multi-Agent Coding Tool: A Buyer&#39;s Checklist — Munder Difflin Blog" />
+<meta property="og:description" content="A decision framework for choosing a multi-agent coding tool — memory, control, visibility, cost, local-first — with a simple scoring rubric you can run." />
+<meta property="og:url" content="https://munderdiffl.in/blog/how-to-choose-a-multi-agent-tool/" />
+<meta property="og:image" content="https://munderdiffl.in/media/og.png" />
+<meta property="og:locale" content="en_US" />
+<meta property="article:published_time" content="2026-06-02T00:00:00.000Z" />
+<meta property="article:author" content="Chaitanya Giri" />
+<meta property="article:tag" content="Comparisons" />
+<meta property="article:tag" content="Multi-Agent" />
+<meta property="article:tag" content="Tools" />
+<meta property="article:tag" content="Getting Started" />
+
+
+<!-- Twitter -->
+<meta name="twitter:card" content="summary_large_image" />
+<meta name="twitter:title" content="How to Choose a Multi-Agent Coding Tool: A Buyer&#39;s Checklist — Munder Difflin Blog" />
+<meta name="twitter:description" content="A decision framework for choosing a multi-agent coding tool — memory, control, visibility, cost, local-first — with a simple scoring rubric you can run." />
+<meta name="twitter:image" content="https://munderdiffl.in/media/og.png" />
+
+<link rel="alternate" type="application/atom+xml" title="Munder Difflin Blog" href="https://munderdiffl.in/blog/feed.xml" />
+<link rel="preconnect" href="https://fonts.googleapis.com" />
+<link rel="preconnect" href="https://fonts.gstatic.com" crossorigin />
+<link href="https://fonts.googleapis.com/css2?family=Geist:wght@400;500;600&family=JetBrains+Mono:wght@400;500;600;700&display=swap" rel="stylesheet" />
+<link rel="stylesheet" href="/blog/assets/blog.css" />
+
+<script type="application/ld+json">
+{
+ "@context": "https://schema.org",
+ "@type": "BlogPosting",
+ "headline": "How to Choose a Multi-Agent Coding Tool: A Buyer's Checklist",
+ "description": "A decision framework for choosing a multi-agent coding tool — memory, control, visibility, cost, local-first — with a simple scoring rubric you can run.",
+ "image": ["https://munderdiffl.in/media/og.png"],
+ "datePublished": "2026-06-02T00:00:00.000Z",
+ "dateModified": "2026-06-02T00:00:00.000Z",
+ "author": { "@type": "Person", "name": "Chaitanya Giri" },
+ "publisher": {
+ "@type": "Organization",
+ "name": "Munder Difflin",
+ "logo": { "@type": "ImageObject", "url": "https://munderdiffl.in/logo.png" }
+ },
+ "mainEntityOfPage": { "@type": "WebPage", "@id": "https://munderdiffl.in/blog/how-to-choose-a-multi-agent-tool/" },
+ "keywords": "agentic coding tools, agentic coding tools, ai coding agent teams, choosing ai tools",
+ "articleSection": "Comparisons",
+ "inLanguage": "en-US",
+ "url": "https://munderdiffl.in/blog/how-to-choose-a-multi-agent-tool/"
+}
+</script>
+<script type="application/ld+json">
+{
+ "@context": "https://schema.org",
+ "@type": "BreadcrumbList",
+ "itemListElement": [
+ { "@type": "ListItem", "position": 1, "name": "Home", "item": "https://munderdiffl.in/" },
+ { "@type": "ListItem", "position": 2, "name": "Blog", "item": "https://munderdiffl.in/blog/" },
+ { "@type": "ListItem", "position": 3, "name": "How to Choose a Multi-Agent Coding Tool: A Buyer's Checklist", "item": "https://munderdiffl.in/blog/how-to-choose-a-multi-agent-tool/" }
+ ]
+}
+</script>
+
+
+</head>
+<body>
+<a class="skip-link" href="#main">Skip to content</a>
+<nav id="nav">
+ <a class="brand" href="/blog/" aria-label="Munder Difflin Blog home">
+ <span class="brand-mark">MD</span>
+ <span class="brand-word">MUNDER DIFFLIN<span class="sep">/</span><span class="blog">BLOG</span></span>
+ </a>
+ <span class="spacer"></span>
+ <div class="links">
+ <a href="/blog/">Latest</a>
+ <a href="/blog/topics/">Topics</a>
+ <a href="/blog/about/">About</a>
+ <a href="https://munderdiffl.in">↗ Product</a>
+ </div>
+ <div class="nav-actions">
+ <a class="btn sm" href="https://munderdiffl.in/blog/feed.xml" aria-label="RSS feed">⤵ RSS</a>
+ <a class="btn sm primary" href="https://munderdiffl.in/#install">⤓ Download</a>
+ </div>
+</nav>
+
+<main id="main">
+
+<article>
+ <header class="post-head wrap">
+ <nav class="crumbs" aria-label="Breadcrumb">
+ <a href="/blog/">Blog</a>
+ <span>/</span>
+ <a href="/blog/topics/comparisons/">Comparisons</a>
+ </nav>
+ <h1>How to Choose a Multi-Agent Coding Tool: A Buyer&#39;s Checklist</h1>
+ <p class="dek">A decision framework for choosing a multi-agent coding tool — memory, control, visibility, cost, local-first — with a simple scoring rubric you can run.</p>
+ <div class="byline">
+ <span class="av" aria-hidden="true">CG</span>
+ <strong>Chaitanya Giri</strong>
+ <span class="dot" aria-hidden="true">·</span>
+ <time datetime="2026-06-02">Jun 2, 2026</time>
+ <span class="dot" aria-hidden="true">·</span>
+ <span>3 min read</span>
+ <span class="tag kind">Comparisons</span>
+ </div>
+ </header>
+
+ <div class="post-wrap wrap">
+ <div class="prose">
+ <div class="callout tldr"><span class="ic">TL;DR</span><p>Choose a <strong>multi-agent coding
+tool</strong> by scoring it on six things that actually change your workflow: <strong>memory</strong>,
+<strong>messaging</strong>, <strong>orchestration</strong>, <strong>visibility</strong>,
+<strong>control</strong>, and <strong>cost &amp; local-first</strong>. Weight each by how much it
+matters to <em>you</em>, score each tool 0–3, and the highest total wins — for your situation, not in
+the abstract.</p></div>
+<p>There’s no single best <a href="/blog/best-claude-code-multi-agent-tools/">agentic coding tool</a> — there’s the
+best one for your workload. The way to find it isn’t reading ten reviews; it’s running the same
+checklist across the contenders. Here’s a framework you can use in fifteen minutes.</p>
+<h2 id="start-with-the-question-behind-the-question" tabindex="-1">Start with the question behind the question <a class="anchor" href="#start-with-the-question-behind-the-question" aria-hidden="true">#</a></h2>
+<p>Before scoring anything, name your actual bottleneck. Most people are solving one of two problems:</p>
+<ul>
+<li><strong>“I need to run agents in parallel without them colliding.”</strong> A session manager or
+worktree-isolating app solves this directly.</li>
+<li><strong>“I’m drowning in coordination — re-explaining context, relaying messages, assigning every
+task.”</strong> That’s a <a href="/#how">coordination</a> problem, and it needs memory, messaging, and an
+orchestrator.</li>
+</ul>
+<p>If you’re in the first camp, optimize for simplicity. If you’re in the second, the checklist below
+will steer you toward heavier, more coordinated tools — and that’s correct.</p>
+<h2 id="the-six-criteria" tabindex="-1">The six criteria <a class="anchor" href="#the-six-criteria" aria-hidden="true">#</a></h2>
+<h3 id="1-memory" tabindex="-1">1. Memory <a class="anchor" href="#1-memory" aria-hidden="true">#</a></h3>
+<p>Does the tool give agents a shared, durable <a href="/blog/give-claude-code-long-term-memory/">long-term
+memory</a> they read on startup and write to as they learn — or
+does each agent start cold every session? Memory is the single biggest multiplier on a team’s output
+over time, because it stops you re-explaining the project.</p>
+<h3 id="2-messaging" tabindex="-1">2. Messaging <a class="anchor" href="#2-messaging" aria-hidden="true">#</a></h3>
+<p>Can agents hand work and findings to each other directly (mailboxes, a router), or are <em>you</em> the
+message bus relaying between windows? Direct messaging is what lets a team self-coordinate.</p>
+<h3 id="3-orchestration" tabindex="-1">3. Orchestration <a class="anchor" href="#3-orchestration" aria-hidden="true">#</a></h3>
+<p>Is there a coordinator that decomposes your intent and routes work — escalating only the critical
+decisions — or do you assign every task by hand? More orchestration means more leverage; less means
+more control.</p>
+<h3 id="4-visibility" tabindex="-1">4. Visibility <a class="anchor" href="#4-visibility" aria-hidden="true">#</a></h3>
+<p>Can you <em>see</em> what the team is doing — a live view, not a wall of terminal tabs? Visibility builds
+trust and catches problems early. Forms vary: a session list, a diff view, a board, a
+<a href="/#how">visual office floor</a>.</p>
+<h3 id="5-control" tabindex="-1">5. Control <a class="anchor" href="#5-control" aria-hidden="true">#</a></h3>
+<p>How much do you steer vs. delegate? Some workloads want a human approving each step; others want to
+describe a goal and walk away. Decide where you sit on that spectrum before you judge a tool’s
+autonomy as a pro or a con.</p>
+<h3 id="6-cost-local-first" tabindex="-1">6. Cost &amp; local-first <a class="anchor" href="#6-cost-local-first" aria-hidden="true">#</a></h3>
+<p>Is it free or paid? Open source or closed? Does it run <a href="/blog/why-local-first-matters-for-ai-agents/">locally on your
+machine</a> (privacy, predictable cost, offline) or in the
+cloud? For many developers, local-first and open source are non-negotiable.</p>
+<h2 id="the-scoring-rubric" tabindex="-1">The scoring rubric <a class="anchor" href="#the-scoring-rubric" aria-hidden="true">#</a></h2>
+<p>For each criterion, give the tool a 0–3:</p>
+<ul>
+<li><strong>0</strong> — absent</li>
+<li><strong>1</strong> — minimal / workaround</li>
+<li><strong>2</strong> — present, partial</li>
+<li><strong>3</strong> — first-class</li>
+</ul>
+<p>Then weight by importance to <em>you</em> (×1 for “nice to have”, ×2 for “matters”, ×3 for “dealbreaker”).
+Multiply, sum, compare. A worked example for a team whose bottleneck is coordination:</p>
+<table>
+<thead>
+<tr>
+<th>Criterion</th>
+<th>Weight</th>
+<th>Tool A (session manager)</th>
+<th>Tool B (coordinated hive)</th>
+</tr>
+</thead>
+<tbody>
+<tr>
+<td>Memory</td>
+<td>×3</td>
+<td>0 → 0</td>
+<td>3 → 9</td>
+</tr>
+<tr>
+<td>Messaging</td>
+<td>×3</td>
+<td>0 → 0</td>
+<td>3 → 9</td>
+</tr>
+<tr>
+<td>Orchestration</td>
+<td>×2</td>
+<td>0 → 0</td>
+<td>3 → 6</td>
+</tr>
+<tr>
+<td>Visibility</td>
+<td>×2</td>
+<td>1 → 2</td>
+<td>3 → 6</td>
+</tr>
+<tr>
+<td>Control</td>
+<td>×1</td>
+<td>3 → 3</td>
+<td>2 → 2</td>
+</tr>
+<tr>
+<td>Cost &amp; local-first</td>
+<td>×2</td>
+<td>3 → 6</td>
+<td>3 → 6</td>
+</tr>
+<tr>
+<td><strong>Total</strong></td>
+<td></td>
+<td><strong>11</strong></td>
+<td><strong>38</strong></td>
+</tr>
+</tbody>
+</table>
+<p>Flip the weights for a team whose bottleneck is “just run three parallel tasks,” and the session
+manager wins handily — that’s the point. The rubric encodes <em>your</em> priorities, so it gives <em>your</em>
+answer. For a ready-made criteria breakdown across the real tools, see <a href="/blog/claude-code-orchestration-tools-compared/">Claude Code orchestration
+tools, compared</a>.</p>
+<h2 id="three-traps-to-avoid" tabindex="-1">Three traps to avoid <a class="anchor" href="#three-traps-to-avoid" aria-hidden="true">#</a></h2>
+<ul>
+<li><strong>Buying for a workload you don’t have.</strong> A coordinated hive is overkill for two independent tasks;
+a session manager is underpowered for a ten-agent project. Score for <em>your</em> reality.</li>
+<li><strong>Treating “more autonomy” as automatically better.</strong> Delegation is leverage <em>if</em> you trust the
+guardrails. Check how a tool escalates the critical stuff before you hand it the wheel.</li>
+<li><strong>Ignoring lock-in.</strong> Open source and local-first cost nothing to leave. Weight that if you’re
+risk-averse.</li>
+</ul>
+<h2 id="run-the-checklist" tabindex="-1">Run the checklist <a class="anchor" href="#run-the-checklist" aria-hidden="true">#</a></h2>
+<p>Pick your two or three finalists from <a href="/blog/best-claude-code-multi-agent-tools/">the roundup</a>, score
+each on the six criteria with your weights, and trust the total. The exercise is fast and it kills
+analysis paralysis.</p>
+<hr>
+<p>If your scores point at memory + messaging + orchestration, Munder Difflin is built squarely for that
+profile — and it’s free to test the thesis. <a href="/#install">Download Munder Difflin</a>; it’s open source and
+local-first.</p>
+
+
+
+
+
+ <hr />
+ <div class="share">
+ <span class="lbl">Tags</span>
+ <a class="tag" href="/blog/tags/comparisons/">Comparisons</a><a class="tag" href="/blog/tags/multi-agent/">Multi-Agent</a><a class="tag" href="/blog/tags/tools/">Tools</a><a class="tag" href="/blog/tags/getting-started/">Getting Started</a>
+ </div>
+
+ </div>
+
+
+ <aside class="toc-rail" aria-label="Table of contents">
+ <div class="tt">On this page</div>
+ <ol>
+ <li class="lvl-2"><a href="#start-with-the-question-behind-the-question">Start with the question behind the question</a></li><li class="lvl-2"><a href="#the-six-criteria">The six criteria</a></li><li class="lvl-3"><a href="#1-memory">1. Memory</a></li><li class="lvl-3"><a href="#2-messaging">2. Messaging</a></li><li class="lvl-3"><a href="#3-orchestration">3. Orchestration</a></li><li class="lvl-3"><a href="#4-visibility">4. Visibility</a></li><li class="lvl-3"><a href="#5-control">5. Control</a></li><li class="lvl-3"><a href="#6-cost-local-first">6. Cost &amp;amp; local-first</a></li><li class="lvl-2"><a href="#the-scoring-rubric">The scoring rubric</a></li><li class="lvl-2"><a href="#three-traps-to-avoid">Three traps to avoid</a></li><li class="lvl-2"><a href="#run-the-checklist">Run the checklist</a></li>
+ </ol>
+ </aside>
+
+ </div>
+
+ <footer class="post-foot wrap"><div class="prevnext">
+ <a class="pn prev" href="/blog/munder-difflin-faq/"><span class="k">← Older</span><span class="t">Munder Difflin FAQ: Everything People Ask</span></a>
+ <a class="pn next" href="/blog/from-one-terminal-to-a-team/"><span class="k">Newer →</span><span class="t">From One Terminal to a Team: Scaling Your Claude Code Workflow</span></a>
+ </div>
+ <section class="related">
+ <h2>Related in Comparisons</h2>
+ <div class="post-grid">
+ <article class="card">
+ <a class="thumb t-comparisons" href="/blog/best-claude-code-multi-agent-tools/" aria-hidden="true" tabindex="-1">
+ <span>COMPARISONS</span>
+ </a>
+ <div class="body">
+ <div class="meta">
+ <time datetime="2026-06-04">Jun 4, 2026</time>
+ <span class="dot" aria-hidden="true"></span>
+ <span>6 min</span>
+ </div>
+ <h3><a href="/blog/best-claude-code-multi-agent-tools/">The Best Tools to Run Multiple Claude Code Agents (2026)</a></h3>
+ <p class="dek">An honest 2026 roundup of tools to run multiple Claude Code agents — Claude Squad, Conductor, Crystal, vibe-kanban, and Munder Difflin — compared.</p>
+ <div class="foot">
+ <span class="tag kind">Comparisons</span>
+ <a class="more" href="/blog/best-claude-code-multi-agent-tools/" aria-label="Read: The Best Tools to Run Multiple Claude Code Agents (2026)">Read →</a>
+ </div>
+ </div>
+</article>
+<article class="card">
+ <a class="thumb t-comparisons" href="/blog/claude-code-orchestration-tools-compared/" aria-hidden="true" tabindex="-1">
+ <span>COMPARISONS</span>
+ </a>
+ <div class="body">
+ <div class="meta">
+ <time datetime="2026-06-04">Jun 4, 2026</time>
+ <span class="dot" aria-hidden="true"></span>
+ <span>3 min</span>
+ </div>
+ <h3><a href="/blog/claude-code-orchestration-tools-compared/">Claude Code Orchestration Tools, Compared</a></h3>
+ <p class="dek">Claude Code orchestration tools compared on memory, messaging, visibility, control, and local-first — across Claude Squad, Conductor, Crystal, and more.</p>
+ <div class="foot">
+ <span class="tag kind">Comparisons</span>
+ <a class="more" href="/blog/claude-code-orchestration-tools-compared/" aria-label="Read: Claude Code Orchestration Tools, Compared">Read →</a>
+ </div>
+ </div>
+</article>
+<article class="card">
+ <a class="thumb t-comparisons" href="/blog/claude-squad-vs-munder-difflin/" aria-hidden="true" tabindex="-1">
+ <span>COMPARISONS</span>
+ </a>
+ <div class="body">
+ <div class="meta">
+ <time datetime="2026-06-04">Jun 4, 2026</time>
+ <span class="dot" aria-hidden="true"></span>
+ <span>3 min</span>
+ </div>
+ <h3><a href="/blog/claude-squad-vs-munder-difflin/">Claude Squad vs Munder Difflin: Which Should You Use?</a></h3>
+ <p class="dek">Claude Squad vs Munder Difflin: a lean terminal session manager against a memory-backed, orchestrated, visual hive. Feature table and an honest verdict.</p>
+ <div class="foot">
+ <span class="tag kind">Comparisons</span>
+ <a class="more" href="/blog/claude-squad-vs-munder-difflin/" aria-label="Read: Claude Squad vs Munder Difflin: Which Should You Use?">Read →</a>
+ </div>
+ </div>
+</article>
+
+ </div>
+ </section>
+
+ </footer>
+</article>
+
+</main>
+<footer>
+ <div class="wrap">
+ <div class="foot-top">
+ <a class="foot-brand brand" href="/blog/">
+ <span class="brand-mark">MD</span>
+ <span class="brand-word">MUNDER DIFFLIN<span class="sep">/</span><span class="blog">BLOG</span></span>
+ </a>
+ <div class="foot-links">
+ <a href="/blog/">Latest</a>
+ <a href="/blog/topics/">Topics</a>
+ <a href="/blog/about/">About</a>
+ <a href="https://munderdiffl.in/blog/feed.xml">RSS</a>
+ <a href="https://github.com/chaitanyagiri/munder-difflin">GitHub</a>
+ <a href="https://munderdiffl.in">munderdiffl.in ↗</a>
+ </div>
+ </div>
+ <div class="foot-meta">
+ © 2026 Munder Difflin · Local-first · MIT-licensed ·
+ Built on <a href="https://munderdiffl.in">Electron, React, Pixi.js, xterm.js &amp; node-pty</a>.
+ Run an office of agents while you sleep.
+ </div>
+ </div>
+</footer>
+
+<script>
+ // sticky-nav border on scroll
+ (function () {
+ var nav = document.getElementById('nav');
+ if (!nav) return;
+ var onScroll = function () { nav.classList.toggle('scrolled', window.scrollY > 8); };
+ onScroll(); window.addEventListener('scroll', onScroll, { passive: true });
+ })();
+</script>
+
+</body>
+</html>
diff --git a/docs/blog/how-to-run-multiple-claude-code-agents/index.html b/docs/blog/how-to-run-multiple-claude-code-agents/index.html
index 8f99e901..f99ed7f7 100644
--- a/docs/blog/how-to-run-multiple-claude-code-agents/index.html
+++ b/docs/blog/how-to-run-multiple-claude-code-agents/index.html
@@ -208,9 +208,70 @@ free and open source.</p>
</div>
<footer class="post-foot wrap"><div class="prevnext">
- <a class="pn prev" href="/blog/give-claude-code-long-term-memory/"><span class="k">← Older</span><span class="t">How to Give Claude Code Long-Term Memory</span></a>
- <span></span>
+ <a class="pn prev" href="/blog/atomic-file-mailboxes-for-agents/"><span class="k">← Older</span><span class="t">Atomic File Mailboxes: How Agents Message Each Other</span></a>
+ <a class="pn next" href="/blog/why-we-built-munder-difflin/"><span class="k">Newer →</span><span class="t">Why We Built Munder Difflin</span></a>
</div>
+ <section class="related">
+ <h2>Related in Guides</h2>
+ <div class="post-grid">
+ <article class="card">
+ <a class="thumb t-guides" href="/blog/claude-code-automation-while-you-sleep/" aria-hidden="true" tabindex="-1">
+ <span>GUIDES</span>
+ </a>
+ <div class="body">
+ <div class="meta">
+ <time datetime="2026-06-04">Jun 4, 2026</time>
+ <span class="dot" aria-hidden="true"></span>
+ <span>5 min</span>
+ </div>
+ <h3><a href="/blog/claude-code-automation-while-you-sleep/">Claude Code Automation: Let Agents Build While You Sleep</a></h3>
+ <p class="dek">Claude Code automation that runs overnight: an autonomous Stop-hook loop, safe permission bypass, and guardrails so you wake up to progress, not chaos.</p>
+ <div class="foot">
+ <span class="tag kind">Guides</span>
+ <a class="more" href="/blog/claude-code-automation-while-you-sleep/" aria-label="Read: Claude Code Automation: Let Agents Build While You Sleep">Read →</a>
+ </div>
+ </div>
+</article>
+<article class="card">
+ <a class="thumb t-guides" href="/blog/mcp-and-skills-in-a-hive/" aria-hidden="true" tabindex="-1">
+ <span>GUIDES</span>
+ </a>
+ <div class="body">
+ <div class="meta">
+ <time datetime="2026-06-03">Jun 3, 2026</time>
+ <span class="dot" aria-hidden="true"></span>
+ <span>6 min</span>
+ </div>
+ <h3><a href="/blog/mcp-and-skills-in-a-hive/">Bringing Your MCP Servers and Skills Into a Hive of Agents</a></h3>
+ <p class="dek">How agents in a hive inherit your existing Claude Code MCP servers, skills, and tools — and how to scope which agent gets which capability.</p>
+ <div class="foot">
+ <span class="tag kind">Guides</span>
+ <a class="more" href="/blog/mcp-and-skills-in-a-hive/" aria-label="Read: Bringing Your MCP Servers and Skills Into a Hive of Agents">Read →</a>
+ </div>
+ </div>
+</article>
+<article class="card">
+ <a class="thumb t-guides" href="/blog/manage-multiple-claude-code-sessions/" aria-hidden="true" tabindex="-1">
+ <span>GUIDES</span>
+ </a>
+ <div class="body">
+ <div class="meta">
+ <time datetime="2026-05-25">May 25, 2026</time>
+ <span class="dot" aria-hidden="true"></span>
+ <span>4 min</span>
+ </div>
+ <h3><a href="/blog/manage-multiple-claude-code-sessions/">How to Manage Multiple Claude Code Sessions Like a Pro</a></h3>
+ <p class="dek">Tactics to manage multiple Claude Code sessions without losing track: naming, roles, context isolation, and when a harness beats juggling terminal tabs.</p>
+ <div class="foot">
+ <span class="tag kind">Guides</span>
+ <a class="more" href="/blog/manage-multiple-claude-code-sessions/" aria-label="Read: How to Manage Multiple Claude Code Sessions Like a Pro">Read →</a>
+ </div>
+ </div>
+</article>
+
+ </div>
+ </section>
+
</footer>
</article>
diff --git a/docs/blog/index.html b/docs/blog/index.html
index 79797420..74b2aa0b 100644
--- a/docs/blog/index.html
+++ b/docs/blog/index.html
@@ -85,19 +85,431 @@
building a self-coordinating hive of agents with a GOD orchestrator you talk to.</p>
<div class="filters" role="navigation" aria-label="Topics">
- <a class="chip" aria-current="page">All<span class="ct">3</span></a>
+ <a class="chip" aria-current="page">All<span class="ct">33</span></a>
- <a class="chip" href="/blog/topics/concepts/">concepts<span class="ct">1</span></a>
+ <a class="chip" href="/blog/topics/comparisons/">comparisons<span class="ct">8</span></a>
- <a class="chip" href="/blog/topics/memory/">memory<span class="ct">1</span></a>
+ <a class="chip" href="/blog/topics/guides/">guides<span class="ct">6</span></a>
- <a class="chip" href="/blog/topics/guides/">guides<span class="ct">1</span></a>
+ <a class="chip" href="/blog/topics/internals/">internals<span class="ct">5</span></a>
+
+ <a class="chip" href="/blog/topics/concepts/">concepts<span class="ct">4</span></a>
+
+ <a class="chip" href="/blog/topics/orchestration/">orchestration<span class="ct">4</span></a>
+
+ <a class="chip" href="/blog/topics/use-cases/">use-cases<span class="ct">3</span></a>
+
+ <a class="chip" href="/blog/topics/memory/">memory<span class="ct">2</span></a>
+
+ <a class="chip" href="/blog/topics/story/">story<span class="ct">1</span></a>
</div>
</header>
<div class="wrap featured"><article class="card">
+ <a class="thumb t-comparisons" href="/blog/best-claude-code-multi-agent-tools/" aria-hidden="true" tabindex="-1">
+ <span>COMPARISONS</span>
+ </a>
+ <div class="body">
+ <div class="meta">
+ <time datetime="2026-06-04">Jun 4, 2026</time>
+ <span class="dot" aria-hidden="true"></span>
+ <span>6 min</span>
+ </div>
+ <h3><a href="/blog/best-claude-code-multi-agent-tools/">The Best Tools to Run Multiple Claude Code Agents (2026)</a></h3>
+ <p class="dek">An honest 2026 roundup of tools to run multiple Claude Code agents — Claude Squad, Conductor, Crystal, vibe-kanban, and Munder Difflin — compared.</p>
+ <div class="foot">
+ <span class="tag kind">Comparisons</span>
+ <a class="more" href="/blog/best-claude-code-multi-agent-tools/" aria-label="Read: The Best Tools to Run Multiple Claude Code Agents (2026)">Read →</a>
+ </div>
+ </div>
+</article>
+
+</div>
+
+
+<section class="wrap">
+ <div class="post-grid">
+ <article class="card">
+ <a class="thumb t-guides" href="/blog/claude-code-automation-while-you-sleep/" aria-hidden="true" tabindex="-1">
+ <span>GUIDES</span>
+ </a>
+ <div class="body">
+ <div class="meta">
+ <time datetime="2026-06-04">Jun 4, 2026</time>
+ <span class="dot" aria-hidden="true"></span>
+ <span>5 min</span>
+ </div>
+ <h3><a href="/blog/claude-code-automation-while-you-sleep/">Claude Code Automation: Let Agents Build While You Sleep</a></h3>
+ <p class="dek">Claude Code automation that runs overnight: an autonomous Stop-hook loop, safe permission bypass, and guardrails so you wake up to progress, not chaos.</p>
+ <div class="foot">
+ <span class="tag kind">Guides</span>
+ <a class="more" href="/blog/claude-code-automation-while-you-sleep/" aria-label="Read: Claude Code Automation: Let Agents Build While You Sleep">Read →</a>
+ </div>
+ </div>
+</article>
+<article class="card">
+ <a class="thumb t-orchestration" href="/blog/claude-code-git-worktrees-vs-hive/" aria-hidden="true" tabindex="-1">
+ <span>ORCHESTRATION</span>
+ </a>
+ <div class="body">
+ <div class="meta">
+ <time datetime="2026-06-04">Jun 4, 2026</time>
+ <span class="dot" aria-hidden="true"></span>
+ <span>5 min</span>
+ </div>
+ <h3><a href="/blog/claude-code-git-worktrees-vs-hive/">Git Worktrees vs a Hive: Two Ways to Parallelize Claude Code</a></h3>
+ <p class="dek">Claude Code git worktrees vs a hive: when isolated worktrees suffice for parallel agents, and when you need memory, messaging, and an orchestrator on top.</p>
+ <div class="foot">
+ <span class="tag kind">Orchestration</span>
+ <a class="more" href="/blog/claude-code-git-worktrees-vs-hive/" aria-label="Read: Git Worktrees vs a Hive: Two Ways to Parallelize Claude Code">Read →</a>
+ </div>
+ </div>
+</article>
+<article class="card">
+ <a class="thumb t-comparisons" href="/blog/claude-code-orchestration-tools-compared/" aria-hidden="true" tabindex="-1">
+ <span>COMPARISONS</span>
+ </a>
+ <div class="body">
+ <div class="meta">
+ <time datetime="2026-06-04">Jun 4, 2026</time>
+ <span class="dot" aria-hidden="true"></span>
+ <span>3 min</span>
+ </div>
+ <h3><a href="/blog/claude-code-orchestration-tools-compared/">Claude Code Orchestration Tools, Compared</a></h3>
+ <p class="dek">Claude Code orchestration tools compared on memory, messaging, visibility, control, and local-first — across Claude Squad, Conductor, Crystal, and more.</p>
+ <div class="foot">
+ <span class="tag kind">Comparisons</span>
+ <a class="more" href="/blog/claude-code-orchestration-tools-compared/" aria-label="Read: Claude Code Orchestration Tools, Compared">Read →</a>
+ </div>
+ </div>
+</article>
+<article class="card">
+ <a class="thumb t-comparisons" href="/blog/claude-squad-vs-munder-difflin/" aria-hidden="true" tabindex="-1">
+ <span>COMPARISONS</span>
+ </a>
+ <div class="body">
+ <div class="meta">
+ <time datetime="2026-06-04">Jun 4, 2026</time>
+ <span class="dot" aria-hidden="true"></span>
+ <span>3 min</span>
+ </div>
+ <h3><a href="/blog/claude-squad-vs-munder-difflin/">Claude Squad vs Munder Difflin: Which Should You Use?</a></h3>
+ <p class="dek">Claude Squad vs Munder Difflin: a lean terminal session manager against a memory-backed, orchestrated, visual hive. Feature table and an honest verdict.</p>
+ <div class="foot">
+ <span class="tag kind">Comparisons</span>
+ <a class="more" href="/blog/claude-squad-vs-munder-difflin/" aria-label="Read: Claude Squad vs Munder Difflin: Which Should You Use?">Read →</a>
+ </div>
+ </div>
+</article>
+<article class="card">
+ <a class="thumb t-internals" href="/blog/building-a-terminal-ui-xterm-node-pty/" aria-hidden="true" tabindex="-1">
+ <span>INTERNALS</span>
+ </a>
+ <div class="body">
+ <div class="meta">
+ <time datetime="2026-06-03">Jun 3, 2026</time>
+ <span class="dot" aria-hidden="true"></span>
+ <span>8 min</span>
+ </div>
+ <h3><a href="/blog/building-a-terminal-ui-xterm-node-pty/">Building a Terminal UI with xterm.js and node-pty</a></h3>
+ <p class="dek">Wire xterm.js to a node-pty backend: stream output, write keystrokes back, handle resize, and keep many live terminals fast with a terminal pool.</p>
+ <div class="foot">
+ <span class="tag kind">Internals</span>
+ <a class="more" href="/blog/building-a-terminal-ui-xterm-node-pty/" aria-label="Read: Building a Terminal UI with xterm.js and node-pty">Read →</a>
+ </div>
+ </div>
+</article>
+<article class="card">
+ <a class="thumb t-internals" href="/blog/claude-code-hooks-explained/" aria-hidden="true" tabindex="-1">
+ <span>INTERNALS</span>
+ </a>
+ <div class="body">
+ <div class="meta">
+ <time datetime="2026-06-03">Jun 3, 2026</time>
+ <span class="dot" aria-hidden="true"></span>
+ <span>6 min</span>
+ </div>
+ <h3><a href="/blog/claude-code-hooks-explained/">Claude Code Hooks, Explained (PreToolUse, PostToolUse, Stop)</a></h3>
+ <p class="dek">A practical tour of Claude Code hooks — the PreToolUse, PostToolUse, and Stop lifecycle — and how a Unix-socket hook shim drives a live office floor.</p>
+ <div class="foot">
+ <span class="tag kind">Internals</span>
+ <a class="more" href="/blog/claude-code-hooks-explained/" aria-label="Read: Claude Code Hooks, Explained (PreToolUse, PostToolUse, Stop)">Read →</a>
+ </div>
+ </div>
+</article>
+<article class="card">
+ <a class="thumb t-comparisons" href="/blog/claude-squad-alternative/" aria-hidden="true" tabindex="-1">
+ <span>COMPARISONS</span>
+ </a>
+ <div class="body">
+ <div class="meta">
+ <time datetime="2026-06-03">Jun 3, 2026</time>
+ <span class="dot" aria-hidden="true"></span>
+ <span>3 min</span>
+ </div>
+ <h3><a href="/blog/claude-squad-alternative/">Looking for a Claude Squad Alternative?</a></h3>
+ <p class="dek">What Claude Squad does well, where it stops, and why a memory-backed, orchestrated hive may be the Claude Squad alternative you&#39;re after.</p>
+ <div class="foot">
+ <span class="tag kind">Comparisons</span>
+ <a class="more" href="/blog/claude-squad-alternative/" aria-label="Read: Looking for a Claude Squad Alternative?">Read →</a>
+ </div>
+ </div>
+</article>
+<article class="card">
+ <a class="thumb t-comparisons" href="/blog/conductor-claude-code-alternative/" aria-hidden="true" tabindex="-1">
+ <span>COMPARISONS</span>
+ </a>
+ <div class="body">
+ <div class="meta">
+ <time datetime="2026-06-03">Jun 3, 2026</time>
+ <span class="dot" aria-hidden="true"></span>
+ <span>3 min</span>
+ </div>
+ <h3><a href="/blog/conductor-claude-code-alternative/">A Conductor Alternative for Orchestrating Claude Code</a></h3>
+ <p class="dek">Conductor is a polished macOS app for parallel Claude Code worktrees. When to pick a cross-platform, orchestrated hive as your Conductor alternative.</p>
+ <div class="foot">
+ <span class="tag kind">Comparisons</span>
+ <a class="more" href="/blog/conductor-claude-code-alternative/" aria-label="Read: A Conductor Alternative for Orchestrating Claude Code">Read →</a>
+ </div>
+ </div>
+</article>
+<article class="card">
+ <a class="thumb t-comparisons" href="/blog/crystal-claude-code-alternative/" aria-hidden="true" tabindex="-1">
+ <span>COMPARISONS</span>
+ </a>
+ <div class="body">
+ <div class="meta">
+ <time datetime="2026-06-03">Jun 3, 2026</time>
+ <span class="dot" aria-hidden="true"></span>
+ <span>3 min</span>
+ </div>
+ <h3><a href="/blog/crystal-claude-code-alternative/">A Crystal Alternative: Multi-Agent Claude Code with Memory</a></h3>
+ <p class="dek">Crystal runs parallel Claude Code worktrees well. Where a memory-backed, orchestrated hive changes the workflow — and when to stick with Crystal.</p>
+ <div class="foot">
+ <span class="tag kind">Comparisons</span>
+ <a class="more" href="/blog/crystal-claude-code-alternative/" aria-label="Read: A Crystal Alternative: Multi-Agent Claude Code with Memory">Read →</a>
+ </div>
+ </div>
+</article>
+<article class="card">
+ <a class="thumb t-guides" href="/blog/mcp-and-skills-in-a-hive/" aria-hidden="true" tabindex="-1">
+ <span>GUIDES</span>
+ </a>
+ <div class="body">
+ <div class="meta">
+ <time datetime="2026-06-03">Jun 3, 2026</time>
+ <span class="dot" aria-hidden="true"></span>
+ <span>6 min</span>
+ </div>
+ <h3><a href="/blog/mcp-and-skills-in-a-hive/">Bringing Your MCP Servers and Skills Into a Hive of Agents</a></h3>
+ <p class="dek">How agents in a hive inherit your existing Claude Code MCP servers, skills, and tools — and how to scope which agent gets which capability.</p>
+ <div class="foot">
+ <span class="tag kind">Guides</span>
+ <a class="more" href="/blog/mcp-and-skills-in-a-hive/" aria-label="Read: Bringing Your MCP Servers and Skills Into a Hive of Agents">Read →</a>
+ </div>
+ </div>
+</article>
+<article class="card">
+ <a class="thumb t-internals" href="/blog/node-pty-electron-real-terminals/" aria-hidden="true" tabindex="-1">
+ <span>INTERNALS</span>
+ </a>
+ <div class="body">
+ <div class="meta">
+ <time datetime="2026-06-03">Jun 3, 2026</time>
+ <span class="dot" aria-hidden="true"></span>
+ <span>7 min</span>
+ </div>
+ <h3><a href="/blog/node-pty-electron-real-terminals/">Real Terminals in Electron with node-pty</a></h3>
+ <p class="dek">How to run byte-for-byte authentic shells inside Electron with node-pty: the native-rebuild gotcha, the macOS PATH trap, and streaming PTY output over IPC.</p>
+ <div class="foot">
+ <span class="tag kind">Internals</span>
+ <a class="more" href="/blog/node-pty-electron-real-terminals/" aria-label="Read: Real Terminals in Electron with node-pty">Read →</a>
+ </div>
+ </div>
+</article>
+<article class="card">
+ <a class="thumb t-comparisons" href="/blog/vibe-kanban-alternative/" aria-hidden="true" tabindex="-1">
+ <span>COMPARISONS</span>
+ </a>
+ <div class="body">
+ <div class="meta">
+ <time datetime="2026-06-03">Jun 3, 2026</time>
+ <span class="dot" aria-hidden="true"></span>
+ <span>3 min</span>
+ </div>
+ <h3><a href="/blog/vibe-kanban-alternative/">A vibe-kanban Alternative for Coordinating AI Agents</a></h3>
+ <p class="dek">vibe-kanban gives you a board to assign tasks to coding agents. When a self-routing hive is the better vibe-kanban alternative — and when a board wins.</p>
+ <div class="foot">
+ <span class="tag kind">Comparisons</span>
+ <a class="more" href="/blog/vibe-kanban-alternative/" aria-label="Read: A vibe-kanban Alternative for Coordinating AI Agents">Read →</a>
+ </div>
+ </div>
+</article>
+<article class="card">
+ <a class="thumb t-concepts" href="/blog/ai-agent-glossary/" aria-hidden="true" tabindex="-1">
+ <span>CONCEPTS</span>
+ </a>
+ <div class="body">
+ <div class="meta">
+ <time datetime="2026-06-02">Jun 2, 2026</time>
+ <span class="dot" aria-hidden="true"></span>
+ <span>3 min</span>
+ </div>
+ <h3><a href="/blog/ai-agent-glossary/">The AI Coding Agent Glossary: Harness, Orchestrator, Hive, Subagent</a></h3>
+ <p class="dek">Plain-English definitions of the AI coding agent terms everyone trips over — harness, orchestrator, hive, subagent, agent memory — each in one line.</p>
+ <div class="foot">
+ <span class="tag kind">Concepts</span>
+ <a class="more" href="/blog/ai-agent-glossary/" aria-label="Read: The AI Coding Agent Glossary: Harness, Orchestrator, Hive, Subagent">Read →</a>
+ </div>
+ </div>
+</article>
+<article class="card">
+ <a class="thumb t-use-cases" href="/blog/from-one-terminal-to-a-team/" aria-hidden="true" tabindex="-1">
+ <span>USE CASES</span>
+ </a>
+ <div class="body">
+ <div class="meta">
+ <time datetime="2026-06-02">Jun 2, 2026</time>
+ <span class="dot" aria-hidden="true"></span>
+ <span>3 min</span>
+ </div>
+ <h3><a href="/blog/from-one-terminal-to-a-team/">From One Terminal to a Team: Scaling Your Claude Code Workflow</a></h3>
+ <p class="dek">The workflow shift from a single Claude Code session to a coordinated team of agents — what changes, where it breaks, and the concrete before-and-after.</p>
+ <div class="foot">
+ <span class="tag kind">Use Cases</span>
+ <a class="more" href="/blog/from-one-terminal-to-a-team/" aria-label="Read: From One Terminal to a Team: Scaling Your Claude Code Workflow">Read →</a>
+ </div>
+ </div>
+</article>
+<article class="card">
+ <a class="thumb t-comparisons" href="/blog/how-to-choose-a-multi-agent-tool/" aria-hidden="true" tabindex="-1">
+ <span>COMPARISONS</span>
+ </a>
+ <div class="body">
+ <div class="meta">
+ <time datetime="2026-06-02">Jun 2, 2026</time>
+ <span class="dot" aria-hidden="true"></span>
+ <span>3 min</span>
+ </div>
+ <h3><a href="/blog/how-to-choose-a-multi-agent-tool/">How to Choose a Multi-Agent Coding Tool: A Buyer&#39;s Checklist</a></h3>
+ <p class="dek">A decision framework for choosing a multi-agent coding tool — memory, control, visibility, cost, local-first — with a simple scoring rubric you can run.</p>
+ <div class="foot">
+ <span class="tag kind">Comparisons</span>
+ <a class="more" href="/blog/how-to-choose-a-multi-agent-tool/" aria-label="Read: How to Choose a Multi-Agent Coding Tool: A Buyer&#39;s Checklist">Read →</a>
+ </div>
+ </div>
+</article>
+<article class="card">
+ <a class="thumb t-concepts" href="/blog/munder-difflin-faq/" aria-hidden="true" tabindex="-1">
+ <span>CONCEPTS</span>
+ </a>
+ <div class="body">
+ <div class="meta">
+ <time datetime="2026-06-02">Jun 2, 2026</time>
+ <span class="dot" aria-hidden="true"></span>
+ <span>1 min</span>
+ </div>
+ <h3><a href="/blog/munder-difflin-faq/">Munder Difflin FAQ: Everything People Ask</a></h3>
+ <p class="dek">Answers to the top Munder Difflin questions — what it is, is it free, does it run locally, which platforms, and how it differs from many terminals.</p>
+ <div class="foot">
+ <span class="tag kind">Concepts</span>
+ <a class="more" href="/blog/munder-difflin-faq/" aria-label="Read: Munder Difflin FAQ: Everything People Ask">Read →</a>
+ </div>
+ </div>
+</article>
+<article class="card">
+ <a class="thumb t-use-cases" href="/blog/run-an-office-of-ai-agents/" aria-hidden="true" tabindex="-1">
+ <span>USE CASES</span>
+ </a>
+ <div class="body">
+ <div class="meta">
+ <time datetime="2026-06-02">Jun 2, 2026</time>
+ <span class="dot" aria-hidden="true"></span>
+ <span>3 min</span>
+ </div>
+ <h3><a href="/blog/run-an-office-of-ai-agents/">Run an Office of AI Agents While You Sleep</a></h3>
+ <p class="dek">What it takes to run a self-coordinating office of AI coding agents that keeps shipping after you log off — and the guardrails that keep it sane.</p>
+ <div class="foot">
+ <span class="tag kind">Use Cases</span>
+ <a class="more" href="/blog/run-an-office-of-ai-agents/" aria-label="Read: Run an Office of AI Agents While You Sleep">Read →</a>
+ </div>
+ </div>
+</article>
+<article class="card">
+ <a class="thumb t-internals" href="/blog/single-committer-git-pattern/" aria-hidden="true" tabindex="-1">
+ <span>INTERNALS</span>
+ </a>
+ <div class="body">
+ <div class="meta">
+ <time datetime="2026-06-02">Jun 2, 2026</time>
+ <span class="dot" aria-hidden="true"></span>
+ <span>5 min</span>
+ </div>
+ <h3><a href="/blog/single-committer-git-pattern/">The Single-Committer Pattern: Multi-Agent Git Without Corruption</a></h3>
+ <p class="dek">Parallel agents corrupt a repo with index.lock races. The single-committer pattern — agents write, one process commits — fixes concurrent git writes.</p>
+ <div class="foot">
+ <span class="tag kind">Internals</span>
+ <a class="more" href="/blog/single-committer-git-pattern/" aria-label="Read: The Single-Committer Pattern: Multi-Agent Git Without Corruption">Read →</a>
+ </div>
+ </div>
+</article>
+<article class="card">
+ <a class="thumb t-concepts" href="/blog/what-are-claude-code-agents/" aria-hidden="true" tabindex="-1">
+ <span>CONCEPTS</span>
+ </a>
+ <div class="body">
+ <div class="meta">
+ <time datetime="2026-06-02">Jun 2, 2026</time>
+ <span class="dot" aria-hidden="true"></span>
+ <span>3 min</span>
+ </div>
+ <h3><a href="/blog/what-are-claude-code-agents/">What Are Claude Code Agents? And How to Use Many at Once</a></h3>
+ <p class="dek">Claude Code agents explained in plain English — what an agent actually is, how subagents differ, and the leap from one agent to a coordinated team.</p>
+ <div class="foot">
+ <span class="tag kind">Concepts</span>
+ <a class="more" href="/blog/what-are-claude-code-agents/" aria-label="Read: What Are Claude Code Agents? And How to Use Many at Once">Read →</a>
+ </div>
+ </div>
+</article>
+<article class="card">
+ <a class="thumb t-use-cases" href="/blog/why-local-first-matters-for-ai-agents/" aria-hidden="true" tabindex="-1">
+ <span>USE CASES</span>
+ </a>
+ <div class="body">
+ <div class="meta">
+ <time datetime="2026-06-02">Jun 2, 2026</time>
+ <span class="dot" aria-hidden="true"></span>
+ <span>3 min</span>
+ </div>
+ <h3><a href="/blog/why-local-first-matters-for-ai-agents/">Why Local-First Matters for Your AI Agents</a></h3>
+ <p class="dek">The control, privacy, and cost case for keeping your AI agents and their memory on your own machine — and what cloud orchestration quietly costs.</p>
+ <div class="foot">
+ <span class="tag kind">Use Cases</span>
+ <a class="more" href="/blog/why-local-first-matters-for-ai-agents/" aria-label="Read: Why Local-First Matters for Your AI Agents">Read →</a>
+ </div>
+ </div>
+</article>
+<article class="card">
+ <a class="thumb t-story" href="/blog/why-we-built-munder-difflin/" aria-hidden="true" tabindex="-1">
+ <span>STORY</span>
+ </a>
+ <div class="body">
+ <div class="meta">
+ <time datetime="2026-06-02">Jun 2, 2026</time>
+ <span class="dot" aria-hidden="true"></span>
+ <span>3 min</span>
+ </div>
+ <h3><a href="/blog/why-we-built-munder-difflin/">Why We Built Munder Difflin</a></h3>
+ <p class="dek">The origin story of Munder Difflin — how the pain of juggling Claude Code terminals led to a coordinated, memory-backed hive of agents you can watch.</p>
+ <div class="foot">
+ <span class="tag kind">Story</span>
+ <a class="more" href="/blog/why-we-built-munder-difflin/" aria-label="Read: Why We Built Munder Difflin">Read →</a>
+ </div>
+ </div>
+</article>
+<article class="card">
<a class="thumb t-guides" href="/blog/how-to-run-multiple-claude-code-agents/" aria-hidden="true" tabindex="-1">
<span>GUIDES</span>
</a>
@@ -115,13 +527,79 @@
</div>
</div>
</article>
-
-</div>
-
-
-<section class="wrap">
- <div class="post-grid">
- <article class="card">
+<article class="card">
+ <a class="thumb t-internals" href="/blog/atomic-file-mailboxes-for-agents/" aria-hidden="true" tabindex="-1">
+ <span>INTERNALS</span>
+ </a>
+ <div class="body">
+ <div class="meta">
+ <time datetime="2026-05-31">May 31, 2026</time>
+ <span class="dot" aria-hidden="true"></span>
+ <span>5 min</span>
+ </div>
+ <h3><a href="/blog/atomic-file-mailboxes-for-agents/">Atomic File Mailboxes: How Agents Message Each Other</a></h3>
+ <p class="dek">Can Claude Code agents talk to each other? Yes — the outbox-router-inbox design that lets agents message safely using plain files and atomic renames.</p>
+ <div class="foot">
+ <span class="tag kind">Internals</span>
+ <a class="more" href="/blog/atomic-file-mailboxes-for-agents/" aria-label="Read: Atomic File Mailboxes: How Agents Message Each Other">Read →</a>
+ </div>
+ </div>
+</article>
+<article class="card">
+ <a class="thumb t-orchestration" href="/blog/how-the-god-orchestrator-works/" aria-hidden="true" tabindex="-1">
+ <span>ORCHESTRATION</span>
+ </a>
+ <div class="body">
+ <div class="meta">
+ <time datetime="2026-05-30">May 30, 2026</time>
+ <span class="dot" aria-hidden="true"></span>
+ <span>6 min</span>
+ </div>
+ <h3><a href="/blog/how-the-god-orchestrator-works/">Inside the GOD Orchestrator: Routing, Adjudication, Escalation</a></h3>
+ <p class="dek">A deep dive into the Claude Code orchestrator: how a GOD agent reads requests, routes work, adjudicates routine traffic, and escalates the critical few.</p>
+ <div class="foot">
+ <span class="tag kind">Orchestration</span>
+ <a class="more" href="/blog/how-the-god-orchestrator-works/" aria-label="Read: Inside the GOD Orchestrator: Routing, Adjudication, Escalation">Read →</a>
+ </div>
+ </div>
+</article>
+<article class="card">
+ <a class="thumb t-orchestration" href="/blog/coordinating-ai-coding-agents/" aria-hidden="true" tabindex="-1">
+ <span>ORCHESTRATION</span>
+ </a>
+ <div class="body">
+ <div class="meta">
+ <time datetime="2026-05-29">May 29, 2026</time>
+ <span class="dot" aria-hidden="true"></span>
+ <span>5 min</span>
+ </div>
+ <h3><a href="/blog/coordinating-ai-coding-agents/">The Best Way to Coordinate AI Coding Agents</a></h3>
+ <p class="dek">The best way to coordinate AI coding agents: single-writer files, a message router, a one-scribe plan, and an orchestrator — cooperate, not clobber.</p>
+ <div class="foot">
+ <span class="tag kind">Orchestration</span>
+ <a class="more" href="/blog/coordinating-ai-coding-agents/" aria-label="Read: The Best Way to Coordinate AI Coding Agents">Read →</a>
+ </div>
+ </div>
+</article>
+<article class="card">
+ <a class="thumb t-orchestration" href="/blog/claude-code-orchestration-guide/" aria-hidden="true" tabindex="-1">
+ <span>ORCHESTRATION</span>
+ </a>
+ <div class="body">
+ <div class="meta">
+ <time datetime="2026-05-28">May 28, 2026</time>
+ <span class="dot" aria-hidden="true"></span>
+ <span>5 min</span>
+ </div>
+ <h3><a href="/blog/claude-code-orchestration-guide/">Orchestrating Claude Code Agents: A Practical Guide</a></h3>
+ <p class="dek">How to orchestrate Claude Code agents in practice: what orchestration means, how a GOD orchestrator routes and escalates work, and how to wire it up.</p>
+ <div class="foot">
+ <span class="tag kind">Orchestration</span>
+ <a class="more" href="/blog/claude-code-orchestration-guide/" aria-label="Read: Orchestrating Claude Code Agents: A Practical Guide">Read →</a>
+ </div>
+ </div>
+</article>
+<article class="card">
<a class="thumb t-memory" href="/blog/give-claude-code-long-term-memory/" aria-hidden="true" tabindex="-1">
<span>MEMORY</span>
</a>
@@ -139,6 +617,78 @@
</div>
</div>
</article>
+<article class="card">
+ <a class="thumb t-memory" href="/blog/semantic-memory-for-ai-agents/" aria-hidden="true" tabindex="-1">
+ <span>MEMORY</span>
+ </a>
+ <div class="body">
+ <div class="meta">
+ <time datetime="2026-05-26">May 26, 2026</time>
+ <span class="dot" aria-hidden="true"></span>
+ <span>6 min</span>
+ </div>
+ <h3><a href="/blog/semantic-memory-for-ai-agents/">Semantic Memory for AI Agents: Recall in Milliseconds</a></h3>
+ <p class="dek">What semantic memory for AI agents is, why a markdown-first store beats a heavy DB, and how a shared palace lets a hive recall a note by meaning, fast.</p>
+ <div class="foot">
+ <span class="tag kind">Memory</span>
+ <a class="more" href="/blog/semantic-memory-for-ai-agents/" aria-label="Read: Semantic Memory for AI Agents: Recall in Milliseconds">Read →</a>
+ </div>
+ </div>
+</article>
+<article class="card">
+ <a class="thumb t-guides" href="/blog/manage-multiple-claude-code-sessions/" aria-hidden="true" tabindex="-1">
+ <span>GUIDES</span>
+ </a>
+ <div class="body">
+ <div class="meta">
+ <time datetime="2026-05-25">May 25, 2026</time>
+ <span class="dot" aria-hidden="true"></span>
+ <span>4 min</span>
+ </div>
+ <h3><a href="/blog/manage-multiple-claude-code-sessions/">How to Manage Multiple Claude Code Sessions Like a Pro</a></h3>
+ <p class="dek">Tactics to manage multiple Claude Code sessions without losing track: naming, roles, context isolation, and when a harness beats juggling terminal tabs.</p>
+ <div class="foot">
+ <span class="tag kind">Guides</span>
+ <a class="more" href="/blog/manage-multiple-claude-code-sessions/" aria-label="Read: How to Manage Multiple Claude Code Sessions Like a Pro">Read →</a>
+ </div>
+ </div>
+</article>
+<article class="card">
+ <a class="thumb t-guides" href="/blog/claude-code-multi-agent-setup-tutorial/" aria-hidden="true" tabindex="-1">
+ <span>GUIDES</span>
+ </a>
+ <div class="body">
+ <div class="meta">
+ <time datetime="2026-05-24">May 24, 2026</time>
+ <span class="dot" aria-hidden="true"></span>
+ <span>5 min</span>
+ </div>
+ <h3><a href="/blog/claude-code-multi-agent-setup-tutorial/">Set Up a Claude Code Multi-Agent Workflow in 10 Minutes</a></h3>
+ <p class="dek">A from-zero Claude Code multi-agent setup: install Munder Difflin, onboard, spawn a few agents, and watch the GOD orchestrator route your first task.</p>
+ <div class="foot">
+ <span class="tag kind">Guides</span>
+ <a class="more" href="/blog/claude-code-multi-agent-setup-tutorial/" aria-label="Read: Set Up a Claude Code Multi-Agent Workflow in 10 Minutes">Read →</a>
+ </div>
+ </div>
+</article>
+<article class="card">
+ <a class="thumb t-guides" href="/blog/claude-code-subagents-vs-multi-agent-harness/" aria-hidden="true" tabindex="-1">
+ <span>GUIDES</span>
+ </a>
+ <div class="body">
+ <div class="meta">
+ <time datetime="2026-05-23">May 23, 2026</time>
+ <span class="dot" aria-hidden="true"></span>
+ <span>5 min</span>
+ </div>
+ <h3><a href="/blog/claude-code-subagents-vs-multi-agent-harness/">Claude Code Subagents vs a Multi-Agent Harness</a></h3>
+ <p class="dek">Claude Code subagents vs a multi-agent harness: where subagents stop and a harness with shared memory, messaging, and an orchestrator takes over.</p>
+ <div class="foot">
+ <span class="tag kind">Guides</span>
+ <a class="more" href="/blog/claude-code-subagents-vs-multi-agent-harness/" aria-label="Read: Claude Code Subagents vs a Multi-Agent Harness">Read →</a>
+ </div>
+ </div>
+</article>
<article class="card">
<a class="thumb t-concepts" href="/blog/what-is-a-multi-agent-harness/" aria-hidden="true" tabindex="-1">
<span>CONCEPTS</span>
diff --git a/docs/blog/manage-multiple-claude-code-sessions/index.html b/docs/blog/manage-multiple-claude-code-sessions/index.html
new file mode 100644
index 00000000..c0c2d66a
--- /dev/null
+++ b/docs/blog/manage-multiple-claude-code-sessions/index.html
@@ -0,0 +1,367 @@
+<!doctype html>
+<html lang="en">
+<head>
+<meta charset="UTF-8" />
+<meta name="viewport" content="width=device-width, initial-scale=1.0" />
+<title>How to Manage Multiple Claude Code Sessions Like a Pro — Munder Difflin Blog</title>
+<meta name="description" content="Tactics to manage multiple Claude Code sessions without losing track: naming, roles, context isolation, and when a harness beats juggling terminal tabs." />
+<link rel="canonical" href="https://munderdiffl.in/blog/manage-multiple-claude-code-sessions/" />
+
+<link rel="icon" type="image/png" href="https://munderdiffl.in/logo.png" />
+<link rel="apple-touch-icon" href="https://munderdiffl.in/logo.png" />
+<meta name="theme-color" content="#F5F2E8" />
+
+<!-- Open Graph -->
+<meta property="og:site_name" content="Munder Difflin Blog" />
+<meta property="og:type" content="article" />
+<meta property="og:title" content="How to Manage Multiple Claude Code Sessions Like a Pro — Munder Difflin Blog" />
+<meta property="og:description" content="Tactics to manage multiple Claude Code sessions without losing track: naming, roles, context isolation, and when a harness beats juggling terminal tabs." />
+<meta property="og:url" content="https://munderdiffl.in/blog/manage-multiple-claude-code-sessions/" />
+<meta property="og:image" content="https://munderdiffl.in/media/og.png" />
+<meta property="og:locale" content="en_US" />
+<meta property="article:published_time" content="2026-05-25T00:00:00.000Z" />
+<meta property="article:author" content="Chaitanya Giri" />
+<meta property="article:tag" content="Guides" />
+<meta property="article:tag" content="Workflow" />
+<meta property="article:tag" content="Claude Code" />
+<meta property="article:tag" content="Multi-Agent" />
+
+
+<!-- Twitter -->
+<meta name="twitter:card" content="summary_large_image" />
+<meta name="twitter:title" content="How to Manage Multiple Claude Code Sessions Like a Pro — Munder Difflin Blog" />
+<meta name="twitter:description" content="Tactics to manage multiple Claude Code sessions without losing track: naming, roles, context isolation, and when a harness beats juggling terminal tabs." />
+<meta name="twitter:image" content="https://munderdiffl.in/media/og.png" />
+
+<link rel="alternate" type="application/atom+xml" title="Munder Difflin Blog" href="https://munderdiffl.in/blog/feed.xml" />
+<link rel="preconnect" href="https://fonts.googleapis.com" />
+<link rel="preconnect" href="https://fonts.gstatic.com" crossorigin />
+<link href="https://fonts.googleapis.com/css2?family=Geist:wght@400;500;600&family=JetBrains+Mono:wght@400;500;600;700&display=swap" rel="stylesheet" />
+<link rel="stylesheet" href="/blog/assets/blog.css" />
+
+<script type="application/ld+json">
+{
+ "@context": "https://schema.org",
+ "@type": "BlogPosting",
+ "headline": "How to Manage Multiple Claude Code Sessions Like a Pro",
+ "description": "Tactics to manage multiple Claude Code sessions without losing track: naming, roles, context isolation, and when a harness beats juggling terminal tabs.",
+ "image": ["https://munderdiffl.in/media/og.png"],
+ "datePublished": "2026-05-25T00:00:00.000Z",
+ "dateModified": "2026-05-25T00:00:00.000Z",
+ "author": { "@type": "Person", "name": "Chaitanya Giri" },
+ "publisher": {
+ "@type": "Organization",
+ "name": "Munder Difflin",
+ "logo": { "@type": "ImageObject", "url": "https://munderdiffl.in/logo.png" }
+ },
+ "mainEntityOfPage": { "@type": "WebPage", "@id": "https://munderdiffl.in/blog/manage-multiple-claude-code-sessions/" },
+ "keywords": "how to manage multiple claude code sessions, manage claude code sessions, claude code workflow, multiple terminals",
+ "articleSection": "Guides",
+ "inLanguage": "en-US",
+ "url": "https://munderdiffl.in/blog/manage-multiple-claude-code-sessions/"
+}
+</script>
+<script type="application/ld+json">
+{
+ "@context": "https://schema.org",
+ "@type": "BreadcrumbList",
+ "itemListElement": [
+ { "@type": "ListItem", "position": 1, "name": "Home", "item": "https://munderdiffl.in/" },
+ { "@type": "ListItem", "position": 2, "name": "Blog", "item": "https://munderdiffl.in/blog/" },
+ { "@type": "ListItem", "position": 3, "name": "How to Manage Multiple Claude Code Sessions Like a Pro", "item": "https://munderdiffl.in/blog/manage-multiple-claude-code-sessions/" }
+ ]
+}
+</script>
+
+<script type="application/ld+json">
+{
+ "@context": "https://schema.org",
+ "@type": "FAQPage",
+ "mainEntity": [
+ { "@type": "Question", "name": "How many Claude Code sessions should I run at once?", "acceptedAnswer": { "@type": "Answer", "text": "As many as you can still account for. Most people stay legible at two to four manual sessions; past that, the tracking overhead grows faster than the throughput, which is the point where a coordinating harness pays off." } },
+ { "@type": "Question", "name": "How do I stop two Claude Code sessions from editing the same file?", "acceptedAnswer": { "@type": "Answer", "text": "Give each session a clearly scoped role so their files rarely overlap, and run shared work through a single coordination rule. In a harness this is automatic: a single-committer git design and per-agent workspaces keep writes from colliding." } },
+ { "@type": "Question", "name": "What's the difference between a session and an agent?", "acceptedAnswer": { "@type": "Answer", "text": "A session is one running `claude` process. An agent is a session with a durable identity — a role, its own memory, and a mailbox — so it persists as a teammate across tasks instead of being a throwaway window." } }
+
+ ]
+}
+</script>
+
+
+</head>
+<body>
+<a class="skip-link" href="#main">Skip to content</a>
+<nav id="nav">
+ <a class="brand" href="/blog/" aria-label="Munder Difflin Blog home">
+ <span class="brand-mark">MD</span>
+ <span class="brand-word">MUNDER DIFFLIN<span class="sep">/</span><span class="blog">BLOG</span></span>
+ </a>
+ <span class="spacer"></span>
+ <div class="links">
+ <a href="/blog/">Latest</a>
+ <a href="/blog/topics/">Topics</a>
+ <a href="/blog/about/">About</a>
+ <a href="https://munderdiffl.in">↗ Product</a>
+ </div>
+ <div class="nav-actions">
+ <a class="btn sm" href="https://munderdiffl.in/blog/feed.xml" aria-label="RSS feed">⤵ RSS</a>
+ <a class="btn sm primary" href="https://munderdiffl.in/#install">⤓ Download</a>
+ </div>
+</nav>
+
+<main id="main">
+
+<article>
+ <header class="post-head wrap">
+ <nav class="crumbs" aria-label="Breadcrumb">
+ <a href="/blog/">Blog</a>
+ <span>/</span>
+ <a href="/blog/topics/guides/">Guides</a>
+ </nav>
+ <h1>How to Manage Multiple Claude Code Sessions Like a Pro</h1>
+ <p class="dek">Tactics to manage multiple Claude Code sessions without losing track: naming, roles, context isolation, and when a harness beats juggling terminal tabs.</p>
+ <div class="byline">
+ <span class="av" aria-hidden="true">CG</span>
+ <strong>Chaitanya Giri</strong>
+ <span class="dot" aria-hidden="true">·</span>
+ <time datetime="2026-05-25">May 25, 2026</time>
+ <span class="dot" aria-hidden="true">·</span>
+ <span>4 min read</span>
+ <span class="tag kind">Guides</span>
+ </div>
+ </header>
+
+ <div class="post-wrap wrap">
+ <div class="prose">
+ <div class="callout tldr"><span class="ic">TL;DR</span><p>To
+<strong>manage multiple Claude Code sessions</strong> without losing track, give each a
+<strong>name and a role</strong>, keep their <strong>contexts isolated</strong> so they don't step on
+each other, and write down what each learns somewhere the others can read. Manual tabs work to about
+three or four sessions; past that, a harness that adds messaging, shared memory, and a single committer
+is what keeps it calm.</p></div>
+<p>Running one Claude Code session is easy. The trouble starts around session three, when “what is each
+of these doing right now?” stops having an obvious answer. Here’s how to keep multiple sessions
+legible — first by hand, then with tooling once the hand-management stops scaling.</p>
+<h2 id="the-three-failure-modes" tabindex="-1">The three failure modes <a class="anchor" href="#the-three-failure-modes" aria-hidden="true">#</a></h2>
+<p>Almost every multi-session mess is one of these:</p>
+<ol>
+<li><strong>Lost track.</strong> Six tabs, and you can’t say what’s in flight without reading each one.</li>
+<li><strong>Collisions.</strong> Two sessions edit the same file or commit at the same moment, and you get
+half-applied changes or a <code>git index.lock</code> error.</li>
+<li><strong>Re-explaining.</strong> Each session forgets what the others figured out, so you become the courier,
+pasting context between windows.</li>
+</ol>
+<p>Good management is just the set of habits that prevent these three. Take them in order.</p>
+<h2 id="habit-1-name-and-scope-every-session" tabindex="-1">Habit 1 — Name and scope every session <a class="anchor" href="#habit-1-name-and-scope-every-session" aria-hidden="true">#</a></h2>
+<p>An unnamed session is an anonymous liability. Give each one a name that <em>is</em> its job:
+<code>test-writer</code>, <code>migration</code>, <code>reviewer</code>, <code>docs</code>. The name does two things — it tells you what the tab
+is for at a glance, and it constrains the session so it doesn’t wander into another’s work.</p>
+<p>Scope follows naming. A session called <code>reviewer</code> reviews; it doesn’t start refactoring. The tighter
+the scope, the less the sessions overlap, which directly defuses failure mode #2.</p>
+<h2 id="habit-2-isolate-context-on-purpose" tabindex="-1">Habit 2 — Isolate context on purpose <a class="anchor" href="#habit-2-isolate-context-on-purpose" aria-hidden="true">#</a></h2>
+<p>Each <code>claude</code> session has its own context window, and that’s a feature: it keeps one task’s noise out
+of another’s reasoning. The mistake is fighting it — trying to keep one giant session that “knows
+everything.” Instead, lean into isolation:</p>
+<ul>
+<li>One session per <strong>independent</strong> unit of work.</li>
+<li>Don’t paste the whole codebase into every session; let each pull only what its task needs.</li>
+<li>When two tasks genuinely depend on each other, that’s a <em>coordination</em> problem, not a reason to
+merge sessions (more on that below).</li>
+</ul>
+<p>Isolation is why parallel sessions are fast. It’s also why they forget — which is the next habit.</p>
+<h2 id="habit-3-externalize-what-each-session-learns" tabindex="-1">Habit 3 — Externalize what each session learns <a class="anchor" href="#habit-3-externalize-what-each-session-learns" aria-hidden="true">#</a></h2>
+<p>Context windows are wiped at the end of a session. Anything a session learned — a convention, a
+gotcha, a decision — is gone unless it’s written somewhere durable. The fix is a small ritual: each
+session writes durable facts to a file, and reads the relevant ones at the start of its next task.</p>
+<pre class="language-markdown"><code class="language-markdown"><span class="token title important"><span class="token punctuation">##</span> build</span>
+<span class="token list punctuation">-</span> The web bundle is built with electron-vite, NOT plain vite. Use <span class="token code-snippet code keyword">`npm run build`</span>.
+<span class="token list punctuation">-</span> node-pty needs an electron-rebuild after install (the postinstall handles it).</code></pre>
+<p>Plain markdown is enough to start. Once the notes pile up, you add a semantic index so a session can
+recall the few relevant notes by meaning instead of re-reading everything — the full version of this
+is <a href="/blog/give-claude-code-long-term-memory/">long-term memory for Claude Code</a>.</p>
+<h2 id="habit-4-give-shared-work-a-single-coordination-rule" tabindex="-1">Habit 4 — Give shared work a single coordination rule <a class="anchor" href="#habit-4-give-shared-work-a-single-coordination-rule" aria-hidden="true">#</a></h2>
+<p>Failure mode #2 — collisions — is the one pure discipline can’t fully solve, because two well-behaved
+sessions can still both decide to commit at the same instant. The rule that fixes it: <strong>one writer per
+thing.</strong> One session owns a file; shared state has one committer. When you do this by hand it means
+agreeing, out loud, who touches what. It’s tedious, and it’s exactly the part that breaks down as you
+add sessions.</p>
+<h2 id="when-manual-management-stops-scaling" tabindex="-1">When manual management stops scaling <a class="anchor" href="#when-manual-management-stops-scaling" aria-hidden="true">#</a></h2>
+<p>Two to four sessions are manageable with the habits above. Past that, the overhead curve bends the
+wrong way — you spend more time being the message bus and the traffic cop than you save running the
+sessions in parallel. That’s the signal to move from “managing sessions” to running a <strong>team</strong>.</p>
+<p>A harness automates all four habits at once:</p>
+<ul>
+<li><strong>Naming and roles</strong> become first-class — each agent gets an identity injected into its system
+prompt, so it knows who it is across tasks.</li>
+<li><strong>Context isolation</strong> stays (every agent is still its own <code>claude</code> process) but coordination no
+longer requires merging them.</li>
+<li><strong>Externalized memory</strong> becomes shared and searchable — each agent’s notes are mined into a
+store the whole team can recall from.</li>
+<li><strong>The single-committer rule</strong> is enforced in code: agents write plain files and never call git;
+one process commits, with retry and stale-lock recovery, so <code>index.lock</code> races simply can’t corrupt
+the repo.</li>
+</ul>
+<p>That’s the leap from a <a href="/blog/claude-code-multi-agent-setup-tutorial/">multi-agent setup</a> you babysit
+to one that runs itself. If you’re not sure you need it yet, you probably don’t — the honest rule is
+to add tooling only when the tabs start costing you more than they return. The next read up is
+<a href="/blog/how-to-run-multiple-claude-code-agents/">how to run multiple Claude Code agents</a>, which walks
+the same progression with the orchestration layer in view.</p>
+<h2 id="a-quick-management-checklist" tabindex="-1">A quick management checklist <a class="anchor" href="#a-quick-management-checklist" aria-hidden="true">#</a></h2>
+<ul>
+<li>[ ] Every session has a name that states its job.</li>
+<li>[ ] Roles are scoped tightly enough that files rarely overlap.</li>
+<li>[ ] Each session writes durable facts to memory and reads them on startup.</li>
+<li>[ ] Shared state has exactly one writer.</li>
+<li>[ ] When you can’t say what every session is doing, you have too many — consolidate or coordinate.</li>
+</ul>
+<hr>
+<p>When the checklist starts feeling like a second job, that’s what Munder Difflin automates: roles,
+isolated agents, shared memory, and a single committer, all on your own machine.
+<a href="https://munderdiffl.in/#install">Download Munder Difflin</a> — it’s free and open source.</p>
+
+
+
+ <section class="faq" aria-label="Frequently asked questions">
+ <h2 id="faq">FAQ</h2>
+
+ <div class="qa">
+ <p class="q">How many Claude Code sessions should I run at once?</p>
+ <p class="a">As many as you can still account for. Most people stay legible at two to four manual sessions; past that, the tracking overhead grows faster than the throughput, which is the point where a coordinating harness pays off.</p>
+ </div>
+
+ <div class="qa">
+ <p class="q">How do I stop two Claude Code sessions from editing the same file?</p>
+ <p class="a">Give each session a clearly scoped role so their files rarely overlap, and run shared work through a single coordination rule. In a harness this is automatic: a single-committer git design and per-agent workspaces keep writes from colliding.</p>
+ </div>
+
+ <div class="qa">
+ <p class="q">What&#39;s the difference between a session and an agent?</p>
+ <p class="a">A session is one running `claude` process. An agent is a session with a durable identity — a role, its own memory, and a mailbox — so it persists as a teammate across tasks instead of being a throwaway window.</p>
+ </div>
+
+ </section>
+
+
+
+ <hr />
+ <div class="share">
+ <span class="lbl">Tags</span>
+ <a class="tag" href="/blog/tags/guides/">Guides</a><a class="tag" href="/blog/tags/workflow/">Workflow</a><a class="tag" href="/blog/tags/claude-code/">Claude Code</a><a class="tag" href="/blog/tags/multi-agent/">Multi-Agent</a>
+ </div>
+
+ </div>
+
+
+ <aside class="toc-rail" aria-label="Table of contents">
+ <div class="tt">On this page</div>
+ <ol>
+ <li class="lvl-2"><a href="#the-three-failure-modes">The three failure modes</a></li><li class="lvl-2"><a href="#habit-1-name-and-scope-every-session">Habit 1 — Name and scope every session</a></li><li class="lvl-2"><a href="#habit-2-isolate-context-on-purpose">Habit 2 — Isolate context on purpose</a></li><li class="lvl-2"><a href="#habit-3-externalize-what-each-session-learns">Habit 3 — Externalize what each session learns</a></li><li class="lvl-2"><a href="#habit-4-give-shared-work-a-single-coordination-rule">Habit 4 — Give shared work a single coordination rule</a></li><li class="lvl-2"><a href="#when-manual-management-stops-scaling">When manual management stops scaling</a></li><li class="lvl-2"><a href="#a-quick-management-checklist">A quick management checklist</a></li>
+ </ol>
+ </aside>
+
+ </div>
+
+ <footer class="post-foot wrap"><div class="prevnext">
+ <a class="pn prev" href="/blog/claude-code-multi-agent-setup-tutorial/"><span class="k">← Older</span><span class="t">Set Up a Claude Code Multi-Agent Workflow in 10 Minutes</span></a>
+ <a class="pn next" href="/blog/semantic-memory-for-ai-agents/"><span class="k">Newer →</span><span class="t">Semantic Memory for AI Agents: Recall in Milliseconds</span></a>
+ </div>
+ <section class="related">
+ <h2>Related in Guides</h2>
+ <div class="post-grid">
+ <article class="card">
+ <a class="thumb t-guides" href="/blog/claude-code-automation-while-you-sleep/" aria-hidden="true" tabindex="-1">
+ <span>GUIDES</span>
+ </a>
+ <div class="body">
+ <div class="meta">
+ <time datetime="2026-06-04">Jun 4, 2026</time>
+ <span class="dot" aria-hidden="true"></span>
+ <span>5 min</span>
+ </div>
+ <h3><a href="/blog/claude-code-automation-while-you-sleep/">Claude Code Automation: Let Agents Build While You Sleep</a></h3>
+ <p class="dek">Claude Code automation that runs overnight: an autonomous Stop-hook loop, safe permission bypass, and guardrails so you wake up to progress, not chaos.</p>
+ <div class="foot">
+ <span class="tag kind">Guides</span>
+ <a class="more" href="/blog/claude-code-automation-while-you-sleep/" aria-label="Read: Claude Code Automation: Let Agents Build While You Sleep">Read →</a>
+ </div>
+ </div>
+</article>
+<article class="card">
+ <a class="thumb t-guides" href="/blog/mcp-and-skills-in-a-hive/" aria-hidden="true" tabindex="-1">
+ <span>GUIDES</span>
+ </a>
+ <div class="body">
+ <div class="meta">
+ <time datetime="2026-06-03">Jun 3, 2026</time>
+ <span class="dot" aria-hidden="true"></span>
+ <span>6 min</span>
+ </div>
+ <h3><a href="/blog/mcp-and-skills-in-a-hive/">Bringing Your MCP Servers and Skills Into a Hive of Agents</a></h3>
+ <p class="dek">How agents in a hive inherit your existing Claude Code MCP servers, skills, and tools — and how to scope which agent gets which capability.</p>
+ <div class="foot">
+ <span class="tag kind">Guides</span>
+ <a class="more" href="/blog/mcp-and-skills-in-a-hive/" aria-label="Read: Bringing Your MCP Servers and Skills Into a Hive of Agents">Read →</a>
+ </div>
+ </div>
+</article>
+<article class="card">
+ <a class="thumb t-guides" href="/blog/how-to-run-multiple-claude-code-agents/" aria-hidden="true" tabindex="-1">
+ <span>GUIDES</span>
+ </a>
+ <div class="body">
+ <div class="meta">
+ <time datetime="2026-06-01">Jun 1, 2026</time>
+ <span class="dot" aria-hidden="true"></span>
+ <span>3 min</span>
+ </div>
+ <h3><a href="/blog/how-to-run-multiple-claude-code-agents/">How to Run Multiple Claude Code Agents (Without Losing Track)</a></h3>
+ <p class="dek">Run several Claude Code agents in parallel without the chaos: give each a role, let them coordinate, and stop alt-tabbing between terminal windows.</p>
+ <div class="foot">
+ <span class="tag kind">Guides</span>
+ <a class="more" href="/blog/how-to-run-multiple-claude-code-agents/" aria-label="Read: How to Run Multiple Claude Code Agents (Without Losing Track)">Read →</a>
+ </div>
+ </div>
+</article>
+
+ </div>
+ </section>
+
+ </footer>
+</article>
+
+</main>
+<footer>
+ <div class="wrap">
+ <div class="foot-top">
+ <a class="foot-brand brand" href="/blog/">
+ <span class="brand-mark">MD</span>
+ <span class="brand-word">MUNDER DIFFLIN<span class="sep">/</span><span class="blog">BLOG</span></span>
+ </a>
+ <div class="foot-links">
+ <a href="/blog/">Latest</a>
+ <a href="/blog/topics/">Topics</a>
+ <a href="/blog/about/">About</a>
+ <a href="https://munderdiffl.in/blog/feed.xml">RSS</a>
+ <a href="https://github.com/chaitanyagiri/munder-difflin">GitHub</a>
+ <a href="https://munderdiffl.in">munderdiffl.in ↗</a>
+ </div>
+ </div>
+ <div class="foot-meta">
+ © 2026 Munder Difflin · Local-first · MIT-licensed ·
+ Built on <a href="https://munderdiffl.in">Electron, React, Pixi.js, xterm.js &amp; node-pty</a>.
+ Run an office of agents while you sleep.
+ </div>
+ </div>
+</footer>
+
+<script>
+ // sticky-nav border on scroll
+ (function () {
+ var nav = document.getElementById('nav');
+ if (!nav) return;
+ var onScroll = function () { nav.classList.toggle('scrolled', window.scrollY > 8); };
+ onScroll(); window.addEventListener('scroll', onScroll, { passive: true });
+ })();
+</script>
+
+</body>
+</html>
diff --git a/docs/blog/mcp-and-skills-in-a-hive/index.html b/docs/blog/mcp-and-skills-in-a-hive/index.html
new file mode 100644
index 00000000..413c16b6
--- /dev/null
+++ b/docs/blog/mcp-and-skills-in-a-hive/index.html
@@ -0,0 +1,383 @@
+<!doctype html>
+<html lang="en">
+<head>
+<meta charset="UTF-8" />
+<meta name="viewport" content="width=device-width, initial-scale=1.0" />
+<title>Bringing Your MCP Servers and Skills Into a Hive of Agents — Munder Difflin Blog</title>
+<meta name="description" content="How agents in a hive inherit your existing Claude Code MCP servers, skills, and tools — and how to scope which agent gets which capability." />
+<link rel="canonical" href="https://munderdiffl.in/blog/mcp-and-skills-in-a-hive/" />
+
+<link rel="icon" type="image/png" href="https://munderdiffl.in/logo.png" />
+<link rel="apple-touch-icon" href="https://munderdiffl.in/logo.png" />
+<meta name="theme-color" content="#F5F2E8" />
+
+<!-- Open Graph -->
+<meta property="og:site_name" content="Munder Difflin Blog" />
+<meta property="og:type" content="article" />
+<meta property="og:title" content="Bringing Your MCP Servers and Skills Into a Hive of Agents — Munder Difflin Blog" />
+<meta property="og:description" content="How agents in a hive inherit your existing Claude Code MCP servers, skills, and tools — and how to scope which agent gets which capability." />
+<meta property="og:url" content="https://munderdiffl.in/blog/mcp-and-skills-in-a-hive/" />
+<meta property="og:image" content="https://munderdiffl.in/media/og.png" />
+<meta property="og:locale" content="en_US" />
+<meta property="article:published_time" content="2026-06-03T00:00:00.000Z" />
+<meta property="article:author" content="Chaitanya Giri" />
+<meta property="article:tag" content="Guides" />
+<meta property="article:tag" content="MCP" />
+<meta property="article:tag" content="Skills" />
+<meta property="article:tag" content="Claude Code" />
+
+
+<!-- Twitter -->
+<meta name="twitter:card" content="summary_large_image" />
+<meta name="twitter:title" content="Bringing Your MCP Servers and Skills Into a Hive of Agents — Munder Difflin Blog" />
+<meta name="twitter:description" content="How agents in a hive inherit your existing Claude Code MCP servers, skills, and tools — and how to scope which agent gets which capability." />
+<meta name="twitter:image" content="https://munderdiffl.in/media/og.png" />
+
+<link rel="alternate" type="application/atom+xml" title="Munder Difflin Blog" href="https://munderdiffl.in/blog/feed.xml" />
+<link rel="preconnect" href="https://fonts.googleapis.com" />
+<link rel="preconnect" href="https://fonts.gstatic.com" crossorigin />
+<link href="https://fonts.googleapis.com/css2?family=Geist:wght@400;500;600&family=JetBrains+Mono:wght@400;500;600;700&display=swap" rel="stylesheet" />
+<link rel="stylesheet" href="/blog/assets/blog.css" />
+
+<script type="application/ld+json">
+{
+ "@context": "https://schema.org",
+ "@type": "BlogPosting",
+ "headline": "Bringing Your MCP Servers and Skills Into a Hive of Agents",
+ "description": "How agents in a hive inherit your existing Claude Code MCP servers, skills, and tools — and how to scope which agent gets which capability.",
+ "image": ["https://munderdiffl.in/media/og.png"],
+ "datePublished": "2026-06-03T00:00:00.000Z",
+ "dateModified": "2026-06-03T00:00:00.000Z",
+ "author": { "@type": "Person", "name": "Chaitanya Giri" },
+ "publisher": {
+ "@type": "Organization",
+ "name": "Munder Difflin",
+ "logo": { "@type": "ImageObject", "url": "https://munderdiffl.in/logo.png" }
+ },
+ "mainEntityOfPage": { "@type": "WebPage", "@id": "https://munderdiffl.in/blog/mcp-and-skills-in-a-hive/" },
+ "keywords": "claude code mcp multi-agent, mcp servers, claude code skills, agent tools",
+ "articleSection": "Guides",
+ "inLanguage": "en-US",
+ "url": "https://munderdiffl.in/blog/mcp-and-skills-in-a-hive/"
+}
+</script>
+<script type="application/ld+json">
+{
+ "@context": "https://schema.org",
+ "@type": "BreadcrumbList",
+ "itemListElement": [
+ { "@type": "ListItem", "position": 1, "name": "Home", "item": "https://munderdiffl.in/" },
+ { "@type": "ListItem", "position": 2, "name": "Blog", "item": "https://munderdiffl.in/blog/" },
+ { "@type": "ListItem", "position": 3, "name": "Bringing Your MCP Servers and Skills Into a Hive of Agents", "item": "https://munderdiffl.in/blog/mcp-and-skills-in-a-hive/" }
+ ]
+}
+</script>
+
+<script type="application/ld+json">
+{
+ "@context": "https://schema.org",
+ "@type": "FAQPage",
+ "mainEntity": [
+ { "@type": "Question", "name": "Do I have to reconfigure MCP servers for each agent in a hive?", "acceptedAnswer": { "@type": "Answer", "text": "No. Because each agent is a real Claude Code session running in your project, it inherits the MCP servers you've already configured — project-scoped and user-scoped alike. The harness adds coordination on top without touching that configuration." } },
+ { "@type": "Question", "name": "Do my Claude Code skills work inside a hive?", "acceptedAnswer": { "@type": "Answer", "text": "Yes. Skills resolve the same way they do in a normal session — from your user and project skill directories — so every agent in the hive can use them. The harness doesn't strip or replace your skills." } },
+ { "@type": "Question", "name": "How do I give different agents different tools?", "acceptedAnswer": { "@type": "Answer", "text": "Scope by directory and role. Project-scoped MCP servers and skills differ per working directory, so an agent pointed at one project gets that project's tools; and each agent's injected role steers which tools it actually reaches for." } }
+
+ ]
+}
+</script>
+
+
+</head>
+<body>
+<a class="skip-link" href="#main">Skip to content</a>
+<nav id="nav">
+ <a class="brand" href="/blog/" aria-label="Munder Difflin Blog home">
+ <span class="brand-mark">MD</span>
+ <span class="brand-word">MUNDER DIFFLIN<span class="sep">/</span><span class="blog">BLOG</span></span>
+ </a>
+ <span class="spacer"></span>
+ <div class="links">
+ <a href="/blog/">Latest</a>
+ <a href="/blog/topics/">Topics</a>
+ <a href="/blog/about/">About</a>
+ <a href="https://munderdiffl.in">↗ Product</a>
+ </div>
+ <div class="nav-actions">
+ <a class="btn sm" href="https://munderdiffl.in/blog/feed.xml" aria-label="RSS feed">⤵ RSS</a>
+ <a class="btn sm primary" href="https://munderdiffl.in/#install">⤓ Download</a>
+ </div>
+</nav>
+
+<main id="main">
+
+<article>
+ <header class="post-head wrap">
+ <nav class="crumbs" aria-label="Breadcrumb">
+ <a href="/blog/">Blog</a>
+ <span>/</span>
+ <a href="/blog/topics/guides/">Guides</a>
+ </nav>
+ <h1>Bringing Your MCP Servers and Skills Into a Hive of Agents</h1>
+ <p class="dek">How agents in a hive inherit your existing Claude Code MCP servers, skills, and tools — and how to scope which agent gets which capability.</p>
+ <div class="byline">
+ <span class="av" aria-hidden="true">CG</span>
+ <strong>Chaitanya Giri</strong>
+ <span class="dot" aria-hidden="true">·</span>
+ <time datetime="2026-06-03">Jun 3, 2026</time>
+ <span class="dot" aria-hidden="true">·</span>
+ <span>6 min read</span>
+ <span class="tag kind">Guides</span>
+ </div>
+ </header>
+
+ <div class="post-wrap wrap">
+ <div class="prose">
+ <div class="callout tldr"><span class="ic">TL;DR</span><p>In a
+<strong>Claude Code MCP multi-agent</strong> hive, your existing <strong>MCP servers and skills come
+along for free</strong> — because each agent is a real <code>claude</code> session in your project, it
+inherits exactly what a normal session would. The harness only <em>adds</em> coordination (identity,
+hooks, environment); it never strips your tools. To scope tools per agent, lean on
+<strong>per-directory project config</strong> and each agent's <strong>role</strong>.</p></div>
+<p>If you’ve invested in Claude Code — wired up MCP servers, written skills, tuned your tools — the last
+thing you want is a harness that makes you redo all of it per agent. The good news: you don’t. The
+design principle that makes a hive practical is that <strong>every agent is a genuine Claude Code session</strong>,
+so your existing setup is inherited, not replaced. This post explains exactly how that works and how to
+scope tools when you want different agents to have different capabilities.</p>
+<h2 id="why-inheritance-is-automatic" tabindex="-1">Why inheritance is automatic <a class="anchor" href="#why-inheritance-is-automatic" aria-hidden="true">#</a></h2>
+<p>Start from what a hive agent actually <em>is</em>. When the harness spawns an agent, it doesn’t reimplement
+Claude or run some stripped-down clone. It launches the real <code>claude</code> CLI in your project directory,
+and adds a few things via launch flags and environment variables:</p>
+<ul>
+<li>an <strong>injected role and protocol</strong> (via <code>--append-system-prompt</code>) so the agent knows who it is and
+how to coordinate,</li>
+<li><strong>lifecycle hooks</strong> (via <code>--settings</code>, pointing at a file outside your repo) so the harness can drive
+the visualization and the autonomous loop,</li>
+<li>and <strong>environment variables</strong> (<code>AGENT_ID</code>, <code>AGENT_NAME</code>, and so on) for hive identity.</li>
+</ul>
+<p>Notice what’s <em>not</em> in that list: anything that disables MCP or skills. The agent is a normal session
+with extras bolted on, so it resolves MCP servers and skills the same way every Claude Code session
+does. Your tools are present because nothing took them away.</p>
+<p>This is the whole reason a harness is lighter than a framework. A framework asks you to rebuild your
+agent inside it. A harness wraps the agent you already run — which is the core idea behind a
+<a href="https://munderdiffl.in/#what">multi-agent harness</a>, and why your investment carries straight over.</p>
+<h3 id="mcp-servers" tabindex="-1">MCP servers <a class="anchor" href="#mcp-servers" aria-hidden="true">#</a></h3>
+<p>MCP (Model Context Protocol) servers extend an agent with external tools and data — your database, your
+issue tracker, your internal APIs. Claude Code resolves MCP servers from configuration: user-scoped
+servers you’ve set up globally, and project-scoped servers defined in the project you’re working in.
+Because a hive agent runs as a real session in that project, it picks up both. Every agent in the hive
+can call the same MCP tools you’d have in a solo session — no per-agent re-registration.</p>
+<h3 id="skills" tabindex="-1">Skills <a class="anchor" href="#skills" aria-hidden="true">#</a></h3>
+<p>Skills work the same way. They resolve from your skill directories — the ones a normal session reads —
+so an agent in the hive can invoke any skill you’ve installed. The harness adds its <em>own</em> lifecycle
+hooks via a separate settings file, which is additive; it doesn’t shadow or remove the skills your
+session would otherwise have.</p>
+<h2 id="hooks-attach-without-touching-your-repo" tabindex="-1">Hooks attach without touching your repo <a class="anchor" href="#hooks-attach-without-touching-your-repo" aria-hidden="true">#</a></h2>
+<p>A natural worry: “if the harness uses <code>--settings</code> to attach hooks, does that clobber my settings or
+my MCP config?” It doesn’t. The hooks live in a settings file the harness writes <strong>outside</strong> your
+project, and <code>--settings</code> is additive — it layers the harness’s hooks alongside your existing
+configuration rather than replacing it. Your repo isn’t modified to make an agent hive-aware; there’s
+no stray settings diff to commit or gitignore. (The hook mechanics are covered in
+<a href="/blog/claude-code-hooks-explained/">Claude Code hooks, explained</a>.)</p>
+<h2 id="a-note-on-the-harnesss-own-memory" tabindex="-1">A note on the harness’s own memory <a class="anchor" href="#a-note-on-the-harnesss-own-memory" aria-hidden="true">#</a></h2>
+<p>Here’s a deliberate design choice worth calling out: the hive’s <strong>semantic memory doesn’t consume an
+MCP slot.</strong> Rather than run memory as an MCP server, the harness drives it through a CLI and points each
+agent’s environment at a shared store. The benefit is that the coordination layer stays out of your
+tool budget — your MCP servers are yours, and the harness’s memory is a companion process beside them,
+not a competitor for the same plumbing. The agent recalls knowledge with plain commands, and your MCP
+configuration is untouched. (The memory layer itself is covered in
+<a href="/blog/semantic-memory-for-ai-agents/">semantic memory for AI agents</a>.)</p>
+<h2 id="scoping-tools-per-agent" tabindex="-1">Scoping tools per agent <a class="anchor" href="#scoping-tools-per-agent" aria-hidden="true">#</a></h2>
+<p>Inheritance gives every agent the <em>same</em> tools by default. Often you want differentiation — a
+<code>db-migrator</code> with database access, a <code>docs</code> agent without it. You scope without fighting the harness,
+using mechanisms Claude Code already provides.</p>
+<h3 id="scope-by-directory" tabindex="-1">Scope by directory <a class="anchor" href="#scope-by-directory" aria-hidden="true">#</a></h3>
+<p>MCP servers and skills can be <strong>project-scoped</strong> — defined in a particular working directory. Since
+each agent is spawned with a <code>cwd</code>, an agent pointed at one project inherits that project’s tools, and
+an agent pointed at another inherits a different set. Directory is your coarse-grained tool boundary:
+put the database MCP server in the project the <code>db-migrator</code> works in, and agents elsewhere simply don’t
+see it.</p>
+<h3 id="scope-by-role" tabindex="-1">Scope by role <a class="anchor" href="#scope-by-role" aria-hidden="true">#</a></h3>
+<p>The finer control is the <strong>role</strong> the harness injects into each agent’s system prompt. An agent told it
+is the <code>reviewer</code> reaches for read and analysis tools; one told it’s the <code>migration</code> agent reaches for
+the database tools. The role doesn’t physically remove a capability, but it steers behavior — a
+well-scoped role keeps an agent in its lane, which is usually what “give this agent different tools”
+really means in practice. Roles are the same routing signal the
+<a href="/blog/claude-code-orchestration-guide/">orchestrator</a> uses to assign work, so they do double duty.</p>
+<h3 id="lean-on-claude-codes-native-controls" tabindex="-1">Lean on Claude Code’s native controls <a class="anchor" href="#lean-on-claude-codes-native-controls" aria-hidden="true">#</a></h3>
+<p>Because agents are real sessions, Claude Code’s own configuration applies — per-project settings and
+permission controls govern what a session in that directory can do. You’re not learning a parallel,
+harness-specific permission system; you’re using the one you already know, per directory, per agent.</p>
+<h2 id="a-practical-setup" tabindex="-1">A practical setup <a class="anchor" href="#a-practical-setup" aria-hidden="true">#</a></h2>
+<p>Putting it together, a tooled-up hive might look like this:</p>
+<ol>
+<li><strong>Keep your MCP servers and skills where they are.</strong> User-scoped tools are available to every agent;
+project-scoped tools follow the project each agent works in.</li>
+<li><strong>Spawn agents with roles that match their tools.</strong> <code>db-migrator</code>, <code>reviewer</code>, <code>docs</code> — the role
+steers each toward the right subset.</li>
+<li><strong>Point sensitive tools at specific projects</strong> so only the agents in those directories inherit them.</li>
+<li><strong>Let the orchestrator route by role</strong>, so the agent with the right tools gets the matching work.</li>
+</ol>
+<p>You end up with a team where each agent has exactly the capabilities its job needs — built entirely
+from configuration you already had, plus roles. That’s the fast path from your existing Claude Code
+setup to a coordinated team, which is the same ten-minute on-ramp as the
+<a href="/blog/claude-code-multi-agent-setup-tutorial/">multi-agent setup tutorial</a>.</p>
+<h2 id="faq" tabindex="-1">FAQ <a class="anchor" href="#faq" aria-hidden="true">#</a></h2>
+<p><strong>Will running many agents multiply my MCP server processes?</strong> It depends on the server and how it’s
+launched, just as it would if you opened several Claude Code sessions yourself — the hive doesn’t change
+that math. Stateless servers handle it fine; for heavy ones, scope them to the agents that actually
+need them.</p>
+<p><strong>Can an agent use a skill that spawns subagents or runs tools?</strong> Yes — the agent has full Claude Code
+capabilities, including skills and subagents. The harness coordinates <em>between</em> agents; it doesn’t
+constrain what each agent can do <em>within</em> its own session.</p>
+<hr>
+<p>Munder Difflin runs your real Claude Code — your MCP servers, your skills, your tools — just
+orchestrated into a hive. <a href="https://munderdiffl.in/#install">Download Munder Difflin</a> to bring your
+existing setup into a coordinated team of agents; it’s free and open source.</p>
+
+
+
+ <section class="faq" aria-label="Frequently asked questions">
+ <h2 id="faq">FAQ</h2>
+
+ <div class="qa">
+ <p class="q">Do I have to reconfigure MCP servers for each agent in a hive?</p>
+ <p class="a">No. Because each agent is a real Claude Code session running in your project, it inherits the MCP servers you&#39;ve already configured — project-scoped and user-scoped alike. The harness adds coordination on top without touching that configuration.</p>
+ </div>
+
+ <div class="qa">
+ <p class="q">Do my Claude Code skills work inside a hive?</p>
+ <p class="a">Yes. Skills resolve the same way they do in a normal session — from your user and project skill directories — so every agent in the hive can use them. The harness doesn&#39;t strip or replace your skills.</p>
+ </div>
+
+ <div class="qa">
+ <p class="q">How do I give different agents different tools?</p>
+ <p class="a">Scope by directory and role. Project-scoped MCP servers and skills differ per working directory, so an agent pointed at one project gets that project&#39;s tools; and each agent&#39;s injected role steers which tools it actually reaches for.</p>
+ </div>
+
+ </section>
+
+
+
+ <hr />
+ <div class="share">
+ <span class="lbl">Tags</span>
+ <a class="tag" href="/blog/tags/guides/">Guides</a><a class="tag" href="/blog/tags/mcp/">MCP</a><a class="tag" href="/blog/tags/skills/">Skills</a><a class="tag" href="/blog/tags/claude-code/">Claude Code</a>
+ </div>
+
+ </div>
+
+
+ <aside class="toc-rail" aria-label="Table of contents">
+ <div class="tt">On this page</div>
+ <ol>
+ <li class="lvl-2"><a href="#why-inheritance-is-automatic">Why inheritance is automatic</a></li><li class="lvl-3"><a href="#mcp-servers">MCP servers</a></li><li class="lvl-3"><a href="#skills">Skills</a></li><li class="lvl-2"><a href="#hooks-attach-without-touching-your-repo">Hooks attach without touching your repo</a></li><li class="lvl-2"><a href="#a-note-on-the-harnesss-own-memory">A note on the harness’s own memory</a></li><li class="lvl-2"><a href="#scoping-tools-per-agent">Scoping tools per agent</a></li><li class="lvl-3"><a href="#scope-by-directory">Scope by directory</a></li><li class="lvl-3"><a href="#scope-by-role">Scope by role</a></li><li class="lvl-3"><a href="#lean-on-claude-codes-native-controls">Lean on Claude Code’s native controls</a></li><li class="lvl-2"><a href="#a-practical-setup">A practical setup</a></li><li class="lvl-2"><a href="#faq">FAQ</a></li>
+ </ol>
+ </aside>
+
+ </div>
+
+ <footer class="post-foot wrap"><div class="prevnext">
+ <a class="pn prev" href="/blog/node-pty-electron-real-terminals/"><span class="k">← Older</span><span class="t">Real Terminals in Electron with node-pty</span></a>
+ <a class="pn next" href="/blog/crystal-claude-code-alternative/"><span class="k">Newer →</span><span class="t">A Crystal Alternative: Multi-Agent Claude Code with Memory</span></a>
+ </div>
+ <section class="related">
+ <h2>Related in Guides</h2>
+ <div class="post-grid">
+ <article class="card">
+ <a class="thumb t-guides" href="/blog/claude-code-automation-while-you-sleep/" aria-hidden="true" tabindex="-1">
+ <span>GUIDES</span>
+ </a>
+ <div class="body">
+ <div class="meta">
+ <time datetime="2026-06-04">Jun 4, 2026</time>
+ <span class="dot" aria-hidden="true"></span>
+ <span>5 min</span>
+ </div>
+ <h3><a href="/blog/claude-code-automation-while-you-sleep/">Claude Code Automation: Let Agents Build While You Sleep</a></h3>
+ <p class="dek">Claude Code automation that runs overnight: an autonomous Stop-hook loop, safe permission bypass, and guardrails so you wake up to progress, not chaos.</p>
+ <div class="foot">
+ <span class="tag kind">Guides</span>
+ <a class="more" href="/blog/claude-code-automation-while-you-sleep/" aria-label="Read: Claude Code Automation: Let Agents Build While You Sleep">Read →</a>
+ </div>
+ </div>
+</article>
+<article class="card">
+ <a class="thumb t-guides" href="/blog/how-to-run-multiple-claude-code-agents/" aria-hidden="true" tabindex="-1">
+ <span>GUIDES</span>
+ </a>
+ <div class="body">
+ <div class="meta">
+ <time datetime="2026-06-01">Jun 1, 2026</time>
+ <span class="dot" aria-hidden="true"></span>
+ <span>3 min</span>
+ </div>
+ <h3><a href="/blog/how-to-run-multiple-claude-code-agents/">How to Run Multiple Claude Code Agents (Without Losing Track)</a></h3>
+ <p class="dek">Run several Claude Code agents in parallel without the chaos: give each a role, let them coordinate, and stop alt-tabbing between terminal windows.</p>
+ <div class="foot">
+ <span class="tag kind">Guides</span>
+ <a class="more" href="/blog/how-to-run-multiple-claude-code-agents/" aria-label="Read: How to Run Multiple Claude Code Agents (Without Losing Track)">Read →</a>
+ </div>
+ </div>
+</article>
+<article class="card">
+ <a class="thumb t-guides" href="/blog/manage-multiple-claude-code-sessions/" aria-hidden="true" tabindex="-1">
+ <span>GUIDES</span>
+ </a>
+ <div class="body">
+ <div class="meta">
+ <time datetime="2026-05-25">May 25, 2026</time>
+ <span class="dot" aria-hidden="true"></span>
+ <span>4 min</span>
+ </div>
+ <h3><a href="/blog/manage-multiple-claude-code-sessions/">How to Manage Multiple Claude Code Sessions Like a Pro</a></h3>
+ <p class="dek">Tactics to manage multiple Claude Code sessions without losing track: naming, roles, context isolation, and when a harness beats juggling terminal tabs.</p>
+ <div class="foot">
+ <span class="tag kind">Guides</span>
+ <a class="more" href="/blog/manage-multiple-claude-code-sessions/" aria-label="Read: How to Manage Multiple Claude Code Sessions Like a Pro">Read →</a>
+ </div>
+ </div>
+</article>
+
+ </div>
+ </section>
+
+ </footer>
+</article>
+
+</main>
+<footer>
+ <div class="wrap">
+ <div class="foot-top">
+ <a class="foot-brand brand" href="/blog/">
+ <span class="brand-mark">MD</span>
+ <span class="brand-word">MUNDER DIFFLIN<span class="sep">/</span><span class="blog">BLOG</span></span>
+ </a>
+ <div class="foot-links">
+ <a href="/blog/">Latest</a>
+ <a href="/blog/topics/">Topics</a>
+ <a href="/blog/about/">About</a>
+ <a href="https://munderdiffl.in/blog/feed.xml">RSS</a>
+ <a href="https://github.com/chaitanyagiri/munder-difflin">GitHub</a>
+ <a href="https://munderdiffl.in">munderdiffl.in ↗</a>
+ </div>
+ </div>
+ <div class="foot-meta">
+ © 2026 Munder Difflin · Local-first · MIT-licensed ·
+ Built on <a href="https://munderdiffl.in">Electron, React, Pixi.js, xterm.js &amp; node-pty</a>.
+ Run an office of agents while you sleep.
+ </div>
+ </div>
+</footer>
+
+<script>
+ // sticky-nav border on scroll
+ (function () {
+ var nav = document.getElementById('nav');
+ if (!nav) return;
+ var onScroll = function () { nav.classList.toggle('scrolled', window.scrollY > 8); };
+ onScroll(); window.addEventListener('scroll', onScroll, { passive: true });
+ })();
+</script>
+
+</body>
+</html>
diff --git a/docs/blog/munder-difflin-faq/index.html b/docs/blog/munder-difflin-faq/index.html
new file mode 100644
index 00000000..df35e088
--- /dev/null
+++ b/docs/blog/munder-difflin-faq/index.html
@@ -0,0 +1,353 @@
+<!doctype html>
+<html lang="en">
+<head>
+<meta charset="UTF-8" />
+<meta name="viewport" content="width=device-width, initial-scale=1.0" />
+<title>Munder Difflin FAQ: Everything People Ask — Munder Difflin Blog</title>
+<meta name="description" content="Answers to the top Munder Difflin questions — what it is, is it free, does it run locally, which platforms, and how it differs from many terminals." />
+<link rel="canonical" href="https://munderdiffl.in/blog/munder-difflin-faq/" />
+
+<link rel="icon" type="image/png" href="https://munderdiffl.in/logo.png" />
+<link rel="apple-touch-icon" href="https://munderdiffl.in/logo.png" />
+<meta name="theme-color" content="#F5F2E8" />
+
+<!-- Open Graph -->
+<meta property="og:site_name" content="Munder Difflin Blog" />
+<meta property="og:type" content="article" />
+<meta property="og:title" content="Munder Difflin FAQ: Everything People Ask — Munder Difflin Blog" />
+<meta property="og:description" content="Answers to the top Munder Difflin questions — what it is, is it free, does it run locally, which platforms, and how it differs from many terminals." />
+<meta property="og:url" content="https://munderdiffl.in/blog/munder-difflin-faq/" />
+<meta property="og:image" content="https://munderdiffl.in/media/og.png" />
+<meta property="og:locale" content="en_US" />
+<meta property="article:published_time" content="2026-06-02T00:00:00.000Z" />
+<meta property="article:author" content="Chaitanya Giri" />
+<meta property="article:tag" content="Concepts" />
+<meta property="article:tag" content="FAQ" />
+<meta property="article:tag" content="Claude Code" />
+<meta property="article:tag" content="Multi-Agent" />
+
+
+<!-- Twitter -->
+<meta name="twitter:card" content="summary_large_image" />
+<meta name="twitter:title" content="Munder Difflin FAQ: Everything People Ask — Munder Difflin Blog" />
+<meta name="twitter:description" content="Answers to the top Munder Difflin questions — what it is, is it free, does it run locally, which platforms, and how it differs from many terminals." />
+<meta name="twitter:image" content="https://munderdiffl.in/media/og.png" />
+
+<link rel="alternate" type="application/atom+xml" title="Munder Difflin Blog" href="https://munderdiffl.in/blog/feed.xml" />
+<link rel="preconnect" href="https://fonts.googleapis.com" />
+<link rel="preconnect" href="https://fonts.gstatic.com" crossorigin />
+<link href="https://fonts.googleapis.com/css2?family=Geist:wght@400;500;600&family=JetBrains+Mono:wght@400;500;600;700&display=swap" rel="stylesheet" />
+<link rel="stylesheet" href="/blog/assets/blog.css" />
+
+<script type="application/ld+json">
+{
+ "@context": "https://schema.org",
+ "@type": "BlogPosting",
+ "headline": "Munder Difflin FAQ: Everything People Ask",
+ "description": "Answers to the top Munder Difflin questions — what it is, is it free, does it run locally, which platforms, and how it differs from many terminals.",
+ "image": ["https://munderdiffl.in/media/og.png"],
+ "datePublished": "2026-06-02T00:00:00.000Z",
+ "dateModified": "2026-06-02T00:00:00.000Z",
+ "author": { "@type": "Person", "name": "Chaitanya Giri" },
+ "publisher": {
+ "@type": "Organization",
+ "name": "Munder Difflin",
+ "logo": { "@type": "ImageObject", "url": "https://munderdiffl.in/logo.png" }
+ },
+ "mainEntityOfPage": { "@type": "WebPage", "@id": "https://munderdiffl.in/blog/munder-difflin-faq/" },
+ "keywords": "munder difflin app, munder difflin download, munder difflin claude code, is munder difflin free",
+ "articleSection": "Concepts",
+ "inLanguage": "en-US",
+ "url": "https://munderdiffl.in/blog/munder-difflin-faq/"
+}
+</script>
+<script type="application/ld+json">
+{
+ "@context": "https://schema.org",
+ "@type": "BreadcrumbList",
+ "itemListElement": [
+ { "@type": "ListItem", "position": 1, "name": "Home", "item": "https://munderdiffl.in/" },
+ { "@type": "ListItem", "position": 2, "name": "Blog", "item": "https://munderdiffl.in/blog/" },
+ { "@type": "ListItem", "position": 3, "name": "Munder Difflin FAQ: Everything People Ask", "item": "https://munderdiffl.in/blog/munder-difflin-faq/" }
+ ]
+}
+</script>
+
+<script type="application/ld+json">
+{
+ "@context": "https://schema.org",
+ "@type": "FAQPage",
+ "mainEntity": [
+ { "@type": "Question", "name": "What is Munder Difflin?", "acceptedAnswer": { "@type": "Answer", "text": "Munder Difflin is a local, open-source desktop app that turns the Claude Code terminals you already run into a self-coordinating hive of agents — with shared long-term memory, inter-agent messaging, and a GOD orchestrator you talk to." } },
+ { "@type": "Question", "name": "Is Munder Difflin free?", "acceptedAnswer": { "@type": "Answer", "text": "Yes. Munder Difflin is free and open source under the MIT license. You can download a build or run it from source — there's no paid tier to unlock the core." } },
+ { "@type": "Question", "name": "Does it run my data or code in the cloud?", "acceptedAnswer": { "@type": "Answer", "text": "No. Munder Difflin is local-first — the harness, agents, and memory all live on your own machine. Your Claude Code sessions talk to Anthropic the same way they already do; Munder Difflin itself doesn't ship your code anywhere." } },
+ { "@type": "Question", "name": "What platforms does Munder Difflin support?", "acceptedAnswer": { "@type": "Answer", "text": "macOS, Windows, and Linux. You can download a build or build it from source in a couple of commands." } },
+ { "@type": "Question", "name": "How is this different from running several Claude Code terminals myself?", "acceptedAnswer": { "@type": "Answer", "text": "Munder Difflin adds the coordination that loose terminals lack: shared long-term memory (MemPalace), inter-agent messaging, a GOD orchestrator that routes work, and a visual office floor — so the sessions act as one team instead of isolated windows that collide and forget." } },
+ { "@type": "Question", "name": "Do I need to know how to code to use it?", "acceptedAnswer": { "@type": "Answer", "text": "You should be comfortable with Claude Code and a terminal, since Munder Difflin coordinates Claude Code agents. But you steer the team in plain language by talking to the GOD orchestrator — you don't script the coordination yourself." } },
+ { "@type": "Question", "name": "What is MemPalace?", "acceptedAnswer": { "@type": "Answer", "text": "MemPalace is Munder Difflin's shared memory layer — a semantic store the whole hive reads and writes, mined automatically from each agent's plain-markdown notes, so agents recall relevant knowledge across sessions." } },
+ { "@type": "Question", "name": "What is the GOD orchestrator?", "acceptedAnswer": { "@type": "Answer", "text": "The GOD orchestrator is a coordinating agent you talk to in plain language. It decomposes your intent, routes work to the right agents, adjudicates routine decisions, and escalates only the genuinely critical ones to you." } },
+ { "@type": "Question", "name": "Can the agents talk to each other?", "acceptedAnswer": { "@type": "Answer", "text": "Yes. Each agent has a mailbox and a router delivers messages between them, so one agent can hand work or findings to another directly — without you relaying it." } },
+ { "@type": "Question", "name": "Does Munder Difflin work with my existing Claude Code setup, MCP servers, and skills?", "acceptedAnswer": { "@type": "Answer", "text": "Yes. It coordinates the Claude Code you already run, including your tools, MCP servers, and skills — it adds a coordination layer rather than replacing your setup." } },
+ { "@type": "Question", "name": "Is Munder Difflin affiliated with Dunder Mifflin or The Office?", "acceptedAnswer": { "@type": "Answer", "text": "No. The name is an affectionate parody — 'the world's best agents, the world's worst paper company.' It's an independent open-source project, not affiliated with NBC or The Office." } },
+ { "@type": "Question", "name": "Where do I download Munder Difflin?", "acceptedAnswer": { "@type": "Answer", "text": "From the install section on munderdiffl.in, which links to the latest release. It's free, open source, and available for macOS, Windows, and Linux." } }
+
+ ]
+}
+</script>
+
+
+</head>
+<body>
+<a class="skip-link" href="#main">Skip to content</a>
+<nav id="nav">
+ <a class="brand" href="/blog/" aria-label="Munder Difflin Blog home">
+ <span class="brand-mark">MD</span>
+ <span class="brand-word">MUNDER DIFFLIN<span class="sep">/</span><span class="blog">BLOG</span></span>
+ </a>
+ <span class="spacer"></span>
+ <div class="links">
+ <a href="/blog/">Latest</a>
+ <a href="/blog/topics/">Topics</a>
+ <a href="/blog/about/">About</a>
+ <a href="https://munderdiffl.in">↗ Product</a>
+ </div>
+ <div class="nav-actions">
+ <a class="btn sm" href="https://munderdiffl.in/blog/feed.xml" aria-label="RSS feed">⤵ RSS</a>
+ <a class="btn sm primary" href="https://munderdiffl.in/#install">⤓ Download</a>
+ </div>
+</nav>
+
+<main id="main">
+
+<article>
+ <header class="post-head wrap">
+ <nav class="crumbs" aria-label="Breadcrumb">
+ <a href="/blog/">Blog</a>
+ <span>/</span>
+ <a href="/blog/topics/concepts/">Concepts</a>
+ </nav>
+ <h1>Munder Difflin FAQ: Everything People Ask</h1>
+ <p class="dek">Answers to the top Munder Difflin questions — what it is, is it free, does it run locally, which platforms, and how it differs from many terminals.</p>
+ <div class="byline">
+ <span class="av" aria-hidden="true">CG</span>
+ <strong>Chaitanya Giri</strong>
+ <span class="dot" aria-hidden="true">·</span>
+ <time datetime="2026-06-02">Jun 2, 2026</time>
+ <span class="dot" aria-hidden="true">·</span>
+ <span>1 min read</span>
+ <span class="tag kind">Concepts</span>
+ </div>
+ </header>
+
+ <div class="post-wrap wrap">
+ <div class="prose">
+ <div class="callout tldr"><span class="ic">TL;DR</span><p><strong>Munder Difflin</strong> is a free,
+open-source (MIT), local-first desktop app that turns the Claude Code terminals you already run into a
+coordinated hive — shared memory, messaging, and a [GOD orchestrator](/#how) you talk to — on macOS,
+Windows, and Linux. The full answers to the questions people ask most are below.</p></div>
+<p>This page answers the questions we hear most about Munder Difflin, kept short and direct. If your
+question isn’t here, the <a href="https://github.com/chaitanyagiri/munder-difflin">GitHub repo</a> and the rest
+of <a href="/blog/">the blog</a> go deeper.</p>
+<h2 id="the-one-sentence-version" tabindex="-1">The one-sentence version <a class="anchor" href="#the-one-sentence-version" aria-hidden="true">#</a></h2>
+<p>Munder Difflin is a <a href="/blog/what-is-a-multi-agent-harness/">multi-agent harness</a> for Claude Code: it
+takes the agents you already run and makes them act like one team — they message each other, share
+long-term memory, and are routed by a coordinator you talk to in plain language, all visualized as a
+live office floor on your own machine.</p>
+<h2 id="still-deciding" tabindex="-1">Still deciding? <a class="anchor" href="#still-deciding" aria-hidden="true">#</a></h2>
+<p>If you’re comparing options, these go deeper than an FAQ can:</p>
+<ul>
+<li><a href="/blog/best-claude-code-multi-agent-tools/">The best tools to run multiple Claude Code agents</a> — the
+honest field roundup.</li>
+<li><a href="/blog/why-we-built-munder-difflin/">Why we built Munder Difflin</a> — the origin story and the problem
+it solves.</li>
+<li><a href="/blog/what-are-claude-code-agents/">What are Claude Code agents?</a> — the basics, if you’re new.</li>
+</ul>
+<hr>
+<p>The fastest way to answer “is this for me?” is to run it. <a href="/#install">Download Munder Difflin</a> — it’s
+free, open source, and local-first.</p>
+
+
+
+ <section class="faq" aria-label="Frequently asked questions">
+ <h2 id="faq">FAQ</h2>
+
+ <div class="qa">
+ <p class="q">What is Munder Difflin?</p>
+ <p class="a">Munder Difflin is a local, open-source desktop app that turns the Claude Code terminals you already run into a self-coordinating hive of agents — with shared long-term memory, inter-agent messaging, and a GOD orchestrator you talk to.</p>
+ </div>
+
+ <div class="qa">
+ <p class="q">Is Munder Difflin free?</p>
+ <p class="a">Yes. Munder Difflin is free and open source under the MIT license. You can download a build or run it from source — there&#39;s no paid tier to unlock the core.</p>
+ </div>
+
+ <div class="qa">
+ <p class="q">Does it run my data or code in the cloud?</p>
+ <p class="a">No. Munder Difflin is local-first — the harness, agents, and memory all live on your own machine. Your Claude Code sessions talk to Anthropic the same way they already do; Munder Difflin itself doesn&#39;t ship your code anywhere.</p>
+ </div>
+
+ <div class="qa">
+ <p class="q">What platforms does Munder Difflin support?</p>
+ <p class="a">macOS, Windows, and Linux. You can download a build or build it from source in a couple of commands.</p>
+ </div>
+
+ <div class="qa">
+ <p class="q">How is this different from running several Claude Code terminals myself?</p>
+ <p class="a">Munder Difflin adds the coordination that loose terminals lack: shared long-term memory (MemPalace), inter-agent messaging, a GOD orchestrator that routes work, and a visual office floor — so the sessions act as one team instead of isolated windows that collide and forget.</p>
+ </div>
+
+ <div class="qa">
+ <p class="q">Do I need to know how to code to use it?</p>
+ <p class="a">You should be comfortable with Claude Code and a terminal, since Munder Difflin coordinates Claude Code agents. But you steer the team in plain language by talking to the GOD orchestrator — you don&#39;t script the coordination yourself.</p>
+ </div>
+
+ <div class="qa">
+ <p class="q">What is MemPalace?</p>
+ <p class="a">MemPalace is Munder Difflin&#39;s shared memory layer — a semantic store the whole hive reads and writes, mined automatically from each agent&#39;s plain-markdown notes, so agents recall relevant knowledge across sessions.</p>
+ </div>
+
+ <div class="qa">
+ <p class="q">What is the GOD orchestrator?</p>
+ <p class="a">The GOD orchestrator is a coordinating agent you talk to in plain language. It decomposes your intent, routes work to the right agents, adjudicates routine decisions, and escalates only the genuinely critical ones to you.</p>
+ </div>
+
+ <div class="qa">
+ <p class="q">Can the agents talk to each other?</p>
+ <p class="a">Yes. Each agent has a mailbox and a router delivers messages between them, so one agent can hand work or findings to another directly — without you relaying it.</p>
+ </div>
+
+ <div class="qa">
+ <p class="q">Does Munder Difflin work with my existing Claude Code setup, MCP servers, and skills?</p>
+ <p class="a">Yes. It coordinates the Claude Code you already run, including your tools, MCP servers, and skills — it adds a coordination layer rather than replacing your setup.</p>
+ </div>
+
+ <div class="qa">
+ <p class="q">Is Munder Difflin affiliated with Dunder Mifflin or The Office?</p>
+ <p class="a">No. The name is an affectionate parody — &#39;the world&#39;s best agents, the world&#39;s worst paper company.&#39; It&#39;s an independent open-source project, not affiliated with NBC or The Office.</p>
+ </div>
+
+ <div class="qa">
+ <p class="q">Where do I download Munder Difflin?</p>
+ <p class="a">From the install section on munderdiffl.in, which links to the latest release. It&#39;s free, open source, and available for macOS, Windows, and Linux.</p>
+ </div>
+
+ </section>
+
+
+
+ <hr />
+ <div class="share">
+ <span class="lbl">Tags</span>
+ <a class="tag" href="/blog/tags/concepts/">Concepts</a><a class="tag" href="/blog/tags/faq/">FAQ</a><a class="tag" href="/blog/tags/claude-code/">Claude Code</a><a class="tag" href="/blog/tags/multi-agent/">Multi-Agent</a>
+ </div>
+
+ </div>
+
+
+ </div>
+
+ <footer class="post-foot wrap"><div class="prevnext">
+ <a class="pn prev" href="/blog/run-an-office-of-ai-agents/"><span class="k">← Older</span><span class="t">Run an Office of AI Agents While You Sleep</span></a>
+ <a class="pn next" href="/blog/how-to-choose-a-multi-agent-tool/"><span class="k">Newer →</span><span class="t">How to Choose a Multi-Agent Coding Tool: A Buyer&#39;s Checklist</span></a>
+ </div>
+ <section class="related">
+ <h2>Related in Concepts</h2>
+ <div class="post-grid">
+ <article class="card">
+ <a class="thumb t-concepts" href="/blog/ai-agent-glossary/" aria-hidden="true" tabindex="-1">
+ <span>CONCEPTS</span>
+ </a>
+ <div class="body">
+ <div class="meta">
+ <time datetime="2026-06-02">Jun 2, 2026</time>
+ <span class="dot" aria-hidden="true"></span>
+ <span>3 min</span>
+ </div>
+ <h3><a href="/blog/ai-agent-glossary/">The AI Coding Agent Glossary: Harness, Orchestrator, Hive, Subagent</a></h3>
+ <p class="dek">Plain-English definitions of the AI coding agent terms everyone trips over — harness, orchestrator, hive, subagent, agent memory — each in one line.</p>
+ <div class="foot">
+ <span class="tag kind">Concepts</span>
+ <a class="more" href="/blog/ai-agent-glossary/" aria-label="Read: The AI Coding Agent Glossary: Harness, Orchestrator, Hive, Subagent">Read →</a>
+ </div>
+ </div>
+</article>
+<article class="card">
+ <a class="thumb t-concepts" href="/blog/what-are-claude-code-agents/" aria-hidden="true" tabindex="-1">
+ <span>CONCEPTS</span>
+ </a>
+ <div class="body">
+ <div class="meta">
+ <time datetime="2026-06-02">Jun 2, 2026</time>
+ <span class="dot" aria-hidden="true"></span>
+ <span>3 min</span>
+ </div>
+ <h3><a href="/blog/what-are-claude-code-agents/">What Are Claude Code Agents? And How to Use Many at Once</a></h3>
+ <p class="dek">Claude Code agents explained in plain English — what an agent actually is, how subagents differ, and the leap from one agent to a coordinated team.</p>
+ <div class="foot">
+ <span class="tag kind">Concepts</span>
+ <a class="more" href="/blog/what-are-claude-code-agents/" aria-label="Read: What Are Claude Code Agents? And How to Use Many at Once">Read →</a>
+ </div>
+ </div>
+</article>
+<article class="card">
+ <a class="thumb t-concepts" href="/blog/what-is-a-multi-agent-harness/" aria-hidden="true" tabindex="-1">
+ <span>CONCEPTS</span>
+ </a>
+ <div class="body">
+ <div class="meta">
+ <time datetime="2026-05-22">May 22, 2026</time>
+ <span class="dot" aria-hidden="true"></span>
+ <span>2 min</span>
+ </div>
+ <h3><a href="/blog/what-is-a-multi-agent-harness/">What Is a Multi-Agent Harness? (Plain-English Guide)</a></h3>
+ <p class="dek">A multi-agent harness coordinates several AI coding agents into one team — here&#39;s what that means, and how it differs from a single agent or a framework.</p>
+ <div class="foot">
+ <span class="tag kind">Concepts</span>
+ <a class="more" href="/blog/what-is-a-multi-agent-harness/" aria-label="Read: What Is a Multi-Agent Harness? (Plain-English Guide)">Read →</a>
+ </div>
+ </div>
+</article>
+
+ </div>
+ </section>
+
+ </footer>
+</article>
+
+</main>
+<footer>
+ <div class="wrap">
+ <div class="foot-top">
+ <a class="foot-brand brand" href="/blog/">
+ <span class="brand-mark">MD</span>
+ <span class="brand-word">MUNDER DIFFLIN<span class="sep">/</span><span class="blog">BLOG</span></span>
+ </a>
+ <div class="foot-links">
+ <a href="/blog/">Latest</a>
+ <a href="/blog/topics/">Topics</a>
+ <a href="/blog/about/">About</a>
+ <a href="https://munderdiffl.in/blog/feed.xml">RSS</a>
+ <a href="https://github.com/chaitanyagiri/munder-difflin">GitHub</a>
+ <a href="https://munderdiffl.in">munderdiffl.in ↗</a>
+ </div>
+ </div>
+ <div class="foot-meta">
+ © 2026 Munder Difflin · Local-first · MIT-licensed ·
+ Built on <a href="https://munderdiffl.in">Electron, React, Pixi.js, xterm.js &amp; node-pty</a>.
+ Run an office of agents while you sleep.
+ </div>
+ </div>
+</footer>
+
+<script>
+ // sticky-nav border on scroll
+ (function () {
+ var nav = document.getElementById('nav');
+ if (!nav) return;
+ var onScroll = function () { nav.classList.toggle('scrolled', window.scrollY > 8); };
+ onScroll(); window.addEventListener('scroll', onScroll, { passive: true });
+ })();
+</script>
+
+</body>
+</html>
diff --git a/docs/blog/node-pty-electron-real-terminals/index.html b/docs/blog/node-pty-electron-real-terminals/index.html
new file mode 100644
index 00000000..4625fbde
--- /dev/null
+++ b/docs/blog/node-pty-electron-real-terminals/index.html
@@ -0,0 +1,423 @@
+<!doctype html>
+<html lang="en">
+<head>
+<meta charset="UTF-8" />
+<meta name="viewport" content="width=device-width, initial-scale=1.0" />
+<title>Real Terminals in Electron with node-pty — Munder Difflin Blog</title>
+<meta name="description" content="How to run byte-for-byte authentic shells inside Electron with node-pty: the native-rebuild gotcha, the macOS PATH trap, and streaming PTY output over IPC." />
+<link rel="canonical" href="https://munderdiffl.in/blog/node-pty-electron-real-terminals/" />
+
+<link rel="icon" type="image/png" href="https://munderdiffl.in/logo.png" />
+<link rel="apple-touch-icon" href="https://munderdiffl.in/logo.png" />
+<meta name="theme-color" content="#F5F2E8" />
+
+<!-- Open Graph -->
+<meta property="og:site_name" content="Munder Difflin Blog" />
+<meta property="og:type" content="article" />
+<meta property="og:title" content="Real Terminals in Electron with node-pty — Munder Difflin Blog" />
+<meta property="og:description" content="How to run byte-for-byte authentic shells inside Electron with node-pty: the native-rebuild gotcha, the macOS PATH trap, and streaming PTY output over IPC." />
+<meta property="og:url" content="https://munderdiffl.in/blog/node-pty-electron-real-terminals/" />
+<meta property="og:image" content="https://munderdiffl.in/media/og.png" />
+<meta property="og:locale" content="en_US" />
+<meta property="article:published_time" content="2026-06-03T00:00:00.000Z" />
+<meta property="article:author" content="Chaitanya Giri" />
+<meta property="article:tag" content="Internals" />
+<meta property="article:tag" content="Electron" />
+<meta property="article:tag" content="node-pty" />
+<meta property="article:tag" content="Terminals" />
+
+
+<!-- Twitter -->
+<meta name="twitter:card" content="summary_large_image" />
+<meta name="twitter:title" content="Real Terminals in Electron with node-pty — Munder Difflin Blog" />
+<meta name="twitter:description" content="How to run byte-for-byte authentic shells inside Electron with node-pty: the native-rebuild gotcha, the macOS PATH trap, and streaming PTY output over IPC." />
+<meta name="twitter:image" content="https://munderdiffl.in/media/og.png" />
+
+<link rel="alternate" type="application/atom+xml" title="Munder Difflin Blog" href="https://munderdiffl.in/blog/feed.xml" />
+<link rel="preconnect" href="https://fonts.googleapis.com" />
+<link rel="preconnect" href="https://fonts.gstatic.com" crossorigin />
+<link href="https://fonts.googleapis.com/css2?family=Geist:wght@400;500;600&family=JetBrains+Mono:wght@400;500;600;700&display=swap" rel="stylesheet" />
+<link rel="stylesheet" href="/blog/assets/blog.css" />
+
+<script type="application/ld+json">
+{
+ "@context": "https://schema.org",
+ "@type": "BlogPosting",
+ "headline": "Real Terminals in Electron with node-pty",
+ "description": "How to run byte-for-byte authentic shells inside Electron with node-pty: the native-rebuild gotcha, the macOS PATH trap, and streaming PTY output over IPC.",
+ "image": ["https://munderdiffl.in/media/og.png"],
+ "datePublished": "2026-06-03T00:00:00.000Z",
+ "dateModified": "2026-06-03T00:00:00.000Z",
+ "author": { "@type": "Person", "name": "Chaitanya Giri" },
+ "publisher": {
+ "@type": "Organization",
+ "name": "Munder Difflin",
+ "logo": { "@type": "ImageObject", "url": "https://munderdiffl.in/logo.png" }
+ },
+ "mainEntityOfPage": { "@type": "WebPage", "@id": "https://munderdiffl.in/blog/node-pty-electron-real-terminals/" },
+ "keywords": "node-pty electron, node-pty, pseudo terminal, electron terminal app",
+ "articleSection": "Internals",
+ "inLanguage": "en-US",
+ "url": "https://munderdiffl.in/blog/node-pty-electron-real-terminals/"
+}
+</script>
+<script type="application/ld+json">
+{
+ "@context": "https://schema.org",
+ "@type": "BreadcrumbList",
+ "itemListElement": [
+ { "@type": "ListItem", "position": 1, "name": "Home", "item": "https://munderdiffl.in/" },
+ { "@type": "ListItem", "position": 2, "name": "Blog", "item": "https://munderdiffl.in/blog/" },
+ { "@type": "ListItem", "position": 3, "name": "Real Terminals in Electron with node-pty", "item": "https://munderdiffl.in/blog/node-pty-electron-real-terminals/" }
+ ]
+}
+</script>
+
+<script type="application/ld+json">
+{
+ "@context": "https://schema.org",
+ "@type": "FAQPage",
+ "mainEntity": [
+ { "@type": "Question", "name": "Why use node-pty instead of child_process for a terminal app?", "acceptedAnswer": { "@type": "Answer", "text": "child_process gives you pipes, not a terminal. Interactive programs detect that they're not attached to a TTY and change behavior — no colors, no prompts, broken full-screen UIs. node-pty allocates a real pseudo-terminal so programs behave exactly as they would in a normal shell." } },
+ { "@type": "Question", "name": "What's the native-rebuild gotcha with node-pty in Electron?", "acceptedAnswer": { "@type": "Answer", "text": "node-pty is a native addon compiled against a specific Node ABI. Electron ships its own Node, so the npm-installed binary won't load. You have to rebuild node-pty against Electron's ABI — typically with electron-rebuild in a postinstall step." } },
+ { "@type": "Question", "name": "Why can't my Electron app find `claude` or other commands?", "acceptedAnswer": { "@type": "Answer", "text": "On macOS, a GUI-launched Electron app doesn't inherit your interactive shell's PATH, so commands installed by nvm, asdf, or Homebrew aren't found. Resolve the command against an interactive login shell, or fall back to known install locations." } }
+
+ ]
+}
+</script>
+
+
+</head>
+<body>
+<a class="skip-link" href="#main">Skip to content</a>
+<nav id="nav">
+ <a class="brand" href="/blog/" aria-label="Munder Difflin Blog home">
+ <span class="brand-mark">MD</span>
+ <span class="brand-word">MUNDER DIFFLIN<span class="sep">/</span><span class="blog">BLOG</span></span>
+ </a>
+ <span class="spacer"></span>
+ <div class="links">
+ <a href="/blog/">Latest</a>
+ <a href="/blog/topics/">Topics</a>
+ <a href="/blog/about/">About</a>
+ <a href="https://munderdiffl.in">↗ Product</a>
+ </div>
+ <div class="nav-actions">
+ <a class="btn sm" href="https://munderdiffl.in/blog/feed.xml" aria-label="RSS feed">⤵ RSS</a>
+ <a class="btn sm primary" href="https://munderdiffl.in/#install">⤓ Download</a>
+ </div>
+</nav>
+
+<main id="main">
+
+<article>
+ <header class="post-head wrap">
+ <nav class="crumbs" aria-label="Breadcrumb">
+ <a href="/blog/">Blog</a>
+ <span>/</span>
+ <a href="/blog/topics/internals/">Internals</a>
+ </nav>
+ <h1>Real Terminals in Electron with node-pty</h1>
+ <p class="dek">How to run byte-for-byte authentic shells inside Electron with node-pty: the native-rebuild gotcha, the macOS PATH trap, and streaming PTY output over IPC.</p>
+ <div class="byline">
+ <span class="av" aria-hidden="true">CG</span>
+ <strong>Chaitanya Giri</strong>
+ <span class="dot" aria-hidden="true">·</span>
+ <time datetime="2026-06-03">Jun 3, 2026</time>
+ <span class="dot" aria-hidden="true">·</span>
+ <span>7 min read</span>
+ <span class="tag kind">Internals</span>
+ </div>
+ </header>
+
+ <div class="post-wrap wrap">
+ <div class="prose">
+ <div class="callout tldr"><span class="ic">TL;DR</span><p>To run real shells inside Electron, use
+<strong>node-pty</strong> — it allocates a genuine pseudo-terminal so programs behave byte-for-byte
+like they do in a normal terminal. The three things that bite everyone:
+<strong>rebuild the native addon against Electron's ABI</strong> (electron-rebuild),
+<strong>resolve commands against an interactive shell PATH</strong> (GUI apps don't inherit it on
+macOS), and <strong>stream output over IPC safely</strong>, guarding sends during window teardown.</p></div>
+<p>If you want to embed a working terminal in a desktop app — a dev tool, an IDE, an agent harness that
+runs <code>claude</code> sessions — <code>node-pty</code> is the foundation. But “embed a terminal” hides three sharp edges
+that every Electron + node-pty project hits. This post is the field guide: what a PTY is, why you need
+one, and the gotchas that turn a one-line <code>spawn</code> into a day of debugging.</p>
+<h2 id="why-a-pseudo-terminal-not-a-pipe" tabindex="-1">Why a pseudo-terminal, not a pipe <a class="anchor" href="#why-a-pseudo-terminal-not-a-pipe" aria-hidden="true">#</a></h2>
+<p>The instinct is to reach for Node’s <code>child_process.spawn</code> and pipe stdout into a <code>&lt;div&gt;</code>. It seems to
+work — until you run anything interactive. Here’s why it breaks.</p>
+<p>Programs check whether their output is attached to a <strong>TTY</strong> (a terminal). When they detect a plain
+pipe instead, they assume “I’m being scripted” and change behavior:</p>
+<ul>
+<li>colors and styling switch off,</li>
+<li>interactive prompts vanish or hang,</li>
+<li>full-screen TUIs (editors, <code>top</code>, anything using the alternate screen buffer) don’t render at all,</li>
+<li>line editing, arrow keys, and signals like Ctrl-C don’t behave.</li>
+</ul>
+<p>A <strong>pseudo-terminal (PTY)</strong> is the fix. It’s a kernel feature that presents a real terminal interface
+to the child process while handing the bytes to your code on the other end. The program thinks it’s
+talking to an honest terminal — because it is — so it behaves exactly as it would in your shell.
+<code>node-pty</code> is the Node binding that allocates one and gives you <code>write</code>, <code>resize</code>, <code>onData</code>, and
+<code>onExit</code>.</p>
+<pre class="language-ts"><code class="language-ts"><span class="token keyword">import</span> <span class="token operator">*</span> <span class="token keyword">as</span> pty <span class="token keyword">from</span> <span class="token string">'node-pty'</span><span class="token punctuation">;</span>
+
+<span class="token keyword">const</span> proc <span class="token operator">=</span> pty<span class="token punctuation">.</span><span class="token function">spawn</span><span class="token punctuation">(</span><span class="token string">'claude'</span><span class="token punctuation">,</span> <span class="token punctuation">[</span><span class="token punctuation">]</span><span class="token punctuation">,</span> <span class="token punctuation">{</span>
+ name<span class="token operator">:</span> <span class="token string">'xterm-256color'</span><span class="token punctuation">,</span>
+ cols<span class="token operator">:</span> <span class="token number">100</span><span class="token punctuation">,</span>
+ rows<span class="token operator">:</span> <span class="token number">30</span><span class="token punctuation">,</span>
+ cwd<span class="token operator">:</span> <span class="token string">'/path/to/project'</span><span class="token punctuation">,</span>
+ env<span class="token operator">:</span> <span class="token punctuation">{</span> <span class="token operator">...</span>process<span class="token punctuation">.</span>env<span class="token punctuation">,</span> <span class="token constant">TERM</span><span class="token operator">:</span> <span class="token string">'xterm-256color'</span><span class="token punctuation">,</span> <span class="token constant">COLORTERM</span><span class="token operator">:</span> <span class="token string">'truecolor'</span> <span class="token punctuation">}</span>
+<span class="token punctuation">}</span><span class="token punctuation">)</span><span class="token punctuation">;</span>
+
+proc<span class="token punctuation">.</span><span class="token function">onData</span><span class="token punctuation">(</span><span class="token punctuation">(</span>data<span class="token punctuation">)</span> <span class="token operator">=></span> <span class="token function">sendToRenderer</span><span class="token punctuation">(</span>data<span class="token punctuation">)</span><span class="token punctuation">)</span><span class="token punctuation">;</span> <span class="token comment">// bytes from the shell</span>
+proc<span class="token punctuation">.</span><span class="token function">onExit</span><span class="token punctuation">(</span><span class="token punctuation">(</span><span class="token punctuation">{</span> exitCode<span class="token punctuation">,</span> signal <span class="token punctuation">}</span><span class="token punctuation">)</span> <span class="token operator">=></span> <span class="token function">cleanup</span><span class="token punctuation">(</span>exitCode<span class="token punctuation">,</span> signal<span class="token punctuation">)</span><span class="token punctuation">)</span><span class="token punctuation">;</span></code></pre>
+<p>Note <code>name: 'xterm-256color'</code> and the <code>TERM</code>/<code>COLORTERM</code> env — they tell the child what terminal it’s
+talking to, which is what unlocks 24-bit color. Set them, or you’ll spend an hour wondering why output
+is monochrome.</p>
+<h2 id="gotcha-1-the-native-rebuild-trap" tabindex="-1">Gotcha 1 — The native-rebuild trap <a class="anchor" href="#gotcha-1-the-native-rebuild-trap" aria-hidden="true">#</a></h2>
+<p>This is the one that stops people cold on first install. <code>node-pty</code> is a <strong>native addon</strong>: it’s
+compiled C++ that links against a specific Node ABI. You <code>npm install node-pty</code>, it builds against your
+system Node, and everything looks fine — until you load it inside Electron and get:</p>
+<pre><code>Error: The module was compiled against a different Node.js ABI version
+</code></pre>
+<p>Electron bundles <strong>its own</strong> Node, with a different ABI than the one npm built against. The binary that
+works in a plain <code>node</code> REPL won’t load in Electron. The fix is to rebuild the addon against Electron’s
+ABI, which is what <code>electron-rebuild</code> does. Wire it into a postinstall script so it happens
+automatically:</p>
+<pre class="language-jsonc"><code class="language-jsonc">{
+ "scripts": {
+ "postinstall": "electron-rebuild -f -w node-pty"
+ }
+}</code></pre>
+<p>The <code>-w node-pty</code> scopes the rebuild to just that module (faster than rebuilding everything), and <code>-f</code>
+forces it. After this runs, the addon loads cleanly inside Electron. Forget it, and the app crashes on
+launch with an ABI error that looks scarier than it is.</p>
+<h2 id="gotcha-2-the-macos-path-trap" tabindex="-1">Gotcha 2 — The macOS PATH trap <a class="anchor" href="#gotcha-2-the-macos-path-trap" aria-hidden="true">#</a></h2>
+<p>You ship the app, double-click it, and your terminal can’t find <code>claude</code> — or <code>node</code>, or <code>git</code>, or
+whatever you installed with nvm, asdf, or Homebrew. Run the same command in a real terminal and it
+works fine. What gives?</p>
+<p>On macOS, an app launched from the <strong>GUI</strong> (Finder, Dock) doesn’t inherit your interactive shell’s
+environment. Your <code>PATH</code> additions live in <code>.zshrc</code>/<code>.zprofile</code>, which a login shell reads — but the
+GUI process never started a login shell, so it gets a bare system <code>PATH</code> that’s missing every
+user-installed tool.</p>
+<p>There are two halves to fixing this:</p>
+<p><strong>Resolve the command’s full path.</strong> Don’t trust a bare command name to be found. Ask an interactive
+login shell where it lives, then fall back to common install locations:</p>
+<pre class="language-ts"><code class="language-ts"><span class="token keyword">function</span> <span class="token function">resolveCommand</span><span class="token punctuation">(</span>command<span class="token operator">:</span> <span class="token builtin">string</span><span class="token punctuation">)</span><span class="token operator">:</span> <span class="token builtin">string</span> <span class="token punctuation">{</span>
+ <span class="token keyword">if</span> <span class="token punctuation">(</span>command<span class="token punctuation">.</span><span class="token function">includes</span><span class="token punctuation">(</span><span class="token string">'/'</span><span class="token punctuation">)</span><span class="token punctuation">)</span> <span class="token keyword">return</span> command<span class="token punctuation">;</span> <span class="token comment">// already absolute</span>
+ <span class="token comment">// Ask the user's login shell — picks up nvm/asdf/brew.</span>
+ <span class="token keyword">const</span> res <span class="token operator">=</span> <span class="token function">spawnSync</span><span class="token punctuation">(</span>process<span class="token punctuation">.</span>env<span class="token punctuation">.</span><span class="token constant">SHELL</span> <span class="token operator">??</span> <span class="token string">'/bin/zsh'</span><span class="token punctuation">,</span> <span class="token punctuation">[</span><span class="token string">'-ilc'</span><span class="token punctuation">,</span> <span class="token template-string"><span class="token template-punctuation string">`</span><span class="token string">which </span><span class="token interpolation"><span class="token interpolation-punctuation punctuation">${</span>command<span class="token interpolation-punctuation punctuation">}</span></span><span class="token template-punctuation string">`</span></span><span class="token punctuation">]</span><span class="token punctuation">,</span> <span class="token punctuation">{</span>
+ encoding<span class="token operator">:</span> <span class="token string">'utf8'</span><span class="token punctuation">,</span> timeout<span class="token operator">:</span> <span class="token number">3000</span>
+ <span class="token punctuation">}</span><span class="token punctuation">)</span><span class="token punctuation">;</span>
+ <span class="token keyword">const</span> found <span class="token operator">=</span> res<span class="token punctuation">.</span>stdout<span class="token punctuation">.</span><span class="token function">trim</span><span class="token punctuation">(</span><span class="token punctuation">)</span><span class="token punctuation">.</span><span class="token function">split</span><span class="token punctuation">(</span><span class="token string">'\n'</span><span class="token punctuation">)</span><span class="token punctuation">.</span><span class="token function">pop</span><span class="token punctuation">(</span><span class="token punctuation">)</span><span class="token punctuation">;</span>
+ <span class="token keyword">if</span> <span class="token punctuation">(</span>found <span class="token operator">&amp;&amp;</span> <span class="token function">existsSync</span><span class="token punctuation">(</span>found<span class="token punctuation">)</span><span class="token punctuation">)</span> <span class="token keyword">return</span> found<span class="token punctuation">;</span>
+ <span class="token comment">// Fall back to known locations.</span>
+ <span class="token keyword">for</span> <span class="token punctuation">(</span><span class="token keyword">const</span> c <span class="token keyword">of</span> <span class="token punctuation">[</span>
+ <span class="token template-string"><span class="token template-punctuation string">`</span><span class="token string">/opt/homebrew/bin/</span><span class="token interpolation"><span class="token interpolation-punctuation punctuation">${</span>command<span class="token interpolation-punctuation punctuation">}</span></span><span class="token template-punctuation string">`</span></span><span class="token punctuation">,</span>
+ <span class="token template-string"><span class="token template-punctuation string">`</span><span class="token string">/usr/local/bin/</span><span class="token interpolation"><span class="token interpolation-punctuation punctuation">${</span>command<span class="token interpolation-punctuation punctuation">}</span></span><span class="token template-punctuation string">`</span></span><span class="token punctuation">,</span>
+ <span class="token template-string"><span class="token template-punctuation string">`</span><span class="token interpolation"><span class="token interpolation-punctuation punctuation">${</span>process<span class="token punctuation">.</span>env<span class="token punctuation">.</span><span class="token constant">HOME</span><span class="token interpolation-punctuation punctuation">}</span></span><span class="token string">/.local/bin/</span><span class="token interpolation"><span class="token interpolation-punctuation punctuation">${</span>command<span class="token interpolation-punctuation punctuation">}</span></span><span class="token template-punctuation string">`</span></span>
+ <span class="token punctuation">]</span><span class="token punctuation">)</span> <span class="token keyword">if</span> <span class="token punctuation">(</span><span class="token function">existsSync</span><span class="token punctuation">(</span>c<span class="token punctuation">)</span><span class="token punctuation">)</span> <span class="token keyword">return</span> c<span class="token punctuation">;</span>
+ <span class="token keyword">return</span> command<span class="token punctuation">;</span> <span class="token comment">// last resort — let it ENOENT</span>
+<span class="token punctuation">}</span></code></pre>
+<p>The <code>-ilc</code> flags matter: <code>-i</code> interactive, <code>-l</code> login, <code>-c</code> run a command — that combination loads the
+same startup files your terminal does, so <code>which</code> finds what you’d expect.</p>
+<p><strong>Give the child a real PATH too.</strong> Even with the binary resolved, the spawned shell needs a full
+<code>PATH</code> so <em>its</em> subprocesses resolve (the <code>claude</code> session that shells out to <code>git</code>, say). Compute the
+login shell’s <code>PATH</code> once and pass it into the PTY’s env:</p>
+<pre class="language-ts"><code class="language-ts"><span class="token keyword">const</span> userPath <span class="token operator">=</span> <span class="token function">spawnSync</span><span class="token punctuation">(</span>process<span class="token punctuation">.</span>env<span class="token punctuation">.</span><span class="token constant">SHELL</span> <span class="token operator">??</span> <span class="token string">'/bin/zsh'</span><span class="token punctuation">,</span> <span class="token punctuation">[</span><span class="token string">'-ilc'</span><span class="token punctuation">,</span> <span class="token string">'echo -n "$PATH"'</span><span class="token punctuation">]</span><span class="token punctuation">,</span>
+ <span class="token punctuation">{</span> encoding<span class="token operator">:</span> <span class="token string">'utf8'</span><span class="token punctuation">,</span> timeout<span class="token operator">:</span> <span class="token number">3000</span> <span class="token punctuation">}</span><span class="token punctuation">)</span><span class="token punctuation">.</span>stdout<span class="token punctuation">.</span><span class="token function">trim</span><span class="token punctuation">(</span><span class="token punctuation">)</span> <span class="token operator">||</span> process<span class="token punctuation">.</span>env<span class="token punctuation">.</span><span class="token constant">PATH</span><span class="token punctuation">;</span></code></pre>
+<p>Skip this and your terminal will run, but anything it tries to launch will mysteriously not be found.</p>
+<h2 id="gotcha-3-streaming-over-ipc-without-crashing-on-quit" tabindex="-1">Gotcha 3 — Streaming over IPC without crashing on quit <a class="anchor" href="#gotcha-3-streaming-over-ipc-without-crashing-on-quit" aria-hidden="true">#</a></h2>
+<p>In Electron, the PTY lives in the <strong>main</strong> process and the UI lives in the <strong>renderer</strong>. So PTY output
+has to cross the process boundary over IPC. The pattern is straightforward — forward each <code>onData</code>
+chunk on a per-session channel:</p>
+<pre class="language-ts"><code class="language-ts">proc<span class="token punctuation">.</span><span class="token function">onData</span><span class="token punctuation">(</span><span class="token punctuation">(</span>data<span class="token punctuation">)</span> <span class="token operator">=></span> webContents<span class="token punctuation">.</span><span class="token function">send</span><span class="token punctuation">(</span><span class="token template-string"><span class="token template-punctuation string">`</span><span class="token string">pty:data:</span><span class="token interpolation"><span class="token interpolation-punctuation punctuation">${</span>id<span class="token interpolation-punctuation punctuation">}</span></span><span class="token template-punctuation string">`</span></span><span class="token punctuation">,</span> data<span class="token punctuation">)</span><span class="token punctuation">)</span><span class="token punctuation">;</span>
+proc<span class="token punctuation">.</span><span class="token function">onExit</span><span class="token punctuation">(</span><span class="token punctuation">(</span><span class="token punctuation">{</span> exitCode<span class="token punctuation">,</span> signal <span class="token punctuation">}</span><span class="token punctuation">)</span> <span class="token operator">=></span> webContents<span class="token punctuation">.</span><span class="token function">send</span><span class="token punctuation">(</span><span class="token template-string"><span class="token template-punctuation string">`</span><span class="token string">pty:exit:</span><span class="token interpolation"><span class="token interpolation-punctuation punctuation">${</span>id<span class="token interpolation-punctuation punctuation">}</span></span><span class="token template-punctuation string">`</span></span><span class="token punctuation">,</span> <span class="token punctuation">{</span> exitCode<span class="token punctuation">,</span> signal <span class="token punctuation">}</span><span class="token punctuation">)</span><span class="token punctuation">)</span><span class="token punctuation">;</span></code></pre>
+<p>But there’s a teardown hazard that produces an ugly crash dialog. During app quit, killing a PTY fires
+<code>onExit</code> <strong>asynchronously</strong>. By the time that callback runs, the window may already be destroyed — and
+calling <code>.send()</code> on a destroyed <code>webContents</code> throws <code>&quot;Object has been destroyed&quot;</code>, which surfaces as
+a main-process crash. The guard is simple but essential: check the target is alive before every send.</p>
+<pre class="language-ts"><code class="language-ts"><span class="token keyword">function</span> <span class="token function">safeSend</span><span class="token punctuation">(</span>channel<span class="token operator">:</span> <span class="token builtin">string</span><span class="token punctuation">,</span> payload<span class="token operator">:</span> <span class="token builtin">unknown</span><span class="token punctuation">)</span> <span class="token punctuation">{</span>
+ <span class="token keyword">const</span> wc <span class="token operator">=</span> <span class="token keyword">this</span><span class="token punctuation">.</span>webContents<span class="token punctuation">;</span>
+ <span class="token keyword">if</span> <span class="token punctuation">(</span><span class="token operator">!</span>wc <span class="token operator">||</span> wc<span class="token punctuation">.</span><span class="token function">isDestroyed</span><span class="token punctuation">(</span><span class="token punctuation">)</span><span class="token punctuation">)</span> <span class="token keyword">return</span><span class="token punctuation">;</span> <span class="token comment">// window torn down — drop it</span>
+ <span class="token keyword">try</span> <span class="token punctuation">{</span> wc<span class="token punctuation">.</span><span class="token function">send</span><span class="token punctuation">(</span>channel<span class="token punctuation">,</span> payload<span class="token punctuation">)</span><span class="token punctuation">;</span> <span class="token punctuation">}</span> <span class="token keyword">catch</span> <span class="token punctuation">{</span> <span class="token comment">/* raced during teardown */</span> <span class="token punctuation">}</span>
+<span class="token punctuation">}</span></code></pre>
+<p>Route every PTY-to-renderer message through that, and quitting the app is clean instead of a crash
+report.</p>
+<h2 id="managing-many-sessions" tabindex="-1">Managing many sessions <a class="anchor" href="#managing-many-sessions" aria-hidden="true">#</a></h2>
+<p>A real app runs more than one terminal, so wrap all of this in a manager keyed by session id —
+<code>spawn</code>, <code>write</code>, <code>resize</code>, <code>kill</code>, <code>list</code>, <code>killAll</code>. Two details pay off at scale:</p>
+<ul>
+<li><strong>Resize is a real operation.</strong> When the UI panel changes size, recompute cols/rows and call
+<code>proc.resize(cols, rows)</code>, or full-screen TUIs will wrap wrong. The renderer side of this — measuring
+the grid and writing keystrokes back — is its own craft, covered in
+<a href="/blog/building-a-terminal-ui-xterm-node-pty/">building a terminal UI with xterm.js and node-pty</a>.</li>
+<li><strong>Clean up on exit.</strong> Remove a session from your map in <code>onExit</code>, and on app quit kill everything so
+you don’t leak child processes.</li>
+</ul>
+<h2 id="why-this-matters-for-an-agent-harness" tabindex="-1">Why this matters for an agent harness <a class="anchor" href="#why-this-matters-for-an-agent-harness" aria-hidden="true">#</a></h2>
+<p>Everything above is in service of a simple idea: if your “agents” are real <code>claude</code> CLI sessions, they
+deserve real terminals. A PTY makes each agent byte-for-byte authentic — same colors, same prompts,
+same behavior as if you’d typed <code>claude</code> yourself. That authenticity is the whole premise of a
+<a href="https://munderdiffl.in/#what">multi-agent harness</a>: you’re not reimplementing the agent, you’re
+running the genuine article and coordinating many of them. And because every session is a real process,
+the same single-writer discipline that keeps their shared state safe — see
+<a href="/blog/single-committer-git-pattern/">the single-committer git pattern</a> — applies cleanly on top.</p>
+<h2 id="faq" tabindex="-1">FAQ <a class="anchor" href="#faq" aria-hidden="true">#</a></h2>
+<p><strong>Does node-pty work on Windows?</strong> Yes — it uses the ConPTY API on modern Windows (and winpty as a
+fallback on older versions). The PATH gotcha is macOS-specific; the native-rebuild gotcha applies
+everywhere.</p>
+<p><strong>Can I avoid the native addon entirely?</strong> Not if you want a true TTY. Pure-JS “terminals” that pipe
+<code>child_process</code> hit exactly the non-TTY problems described up top. node-pty exists because a real
+pseudo-terminal needs a kernel-level allocation.</p>
+<hr>
+<p>Munder Difflin runs every Claude Code agent in a real node-pty terminal — authentic shells, streamed
+to a live UI, coordinated as a hive. <a href="https://munderdiffl.in/#install">Download Munder Difflin</a> to see
+real terminals driving real agents; it’s free and open source.</p>
+
+
+
+ <section class="faq" aria-label="Frequently asked questions">
+ <h2 id="faq">FAQ</h2>
+
+ <div class="qa">
+ <p class="q">Why use node-pty instead of child_process for a terminal app?</p>
+ <p class="a">child_process gives you pipes, not a terminal. Interactive programs detect that they&#39;re not attached to a TTY and change behavior — no colors, no prompts, broken full-screen UIs. node-pty allocates a real pseudo-terminal so programs behave exactly as they would in a normal shell.</p>
+ </div>
+
+ <div class="qa">
+ <p class="q">What&#39;s the native-rebuild gotcha with node-pty in Electron?</p>
+ <p class="a">node-pty is a native addon compiled against a specific Node ABI. Electron ships its own Node, so the npm-installed binary won&#39;t load. You have to rebuild node-pty against Electron&#39;s ABI — typically with electron-rebuild in a postinstall step.</p>
+ </div>
+
+ <div class="qa">
+ <p class="q">Why can&#39;t my Electron app find `claude` or other commands?</p>
+ <p class="a">On macOS, a GUI-launched Electron app doesn&#39;t inherit your interactive shell&#39;s PATH, so commands installed by nvm, asdf, or Homebrew aren&#39;t found. Resolve the command against an interactive login shell, or fall back to known install locations.</p>
+ </div>
+
+ </section>
+
+
+
+ <hr />
+ <div class="share">
+ <span class="lbl">Tags</span>
+ <a class="tag" href="/blog/tags/internals/">Internals</a><a class="tag" href="/blog/tags/electron/">Electron</a><a class="tag" href="/blog/tags/node-pty/">node-pty</a><a class="tag" href="/blog/tags/terminals/">Terminals</a>
+ </div>
+
+ </div>
+
+
+ <aside class="toc-rail" aria-label="Table of contents">
+ <div class="tt">On this page</div>
+ <ol>
+ <li class="lvl-2"><a href="#why-a-pseudo-terminal-not-a-pipe">Why a pseudo-terminal, not a pipe</a></li><li class="lvl-2"><a href="#gotcha-1-the-native-rebuild-trap">Gotcha 1 — The native-rebuild trap</a></li><li class="lvl-2"><a href="#gotcha-2-the-macos-path-trap">Gotcha 2 — The macOS PATH trap</a></li><li class="lvl-2"><a href="#gotcha-3-streaming-over-ipc-without-crashing-on-quit">Gotcha 3 — Streaming over IPC without crashing on quit</a></li><li class="lvl-2"><a href="#managing-many-sessions">Managing many sessions</a></li><li class="lvl-2"><a href="#why-this-matters-for-an-agent-harness">Why this matters for an agent harness</a></li><li class="lvl-2"><a href="#faq">FAQ</a></li>
+ </ol>
+ </aside>
+
+ </div>
+
+ <footer class="post-foot wrap"><div class="prevnext">
+ <a class="pn prev" href="/blog/vibe-kanban-alternative/"><span class="k">← Older</span><span class="t">A vibe-kanban Alternative for Coordinating AI Agents</span></a>
+ <a class="pn next" href="/blog/mcp-and-skills-in-a-hive/"><span class="k">Newer →</span><span class="t">Bringing Your MCP Servers and Skills Into a Hive of Agents</span></a>
+ </div>
+ <section class="related">
+ <h2>Related in Internals</h2>
+ <div class="post-grid">
+ <article class="card">
+ <a class="thumb t-internals" href="/blog/building-a-terminal-ui-xterm-node-pty/" aria-hidden="true" tabindex="-1">
+ <span>INTERNALS</span>
+ </a>
+ <div class="body">
+ <div class="meta">
+ <time datetime="2026-06-03">Jun 3, 2026</time>
+ <span class="dot" aria-hidden="true"></span>
+ <span>8 min</span>
+ </div>
+ <h3><a href="/blog/building-a-terminal-ui-xterm-node-pty/">Building a Terminal UI with xterm.js and node-pty</a></h3>
+ <p class="dek">Wire xterm.js to a node-pty backend: stream output, write keystrokes back, handle resize, and keep many live terminals fast with a terminal pool.</p>
+ <div class="foot">
+ <span class="tag kind">Internals</span>
+ <a class="more" href="/blog/building-a-terminal-ui-xterm-node-pty/" aria-label="Read: Building a Terminal UI with xterm.js and node-pty">Read →</a>
+ </div>
+ </div>
+</article>
+<article class="card">
+ <a class="thumb t-internals" href="/blog/claude-code-hooks-explained/" aria-hidden="true" tabindex="-1">
+ <span>INTERNALS</span>
+ </a>
+ <div class="body">
+ <div class="meta">
+ <time datetime="2026-06-03">Jun 3, 2026</time>
+ <span class="dot" aria-hidden="true"></span>
+ <span>6 min</span>
+ </div>
+ <h3><a href="/blog/claude-code-hooks-explained/">Claude Code Hooks, Explained (PreToolUse, PostToolUse, Stop)</a></h3>
+ <p class="dek">A practical tour of Claude Code hooks — the PreToolUse, PostToolUse, and Stop lifecycle — and how a Unix-socket hook shim drives a live office floor.</p>
+ <div class="foot">
+ <span class="tag kind">Internals</span>
+ <a class="more" href="/blog/claude-code-hooks-explained/" aria-label="Read: Claude Code Hooks, Explained (PreToolUse, PostToolUse, Stop)">Read →</a>
+ </div>
+ </div>
+</article>
+<article class="card">
+ <a class="thumb t-internals" href="/blog/single-committer-git-pattern/" aria-hidden="true" tabindex="-1">
+ <span>INTERNALS</span>
+ </a>
+ <div class="body">
+ <div class="meta">
+ <time datetime="2026-06-02">Jun 2, 2026</time>
+ <span class="dot" aria-hidden="true"></span>
+ <span>5 min</span>
+ </div>
+ <h3><a href="/blog/single-committer-git-pattern/">The Single-Committer Pattern: Multi-Agent Git Without Corruption</a></h3>
+ <p class="dek">Parallel agents corrupt a repo with index.lock races. The single-committer pattern — agents write, one process commits — fixes concurrent git writes.</p>
+ <div class="foot">
+ <span class="tag kind">Internals</span>
+ <a class="more" href="/blog/single-committer-git-pattern/" aria-label="Read: The Single-Committer Pattern: Multi-Agent Git Without Corruption">Read →</a>
+ </div>
+ </div>
+</article>
+
+ </div>
+ </section>
+
+ </footer>
+</article>
+
+</main>
+<footer>
+ <div class="wrap">
+ <div class="foot-top">
+ <a class="foot-brand brand" href="/blog/">
+ <span class="brand-mark">MD</span>
+ <span class="brand-word">MUNDER DIFFLIN<span class="sep">/</span><span class="blog">BLOG</span></span>
+ </a>
+ <div class="foot-links">
+ <a href="/blog/">Latest</a>
+ <a href="/blog/topics/">Topics</a>
+ <a href="/blog/about/">About</a>
+ <a href="https://munderdiffl.in/blog/feed.xml">RSS</a>
+ <a href="https://github.com/chaitanyagiri/munder-difflin">GitHub</a>
+ <a href="https://munderdiffl.in">munderdiffl.in ↗</a>
+ </div>
+ </div>
+ <div class="foot-meta">
+ © 2026 Munder Difflin · Local-first · MIT-licensed ·
+ Built on <a href="https://munderdiffl.in">Electron, React, Pixi.js, xterm.js &amp; node-pty</a>.
+ Run an office of agents while you sleep.
+ </div>
+ </div>
+</footer>
+
+<script>
+ // sticky-nav border on scroll
+ (function () {
+ var nav = document.getElementById('nav');
+ if (!nav) return;
+ var onScroll = function () { nav.classList.toggle('scrolled', window.scrollY > 8); };
+ onScroll(); window.addEventListener('scroll', onScroll, { passive: true });
+ })();
+</script>
+
+</body>
+</html>
diff --git a/docs/blog/run-an-office-of-ai-agents/index.html b/docs/blog/run-an-office-of-ai-agents/index.html
new file mode 100644
index 00000000..f7382003
--- /dev/null
+++ b/docs/blog/run-an-office-of-ai-agents/index.html
@@ -0,0 +1,287 @@
+<!doctype html>
+<html lang="en">
+<head>
+<meta charset="UTF-8" />
+<meta name="viewport" content="width=device-width, initial-scale=1.0" />
+<title>Run an Office of AI Agents While You Sleep — Munder Difflin Blog</title>
+<meta name="description" content="What it takes to run a self-coordinating office of AI coding agents that keeps shipping after you log off — and the guardrails that keep it sane." />
+<link rel="canonical" href="https://munderdiffl.in/blog/run-an-office-of-ai-agents/" />
+
+<link rel="icon" type="image/png" href="https://munderdiffl.in/logo.png" />
+<link rel="apple-touch-icon" href="https://munderdiffl.in/logo.png" />
+<meta name="theme-color" content="#F5F2E8" />
+
+<!-- Open Graph -->
+<meta property="og:site_name" content="Munder Difflin Blog" />
+<meta property="og:type" content="article" />
+<meta property="og:title" content="Run an Office of AI Agents While You Sleep — Munder Difflin Blog" />
+<meta property="og:description" content="What it takes to run a self-coordinating office of AI coding agents that keeps shipping after you log off — and the guardrails that keep it sane." />
+<meta property="og:url" content="https://munderdiffl.in/blog/run-an-office-of-ai-agents/" />
+<meta property="og:image" content="https://munderdiffl.in/media/og.png" />
+<meta property="og:locale" content="en_US" />
+<meta property="article:published_time" content="2026-06-02T00:00:00.000Z" />
+<meta property="article:author" content="Chaitanya Giri" />
+<meta property="article:tag" content="Use Cases" />
+<meta property="article:tag" content="Multi-Agent" />
+<meta property="article:tag" content="Automation" />
+<meta property="article:tag" content="Story" />
+
+
+<!-- Twitter -->
+<meta name="twitter:card" content="summary_large_image" />
+<meta name="twitter:title" content="Run an Office of AI Agents While You Sleep — Munder Difflin Blog" />
+<meta name="twitter:description" content="What it takes to run a self-coordinating office of AI coding agents that keeps shipping after you log off — and the guardrails that keep it sane." />
+<meta name="twitter:image" content="https://munderdiffl.in/media/og.png" />
+
+<link rel="alternate" type="application/atom+xml" title="Munder Difflin Blog" href="https://munderdiffl.in/blog/feed.xml" />
+<link rel="preconnect" href="https://fonts.googleapis.com" />
+<link rel="preconnect" href="https://fonts.gstatic.com" crossorigin />
+<link href="https://fonts.googleapis.com/css2?family=Geist:wght@400;500;600&family=JetBrains+Mono:wght@400;500;600;700&display=swap" rel="stylesheet" />
+<link rel="stylesheet" href="/blog/assets/blog.css" />
+
+<script type="application/ld+json">
+{
+ "@context": "https://schema.org",
+ "@type": "BlogPosting",
+ "headline": "Run an Office of AI Agents While You Sleep",
+ "description": "What it takes to run a self-coordinating office of AI coding agents that keeps shipping after you log off — and the guardrails that keep it sane.",
+ "image": ["https://munderdiffl.in/media/og.png"],
+ "datePublished": "2026-06-02T00:00:00.000Z",
+ "dateModified": "2026-06-02T00:00:00.000Z",
+ "author": { "@type": "Person", "name": "Chaitanya Giri" },
+ "publisher": {
+ "@type": "Organization",
+ "name": "Munder Difflin",
+ "logo": { "@type": "ImageObject", "url": "https://munderdiffl.in/logo.png" }
+ },
+ "mainEntityOfPage": { "@type": "WebPage", "@id": "https://munderdiffl.in/blog/run-an-office-of-ai-agents/" },
+ "keywords": "autonomous software team ai, ai pair programming team, ai coding agent teams, run agents while you sleep",
+ "articleSection": "Use Cases",
+ "inLanguage": "en-US",
+ "url": "https://munderdiffl.in/blog/run-an-office-of-ai-agents/"
+}
+</script>
+<script type="application/ld+json">
+{
+ "@context": "https://schema.org",
+ "@type": "BreadcrumbList",
+ "itemListElement": [
+ { "@type": "ListItem", "position": 1, "name": "Home", "item": "https://munderdiffl.in/" },
+ { "@type": "ListItem", "position": 2, "name": "Blog", "item": "https://munderdiffl.in/blog/" },
+ { "@type": "ListItem", "position": 3, "name": "Run an Office of AI Agents While You Sleep", "item": "https://munderdiffl.in/blog/run-an-office-of-ai-agents/" }
+ ]
+}
+</script>
+
+
+</head>
+<body>
+<a class="skip-link" href="#main">Skip to content</a>
+<nav id="nav">
+ <a class="brand" href="/blog/" aria-label="Munder Difflin Blog home">
+ <span class="brand-mark">MD</span>
+ <span class="brand-word">MUNDER DIFFLIN<span class="sep">/</span><span class="blog">BLOG</span></span>
+ </a>
+ <span class="spacer"></span>
+ <div class="links">
+ <a href="/blog/">Latest</a>
+ <a href="/blog/topics/">Topics</a>
+ <a href="/blog/about/">About</a>
+ <a href="https://munderdiffl.in">↗ Product</a>
+ </div>
+ <div class="nav-actions">
+ <a class="btn sm" href="https://munderdiffl.in/blog/feed.xml" aria-label="RSS feed">⤵ RSS</a>
+ <a class="btn sm primary" href="https://munderdiffl.in/#install">⤓ Download</a>
+ </div>
+</nav>
+
+<main id="main">
+
+<article>
+ <header class="post-head wrap">
+ <nav class="crumbs" aria-label="Breadcrumb">
+ <a href="/blog/">Blog</a>
+ <span>/</span>
+ <a href="/blog/topics/use-cases/">Use Cases</a>
+ </nav>
+ <h1>Run an Office of AI Agents While You Sleep</h1>
+ <p class="dek">What it takes to run a self-coordinating office of AI coding agents that keeps shipping after you log off — and the guardrails that keep it sane.</p>
+ <div class="byline">
+ <span class="av" aria-hidden="true">CG</span>
+ <strong>Chaitanya Giri</strong>
+ <span class="dot" aria-hidden="true">·</span>
+ <time datetime="2026-06-02">Jun 2, 2026</time>
+ <span class="dot" aria-hidden="true">·</span>
+ <span>3 min read</span>
+ <span class="tag kind">Use Cases</span>
+ </div>
+ </header>
+
+ <div class="post-wrap wrap">
+ <div class="prose">
+ <div class="callout tldr"><span class="ic">TL;DR</span><p>Imagine an <strong>office of AI
+agents</strong> — each with a role, a shared memory, and a coordinator — that keeps working a backlog
+after you close the laptop. It's not magic and it's not hands-off forever: it works because of
+<strong>roles, shared memory, messaging, an orchestrator, and guardrails</strong> that escalate the
+risky calls to you. Here's the realistic version of the dream.</p></div>
+<p>There’s a specific fantasy that pulls people toward multi-agent tools: log off at night, and a team of
+agents keeps shipping. It’s a good fantasy — and a more achievable one than it sounds, <em>if</em> you build
+it on the right foundations. Here’s what that office actually looks like.</p>
+<h2 id="the-picture" tabindex="-1">The picture <a class="anchor" href="#the-picture" aria-hidden="true">#</a></h2>
+<p>Picture a floor of agents, each at a desk with a job. One’s writing tests. One’s chewing through a
+refactor. One’s updating docs to match. A coordinator — you talk to it like a manager — has the
+backlog and routes the next task to whoever’s free. They message each other when work hands off. They
+share a memory of the project so nobody re-learns what’s already known. You can watch it happen, or
+close the laptop and check the morning’s progress over coffee.</p>
+<p>That’s not a metaphor for Munder Difflin — it’s literally <a href="/#how">the office floor</a>. But the picture
+only works because of what’s underneath it.</p>
+<h2 id="what-makes-it-actually-work" tabindex="-1">What makes it actually work <a class="anchor" href="#what-makes-it-actually-work" aria-hidden="true">#</a></h2>
+<p>A self-running office isn’t “point agents at a repo and hope.” Four pieces carry the weight:</p>
+<h3 id="roles" tabindex="-1">Roles <a class="anchor" href="#roles" aria-hidden="true">#</a></h3>
+<p>Each agent has a scoped job, so it doesn’t wander into another’s work or duplicate effort. Roles make
+“who does this?” obvious and keep parallel agents out of each other’s lanes.</p>
+<h3 id="shared-memory" tabindex="-1">Shared memory <a class="anchor" href="#shared-memory" aria-hidden="true">#</a></h3>
+<p>The team reads from and writes to a <a href="/blog/give-claude-code-long-term-memory/">shared long-term
+memory</a>. When the test-writer learns a convention, the
+refactorer inherits it. Knowledge compounds overnight instead of resetting each session.</p>
+<h3 id="messaging-an-orchestrator" tabindex="-1">Messaging + an orchestrator <a class="anchor" href="#messaging-an-orchestrator" aria-hidden="true">#</a></h3>
+<p>Agents hand work to each other through mailboxes, and an <a href="/#how">orchestrator</a> decomposes your intent
+and routes the pieces. That’s the difference between a <em>team</em> and a pile of parallel sessions — and
+it’s what lets work flow while you’re away.</p>
+<h3 id="guardrails" tabindex="-1">Guardrails <a class="anchor" href="#guardrails" aria-hidden="true">#</a></h3>
+<p>This is the part the fantasy skips. Unattended agents need a <a href="/#why">human-in-the-loop</a> line: routine
+work proceeds, but the risky stuff — spending real money, destructive operations, big scope changes —
+queues for your approval. You wake up to <em>progress</em>, not surprises.</p>
+<h2 id="whats-realistic-and-what-isnt" tabindex="-1">What’s realistic (and what isn’t) <a class="anchor" href="#whats-realistic-and-what-isnt" aria-hidden="true">#</a></h2>
+<p>Honesty matters here, because over-promising is how people get burned:</p>
+<ul>
+<li><strong>Realistic:</strong> a team grinding through a well-scoped backlog of bounded tasks overnight — tests,
+refactors, docs, migrations, investigations — with a clear record of what each agent did.</li>
+<li><strong>Realistic:</strong> waking up to mostly-done work that you review and finish, having saved hours of
+context-switching.</li>
+<li><strong>Not realistic:</strong> handing over an ambiguous, open-ended goal and expecting a finished product with
+zero review. Agents are leveraged labor, not oracles.</li>
+</ul>
+<p>The skill is in the scoping and the guardrails, not in trusting blindly. Done right, the leverage is
+real.</p>
+<h2 id="how-to-get-there" tabindex="-1">How to get there <a class="anchor" href="#how-to-get-there" aria-hidden="true">#</a></h2>
+<p>You don’t start with an overnight office — you grow into one. The arc is always the same: one session,
+then a few manual terminals, then a coordinated team. We map that progression in <a href="/blog/from-one-terminal-to-a-team/">from one terminal to
+a team</a>, and the foundational habits in <a href="/blog/how-to-run-multiple-claude-code-agents/">how to run multiple
+Claude Code agents</a>.</p>
+<p>Keeping the whole office <a href="/blog/why-local-first-matters-for-ai-agents/">local-first</a> is what makes it
+sane to leave running: it’s your machine, your files, your rules.</p>
+<hr>
+<p>Munder Difflin is exactly this office — roles, shared memory, messaging, a GOD orchestrator, and a
+floor you can watch, all local. <a href="/#install">Download Munder Difflin</a> and staff your own; it’s free and
+open source.</p>
+
+
+
+
+
+ <hr />
+ <div class="share">
+ <span class="lbl">Tags</span>
+ <a class="tag" href="/blog/tags/use-cases/">Use Cases</a><a class="tag" href="/blog/tags/multi-agent/">Multi-Agent</a><a class="tag" href="/blog/tags/automation/">Automation</a><a class="tag" href="/blog/tags/story/">Story</a>
+ </div>
+
+ </div>
+
+
+ <aside class="toc-rail" aria-label="Table of contents">
+ <div class="tt">On this page</div>
+ <ol>
+ <li class="lvl-2"><a href="#the-picture">The picture</a></li><li class="lvl-2"><a href="#what-makes-it-actually-work">What makes it actually work</a></li><li class="lvl-3"><a href="#roles">Roles</a></li><li class="lvl-3"><a href="#shared-memory">Shared memory</a></li><li class="lvl-3"><a href="#messaging-an-orchestrator">Messaging + an orchestrator</a></li><li class="lvl-3"><a href="#guardrails">Guardrails</a></li><li class="lvl-2"><a href="#whats-realistic-and-what-isnt">What’s realistic (and what isn’t)</a></li><li class="lvl-2"><a href="#how-to-get-there">How to get there</a></li>
+ </ol>
+ </aside>
+
+ </div>
+
+ <footer class="post-foot wrap"><div class="prevnext">
+ <a class="pn prev" href="/blog/single-committer-git-pattern/"><span class="k">← Older</span><span class="t">The Single-Committer Pattern: Multi-Agent Git Without Corruption</span></a>
+ <a class="pn next" href="/blog/munder-difflin-faq/"><span class="k">Newer →</span><span class="t">Munder Difflin FAQ: Everything People Ask</span></a>
+ </div>
+ <section class="related">
+ <h2>Related in Use Cases</h2>
+ <div class="post-grid">
+ <article class="card">
+ <a class="thumb t-use-cases" href="/blog/from-one-terminal-to-a-team/" aria-hidden="true" tabindex="-1">
+ <span>USE CASES</span>
+ </a>
+ <div class="body">
+ <div class="meta">
+ <time datetime="2026-06-02">Jun 2, 2026</time>
+ <span class="dot" aria-hidden="true"></span>
+ <span>3 min</span>
+ </div>
+ <h3><a href="/blog/from-one-terminal-to-a-team/">From One Terminal to a Team: Scaling Your Claude Code Workflow</a></h3>
+ <p class="dek">The workflow shift from a single Claude Code session to a coordinated team of agents — what changes, where it breaks, and the concrete before-and-after.</p>
+ <div class="foot">
+ <span class="tag kind">Use Cases</span>
+ <a class="more" href="/blog/from-one-terminal-to-a-team/" aria-label="Read: From One Terminal to a Team: Scaling Your Claude Code Workflow">Read →</a>
+ </div>
+ </div>
+</article>
+<article class="card">
+ <a class="thumb t-use-cases" href="/blog/why-local-first-matters-for-ai-agents/" aria-hidden="true" tabindex="-1">
+ <span>USE CASES</span>
+ </a>
+ <div class="body">
+ <div class="meta">
+ <time datetime="2026-06-02">Jun 2, 2026</time>
+ <span class="dot" aria-hidden="true"></span>
+ <span>3 min</span>
+ </div>
+ <h3><a href="/blog/why-local-first-matters-for-ai-agents/">Why Local-First Matters for Your AI Agents</a></h3>
+ <p class="dek">The control, privacy, and cost case for keeping your AI agents and their memory on your own machine — and what cloud orchestration quietly costs.</p>
+ <div class="foot">
+ <span class="tag kind">Use Cases</span>
+ <a class="more" href="/blog/why-local-first-matters-for-ai-agents/" aria-label="Read: Why Local-First Matters for Your AI Agents">Read →</a>
+ </div>
+ </div>
+</article>
+
+ </div>
+ </section>
+
+ </footer>
+</article>
+
+</main>
+<footer>
+ <div class="wrap">
+ <div class="foot-top">
+ <a class="foot-brand brand" href="/blog/">
+ <span class="brand-mark">MD</span>
+ <span class="brand-word">MUNDER DIFFLIN<span class="sep">/</span><span class="blog">BLOG</span></span>
+ </a>
+ <div class="foot-links">
+ <a href="/blog/">Latest</a>
+ <a href="/blog/topics/">Topics</a>
+ <a href="/blog/about/">About</a>
+ <a href="https://munderdiffl.in/blog/feed.xml">RSS</a>
+ <a href="https://github.com/chaitanyagiri/munder-difflin">GitHub</a>
+ <a href="https://munderdiffl.in">munderdiffl.in ↗</a>
+ </div>
+ </div>
+ <div class="foot-meta">
+ © 2026 Munder Difflin · Local-first · MIT-licensed ·
+ Built on <a href="https://munderdiffl.in">Electron, React, Pixi.js, xterm.js &amp; node-pty</a>.
+ Run an office of agents while you sleep.
+ </div>
+ </div>
+</footer>
+
+<script>
+ // sticky-nav border on scroll
+ (function () {
+ var nav = document.getElementById('nav');
+ if (!nav) return;
+ var onScroll = function () { nav.classList.toggle('scrolled', window.scrollY > 8); };
+ onScroll(); window.addEventListener('scroll', onScroll, { passive: true });
+ })();
+</script>
+
+</body>
+</html>
diff --git a/docs/blog/semantic-memory-for-ai-agents/index.html b/docs/blog/semantic-memory-for-ai-agents/index.html
new file mode 100644
index 00000000..5cd52579
--- /dev/null
+++ b/docs/blog/semantic-memory-for-ai-agents/index.html
@@ -0,0 +1,364 @@
+<!doctype html>
+<html lang="en">
+<head>
+<meta charset="UTF-8" />
+<meta name="viewport" content="width=device-width, initial-scale=1.0" />
+<title>Semantic Memory for AI Agents: Recall in Milliseconds — Munder Difflin Blog</title>
+<meta name="description" content="What semantic memory for AI agents is, why a markdown-first store beats a heavy DB, and how a shared palace lets a hive recall a note by meaning, fast." />
+<link rel="canonical" href="https://munderdiffl.in/blog/semantic-memory-for-ai-agents/" />
+
+<link rel="icon" type="image/png" href="https://munderdiffl.in/logo.png" />
+<link rel="apple-touch-icon" href="https://munderdiffl.in/logo.png" />
+<meta name="theme-color" content="#F5F2E8" />
+
+<!-- Open Graph -->
+<meta property="og:site_name" content="Munder Difflin Blog" />
+<meta property="og:type" content="article" />
+<meta property="og:title" content="Semantic Memory for AI Agents: Recall in Milliseconds — Munder Difflin Blog" />
+<meta property="og:description" content="What semantic memory for AI agents is, why a markdown-first store beats a heavy DB, and how a shared palace lets a hive recall a note by meaning, fast." />
+<meta property="og:url" content="https://munderdiffl.in/blog/semantic-memory-for-ai-agents/" />
+<meta property="og:image" content="https://munderdiffl.in/media/og.png" />
+<meta property="og:locale" content="en_US" />
+<meta property="article:published_time" content="2026-05-26T00:00:00.000Z" />
+<meta property="article:author" content="Chaitanya Giri" />
+<meta property="article:tag" content="Memory" />
+<meta property="article:tag" content="MemPalace" />
+<meta property="article:tag" content="Multi-Agent" />
+<meta property="article:tag" content="Claude Code" />
+
+
+<!-- Twitter -->
+<meta name="twitter:card" content="summary_large_image" />
+<meta name="twitter:title" content="Semantic Memory for AI Agents: Recall in Milliseconds — Munder Difflin Blog" />
+<meta name="twitter:description" content="What semantic memory for AI agents is, why a markdown-first store beats a heavy DB, and how a shared palace lets a hive recall a note by meaning, fast." />
+<meta name="twitter:image" content="https://munderdiffl.in/media/og.png" />
+
+<link rel="alternate" type="application/atom+xml" title="Munder Difflin Blog" href="https://munderdiffl.in/blog/feed.xml" />
+<link rel="preconnect" href="https://fonts.googleapis.com" />
+<link rel="preconnect" href="https://fonts.gstatic.com" crossorigin />
+<link href="https://fonts.googleapis.com/css2?family=Geist:wght@400;500;600&family=JetBrains+Mono:wght@400;500;600;700&display=swap" rel="stylesheet" />
+<link rel="stylesheet" href="/blog/assets/blog.css" />
+
+<script type="application/ld+json">
+{
+ "@context": "https://schema.org",
+ "@type": "BlogPosting",
+ "headline": "Semantic Memory for AI Agents: Recall in Milliseconds",
+ "description": "What semantic memory for AI agents is, why a markdown-first store beats a heavy DB, and how a shared palace lets a hive recall a note by meaning, fast.",
+ "image": ["https://munderdiffl.in/media/og.png"],
+ "datePublished": "2026-05-26T00:00:00.000Z",
+ "dateModified": "2026-05-26T00:00:00.000Z",
+ "author": { "@type": "Person", "name": "Chaitanya Giri" },
+ "publisher": {
+ "@type": "Organization",
+ "name": "Munder Difflin",
+ "logo": { "@type": "ImageObject", "url": "https://munderdiffl.in/logo.png" }
+ },
+ "mainEntityOfPage": { "@type": "WebPage", "@id": "https://munderdiffl.in/blog/semantic-memory-for-ai-agents/" },
+ "keywords": "semantic memory for ai agents, semantic memory, vector recall, agent memory layer",
+ "articleSection": "Memory",
+ "inLanguage": "en-US",
+ "url": "https://munderdiffl.in/blog/semantic-memory-for-ai-agents/"
+}
+</script>
+<script type="application/ld+json">
+{
+ "@context": "https://schema.org",
+ "@type": "BreadcrumbList",
+ "itemListElement": [
+ { "@type": "ListItem", "position": 1, "name": "Home", "item": "https://munderdiffl.in/" },
+ { "@type": "ListItem", "position": 2, "name": "Blog", "item": "https://munderdiffl.in/blog/" },
+ { "@type": "ListItem", "position": 3, "name": "Semantic Memory for AI Agents: Recall in Milliseconds", "item": "https://munderdiffl.in/blog/semantic-memory-for-ai-agents/" }
+ ]
+}
+</script>
+
+<script type="application/ld+json">
+{
+ "@context": "https://schema.org",
+ "@type": "FAQPage",
+ "mainEntity": [
+ { "@type": "Question", "name": "What is semantic memory for an AI agent?", "acceptedAnswer": { "@type": "Answer", "text": "It's a layer that lets an agent recall past knowledge by meaning rather than exact keywords. Notes are embedded into vectors; at recall time the agent's query is embedded too and the closest notes are returned — so 'how do we build the web bundle?' finds a note about electron-vite even if it never used those words." } },
+ { "@type": "Question", "name": "Why markdown-first instead of a vector database?", "acceptedAnswer": { "@type": "Answer", "text": "Markdown notes are human-readable, diffable in git, and degrade gracefully — if the index breaks, the files still work. A heavyweight vector DB wants to own the agent runtime and adds operational weight you don't need for a handful of agents. The index sits on top of the markdown, not in place of it." } },
+ { "@type": "Question", "name": "How does shared memory help a team of agents?", "acceptedAnswer": { "@type": "Answer", "text": "Each agent's notes are mined into a shared store, so one agent can recall what another learned. The team stops re-discovering the same facts, and the human stops re-explaining context every session." } }
+
+ ]
+}
+</script>
+
+
+</head>
+<body>
+<a class="skip-link" href="#main">Skip to content</a>
+<nav id="nav">
+ <a class="brand" href="/blog/" aria-label="Munder Difflin Blog home">
+ <span class="brand-mark">MD</span>
+ <span class="brand-word">MUNDER DIFFLIN<span class="sep">/</span><span class="blog">BLOG</span></span>
+ </a>
+ <span class="spacer"></span>
+ <div class="links">
+ <a href="/blog/">Latest</a>
+ <a href="/blog/topics/">Topics</a>
+ <a href="/blog/about/">About</a>
+ <a href="https://munderdiffl.in">↗ Product</a>
+ </div>
+ <div class="nav-actions">
+ <a class="btn sm" href="https://munderdiffl.in/blog/feed.xml" aria-label="RSS feed">⤵ RSS</a>
+ <a class="btn sm primary" href="https://munderdiffl.in/#install">⤓ Download</a>
+ </div>
+</nav>
+
+<main id="main">
+
+<article>
+ <header class="post-head wrap">
+ <nav class="crumbs" aria-label="Breadcrumb">
+ <a href="/blog/">Blog</a>
+ <span>/</span>
+ <a href="/blog/topics/memory/">Memory</a>
+ </nav>
+ <h1>Semantic Memory for AI Agents: Recall in Milliseconds</h1>
+ <p class="dek">What semantic memory for AI agents is, why a markdown-first store beats a heavy DB, and how a shared palace lets a hive recall a note by meaning, fast.</p>
+ <div class="byline">
+ <span class="av" aria-hidden="true">CG</span>
+ <strong>Chaitanya Giri</strong>
+ <span class="dot" aria-hidden="true">·</span>
+ <time datetime="2026-05-26">May 26, 2026</time>
+ <span class="dot" aria-hidden="true">·</span>
+ <span>6 min read</span>
+ <span class="tag kind">Memory</span>
+ </div>
+ </header>
+
+ <div class="post-wrap wrap">
+ <div class="prose">
+ <div class="callout tldr"><span class="ic">TL;DR</span><p><strong>Semantic memory</strong> lets an
+agent recall past knowledge by <strong>meaning</strong>, not exact keywords. The durable approach is
+<strong>markdown-first</strong>: agents write plain notes; a semantic index sits on top so they recall
+the few relevant ones instead of re-reading everything. Make it <strong>shared</strong> across a hive
+and one agent can use what another learned — recall stays fast and the context window stays small even
+as the knowledge base grows.</p></div>
+<p>An agent’s working memory is its context window, and the context window is wiped at the end of every
+session. So “memory” for agents is really two problems: <em>storing</em> what they learn durably, and
+<em>recalling</em> the right piece at the right time without dragging everything back into context. Semantic
+memory solves the second. This post explains what it is, why markdown-first is the right foundation,
+and how a shared memory layer changes how a team of agents behaves.</p>
+<h2 id="keyword-recall-isnt-enough" tabindex="-1">Keyword recall isn’t enough <a class="anchor" href="#keyword-recall-isnt-enough" aria-hidden="true">#</a></h2>
+<p>The first instinct is to store notes and grep them. It works until it doesn’t. An agent that learned</p>
+<blockquote>
+<p>“The web bundle is built with electron-vite, not plain vite.”</p>
+</blockquote>
+<p>won’t be found by a query like <em>“how do we compile the front-end?”</em> — no shared keywords. Keyword
+search matches strings; agents think in concepts. The gap between “compile the front-end” and
+“build the web bundle with electron-vite” is exactly where keyword recall fails and the agent
+re-discovers something it already knew.</p>
+<h2 id="what-semantic-recall-actually-does" tabindex="-1">What semantic recall actually does <a class="anchor" href="#what-semantic-recall-actually-does" aria-hidden="true">#</a></h2>
+<p>Semantic memory closes that gap with <strong>embeddings</strong>. The idea, in three steps:</p>
+<ol>
+<li><strong>Embed each note</strong> into a vector — a list of numbers that captures its meaning, so notes about
+similar things land near each other in vector space.</li>
+<li><strong>At recall time, embed the query</strong> the same way.</li>
+<li><strong>Return the nearest notes</strong> by vector similarity.</li>
+</ol>
+<p>Now <em>“how do we compile the front-end?”</em> lands near the electron-vite note even though they share no
+words, because they mean the same thing. The agent recalls by meaning, pulls the two or three most
+relevant notes into context, and acts — instead of either re-reading its whole history or missing the
+note entirely.</p>
+<p>The payoff compounds: recall stays <strong>near-instant</strong> and the context window stays <strong>small</strong> even as the
+note collection grows into the hundreds. You inject the few notes that matter, not the whole archive.</p>
+<h2 id="why-markdown-first-beats-a-heavyweight-db" tabindex="-1">Why markdown-first beats a heavyweight DB <a class="anchor" href="#why-markdown-first-beats-a-heavyweight-db" aria-hidden="true">#</a></h2>
+<p>There’s a strong temptation to reach for a dedicated vector database or a full agent-memory framework.
+For a handful of agents, that’s the wrong trade. The more robust foundation is <strong>markdown-first</strong>:
+agents write durable facts to plain markdown files, and a semantic index is built <em>on top</em> of those
+files. Three reasons this wins:</p>
+<ul>
+<li><strong>Human-readable.</strong> You can open an agent’s <code>memory.md</code> and see exactly what it “knows.” Memory you
+can’t read is memory you can’t trust.</li>
+<li><strong>Diffable.</strong> The notes live in git. You watch memory change over time, and you can review it like
+any other artifact.</li>
+<li><strong>Degrades gracefully.</strong> If the fancy index breaks or isn’t installed, the markdown files still
+work — the agent reads them directly. A database that won’t open takes the memory with it; a folder
+of markdown never does.</li>
+</ul>
+<p>There’s also an architectural reason. Heavyweight memory frameworks tend to want to <em>own the agent
+runtime</em> — they assume they’re the thing running the loop. But when your agents are real <code>claude</code>
+sessions, the runtime is already Claude Code. The memory layer should be a lightweight companion to
+that, not a replacement for it. Markdown files plus a CLI-driven index fit that shape; a framework that
+wants to be in charge doesn’t. (For the deeper case, see
+<a href="/blog/give-claude-code-long-term-memory/">how to give Claude Code long-term memory</a>.)</p>
+<h2 id="the-shape-of-a-shared-memory-layer" tabindex="-1">The shape of a shared memory layer <a class="anchor" href="#the-shape-of-a-shared-memory-layer" aria-hidden="true">#</a></h2>
+<p>Here’s how Munder Difflin implements semantic memory for a whole hive, via the <strong>MemPalace</strong> layer.
+It’s worth walking the moving parts because they show what “fast, shared recall” requires in practice.</p>
+<h3 id="one-palace-many-wings" tabindex="-1">One palace, many wings <a class="anchor" href="#one-palace-many-wings" aria-hidden="true">#</a></h3>
+<p>The harness keeps a single shared <strong>palace</strong> for the whole team and points every agent’s environment
+at it. Each agent’s own notes go into its own <strong>wing</strong> of that palace. The result: agents have private
+authorship (each writes only its own <code>memory.md</code>, keeping the single-writer rule intact) but <strong>shared
+recall</strong> — a query can search the whole palace or scope to one agent’s wing.</p>
+<p>That shared recall is what turns a pile of agents into a team that learns. When the researcher figures
+out a build quirk, the coder can recall it later without anyone copy-pasting. The human stops being the
+courier of context between sessions.</p>
+<h3 id="mining-notes-become-searchable-automatically" tabindex="-1">Mining: notes become searchable automatically <a class="anchor" href="#mining-notes-become-searchable-automatically" aria-hidden="true">#</a></h3>
+<p>Agents don’t manage the index by hand. The harness <strong>mines</strong> each agent’s <code>memory.md</code> into its wing on
+a schedule, and — crucially — only when the file has actually changed (it checks the modification
+time and skips unchanged memories, so it doesn’t reload the embedding model for nothing). Write a
+durable fact to your markdown, and it becomes searchable by the whole team a few minutes later, with no
+extra step.</p>
+<h3 id="recall-search-and-wake-up" tabindex="-1">Recall: search and wake-up <a class="anchor" href="#recall-search-and-wake-up" aria-hidden="true">#</a></h3>
+<p>Agents recall in two ways:</p>
+<ul>
+<li><strong><code>search &quot;&lt;query&gt;&quot;</code></strong> returns the most relevant notes by meaning, optionally scoped to one wing or
+widened to more results. This is targeted recall: “what do we know about X?”</li>
+<li><strong><code>wake-up</code></strong> returns a short digest — a few hundred tokens of what matters — meant to be read at the
+<em>start</em> of a task, so an agent boots with the team’s relevant knowledge already in hand.</li>
+</ul>
+<p>Both are plain CLI calls the agent can run itself. There’s no MCP server to stand up, no database to
+administer — the index is a companion to the markdown, driven by a command.</p>
+<h3 id="degrade-and-detect" tabindex="-1">Degrade-and-detect <a class="anchor" href="#degrade-and-detect" aria-hidden="true">#</a></h3>
+<p>If the semantic layer isn’t installed at all, none of this errors — it’s a no-op, and agents fall back
+to reading their markdown directly. The fast path is an upgrade, not a dependency. That’s the
+markdown-first principle paying off: the floor never falls out from under the team.</p>
+<h2 id="how-fast-is-fast" tabindex="-1">How fast is “fast”? <a class="anchor" href="#how-fast-is-fast" aria-hidden="true">#</a></h2>
+<p>The “milliseconds” promise is about the <em>experience</em>, and it’s worth being precise. Recall feels
+instant because the expensive work — turning notes into vectors — happens ahead of time, during
+mining. At recall time you embed one short query and compare it against pre-computed vectors, which is
+cheap. The agent gets its handful of relevant notes back without a perceptible wait, and without
+dragging its whole history into context. Compared to the alternative — re-reading everything, or worse,
+re-discovering it — it’s the difference between remembering and relearning.</p>
+<p>A practical note: lighter embedding models keep recall snappy on modest hardware, which matters when
+everything runs locally. A small, fast model is the sensible default; a larger multilingual one is
+there when you need it. The point is that <em>local</em> and <em>fast</em> aren’t in tension here.</p>
+<h2 id="what-shared-memory-changes-day-to-day" tabindex="-1">What shared memory changes day to day <a class="anchor" href="#what-shared-memory-changes-day-to-day" aria-hidden="true">#</a></h2>
+<p>The abstract benefit is “agents remember.” The concrete one shows up in your habits:</p>
+<ul>
+<li>Your briefs get <strong>shorter</strong> every week, because the team stops needing context re-explained.</li>
+<li>Agents stop <strong>contradicting</strong> each other, because they recall the same shared decisions.</li>
+<li>A new agent added to the team is <strong>useful immediately</strong> — it wakes up into the hive’s accumulated
+knowledge instead of a blank slate.</li>
+</ul>
+<p>That’s the quiet superpower of a memory layer: it makes a <a href="/blog/coordinating-ai-coding-agents/">coordinated team</a>
+get better over time instead of starting cold every run. It’s also what lets the
+<a href="/blog/how-the-god-orchestrator-works/">GOD orchestrator</a> route well — it can recall what’s been tried
+and who knows what.</p>
+<h2 id="faq" tabindex="-1">FAQ <a class="anchor" href="#faq" aria-hidden="true">#</a></h2>
+<p><strong>Does semantic memory replace the markdown notes?</strong> No — it sits on top of them. The markdown is the
+source of truth; the index is a recall accelerator built from it. That ordering is the whole point.</p>
+<p><strong>Who decides what gets remembered?</strong> The agents do, by writing durable facts to their own memory as
+they work. Good memory hygiene — small, atomic, factual notes — makes recall sharp; rambling notes make
+it fuzzy.</p>
+<hr>
+<p>Munder Difflin gives every Claude Code agent markdown memory plus a shared semantic palace the whole
+hive can recall from — local, fast, and graceful when offline.
+<a href="https://munderdiffl.in/#install">Download Munder Difflin</a> to give your agents memory that actually
+sticks; it’s free and open source.</p>
+
+
+
+ <section class="faq" aria-label="Frequently asked questions">
+ <h2 id="faq">FAQ</h2>
+
+ <div class="qa">
+ <p class="q">What is semantic memory for an AI agent?</p>
+ <p class="a">It&#39;s a layer that lets an agent recall past knowledge by meaning rather than exact keywords. Notes are embedded into vectors; at recall time the agent&#39;s query is embedded too and the closest notes are returned — so &#39;how do we build the web bundle?&#39; finds a note about electron-vite even if it never used those words.</p>
+ </div>
+
+ <div class="qa">
+ <p class="q">Why markdown-first instead of a vector database?</p>
+ <p class="a">Markdown notes are human-readable, diffable in git, and degrade gracefully — if the index breaks, the files still work. A heavyweight vector DB wants to own the agent runtime and adds operational weight you don&#39;t need for a handful of agents. The index sits on top of the markdown, not in place of it.</p>
+ </div>
+
+ <div class="qa">
+ <p class="q">How does shared memory help a team of agents?</p>
+ <p class="a">Each agent&#39;s notes are mined into a shared store, so one agent can recall what another learned. The team stops re-discovering the same facts, and the human stops re-explaining context every session.</p>
+ </div>
+
+ </section>
+
+
+
+ <hr />
+ <div class="share">
+ <span class="lbl">Tags</span>
+ <a class="tag" href="/blog/tags/memory/">Memory</a><a class="tag" href="/blog/tags/mempalace/">MemPalace</a><a class="tag" href="/blog/tags/multi-agent/">Multi-Agent</a><a class="tag" href="/blog/tags/claude-code/">Claude Code</a>
+ </div>
+
+ </div>
+
+
+ <aside class="toc-rail" aria-label="Table of contents">
+ <div class="tt">On this page</div>
+ <ol>
+ <li class="lvl-2"><a href="#keyword-recall-isnt-enough">Keyword recall isn’t enough</a></li><li class="lvl-2"><a href="#what-semantic-recall-actually-does">What semantic recall actually does</a></li><li class="lvl-2"><a href="#why-markdown-first-beats-a-heavyweight-db">Why markdown-first beats a heavyweight DB</a></li><li class="lvl-2"><a href="#the-shape-of-a-shared-memory-layer">The shape of a shared memory layer</a></li><li class="lvl-3"><a href="#one-palace-many-wings">One palace, many wings</a></li><li class="lvl-3"><a href="#mining-notes-become-searchable-automatically">Mining: notes become searchable automatically</a></li><li class="lvl-3"><a href="#recall-search-and-wake-up">Recall: search and wake-up</a></li><li class="lvl-3"><a href="#degrade-and-detect">Degrade-and-detect</a></li><li class="lvl-2"><a href="#how-fast-is-fast">How fast is “fast”?</a></li><li class="lvl-2"><a href="#what-shared-memory-changes-day-to-day">What shared memory changes day to day</a></li><li class="lvl-2"><a href="#faq">FAQ</a></li>
+ </ol>
+ </aside>
+
+ </div>
+
+ <footer class="post-foot wrap"><div class="prevnext">
+ <a class="pn prev" href="/blog/manage-multiple-claude-code-sessions/"><span class="k">← Older</span><span class="t">How to Manage Multiple Claude Code Sessions Like a Pro</span></a>
+ <a class="pn next" href="/blog/give-claude-code-long-term-memory/"><span class="k">Newer →</span><span class="t">How to Give Claude Code Long-Term Memory</span></a>
+ </div>
+ <section class="related">
+ <h2>Related in Memory</h2>
+ <div class="post-grid">
+ <article class="card">
+ <a class="thumb t-memory" href="/blog/give-claude-code-long-term-memory/" aria-hidden="true" tabindex="-1">
+ <span>MEMORY</span>
+ </a>
+ <div class="body">
+ <div class="meta">
+ <time datetime="2026-05-27">May 27, 2026</time>
+ <span class="dot" aria-hidden="true"></span>
+ <span>3 min</span>
+ </div>
+ <h3><a href="/blog/give-claude-code-long-term-memory/">How to Give Claude Code Long-Term Memory</a></h3>
+ <p class="dek">Claude Code forgets between sessions. Here&#39;s how a markdown-first memory layer with semantic recall lets your agents remember across runs.</p>
+ <div class="foot">
+ <span class="tag kind">Memory</span>
+ <a class="more" href="/blog/give-claude-code-long-term-memory/" aria-label="Read: How to Give Claude Code Long-Term Memory">Read →</a>
+ </div>
+ </div>
+</article>
+
+ </div>
+ </section>
+
+ </footer>
+</article>
+
+</main>
+<footer>
+ <div class="wrap">
+ <div class="foot-top">
+ <a class="foot-brand brand" href="/blog/">
+ <span class="brand-mark">MD</span>
+ <span class="brand-word">MUNDER DIFFLIN<span class="sep">/</span><span class="blog">BLOG</span></span>
+ </a>
+ <div class="foot-links">
+ <a href="/blog/">Latest</a>
+ <a href="/blog/topics/">Topics</a>
+ <a href="/blog/about/">About</a>
+ <a href="https://munderdiffl.in/blog/feed.xml">RSS</a>
+ <a href="https://github.com/chaitanyagiri/munder-difflin">GitHub</a>
+ <a href="https://munderdiffl.in">munderdiffl.in ↗</a>
+ </div>
+ </div>
+ <div class="foot-meta">
+ © 2026 Munder Difflin · Local-first · MIT-licensed ·
+ Built on <a href="https://munderdiffl.in">Electron, React, Pixi.js, xterm.js &amp; node-pty</a>.
+ Run an office of agents while you sleep.
+ </div>
+ </div>
+</footer>
+
+<script>
+ // sticky-nav border on scroll
+ (function () {
+ var nav = document.getElementById('nav');
+ if (!nav) return;
+ var onScroll = function () { nav.classList.toggle('scrolled', window.scrollY > 8); };
+ onScroll(); window.addEventListener('scroll', onScroll, { passive: true });
+ })();
+</script>
+
+</body>
+</html>
diff --git a/docs/blog/single-committer-git-pattern/index.html b/docs/blog/single-committer-git-pattern/index.html
new file mode 100644
index 00000000..147cc75f
--- /dev/null
+++ b/docs/blog/single-committer-git-pattern/index.html
@@ -0,0 +1,389 @@
+<!doctype html>
+<html lang="en">
+<head>
+<meta charset="UTF-8" />
+<meta name="viewport" content="width=device-width, initial-scale=1.0" />
+<title>The Single-Committer Pattern: Multi-Agent Git Without Corruption — Munder Difflin Blog</title>
+<meta name="description" content="Parallel agents corrupt a repo with index.lock races. The single-committer pattern — agents write, one process commits — fixes concurrent git writes." />
+<link rel="canonical" href="https://munderdiffl.in/blog/single-committer-git-pattern/" />
+
+<link rel="icon" type="image/png" href="https://munderdiffl.in/logo.png" />
+<link rel="apple-touch-icon" href="https://munderdiffl.in/logo.png" />
+<meta name="theme-color" content="#F5F2E8" />
+
+<!-- Open Graph -->
+<meta property="og:site_name" content="Munder Difflin Blog" />
+<meta property="og:type" content="article" />
+<meta property="og:title" content="The Single-Committer Pattern: Multi-Agent Git Without Corruption — Munder Difflin Blog" />
+<meta property="og:description" content="Parallel agents corrupt a repo with index.lock races. The single-committer pattern — agents write, one process commits — fixes concurrent git writes." />
+<meta property="og:url" content="https://munderdiffl.in/blog/single-committer-git-pattern/" />
+<meta property="og:image" content="https://munderdiffl.in/media/og.png" />
+<meta property="og:locale" content="en_US" />
+<meta property="article:published_time" content="2026-06-02T00:00:00.000Z" />
+<meta property="article:author" content="Chaitanya Giri" />
+<meta property="article:tag" content="Internals" />
+<meta property="article:tag" content="Git" />
+<meta property="article:tag" content="Multi-Agent" />
+<meta property="article:tag" content="Concurrency" />
+
+
+<!-- Twitter -->
+<meta name="twitter:card" content="summary_large_image" />
+<meta name="twitter:title" content="The Single-Committer Pattern: Multi-Agent Git Without Corruption — Munder Difflin Blog" />
+<meta name="twitter:description" content="Parallel agents corrupt a repo with index.lock races. The single-committer pattern — agents write, one process commits — fixes concurrent git writes." />
+<meta name="twitter:image" content="https://munderdiffl.in/media/og.png" />
+
+<link rel="alternate" type="application/atom+xml" title="Munder Difflin Blog" href="https://munderdiffl.in/blog/feed.xml" />
+<link rel="preconnect" href="https://fonts.googleapis.com" />
+<link rel="preconnect" href="https://fonts.gstatic.com" crossorigin />
+<link href="https://fonts.googleapis.com/css2?family=Geist:wght@400;500;600&family=JetBrains+Mono:wght@400;500;600;700&display=swap" rel="stylesheet" />
+<link rel="stylesheet" href="/blog/assets/blog.css" />
+
+<script type="application/ld+json">
+{
+ "@context": "https://schema.org",
+ "@type": "BlogPosting",
+ "headline": "The Single-Committer Pattern: Multi-Agent Git Without Corruption",
+ "description": "Parallel agents corrupt a repo with index.lock races. The single-committer pattern — agents write, one process commits — fixes concurrent git writes.",
+ "image": ["https://munderdiffl.in/media/og.png"],
+ "datePublished": "2026-06-02T00:00:00.000Z",
+ "dateModified": "2026-06-02T00:00:00.000Z",
+ "author": { "@type": "Person", "name": "Chaitanya Giri" },
+ "publisher": {
+ "@type": "Organization",
+ "name": "Munder Difflin",
+ "logo": { "@type": "ImageObject", "url": "https://munderdiffl.in/logo.png" }
+ },
+ "mainEntityOfPage": { "@type": "WebPage", "@id": "https://munderdiffl.in/blog/single-committer-git-pattern/" },
+ "keywords": "single committer git multi agent, git index.lock, multi-agent git, concurrent git writes",
+ "articleSection": "Internals",
+ "inLanguage": "en-US",
+ "url": "https://munderdiffl.in/blog/single-committer-git-pattern/"
+}
+</script>
+<script type="application/ld+json">
+{
+ "@context": "https://schema.org",
+ "@type": "BreadcrumbList",
+ "itemListElement": [
+ { "@type": "ListItem", "position": 1, "name": "Home", "item": "https://munderdiffl.in/" },
+ { "@type": "ListItem", "position": 2, "name": "Blog", "item": "https://munderdiffl.in/blog/" },
+ { "@type": "ListItem", "position": 3, "name": "The Single-Committer Pattern: Multi-Agent Git Without Corruption", "item": "https://munderdiffl.in/blog/single-committer-git-pattern/" }
+ ]
+}
+</script>
+
+<script type="application/ld+json">
+{
+ "@context": "https://schema.org",
+ "@type": "FAQPage",
+ "mainEntity": [
+ { "@type": "Question", "name": "What causes git index.lock errors with multiple agents?", "acceptedAnswer": { "@type": "Answer", "text": "Git takes an exclusive lock on .git/index while staging or committing. If two processes run git at the same time, the second finds the lock held and fails — or worse, a crashed process leaves a stale lock behind that blocks every future commit." } },
+ { "@type": "Question", "name": "How do you let many agents share one git repo safely?", "acceptedAnswer": { "@type": "Answer", "text": "Don't let the agents call git at all. Agents write plain files; a single coordinating process owns every commit, serializing them. Concurrency on the repo drops to one writer, so the lock is never contended." } },
+ { "@type": "Question", "name": "Do agents lose anything by not running git themselves?", "acceptedAnswer": { "@type": "Answer", "text": "No. They still create, edit, and delete files freely. They just don't stage or commit — that's delegated to one committer, which turns git into a clean, serialized audit log of the team's work." } }
+
+ ]
+}
+</script>
+
+
+</head>
+<body>
+<a class="skip-link" href="#main">Skip to content</a>
+<nav id="nav">
+ <a class="brand" href="/blog/" aria-label="Munder Difflin Blog home">
+ <span class="brand-mark">MD</span>
+ <span class="brand-word">MUNDER DIFFLIN<span class="sep">/</span><span class="blog">BLOG</span></span>
+ </a>
+ <span class="spacer"></span>
+ <div class="links">
+ <a href="/blog/">Latest</a>
+ <a href="/blog/topics/">Topics</a>
+ <a href="/blog/about/">About</a>
+ <a href="https://munderdiffl.in">↗ Product</a>
+ </div>
+ <div class="nav-actions">
+ <a class="btn sm" href="https://munderdiffl.in/blog/feed.xml" aria-label="RSS feed">⤵ RSS</a>
+ <a class="btn sm primary" href="https://munderdiffl.in/#install">⤓ Download</a>
+ </div>
+</nav>
+
+<main id="main">
+
+<article>
+ <header class="post-head wrap">
+ <nav class="crumbs" aria-label="Breadcrumb">
+ <a href="/blog/">Blog</a>
+ <span>/</span>
+ <a href="/blog/topics/internals/">Internals</a>
+ </nav>
+ <h1>The Single-Committer Pattern: Multi-Agent Git Without Corruption</h1>
+ <p class="dek">Parallel agents corrupt a repo with index.lock races. The single-committer pattern — agents write, one process commits — fixes concurrent git writes.</p>
+ <div class="byline">
+ <span class="av" aria-hidden="true">CG</span>
+ <strong>Chaitanya Giri</strong>
+ <span class="dot" aria-hidden="true">·</span>
+ <time datetime="2026-06-02">Jun 2, 2026</time>
+ <span class="dot" aria-hidden="true">·</span>
+ <span>5 min read</span>
+ <span class="tag kind">Internals</span>
+ </div>
+ </header>
+
+ <div class="post-wrap wrap">
+ <div class="prose">
+ <div class="callout tldr"><span class="ic">TL;DR</span><p>Run several agents against one git repo and
+they'll race on <code>.git/index.lock</code>, producing failed and half-staged commits. The
+<strong>single-committer pattern</strong> fixes it: <strong>agents only write plain files; one process
+owns every commit</strong>, serialized, with retry-and-backoff and stale-lock recovery. Concurrency on
+the repo drops to exactly one writer, so corruption becomes impossible — and git turns into a tidy
+audit log of everything the team did.</p></div>
+<p>If you’ve ever pointed two automated agents at the same repository, you’ve probably met this error:</p>
+<pre><code>fatal: Unable to create '/path/.git/index.lock': File exists.
+</code></pre>
+<p>It looks transient. It isn’t a fluke — it’s git telling you that two processes tried to write its index
+at once. As you add agents, it goes from occasional to constant, and a crashed agent can leave a stale
+lock that blocks <em>every</em> future commit. This post explains why it happens and the pattern that ends it.</p>
+<h2 id="why-concurrent-git-writes-corrupt" tabindex="-1">Why concurrent git writes corrupt <a class="anchor" href="#why-concurrent-git-writes-corrupt" aria-hidden="true">#</a></h2>
+<p>Git is not designed for concurrent writers. When you stage or commit, git takes an <strong>exclusive lock</strong>
+by creating <code>.git/index.lock</code>; it does its work against that file, then atomically renames it over
+<code>.git/index</code> and releases the lock. The lock guarantees that only one operation mutates the index at a
+time.</p>
+<p>That’s fine for a human typing one command. It falls apart with parallel agents:</p>
+<ul>
+<li><strong>Contention.</strong> Two agents commit at the same instant. One gets the lock; the other finds
+<code>index.lock</code> already present and fails outright.</li>
+<li><strong>Half-applied state.</strong> Interleaved <code>git add</code>/<code>git commit</code> from different processes can stage a
+partial set of changes — a commit that doesn’t reflect any single agent’s intent.</li>
+<li><strong>Stale locks.</strong> An agent crashes (or is killed) mid-commit and never removes its <code>index.lock</code>. Now
+the lock file is orphaned, and every subsequent commit — by anyone — fails until someone deletes it
+by hand.</li>
+</ul>
+<p>You can’t “be careful” your way out of this. Two well-behaved agents that simply finish at the same
+second will collide. The guarantee has to come from the design, not the agents’ manners.</p>
+<h2 id="the-pattern-one-writer-for-git" tabindex="-1">The pattern: one writer for git <a class="anchor" href="#the-pattern-one-writer-for-git" aria-hidden="true">#</a></h2>
+<p>The single-committer pattern is exactly what it sounds like: <strong>only one process is ever allowed to run
+git.</strong> Everything else is downstream of that rule.</p>
+<ul>
+<li><strong>Agents write plain files.</strong> They create, edit, and delete files in their workspaces freely. They
+do <em>not</em> run <code>git add</code>, <code>git commit</code>, or anything else that touches the index. As far as the agents
+are concerned, git doesn’t exist.</li>
+<li><strong>One coordinating process commits.</strong> A single committer watches the shared state, stages changes,
+and commits them — one at a time, in order. Because it’s the only thing calling git, <code>index.lock</code> is
+never contended. There is no second writer to race with.</li>
+</ul>
+<p>This collapses a hard concurrency problem into a trivial one. The repo has many <em>readers</em> and exactly
+one <em>writer</em>, which is the configuration git is perfectly happy with.</p>
+<h2 id="making-the-single-committer-bulletproof" tabindex="-1">Making the single committer bulletproof <a class="anchor" href="#making-the-single-committer-bulletproof" aria-hidden="true">#</a></h2>
+<p>“One committer” removes contention between agents, but the committer still has to handle the messy
+real world: a previous run that died, an occasional transient failure. A production-grade committer
+does three things.</p>
+<h3 id="1-retry-with-backoff" tabindex="-1">1. Retry with backoff <a class="anchor" href="#1-retry-with-backoff" aria-hidden="true">#</a></h3>
+<p>Even a lone committer can hit a lock left by something else (a stray <code>git</code> you ran in another terminal,
+a hook). So each commit attempt is wrapped in a small retry loop: try to commit; if it fails on a lock,
+wait a short, growing interval and try again. A handful of attempts with increasing backoff absorbs any
+brief contention without surfacing an error to the user.</p>
+<pre class="language-text"><code class="language-text">for attempt in 0..5:
+ clear stale lock if present
+ git add -A
+ git commit -m <message>
+ → success? return
+ → "nothing to commit"? return # not an error
+ → lock error? sleep 50ms * (attempt + 1); retry
+ → other failure? give up quietly; the next change retries</code></pre>
+<h3 id="2-stale-lock-recovery" tabindex="-1">2. Stale-lock recovery <a class="anchor" href="#2-stale-lock-recovery" aria-hidden="true">#</a></h3>
+<p>A lock file that’s been sitting untouched for a while almost certainly belongs to a dead process. The
+committer checks the lock’s age before each attempt and, if it’s older than a threshold (say, ten
+seconds with no modification), removes it. That single check is what turns “a crashed agent bricked our
+commits” into a non-event — the next commit cleans up and proceeds.</p>
+<h3 id="3-a-deterministic-git-identity" tabindex="-1">3. A deterministic git identity <a class="anchor" href="#3-a-deterministic-git-identity" aria-hidden="true">#</a></h3>
+<p>Because the committer commits on behalf of the whole team, it uses a fixed identity and disables
+signing, so commits never block on a GPG prompt or a missing <code>user.name</code>:</p>
+<pre class="language-bash"><code class="language-bash"><span class="token function">git</span> <span class="token parameter variable">-c</span> <span class="token assign-left variable">commit.gpgsign</span><span class="token operator">=</span>false <span class="token parameter variable">-c</span> <span class="token assign-left variable">user.name</span><span class="token operator">=</span>Hive <span class="token parameter variable">-c</span> <span class="token assign-left variable">user.email</span><span class="token operator">=</span>hive@local commit <span class="token parameter variable">-m</span> <span class="token string">"…"</span></code></pre>
+<p>Now every coordination step is a clean, attributable commit, and nothing can hang waiting for
+interactive input.</p>
+<h2 id="the-bonus-git-becomes-an-audit-log" tabindex="-1">The bonus: git becomes an audit log <a class="anchor" href="#the-bonus-git-becomes-an-audit-log" aria-hidden="true">#</a></h2>
+<p>Here’s the part that turns a workaround into an asset. Once one process owns every commit, the repo
+stops being a liability and becomes a <strong>serialized history of everything the team did</strong>. Each routed
+message, each task assignment, each memory update lands as its own commit, in order. When a multi-agent
+run goes sideways, you don’t guess — you read the log.</p>
+<p>That pairs naturally with the messaging layer: agents coordinate through files (see
+<a href="/blog/atomic-file-mailboxes-for-agents/">atomic file mailboxes</a>), and the single committer commits
+those file changes as they happen. The same single-writer discipline runs through both — it’s the
+backbone of <a href="/blog/coordinating-ai-coding-agents/">coordinating AI coding agents</a> without collisions.</p>
+<h2 id="what-about-the-users-own-repo" tabindex="-1">What about the user’s own repo? <a class="anchor" href="#what-about-the-users-own-repo" aria-hidden="true">#</a></h2>
+<p>A fair question: if agents are editing your <em>actual</em> code repository, who commits <em>that</em>? The
+single-committer pattern is about the <strong>coordination</strong> repo — the shared state the agents use to talk,
+remember, and track tasks. Your source repo is separate, and you stay in control of its commits the way
+you always have (or you delegate them deliberately to one agent with that role). The point is that the
+machinery the agents rely on to cooperate never corrupts itself, no matter how many of them are running.</p>
+<h2 id="when-you-need-this" tabindex="-1">When you need this <a class="anchor" href="#when-you-need-this" aria-hidden="true">#</a></h2>
+<p>You need the single-committer pattern the moment <strong>more than one automated process</strong> shares a git repo:</p>
+<ul>
+<li>multiple coding agents in the same project,</li>
+<li>an agent plus a background job that both commit,</li>
+<li>any “swarm” or “hive” where coordination state lives in git.</li>
+</ul>
+<p>If it’s just you and one agent taking turns, you’ll rarely see a lock. Add a second concurrent writer
+and the races begin — which is precisely when this pattern stops being optional.</p>
+<h2 id="faq" tabindex="-1">FAQ <a class="anchor" href="#faq" aria-hidden="true">#</a></h2>
+<p><strong>Why not use git worktrees to isolate each agent?</strong> Worktrees give each agent its own working
+directory, which helps with <em>file</em> isolation — but each worktree still has its own index, and shared
+refs can still contend. Worktrees and single-committer solve different halves of the problem; see
+<a href="/blog/claude-code-git-worktrees-vs-hive/">git worktrees vs a hive</a> for when each applies.</p>
+<p><strong>Isn’t a lock just a retry-until-it-works situation?</strong> Retrying helps with transient contention, but
+it does nothing for a <em>stale</em> lock from a dead process — that one never clears on its own. You need the
+age-based cleanup, not just retries.</p>
+<hr>
+<p>Munder Difflin uses the single-committer pattern for its entire coordination layer: agents write
+files, one process commits with retry and stale-lock recovery, and the repo stays a clean audit log.
+<a href="https://munderdiffl.in/#install">Download Munder Difflin</a> to run a hive of Claude Code agents that
+never corrupt their own state; it’s free and open source.</p>
+
+
+
+ <section class="faq" aria-label="Frequently asked questions">
+ <h2 id="faq">FAQ</h2>
+
+ <div class="qa">
+ <p class="q">What causes git index.lock errors with multiple agents?</p>
+ <p class="a">Git takes an exclusive lock on .git/index while staging or committing. If two processes run git at the same time, the second finds the lock held and fails — or worse, a crashed process leaves a stale lock behind that blocks every future commit.</p>
+ </div>
+
+ <div class="qa">
+ <p class="q">How do you let many agents share one git repo safely?</p>
+ <p class="a">Don&#39;t let the agents call git at all. Agents write plain files; a single coordinating process owns every commit, serializing them. Concurrency on the repo drops to one writer, so the lock is never contended.</p>
+ </div>
+
+ <div class="qa">
+ <p class="q">Do agents lose anything by not running git themselves?</p>
+ <p class="a">No. They still create, edit, and delete files freely. They just don&#39;t stage or commit — that&#39;s delegated to one committer, which turns git into a clean, serialized audit log of the team&#39;s work.</p>
+ </div>
+
+ </section>
+
+
+
+ <hr />
+ <div class="share">
+ <span class="lbl">Tags</span>
+ <a class="tag" href="/blog/tags/internals/">Internals</a><a class="tag" href="/blog/tags/git/">Git</a><a class="tag" href="/blog/tags/multi-agent/">Multi-Agent</a><a class="tag" href="/blog/tags/concurrency/">Concurrency</a>
+ </div>
+
+ </div>
+
+
+ <aside class="toc-rail" aria-label="Table of contents">
+ <div class="tt">On this page</div>
+ <ol>
+ <li class="lvl-2"><a href="#why-concurrent-git-writes-corrupt">Why concurrent git writes corrupt</a></li><li class="lvl-2"><a href="#the-pattern-one-writer-for-git">The pattern: one writer for git</a></li><li class="lvl-2"><a href="#making-the-single-committer-bulletproof">Making the single committer bulletproof</a></li><li class="lvl-3"><a href="#1-retry-with-backoff">1. Retry with backoff</a></li><li class="lvl-3"><a href="#2-stale-lock-recovery">2. Stale-lock recovery</a></li><li class="lvl-3"><a href="#3-a-deterministic-git-identity">3. A deterministic git identity</a></li><li class="lvl-2"><a href="#the-bonus-git-becomes-an-audit-log">The bonus: git becomes an audit log</a></li><li class="lvl-2"><a href="#what-about-the-users-own-repo">What about the user’s own repo?</a></li><li class="lvl-2"><a href="#when-you-need-this">When you need this</a></li><li class="lvl-2"><a href="#faq">FAQ</a></li>
+ </ol>
+ </aside>
+
+ </div>
+
+ <footer class="post-foot wrap"><div class="prevnext">
+ <a class="pn prev" href="/blog/what-are-claude-code-agents/"><span class="k">← Older</span><span class="t">What Are Claude Code Agents? And How to Use Many at Once</span></a>
+ <a class="pn next" href="/blog/run-an-office-of-ai-agents/"><span class="k">Newer →</span><span class="t">Run an Office of AI Agents While You Sleep</span></a>
+ </div>
+ <section class="related">
+ <h2>Related in Internals</h2>
+ <div class="post-grid">
+ <article class="card">
+ <a class="thumb t-internals" href="/blog/building-a-terminal-ui-xterm-node-pty/" aria-hidden="true" tabindex="-1">
+ <span>INTERNALS</span>
+ </a>
+ <div class="body">
+ <div class="meta">
+ <time datetime="2026-06-03">Jun 3, 2026</time>
+ <span class="dot" aria-hidden="true"></span>
+ <span>8 min</span>
+ </div>
+ <h3><a href="/blog/building-a-terminal-ui-xterm-node-pty/">Building a Terminal UI with xterm.js and node-pty</a></h3>
+ <p class="dek">Wire xterm.js to a node-pty backend: stream output, write keystrokes back, handle resize, and keep many live terminals fast with a terminal pool.</p>
+ <div class="foot">
+ <span class="tag kind">Internals</span>
+ <a class="more" href="/blog/building-a-terminal-ui-xterm-node-pty/" aria-label="Read: Building a Terminal UI with xterm.js and node-pty">Read →</a>
+ </div>
+ </div>
+</article>
+<article class="card">
+ <a class="thumb t-internals" href="/blog/claude-code-hooks-explained/" aria-hidden="true" tabindex="-1">
+ <span>INTERNALS</span>
+ </a>
+ <div class="body">
+ <div class="meta">
+ <time datetime="2026-06-03">Jun 3, 2026</time>
+ <span class="dot" aria-hidden="true"></span>
+ <span>6 min</span>
+ </div>
+ <h3><a href="/blog/claude-code-hooks-explained/">Claude Code Hooks, Explained (PreToolUse, PostToolUse, Stop)</a></h3>
+ <p class="dek">A practical tour of Claude Code hooks — the PreToolUse, PostToolUse, and Stop lifecycle — and how a Unix-socket hook shim drives a live office floor.</p>
+ <div class="foot">
+ <span class="tag kind">Internals</span>
+ <a class="more" href="/blog/claude-code-hooks-explained/" aria-label="Read: Claude Code Hooks, Explained (PreToolUse, PostToolUse, Stop)">Read →</a>
+ </div>
+ </div>
+</article>
+<article class="card">
+ <a class="thumb t-internals" href="/blog/node-pty-electron-real-terminals/" aria-hidden="true" tabindex="-1">
+ <span>INTERNALS</span>
+ </a>
+ <div class="body">
+ <div class="meta">
+ <time datetime="2026-06-03">Jun 3, 2026</time>
+ <span class="dot" aria-hidden="true"></span>
+ <span>7 min</span>
+ </div>
+ <h3><a href="/blog/node-pty-electron-real-terminals/">Real Terminals in Electron with node-pty</a></h3>
+ <p class="dek">How to run byte-for-byte authentic shells inside Electron with node-pty: the native-rebuild gotcha, the macOS PATH trap, and streaming PTY output over IPC.</p>
+ <div class="foot">
+ <span class="tag kind">Internals</span>
+ <a class="more" href="/blog/node-pty-electron-real-terminals/" aria-label="Read: Real Terminals in Electron with node-pty">Read →</a>
+ </div>
+ </div>
+</article>
+
+ </div>
+ </section>
+
+ </footer>
+</article>
+
+</main>
+<footer>
+ <div class="wrap">
+ <div class="foot-top">
+ <a class="foot-brand brand" href="/blog/">
+ <span class="brand-mark">MD</span>
+ <span class="brand-word">MUNDER DIFFLIN<span class="sep">/</span><span class="blog">BLOG</span></span>
+ </a>
+ <div class="foot-links">
+ <a href="/blog/">Latest</a>
+ <a href="/blog/topics/">Topics</a>
+ <a href="/blog/about/">About</a>
+ <a href="https://munderdiffl.in/blog/feed.xml">RSS</a>
+ <a href="https://github.com/chaitanyagiri/munder-difflin">GitHub</a>
+ <a href="https://munderdiffl.in">munderdiffl.in ↗</a>
+ </div>
+ </div>
+ <div class="foot-meta">
+ © 2026 Munder Difflin · Local-first · MIT-licensed ·
+ Built on <a href="https://munderdiffl.in">Electron, React, Pixi.js, xterm.js &amp; node-pty</a>.
+ Run an office of agents while you sleep.
+ </div>
+ </div>
+</footer>
+
+<script>
+ // sticky-nav border on scroll
+ (function () {
+ var nav = document.getElementById('nav');
+ if (!nav) return;
+ var onScroll = function () { nav.classList.toggle('scrolled', window.scrollY > 8); };
+ onScroll(); window.addEventListener('scroll', onScroll, { passive: true });
+ })();
+</script>
+
+</body>
+</html>
diff --git a/docs/blog/tags/automation/index.html b/docs/blog/tags/automation/index.html
new file mode 100644
index 00000000..5ef5897b
--- /dev/null
+++ b/docs/blog/tags/automation/index.html
@@ -0,0 +1,160 @@
+<!doctype html>
+<html lang="en">
+<head>
+<meta charset="UTF-8" />
+<meta name="viewport" content="width=device-width, initial-scale=1.0" />
+<title>Automation — Munder Difflin Blog</title>
+<meta name="description" content="Munder Difflin blog posts tagged Automation." />
+<link rel="canonical" href="https://munderdiffl.in/blog/tags/automation/" />
+
+<link rel="icon" type="image/png" href="https://munderdiffl.in/logo.png" />
+<link rel="apple-touch-icon" href="https://munderdiffl.in/logo.png" />
+<meta name="theme-color" content="#F5F2E8" />
+
+<!-- Open Graph -->
+<meta property="og:site_name" content="Munder Difflin Blog" />
+<meta property="og:type" content="website" />
+<meta property="og:title" content="Automation — Munder Difflin Blog" />
+<meta property="og:description" content="Munder Difflin blog posts tagged Automation." />
+<meta property="og:url" content="https://munderdiffl.in/blog/tags/automation/" />
+<meta property="og:image" content="https://munderdiffl.in/media/og.png" />
+<meta property="og:locale" content="en_US" />
+
+
+<!-- Twitter -->
+<meta name="twitter:card" content="summary_large_image" />
+<meta name="twitter:title" content="Automation — Munder Difflin Blog" />
+<meta name="twitter:description" content="Munder Difflin blog posts tagged Automation." />
+<meta name="twitter:image" content="https://munderdiffl.in/media/og.png" />
+
+<link rel="alternate" type="application/atom+xml" title="Munder Difflin Blog" href="https://munderdiffl.in/blog/feed.xml" />
+<link rel="preconnect" href="https://fonts.googleapis.com" />
+<link rel="preconnect" href="https://fonts.gstatic.com" crossorigin />
+<link href="https://fonts.googleapis.com/css2?family=Geist:wght@400;500;600&family=JetBrains+Mono:wght@400;500;600;700&display=swap" rel="stylesheet" />
+<link rel="stylesheet" href="/blog/assets/blog.css" />
+
+</head>
+<body>
+<a class="skip-link" href="#main">Skip to content</a>
+<nav id="nav">
+ <a class="brand" href="/blog/" aria-label="Munder Difflin Blog home">
+ <span class="brand-mark">MD</span>
+ <span class="brand-word">MUNDER DIFFLIN<span class="sep">/</span><span class="blog">BLOG</span></span>
+ </a>
+ <span class="spacer"></span>
+ <div class="links">
+ <a href="/blog/">Latest</a>
+ <a href="/blog/topics/">Topics</a>
+ <a href="/blog/about/">About</a>
+ <a href="https://munderdiffl.in">↗ Product</a>
+ </div>
+ <div class="nav-actions">
+ <a class="btn sm" href="https://munderdiffl.in/blog/feed.xml" aria-label="RSS feed">⤵ RSS</a>
+ <a class="btn sm primary" href="https://munderdiffl.in/#install">⤓ Download</a>
+ </div>
+</nav>
+
+<main id="main">
+<header class="page-head wrap">
+ <p class="eyebrow">Tag</p>
+ <h1>#Automation</h1>
+ <p class="lead">3 posts tagged <strong>Automation</strong>.</p>
+</header>
+<section class="wrap">
+ <div class="post-grid">
+ <article class="card">
+ <a class="thumb t-guides" href="/blog/claude-code-automation-while-you-sleep/" aria-hidden="true" tabindex="-1">
+ <span>GUIDES</span>
+ </a>
+ <div class="body">
+ <div class="meta">
+ <time datetime="2026-06-04">Jun 4, 2026</time>
+ <span class="dot" aria-hidden="true"></span>
+ <span>5 min</span>
+ </div>
+ <h3><a href="/blog/claude-code-automation-while-you-sleep/">Claude Code Automation: Let Agents Build While You Sleep</a></h3>
+ <p class="dek">Claude Code automation that runs overnight: an autonomous Stop-hook loop, safe permission bypass, and guardrails so you wake up to progress, not chaos.</p>
+ <div class="foot">
+ <span class="tag kind">Guides</span>
+ <a class="more" href="/blog/claude-code-automation-while-you-sleep/" aria-label="Read: Claude Code Automation: Let Agents Build While You Sleep">Read →</a>
+ </div>
+ </div>
+</article>
+<article class="card">
+ <a class="thumb t-internals" href="/blog/claude-code-hooks-explained/" aria-hidden="true" tabindex="-1">
+ <span>INTERNALS</span>
+ </a>
+ <div class="body">
+ <div class="meta">
+ <time datetime="2026-06-03">Jun 3, 2026</time>
+ <span class="dot" aria-hidden="true"></span>
+ <span>6 min</span>
+ </div>
+ <h3><a href="/blog/claude-code-hooks-explained/">Claude Code Hooks, Explained (PreToolUse, PostToolUse, Stop)</a></h3>
+ <p class="dek">A practical tour of Claude Code hooks — the PreToolUse, PostToolUse, and Stop lifecycle — and how a Unix-socket hook shim drives a live office floor.</p>
+ <div class="foot">
+ <span class="tag kind">Internals</span>
+ <a class="more" href="/blog/claude-code-hooks-explained/" aria-label="Read: Claude Code Hooks, Explained (PreToolUse, PostToolUse, Stop)">Read →</a>
+ </div>
+ </div>
+</article>
+<article class="card">
+ <a class="thumb t-use-cases" href="/blog/run-an-office-of-ai-agents/" aria-hidden="true" tabindex="-1">
+ <span>USE CASES</span>
+ </a>
+ <div class="body">
+ <div class="meta">
+ <time datetime="2026-06-02">Jun 2, 2026</time>
+ <span class="dot" aria-hidden="true"></span>
+ <span>3 min</span>
+ </div>
+ <h3><a href="/blog/run-an-office-of-ai-agents/">Run an Office of AI Agents While You Sleep</a></h3>
+ <p class="dek">What it takes to run a self-coordinating office of AI coding agents that keeps shipping after you log off — and the guardrails that keep it sane.</p>
+ <div class="foot">
+ <span class="tag kind">Use Cases</span>
+ <a class="more" href="/blog/run-an-office-of-ai-agents/" aria-label="Read: Run an Office of AI Agents While You Sleep">Read →</a>
+ </div>
+ </div>
+</article>
+
+ </div>
+</section>
+
+
+</main>
+<footer>
+ <div class="wrap">
+ <div class="foot-top">
+ <a class="foot-brand brand" href="/blog/">
+ <span class="brand-mark">MD</span>
+ <span class="brand-word">MUNDER DIFFLIN<span class="sep">/</span><span class="blog">BLOG</span></span>
+ </a>
+ <div class="foot-links">
+ <a href="/blog/">Latest</a>
+ <a href="/blog/topics/">Topics</a>
+ <a href="/blog/about/">About</a>
+ <a href="https://munderdiffl.in/blog/feed.xml">RSS</a>
+ <a href="https://github.com/chaitanyagiri/munder-difflin">GitHub</a>
+ <a href="https://munderdiffl.in">munderdiffl.in ↗</a>
+ </div>
+ </div>
+ <div class="foot-meta">
+ © 2026 Munder Difflin · Local-first · MIT-licensed ·
+ Built on <a href="https://munderdiffl.in">Electron, React, Pixi.js, xterm.js &amp; node-pty</a>.
+ Run an office of agents while you sleep.
+ </div>
+ </div>
+</footer>
+
+<script>
+ // sticky-nav border on scroll
+ (function () {
+ var nav = document.getElementById('nav');
+ if (!nav) return;
+ var onScroll = function () { nav.classList.toggle('scrolled', window.scrollY > 8); };
+ onScroll(); window.addEventListener('scroll', onScroll, { passive: true });
+ })();
+</script>
+
+</body>
+</html>
diff --git a/docs/blog/tags/autonomous/index.html b/docs/blog/tags/autonomous/index.html
new file mode 100644
index 00000000..44857e28
--- /dev/null
+++ b/docs/blog/tags/autonomous/index.html
@@ -0,0 +1,124 @@
+<!doctype html>
+<html lang="en">
+<head>
+<meta charset="UTF-8" />
+<meta name="viewport" content="width=device-width, initial-scale=1.0" />
+<title>Autonomous — Munder Difflin Blog</title>
+<meta name="description" content="Munder Difflin blog posts tagged Autonomous." />
+<link rel="canonical" href="https://munderdiffl.in/blog/tags/autonomous/" />
+
+<link rel="icon" type="image/png" href="https://munderdiffl.in/logo.png" />
+<link rel="apple-touch-icon" href="https://munderdiffl.in/logo.png" />
+<meta name="theme-color" content="#F5F2E8" />
+
+<!-- Open Graph -->
+<meta property="og:site_name" content="Munder Difflin Blog" />
+<meta property="og:type" content="website" />
+<meta property="og:title" content="Autonomous — Munder Difflin Blog" />
+<meta property="og:description" content="Munder Difflin blog posts tagged Autonomous." />
+<meta property="og:url" content="https://munderdiffl.in/blog/tags/autonomous/" />
+<meta property="og:image" content="https://munderdiffl.in/media/og.png" />
+<meta property="og:locale" content="en_US" />
+
+
+<!-- Twitter -->
+<meta name="twitter:card" content="summary_large_image" />
+<meta name="twitter:title" content="Autonomous — Munder Difflin Blog" />
+<meta name="twitter:description" content="Munder Difflin blog posts tagged Autonomous." />
+<meta name="twitter:image" content="https://munderdiffl.in/media/og.png" />
+
+<link rel="alternate" type="application/atom+xml" title="Munder Difflin Blog" href="https://munderdiffl.in/blog/feed.xml" />
+<link rel="preconnect" href="https://fonts.googleapis.com" />
+<link rel="preconnect" href="https://fonts.gstatic.com" crossorigin />
+<link href="https://fonts.googleapis.com/css2?family=Geist:wght@400;500;600&family=JetBrains+Mono:wght@400;500;600;700&display=swap" rel="stylesheet" />
+<link rel="stylesheet" href="/blog/assets/blog.css" />
+
+</head>
+<body>
+<a class="skip-link" href="#main">Skip to content</a>
+<nav id="nav">
+ <a class="brand" href="/blog/" aria-label="Munder Difflin Blog home">
+ <span class="brand-mark">MD</span>
+ <span class="brand-word">MUNDER DIFFLIN<span class="sep">/</span><span class="blog">BLOG</span></span>
+ </a>
+ <span class="spacer"></span>
+ <div class="links">
+ <a href="/blog/">Latest</a>
+ <a href="/blog/topics/">Topics</a>
+ <a href="/blog/about/">About</a>
+ <a href="https://munderdiffl.in">↗ Product</a>
+ </div>
+ <div class="nav-actions">
+ <a class="btn sm" href="https://munderdiffl.in/blog/feed.xml" aria-label="RSS feed">⤵ RSS</a>
+ <a class="btn sm primary" href="https://munderdiffl.in/#install">⤓ Download</a>
+ </div>
+</nav>
+
+<main id="main">
+<header class="page-head wrap">
+ <p class="eyebrow">Tag</p>
+ <h1>#Autonomous</h1>
+ <p class="lead">1 post tagged <strong>Autonomous</strong>.</p>
+</header>
+<section class="wrap">
+ <div class="post-grid">
+ <article class="card">
+ <a class="thumb t-guides" href="/blog/claude-code-automation-while-you-sleep/" aria-hidden="true" tabindex="-1">
+ <span>GUIDES</span>
+ </a>
+ <div class="body">
+ <div class="meta">
+ <time datetime="2026-06-04">Jun 4, 2026</time>
+ <span class="dot" aria-hidden="true"></span>
+ <span>5 min</span>
+ </div>
+ <h3><a href="/blog/claude-code-automation-while-you-sleep/">Claude Code Automation: Let Agents Build While You Sleep</a></h3>
+ <p class="dek">Claude Code automation that runs overnight: an autonomous Stop-hook loop, safe permission bypass, and guardrails so you wake up to progress, not chaos.</p>
+ <div class="foot">
+ <span class="tag kind">Guides</span>
+ <a class="more" href="/blog/claude-code-automation-while-you-sleep/" aria-label="Read: Claude Code Automation: Let Agents Build While You Sleep">Read →</a>
+ </div>
+ </div>
+</article>
+
+ </div>
+</section>
+
+
+</main>
+<footer>
+ <div class="wrap">
+ <div class="foot-top">
+ <a class="foot-brand brand" href="/blog/">
+ <span class="brand-mark">MD</span>
+ <span class="brand-word">MUNDER DIFFLIN<span class="sep">/</span><span class="blog">BLOG</span></span>
+ </a>
+ <div class="foot-links">
+ <a href="/blog/">Latest</a>
+ <a href="/blog/topics/">Topics</a>
+ <a href="/blog/about/">About</a>
+ <a href="https://munderdiffl.in/blog/feed.xml">RSS</a>
+ <a href="https://github.com/chaitanyagiri/munder-difflin">GitHub</a>
+ <a href="https://munderdiffl.in">munderdiffl.in ↗</a>
+ </div>
+ </div>
+ <div class="foot-meta">
+ © 2026 Munder Difflin · Local-first · MIT-licensed ·
+ Built on <a href="https://munderdiffl.in">Electron, React, Pixi.js, xterm.js &amp; node-pty</a>.
+ Run an office of agents while you sleep.
+ </div>
+ </div>
+</footer>
+
+<script>
+ // sticky-nav border on scroll
+ (function () {
+ var nav = document.getElementById('nav');
+ if (!nav) return;
+ var onScroll = function () { nav.classList.toggle('scrolled', window.scrollY > 8); };
+ onScroll(); window.addEventListener('scroll', onScroll, { passive: true });
+ })();
+</script>
+
+</body>
+</html>
diff --git a/docs/blog/tags/claude-code/index.html b/docs/blog/tags/claude-code/index.html
index d37b9cc2..13ac8135 100644
--- a/docs/blog/tags/claude-code/index.html
+++ b/docs/blog/tags/claude-code/index.html
@@ -58,11 +58,263 @@
<header class="page-head wrap">
<p class="eyebrow">Tag</p>
<h1>#Claude Code</h1>
- <p class="lead">3 posts tagged <strong>Claude Code</strong>.</p>
+ <p class="lead">24 posts tagged <strong>Claude Code</strong>.</p>
</header>
<section class="wrap">
<div class="post-grid">
<article class="card">
+ <a class="thumb t-comparisons" href="/blog/best-claude-code-multi-agent-tools/" aria-hidden="true" tabindex="-1">
+ <span>COMPARISONS</span>
+ </a>
+ <div class="body">
+ <div class="meta">
+ <time datetime="2026-06-04">Jun 4, 2026</time>
+ <span class="dot" aria-hidden="true"></span>
+ <span>6 min</span>
+ </div>
+ <h3><a href="/blog/best-claude-code-multi-agent-tools/">The Best Tools to Run Multiple Claude Code Agents (2026)</a></h3>
+ <p class="dek">An honest 2026 roundup of tools to run multiple Claude Code agents — Claude Squad, Conductor, Crystal, vibe-kanban, and Munder Difflin — compared.</p>
+ <div class="foot">
+ <span class="tag kind">Comparisons</span>
+ <a class="more" href="/blog/best-claude-code-multi-agent-tools/" aria-label="Read: The Best Tools to Run Multiple Claude Code Agents (2026)">Read →</a>
+ </div>
+ </div>
+</article>
+<article class="card">
+ <a class="thumb t-guides" href="/blog/claude-code-automation-while-you-sleep/" aria-hidden="true" tabindex="-1">
+ <span>GUIDES</span>
+ </a>
+ <div class="body">
+ <div class="meta">
+ <time datetime="2026-06-04">Jun 4, 2026</time>
+ <span class="dot" aria-hidden="true"></span>
+ <span>5 min</span>
+ </div>
+ <h3><a href="/blog/claude-code-automation-while-you-sleep/">Claude Code Automation: Let Agents Build While You Sleep</a></h3>
+ <p class="dek">Claude Code automation that runs overnight: an autonomous Stop-hook loop, safe permission bypass, and guardrails so you wake up to progress, not chaos.</p>
+ <div class="foot">
+ <span class="tag kind">Guides</span>
+ <a class="more" href="/blog/claude-code-automation-while-you-sleep/" aria-label="Read: Claude Code Automation: Let Agents Build While You Sleep">Read →</a>
+ </div>
+ </div>
+</article>
+<article class="card">
+ <a class="thumb t-orchestration" href="/blog/claude-code-git-worktrees-vs-hive/" aria-hidden="true" tabindex="-1">
+ <span>ORCHESTRATION</span>
+ </a>
+ <div class="body">
+ <div class="meta">
+ <time datetime="2026-06-04">Jun 4, 2026</time>
+ <span class="dot" aria-hidden="true"></span>
+ <span>5 min</span>
+ </div>
+ <h3><a href="/blog/claude-code-git-worktrees-vs-hive/">Git Worktrees vs a Hive: Two Ways to Parallelize Claude Code</a></h3>
+ <p class="dek">Claude Code git worktrees vs a hive: when isolated worktrees suffice for parallel agents, and when you need memory, messaging, and an orchestrator on top.</p>
+ <div class="foot">
+ <span class="tag kind">Orchestration</span>
+ <a class="more" href="/blog/claude-code-git-worktrees-vs-hive/" aria-label="Read: Git Worktrees vs a Hive: Two Ways to Parallelize Claude Code">Read →</a>
+ </div>
+ </div>
+</article>
+<article class="card">
+ <a class="thumb t-comparisons" href="/blog/claude-code-orchestration-tools-compared/" aria-hidden="true" tabindex="-1">
+ <span>COMPARISONS</span>
+ </a>
+ <div class="body">
+ <div class="meta">
+ <time datetime="2026-06-04">Jun 4, 2026</time>
+ <span class="dot" aria-hidden="true"></span>
+ <span>3 min</span>
+ </div>
+ <h3><a href="/blog/claude-code-orchestration-tools-compared/">Claude Code Orchestration Tools, Compared</a></h3>
+ <p class="dek">Claude Code orchestration tools compared on memory, messaging, visibility, control, and local-first — across Claude Squad, Conductor, Crystal, and more.</p>
+ <div class="foot">
+ <span class="tag kind">Comparisons</span>
+ <a class="more" href="/blog/claude-code-orchestration-tools-compared/" aria-label="Read: Claude Code Orchestration Tools, Compared">Read →</a>
+ </div>
+ </div>
+</article>
+<article class="card">
+ <a class="thumb t-comparisons" href="/blog/claude-squad-vs-munder-difflin/" aria-hidden="true" tabindex="-1">
+ <span>COMPARISONS</span>
+ </a>
+ <div class="body">
+ <div class="meta">
+ <time datetime="2026-06-04">Jun 4, 2026</time>
+ <span class="dot" aria-hidden="true"></span>
+ <span>3 min</span>
+ </div>
+ <h3><a href="/blog/claude-squad-vs-munder-difflin/">Claude Squad vs Munder Difflin: Which Should You Use?</a></h3>
+ <p class="dek">Claude Squad vs Munder Difflin: a lean terminal session manager against a memory-backed, orchestrated, visual hive. Feature table and an honest verdict.</p>
+ <div class="foot">
+ <span class="tag kind">Comparisons</span>
+ <a class="more" href="/blog/claude-squad-vs-munder-difflin/" aria-label="Read: Claude Squad vs Munder Difflin: Which Should You Use?">Read →</a>
+ </div>
+ </div>
+</article>
+<article class="card">
+ <a class="thumb t-internals" href="/blog/claude-code-hooks-explained/" aria-hidden="true" tabindex="-1">
+ <span>INTERNALS</span>
+ </a>
+ <div class="body">
+ <div class="meta">
+ <time datetime="2026-06-03">Jun 3, 2026</time>
+ <span class="dot" aria-hidden="true"></span>
+ <span>6 min</span>
+ </div>
+ <h3><a href="/blog/claude-code-hooks-explained/">Claude Code Hooks, Explained (PreToolUse, PostToolUse, Stop)</a></h3>
+ <p class="dek">A practical tour of Claude Code hooks — the PreToolUse, PostToolUse, and Stop lifecycle — and how a Unix-socket hook shim drives a live office floor.</p>
+ <div class="foot">
+ <span class="tag kind">Internals</span>
+ <a class="more" href="/blog/claude-code-hooks-explained/" aria-label="Read: Claude Code Hooks, Explained (PreToolUse, PostToolUse, Stop)">Read →</a>
+ </div>
+ </div>
+</article>
+<article class="card">
+ <a class="thumb t-comparisons" href="/blog/claude-squad-alternative/" aria-hidden="true" tabindex="-1">
+ <span>COMPARISONS</span>
+ </a>
+ <div class="body">
+ <div class="meta">
+ <time datetime="2026-06-03">Jun 3, 2026</time>
+ <span class="dot" aria-hidden="true"></span>
+ <span>3 min</span>
+ </div>
+ <h3><a href="/blog/claude-squad-alternative/">Looking for a Claude Squad Alternative?</a></h3>
+ <p class="dek">What Claude Squad does well, where it stops, and why a memory-backed, orchestrated hive may be the Claude Squad alternative you&#39;re after.</p>
+ <div class="foot">
+ <span class="tag kind">Comparisons</span>
+ <a class="more" href="/blog/claude-squad-alternative/" aria-label="Read: Looking for a Claude Squad Alternative?">Read →</a>
+ </div>
+ </div>
+</article>
+<article class="card">
+ <a class="thumb t-comparisons" href="/blog/conductor-claude-code-alternative/" aria-hidden="true" tabindex="-1">
+ <span>COMPARISONS</span>
+ </a>
+ <div class="body">
+ <div class="meta">
+ <time datetime="2026-06-03">Jun 3, 2026</time>
+ <span class="dot" aria-hidden="true"></span>
+ <span>3 min</span>
+ </div>
+ <h3><a href="/blog/conductor-claude-code-alternative/">A Conductor Alternative for Orchestrating Claude Code</a></h3>
+ <p class="dek">Conductor is a polished macOS app for parallel Claude Code worktrees. When to pick a cross-platform, orchestrated hive as your Conductor alternative.</p>
+ <div class="foot">
+ <span class="tag kind">Comparisons</span>
+ <a class="more" href="/blog/conductor-claude-code-alternative/" aria-label="Read: A Conductor Alternative for Orchestrating Claude Code">Read →</a>
+ </div>
+ </div>
+</article>
+<article class="card">
+ <a class="thumb t-comparisons" href="/blog/crystal-claude-code-alternative/" aria-hidden="true" tabindex="-1">
+ <span>COMPARISONS</span>
+ </a>
+ <div class="body">
+ <div class="meta">
+ <time datetime="2026-06-03">Jun 3, 2026</time>
+ <span class="dot" aria-hidden="true"></span>
+ <span>3 min</span>
+ </div>
+ <h3><a href="/blog/crystal-claude-code-alternative/">A Crystal Alternative: Multi-Agent Claude Code with Memory</a></h3>
+ <p class="dek">Crystal runs parallel Claude Code worktrees well. Where a memory-backed, orchestrated hive changes the workflow — and when to stick with Crystal.</p>
+ <div class="foot">
+ <span class="tag kind">Comparisons</span>
+ <a class="more" href="/blog/crystal-claude-code-alternative/" aria-label="Read: A Crystal Alternative: Multi-Agent Claude Code with Memory">Read →</a>
+ </div>
+ </div>
+</article>
+<article class="card">
+ <a class="thumb t-guides" href="/blog/mcp-and-skills-in-a-hive/" aria-hidden="true" tabindex="-1">
+ <span>GUIDES</span>
+ </a>
+ <div class="body">
+ <div class="meta">
+ <time datetime="2026-06-03">Jun 3, 2026</time>
+ <span class="dot" aria-hidden="true"></span>
+ <span>6 min</span>
+ </div>
+ <h3><a href="/blog/mcp-and-skills-in-a-hive/">Bringing Your MCP Servers and Skills Into a Hive of Agents</a></h3>
+ <p class="dek">How agents in a hive inherit your existing Claude Code MCP servers, skills, and tools — and how to scope which agent gets which capability.</p>
+ <div class="foot">
+ <span class="tag kind">Guides</span>
+ <a class="more" href="/blog/mcp-and-skills-in-a-hive/" aria-label="Read: Bringing Your MCP Servers and Skills Into a Hive of Agents">Read →</a>
+ </div>
+ </div>
+</article>
+<article class="card">
+ <a class="thumb t-use-cases" href="/blog/from-one-terminal-to-a-team/" aria-hidden="true" tabindex="-1">
+ <span>USE CASES</span>
+ </a>
+ <div class="body">
+ <div class="meta">
+ <time datetime="2026-06-02">Jun 2, 2026</time>
+ <span class="dot" aria-hidden="true"></span>
+ <span>3 min</span>
+ </div>
+ <h3><a href="/blog/from-one-terminal-to-a-team/">From One Terminal to a Team: Scaling Your Claude Code Workflow</a></h3>
+ <p class="dek">The workflow shift from a single Claude Code session to a coordinated team of agents — what changes, where it breaks, and the concrete before-and-after.</p>
+ <div class="foot">
+ <span class="tag kind">Use Cases</span>
+ <a class="more" href="/blog/from-one-terminal-to-a-team/" aria-label="Read: From One Terminal to a Team: Scaling Your Claude Code Workflow">Read →</a>
+ </div>
+ </div>
+</article>
+<article class="card">
+ <a class="thumb t-concepts" href="/blog/munder-difflin-faq/" aria-hidden="true" tabindex="-1">
+ <span>CONCEPTS</span>
+ </a>
+ <div class="body">
+ <div class="meta">
+ <time datetime="2026-06-02">Jun 2, 2026</time>
+ <span class="dot" aria-hidden="true"></span>
+ <span>1 min</span>
+ </div>
+ <h3><a href="/blog/munder-difflin-faq/">Munder Difflin FAQ: Everything People Ask</a></h3>
+ <p class="dek">Answers to the top Munder Difflin questions — what it is, is it free, does it run locally, which platforms, and how it differs from many terminals.</p>
+ <div class="foot">
+ <span class="tag kind">Concepts</span>
+ <a class="more" href="/blog/munder-difflin-faq/" aria-label="Read: Munder Difflin FAQ: Everything People Ask">Read →</a>
+ </div>
+ </div>
+</article>
+<article class="card">
+ <a class="thumb t-concepts" href="/blog/what-are-claude-code-agents/" aria-hidden="true" tabindex="-1">
+ <span>CONCEPTS</span>
+ </a>
+ <div class="body">
+ <div class="meta">
+ <time datetime="2026-06-02">Jun 2, 2026</time>
+ <span class="dot" aria-hidden="true"></span>
+ <span>3 min</span>
+ </div>
+ <h3><a href="/blog/what-are-claude-code-agents/">What Are Claude Code Agents? And How to Use Many at Once</a></h3>
+ <p class="dek">Claude Code agents explained in plain English — what an agent actually is, how subagents differ, and the leap from one agent to a coordinated team.</p>
+ <div class="foot">
+ <span class="tag kind">Concepts</span>
+ <a class="more" href="/blog/what-are-claude-code-agents/" aria-label="Read: What Are Claude Code Agents? And How to Use Many at Once">Read →</a>
+ </div>
+ </div>
+</article>
+<article class="card">
+ <a class="thumb t-story" href="/blog/why-we-built-munder-difflin/" aria-hidden="true" tabindex="-1">
+ <span>STORY</span>
+ </a>
+ <div class="body">
+ <div class="meta">
+ <time datetime="2026-06-02">Jun 2, 2026</time>
+ <span class="dot" aria-hidden="true"></span>
+ <span>3 min</span>
+ </div>
+ <h3><a href="/blog/why-we-built-munder-difflin/">Why We Built Munder Difflin</a></h3>
+ <p class="dek">The origin story of Munder Difflin — how the pain of juggling Claude Code terminals led to a coordinated, memory-backed hive of agents you can watch.</p>
+ <div class="foot">
+ <span class="tag kind">Story</span>
+ <a class="more" href="/blog/why-we-built-munder-difflin/" aria-label="Read: Why We Built Munder Difflin">Read →</a>
+ </div>
+ </div>
+</article>
+<article class="card">
<a class="thumb t-guides" href="/blog/how-to-run-multiple-claude-code-agents/" aria-hidden="true" tabindex="-1">
<span>GUIDES</span>
</a>
@@ -80,6 +332,60 @@
</div>
</div>
</article>
+<article class="card">
+ <a class="thumb t-internals" href="/blog/atomic-file-mailboxes-for-agents/" aria-hidden="true" tabindex="-1">
+ <span>INTERNALS</span>
+ </a>
+ <div class="body">
+ <div class="meta">
+ <time datetime="2026-05-31">May 31, 2026</time>
+ <span class="dot" aria-hidden="true"></span>
+ <span>5 min</span>
+ </div>
+ <h3><a href="/blog/atomic-file-mailboxes-for-agents/">Atomic File Mailboxes: How Agents Message Each Other</a></h3>
+ <p class="dek">Can Claude Code agents talk to each other? Yes — the outbox-router-inbox design that lets agents message safely using plain files and atomic renames.</p>
+ <div class="foot">
+ <span class="tag kind">Internals</span>
+ <a class="more" href="/blog/atomic-file-mailboxes-for-agents/" aria-label="Read: Atomic File Mailboxes: How Agents Message Each Other">Read →</a>
+ </div>
+ </div>
+</article>
+<article class="card">
+ <a class="thumb t-orchestration" href="/blog/coordinating-ai-coding-agents/" aria-hidden="true" tabindex="-1">
+ <span>ORCHESTRATION</span>
+ </a>
+ <div class="body">
+ <div class="meta">
+ <time datetime="2026-05-29">May 29, 2026</time>
+ <span class="dot" aria-hidden="true"></span>
+ <span>5 min</span>
+ </div>
+ <h3><a href="/blog/coordinating-ai-coding-agents/">The Best Way to Coordinate AI Coding Agents</a></h3>
+ <p class="dek">The best way to coordinate AI coding agents: single-writer files, a message router, a one-scribe plan, and an orchestrator — cooperate, not clobber.</p>
+ <div class="foot">
+ <span class="tag kind">Orchestration</span>
+ <a class="more" href="/blog/coordinating-ai-coding-agents/" aria-label="Read: The Best Way to Coordinate AI Coding Agents">Read →</a>
+ </div>
+ </div>
+</article>
+<article class="card">
+ <a class="thumb t-orchestration" href="/blog/claude-code-orchestration-guide/" aria-hidden="true" tabindex="-1">
+ <span>ORCHESTRATION</span>
+ </a>
+ <div class="body">
+ <div class="meta">
+ <time datetime="2026-05-28">May 28, 2026</time>
+ <span class="dot" aria-hidden="true"></span>
+ <span>5 min</span>
+ </div>
+ <h3><a href="/blog/claude-code-orchestration-guide/">Orchestrating Claude Code Agents: A Practical Guide</a></h3>
+ <p class="dek">How to orchestrate Claude Code agents in practice: what orchestration means, how a GOD orchestrator routes and escalates work, and how to wire it up.</p>
+ <div class="foot">
+ <span class="tag kind">Orchestration</span>
+ <a class="more" href="/blog/claude-code-orchestration-guide/" aria-label="Read: Orchestrating Claude Code Agents: A Practical Guide">Read →</a>
+ </div>
+ </div>
+</article>
<article class="card">
<a class="thumb t-memory" href="/blog/give-claude-code-long-term-memory/" aria-hidden="true" tabindex="-1">
<span>MEMORY</span>
@@ -98,6 +404,78 @@
</div>
</div>
</article>
+<article class="card">
+ <a class="thumb t-memory" href="/blog/semantic-memory-for-ai-agents/" aria-hidden="true" tabindex="-1">
+ <span>MEMORY</span>
+ </a>
+ <div class="body">
+ <div class="meta">
+ <time datetime="2026-05-26">May 26, 2026</time>
+ <span class="dot" aria-hidden="true"></span>
+ <span>6 min</span>
+ </div>
+ <h3><a href="/blog/semantic-memory-for-ai-agents/">Semantic Memory for AI Agents: Recall in Milliseconds</a></h3>
+ <p class="dek">What semantic memory for AI agents is, why a markdown-first store beats a heavy DB, and how a shared palace lets a hive recall a note by meaning, fast.</p>
+ <div class="foot">
+ <span class="tag kind">Memory</span>
+ <a class="more" href="/blog/semantic-memory-for-ai-agents/" aria-label="Read: Semantic Memory for AI Agents: Recall in Milliseconds">Read →</a>
+ </div>
+ </div>
+</article>
+<article class="card">
+ <a class="thumb t-guides" href="/blog/manage-multiple-claude-code-sessions/" aria-hidden="true" tabindex="-1">
+ <span>GUIDES</span>
+ </a>
+ <div class="body">
+ <div class="meta">
+ <time datetime="2026-05-25">May 25, 2026</time>
+ <span class="dot" aria-hidden="true"></span>
+ <span>4 min</span>
+ </div>
+ <h3><a href="/blog/manage-multiple-claude-code-sessions/">How to Manage Multiple Claude Code Sessions Like a Pro</a></h3>
+ <p class="dek">Tactics to manage multiple Claude Code sessions without losing track: naming, roles, context isolation, and when a harness beats juggling terminal tabs.</p>
+ <div class="foot">
+ <span class="tag kind">Guides</span>
+ <a class="more" href="/blog/manage-multiple-claude-code-sessions/" aria-label="Read: How to Manage Multiple Claude Code Sessions Like a Pro">Read →</a>
+ </div>
+ </div>
+</article>
+<article class="card">
+ <a class="thumb t-guides" href="/blog/claude-code-multi-agent-setup-tutorial/" aria-hidden="true" tabindex="-1">
+ <span>GUIDES</span>
+ </a>
+ <div class="body">
+ <div class="meta">
+ <time datetime="2026-05-24">May 24, 2026</time>
+ <span class="dot" aria-hidden="true"></span>
+ <span>5 min</span>
+ </div>
+ <h3><a href="/blog/claude-code-multi-agent-setup-tutorial/">Set Up a Claude Code Multi-Agent Workflow in 10 Minutes</a></h3>
+ <p class="dek">A from-zero Claude Code multi-agent setup: install Munder Difflin, onboard, spawn a few agents, and watch the GOD orchestrator route your first task.</p>
+ <div class="foot">
+ <span class="tag kind">Guides</span>
+ <a class="more" href="/blog/claude-code-multi-agent-setup-tutorial/" aria-label="Read: Set Up a Claude Code Multi-Agent Workflow in 10 Minutes">Read →</a>
+ </div>
+ </div>
+</article>
+<article class="card">
+ <a class="thumb t-guides" href="/blog/claude-code-subagents-vs-multi-agent-harness/" aria-hidden="true" tabindex="-1">
+ <span>GUIDES</span>
+ </a>
+ <div class="body">
+ <div class="meta">
+ <time datetime="2026-05-23">May 23, 2026</time>
+ <span class="dot" aria-hidden="true"></span>
+ <span>5 min</span>
+ </div>
+ <h3><a href="/blog/claude-code-subagents-vs-multi-agent-harness/">Claude Code Subagents vs a Multi-Agent Harness</a></h3>
+ <p class="dek">Claude Code subagents vs a multi-agent harness: where subagents stop and a harness with shared memory, messaging, and an orchestrator takes over.</p>
+ <div class="foot">
+ <span class="tag kind">Guides</span>
+ <a class="more" href="/blog/claude-code-subagents-vs-multi-agent-harness/" aria-label="Read: Claude Code Subagents vs a Multi-Agent Harness">Read →</a>
+ </div>
+ </div>
+</article>
<article class="card">
<a class="thumb t-concepts" href="/blog/what-is-a-multi-agent-harness/" aria-hidden="true" tabindex="-1">
<span>CONCEPTS</span>
diff --git a/docs/blog/tags/comparisons/index.html b/docs/blog/tags/comparisons/index.html
new file mode 100644
index 00000000..8fa9c2d4
--- /dev/null
+++ b/docs/blog/tags/comparisons/index.html
@@ -0,0 +1,250 @@
+<!doctype html>
+<html lang="en">
+<head>
+<meta charset="UTF-8" />
+<meta name="viewport" content="width=device-width, initial-scale=1.0" />
+<title>Comparisons — Munder Difflin Blog</title>
+<meta name="description" content="Munder Difflin blog posts tagged Comparisons." />
+<link rel="canonical" href="https://munderdiffl.in/blog/tags/comparisons/" />
+
+<link rel="icon" type="image/png" href="https://munderdiffl.in/logo.png" />
+<link rel="apple-touch-icon" href="https://munderdiffl.in/logo.png" />
+<meta name="theme-color" content="#F5F2E8" />
+
+<!-- Open Graph -->
+<meta property="og:site_name" content="Munder Difflin Blog" />
+<meta property="og:type" content="website" />
+<meta property="og:title" content="Comparisons — Munder Difflin Blog" />
+<meta property="og:description" content="Munder Difflin blog posts tagged Comparisons." />
+<meta property="og:url" content="https://munderdiffl.in/blog/tags/comparisons/" />
+<meta property="og:image" content="https://munderdiffl.in/media/og.png" />
+<meta property="og:locale" content="en_US" />
+
+
+<!-- Twitter -->
+<meta name="twitter:card" content="summary_large_image" />
+<meta name="twitter:title" content="Comparisons — Munder Difflin Blog" />
+<meta name="twitter:description" content="Munder Difflin blog posts tagged Comparisons." />
+<meta name="twitter:image" content="https://munderdiffl.in/media/og.png" />
+
+<link rel="alternate" type="application/atom+xml" title="Munder Difflin Blog" href="https://munderdiffl.in/blog/feed.xml" />
+<link rel="preconnect" href="https://fonts.googleapis.com" />
+<link rel="preconnect" href="https://fonts.gstatic.com" crossorigin />
+<link href="https://fonts.googleapis.com/css2?family=Geist:wght@400;500;600&family=JetBrains+Mono:wght@400;500;600;700&display=swap" rel="stylesheet" />
+<link rel="stylesheet" href="/blog/assets/blog.css" />
+
+</head>
+<body>
+<a class="skip-link" href="#main">Skip to content</a>
+<nav id="nav">
+ <a class="brand" href="/blog/" aria-label="Munder Difflin Blog home">
+ <span class="brand-mark">MD</span>
+ <span class="brand-word">MUNDER DIFFLIN<span class="sep">/</span><span class="blog">BLOG</span></span>
+ </a>
+ <span class="spacer"></span>
+ <div class="links">
+ <a href="/blog/">Latest</a>
+ <a href="/blog/topics/">Topics</a>
+ <a href="/blog/about/">About</a>
+ <a href="https://munderdiffl.in">↗ Product</a>
+ </div>
+ <div class="nav-actions">
+ <a class="btn sm" href="https://munderdiffl.in/blog/feed.xml" aria-label="RSS feed">⤵ RSS</a>
+ <a class="btn sm primary" href="https://munderdiffl.in/#install">⤓ Download</a>
+ </div>
+</nav>
+
+<main id="main">
+<header class="page-head wrap">
+ <p class="eyebrow">Tag</p>
+ <h1>#Comparisons</h1>
+ <p class="lead">8 posts tagged <strong>Comparisons</strong>.</p>
+</header>
+<section class="wrap">
+ <div class="post-grid">
+ <article class="card">
+ <a class="thumb t-comparisons" href="/blog/best-claude-code-multi-agent-tools/" aria-hidden="true" tabindex="-1">
+ <span>COMPARISONS</span>
+ </a>
+ <div class="body">
+ <div class="meta">
+ <time datetime="2026-06-04">Jun 4, 2026</time>
+ <span class="dot" aria-hidden="true"></span>
+ <span>6 min</span>
+ </div>
+ <h3><a href="/blog/best-claude-code-multi-agent-tools/">The Best Tools to Run Multiple Claude Code Agents (2026)</a></h3>
+ <p class="dek">An honest 2026 roundup of tools to run multiple Claude Code agents — Claude Squad, Conductor, Crystal, vibe-kanban, and Munder Difflin — compared.</p>
+ <div class="foot">
+ <span class="tag kind">Comparisons</span>
+ <a class="more" href="/blog/best-claude-code-multi-agent-tools/" aria-label="Read: The Best Tools to Run Multiple Claude Code Agents (2026)">Read →</a>
+ </div>
+ </div>
+</article>
+<article class="card">
+ <a class="thumb t-comparisons" href="/blog/claude-code-orchestration-tools-compared/" aria-hidden="true" tabindex="-1">
+ <span>COMPARISONS</span>
+ </a>
+ <div class="body">
+ <div class="meta">
+ <time datetime="2026-06-04">Jun 4, 2026</time>
+ <span class="dot" aria-hidden="true"></span>
+ <span>3 min</span>
+ </div>
+ <h3><a href="/blog/claude-code-orchestration-tools-compared/">Claude Code Orchestration Tools, Compared</a></h3>
+ <p class="dek">Claude Code orchestration tools compared on memory, messaging, visibility, control, and local-first — across Claude Squad, Conductor, Crystal, and more.</p>
+ <div class="foot">
+ <span class="tag kind">Comparisons</span>
+ <a class="more" href="/blog/claude-code-orchestration-tools-compared/" aria-label="Read: Claude Code Orchestration Tools, Compared">Read →</a>
+ </div>
+ </div>
+</article>
+<article class="card">
+ <a class="thumb t-comparisons" href="/blog/claude-squad-vs-munder-difflin/" aria-hidden="true" tabindex="-1">
+ <span>COMPARISONS</span>
+ </a>
+ <div class="body">
+ <div class="meta">
+ <time datetime="2026-06-04">Jun 4, 2026</time>
+ <span class="dot" aria-hidden="true"></span>
+ <span>3 min</span>
+ </div>
+ <h3><a href="/blog/claude-squad-vs-munder-difflin/">Claude Squad vs Munder Difflin: Which Should You Use?</a></h3>
+ <p class="dek">Claude Squad vs Munder Difflin: a lean terminal session manager against a memory-backed, orchestrated, visual hive. Feature table and an honest verdict.</p>
+ <div class="foot">
+ <span class="tag kind">Comparisons</span>
+ <a class="more" href="/blog/claude-squad-vs-munder-difflin/" aria-label="Read: Claude Squad vs Munder Difflin: Which Should You Use?">Read →</a>
+ </div>
+ </div>
+</article>
+<article class="card">
+ <a class="thumb t-comparisons" href="/blog/claude-squad-alternative/" aria-hidden="true" tabindex="-1">
+ <span>COMPARISONS</span>
+ </a>
+ <div class="body">
+ <div class="meta">
+ <time datetime="2026-06-03">Jun 3, 2026</time>
+ <span class="dot" aria-hidden="true"></span>
+ <span>3 min</span>
+ </div>
+ <h3><a href="/blog/claude-squad-alternative/">Looking for a Claude Squad Alternative?</a></h3>
+ <p class="dek">What Claude Squad does well, where it stops, and why a memory-backed, orchestrated hive may be the Claude Squad alternative you&#39;re after.</p>
+ <div class="foot">
+ <span class="tag kind">Comparisons</span>
+ <a class="more" href="/blog/claude-squad-alternative/" aria-label="Read: Looking for a Claude Squad Alternative?">Read →</a>
+ </div>
+ </div>
+</article>
+<article class="card">
+ <a class="thumb t-comparisons" href="/blog/conductor-claude-code-alternative/" aria-hidden="true" tabindex="-1">
+ <span>COMPARISONS</span>
+ </a>
+ <div class="body">
+ <div class="meta">
+ <time datetime="2026-06-03">Jun 3, 2026</time>
+ <span class="dot" aria-hidden="true"></span>
+ <span>3 min</span>
+ </div>
+ <h3><a href="/blog/conductor-claude-code-alternative/">A Conductor Alternative for Orchestrating Claude Code</a></h3>
+ <p class="dek">Conductor is a polished macOS app for parallel Claude Code worktrees. When to pick a cross-platform, orchestrated hive as your Conductor alternative.</p>
+ <div class="foot">
+ <span class="tag kind">Comparisons</span>
+ <a class="more" href="/blog/conductor-claude-code-alternative/" aria-label="Read: A Conductor Alternative for Orchestrating Claude Code">Read →</a>
+ </div>
+ </div>
+</article>
+<article class="card">
+ <a class="thumb t-comparisons" href="/blog/crystal-claude-code-alternative/" aria-hidden="true" tabindex="-1">
+ <span>COMPARISONS</span>
+ </a>
+ <div class="body">
+ <div class="meta">
+ <time datetime="2026-06-03">Jun 3, 2026</time>
+ <span class="dot" aria-hidden="true"></span>
+ <span>3 min</span>
+ </div>
+ <h3><a href="/blog/crystal-claude-code-alternative/">A Crystal Alternative: Multi-Agent Claude Code with Memory</a></h3>
+ <p class="dek">Crystal runs parallel Claude Code worktrees well. Where a memory-backed, orchestrated hive changes the workflow — and when to stick with Crystal.</p>
+ <div class="foot">
+ <span class="tag kind">Comparisons</span>
+ <a class="more" href="/blog/crystal-claude-code-alternative/" aria-label="Read: A Crystal Alternative: Multi-Agent Claude Code with Memory">Read →</a>
+ </div>
+ </div>
+</article>
+<article class="card">
+ <a class="thumb t-comparisons" href="/blog/vibe-kanban-alternative/" aria-hidden="true" tabindex="-1">
+ <span>COMPARISONS</span>
+ </a>
+ <div class="body">
+ <div class="meta">
+ <time datetime="2026-06-03">Jun 3, 2026</time>
+ <span class="dot" aria-hidden="true"></span>
+ <span>3 min</span>
+ </div>
+ <h3><a href="/blog/vibe-kanban-alternative/">A vibe-kanban Alternative for Coordinating AI Agents</a></h3>
+ <p class="dek">vibe-kanban gives you a board to assign tasks to coding agents. When a self-routing hive is the better vibe-kanban alternative — and when a board wins.</p>
+ <div class="foot">
+ <span class="tag kind">Comparisons</span>
+ <a class="more" href="/blog/vibe-kanban-alternative/" aria-label="Read: A vibe-kanban Alternative for Coordinating AI Agents">Read →</a>
+ </div>
+ </div>
+</article>
+<article class="card">
+ <a class="thumb t-comparisons" href="/blog/how-to-choose-a-multi-agent-tool/" aria-hidden="true" tabindex="-1">
+ <span>COMPARISONS</span>
+ </a>
+ <div class="body">
+ <div class="meta">
+ <time datetime="2026-06-02">Jun 2, 2026</time>
+ <span class="dot" aria-hidden="true"></span>
+ <span>3 min</span>
+ </div>
+ <h3><a href="/blog/how-to-choose-a-multi-agent-tool/">How to Choose a Multi-Agent Coding Tool: A Buyer&#39;s Checklist</a></h3>
+ <p class="dek">A decision framework for choosing a multi-agent coding tool — memory, control, visibility, cost, local-first — with a simple scoring rubric you can run.</p>
+ <div class="foot">
+ <span class="tag kind">Comparisons</span>
+ <a class="more" href="/blog/how-to-choose-a-multi-agent-tool/" aria-label="Read: How to Choose a Multi-Agent Coding Tool: A Buyer&#39;s Checklist">Read →</a>
+ </div>
+ </div>
+</article>
+
+ </div>
+</section>
+
+
+</main>
+<footer>
+ <div class="wrap">
+ <div class="foot-top">
+ <a class="foot-brand brand" href="/blog/">
+ <span class="brand-mark">MD</span>
+ <span class="brand-word">MUNDER DIFFLIN<span class="sep">/</span><span class="blog">BLOG</span></span>
+ </a>
+ <div class="foot-links">
+ <a href="/blog/">Latest</a>
+ <a href="/blog/topics/">Topics</a>
+ <a href="/blog/about/">About</a>
+ <a href="https://munderdiffl.in/blog/feed.xml">RSS</a>
+ <a href="https://github.com/chaitanyagiri/munder-difflin">GitHub</a>
+ <a href="https://munderdiffl.in">munderdiffl.in ↗</a>
+ </div>
+ </div>
+ <div class="foot-meta">
+ © 2026 Munder Difflin · Local-first · MIT-licensed ·
+ Built on <a href="https://munderdiffl.in">Electron, React, Pixi.js, xterm.js &amp; node-pty</a>.
+ Run an office of agents while you sleep.
+ </div>
+ </div>
+</footer>
+
+<script>
+ // sticky-nav border on scroll
+ (function () {
+ var nav = document.getElementById('nav');
+ if (!nav) return;
+ var onScroll = function () { nav.classList.toggle('scrolled', window.scrollY > 8); };
+ onScroll(); window.addEventListener('scroll', onScroll, { passive: true });
+ })();
+</script>
+
+</body>
+</html>
diff --git a/docs/blog/tags/concepts/index.html b/docs/blog/tags/concepts/index.html
index eb3dea67..5596d286 100644
--- a/docs/blog/tags/concepts/index.html
+++ b/docs/blog/tags/concepts/index.html
@@ -58,11 +58,65 @@
<header class="page-head wrap">
<p class="eyebrow">Tag</p>
<h1>#Concepts</h1>
- <p class="lead">1 post tagged <strong>Concepts</strong>.</p>
+ <p class="lead">4 posts tagged <strong>Concepts</strong>.</p>
</header>
<section class="wrap">
<div class="post-grid">
<article class="card">
+ <a class="thumb t-concepts" href="/blog/ai-agent-glossary/" aria-hidden="true" tabindex="-1">
+ <span>CONCEPTS</span>
+ </a>
+ <div class="body">
+ <div class="meta">
+ <time datetime="2026-06-02">Jun 2, 2026</time>
+ <span class="dot" aria-hidden="true"></span>
+ <span>3 min</span>
+ </div>
+ <h3><a href="/blog/ai-agent-glossary/">The AI Coding Agent Glossary: Harness, Orchestrator, Hive, Subagent</a></h3>
+ <p class="dek">Plain-English definitions of the AI coding agent terms everyone trips over — harness, orchestrator, hive, subagent, agent memory — each in one line.</p>
+ <div class="foot">
+ <span class="tag kind">Concepts</span>
+ <a class="more" href="/blog/ai-agent-glossary/" aria-label="Read: The AI Coding Agent Glossary: Harness, Orchestrator, Hive, Subagent">Read →</a>
+ </div>
+ </div>
+</article>
+<article class="card">
+ <a class="thumb t-concepts" href="/blog/munder-difflin-faq/" aria-hidden="true" tabindex="-1">
+ <span>CONCEPTS</span>
+ </a>
+ <div class="body">
+ <div class="meta">
+ <time datetime="2026-06-02">Jun 2, 2026</time>
+ <span class="dot" aria-hidden="true"></span>
+ <span>1 min</span>
+ </div>
+ <h3><a href="/blog/munder-difflin-faq/">Munder Difflin FAQ: Everything People Ask</a></h3>
+ <p class="dek">Answers to the top Munder Difflin questions — what it is, is it free, does it run locally, which platforms, and how it differs from many terminals.</p>
+ <div class="foot">
+ <span class="tag kind">Concepts</span>
+ <a class="more" href="/blog/munder-difflin-faq/" aria-label="Read: Munder Difflin FAQ: Everything People Ask">Read →</a>
+ </div>
+ </div>
+</article>
+<article class="card">
+ <a class="thumb t-concepts" href="/blog/what-are-claude-code-agents/" aria-hidden="true" tabindex="-1">
+ <span>CONCEPTS</span>
+ </a>
+ <div class="body">
+ <div class="meta">
+ <time datetime="2026-06-02">Jun 2, 2026</time>
+ <span class="dot" aria-hidden="true"></span>
+ <span>3 min</span>
+ </div>
+ <h3><a href="/blog/what-are-claude-code-agents/">What Are Claude Code Agents? And How to Use Many at Once</a></h3>
+ <p class="dek">Claude Code agents explained in plain English — what an agent actually is, how subagents differ, and the leap from one agent to a coordinated team.</p>
+ <div class="foot">
+ <span class="tag kind">Concepts</span>
+ <a class="more" href="/blog/what-are-claude-code-agents/" aria-label="Read: What Are Claude Code Agents? And How to Use Many at Once">Read →</a>
+ </div>
+ </div>
+</article>
+<article class="card">
<a class="thumb t-concepts" href="/blog/what-is-a-multi-agent-harness/" aria-hidden="true" tabindex="-1">
<span>CONCEPTS</span>
</a>
diff --git a/docs/blog/tags/concurrency/index.html b/docs/blog/tags/concurrency/index.html
new file mode 100644
index 00000000..445feed2
--- /dev/null
+++ b/docs/blog/tags/concurrency/index.html
@@ -0,0 +1,124 @@
+<!doctype html>
+<html lang="en">
+<head>
+<meta charset="UTF-8" />
+<meta name="viewport" content="width=device-width, initial-scale=1.0" />
+<title>Concurrency — Munder Difflin Blog</title>
+<meta name="description" content="Munder Difflin blog posts tagged Concurrency." />
+<link rel="canonical" href="https://munderdiffl.in/blog/tags/concurrency/" />
+
+<link rel="icon" type="image/png" href="https://munderdiffl.in/logo.png" />
+<link rel="apple-touch-icon" href="https://munderdiffl.in/logo.png" />
+<meta name="theme-color" content="#F5F2E8" />
+
+<!-- Open Graph -->
+<meta property="og:site_name" content="Munder Difflin Blog" />
+<meta property="og:type" content="website" />
+<meta property="og:title" content="Concurrency — Munder Difflin Blog" />
+<meta property="og:description" content="Munder Difflin blog posts tagged Concurrency." />
+<meta property="og:url" content="https://munderdiffl.in/blog/tags/concurrency/" />
+<meta property="og:image" content="https://munderdiffl.in/media/og.png" />
+<meta property="og:locale" content="en_US" />
+
+
+<!-- Twitter -->
+<meta name="twitter:card" content="summary_large_image" />
+<meta name="twitter:title" content="Concurrency — Munder Difflin Blog" />
+<meta name="twitter:description" content="Munder Difflin blog posts tagged Concurrency." />
+<meta name="twitter:image" content="https://munderdiffl.in/media/og.png" />
+
+<link rel="alternate" type="application/atom+xml" title="Munder Difflin Blog" href="https://munderdiffl.in/blog/feed.xml" />
+<link rel="preconnect" href="https://fonts.googleapis.com" />
+<link rel="preconnect" href="https://fonts.gstatic.com" crossorigin />
+<link href="https://fonts.googleapis.com/css2?family=Geist:wght@400;500;600&family=JetBrains+Mono:wght@400;500;600;700&display=swap" rel="stylesheet" />
+<link rel="stylesheet" href="/blog/assets/blog.css" />
+
+</head>
+<body>
+<a class="skip-link" href="#main">Skip to content</a>
+<nav id="nav">
+ <a class="brand" href="/blog/" aria-label="Munder Difflin Blog home">
+ <span class="brand-mark">MD</span>
+ <span class="brand-word">MUNDER DIFFLIN<span class="sep">/</span><span class="blog">BLOG</span></span>
+ </a>
+ <span class="spacer"></span>
+ <div class="links">
+ <a href="/blog/">Latest</a>
+ <a href="/blog/topics/">Topics</a>
+ <a href="/blog/about/">About</a>
+ <a href="https://munderdiffl.in">↗ Product</a>
+ </div>
+ <div class="nav-actions">
+ <a class="btn sm" href="https://munderdiffl.in/blog/feed.xml" aria-label="RSS feed">⤵ RSS</a>
+ <a class="btn sm primary" href="https://munderdiffl.in/#install">⤓ Download</a>
+ </div>
+</nav>
+
+<main id="main">
+<header class="page-head wrap">
+ <p class="eyebrow">Tag</p>
+ <h1>#Concurrency</h1>
+ <p class="lead">1 post tagged <strong>Concurrency</strong>.</p>
+</header>
+<section class="wrap">
+ <div class="post-grid">
+ <article class="card">
+ <a class="thumb t-internals" href="/blog/single-committer-git-pattern/" aria-hidden="true" tabindex="-1">
+ <span>INTERNALS</span>
+ </a>
+ <div class="body">
+ <div class="meta">
+ <time datetime="2026-06-02">Jun 2, 2026</time>
+ <span class="dot" aria-hidden="true"></span>
+ <span>5 min</span>
+ </div>
+ <h3><a href="/blog/single-committer-git-pattern/">The Single-Committer Pattern: Multi-Agent Git Without Corruption</a></h3>
+ <p class="dek">Parallel agents corrupt a repo with index.lock races. The single-committer pattern — agents write, one process commits — fixes concurrent git writes.</p>
+ <div class="foot">
+ <span class="tag kind">Internals</span>
+ <a class="more" href="/blog/single-committer-git-pattern/" aria-label="Read: The Single-Committer Pattern: Multi-Agent Git Without Corruption">Read →</a>
+ </div>
+ </div>
+</article>
+
+ </div>
+</section>
+
+
+</main>
+<footer>
+ <div class="wrap">
+ <div class="foot-top">
+ <a class="foot-brand brand" href="/blog/">
+ <span class="brand-mark">MD</span>
+ <span class="brand-word">MUNDER DIFFLIN<span class="sep">/</span><span class="blog">BLOG</span></span>
+ </a>
+ <div class="foot-links">
+ <a href="/blog/">Latest</a>
+ <a href="/blog/topics/">Topics</a>
+ <a href="/blog/about/">About</a>
+ <a href="https://munderdiffl.in/blog/feed.xml">RSS</a>
+ <a href="https://github.com/chaitanyagiri/munder-difflin">GitHub</a>
+ <a href="https://munderdiffl.in">munderdiffl.in ↗</a>
+ </div>
+ </div>
+ <div class="foot-meta">
+ © 2026 Munder Difflin · Local-first · MIT-licensed ·
+ Built on <a href="https://munderdiffl.in">Electron, React, Pixi.js, xterm.js &amp; node-pty</a>.
+ Run an office of agents while you sleep.
+ </div>
+ </div>
+</footer>
+
+<script>
+ // sticky-nav border on scroll
+ (function () {
+ var nav = document.getElementById('nav');
+ if (!nav) return;
+ var onScroll = function () { nav.classList.toggle('scrolled', window.scrollY > 8); };
+ onScroll(); window.addEventListener('scroll', onScroll, { passive: true });
+ })();
+</script>
+
+</body>
+</html>
diff --git a/docs/blog/tags/coordination/index.html b/docs/blog/tags/coordination/index.html
new file mode 100644
index 00000000..a65862c8
--- /dev/null
+++ b/docs/blog/tags/coordination/index.html
@@ -0,0 +1,124 @@
+<!doctype html>
+<html lang="en">
+<head>
+<meta charset="UTF-8" />
+<meta name="viewport" content="width=device-width, initial-scale=1.0" />
+<title>Coordination — Munder Difflin Blog</title>
+<meta name="description" content="Munder Difflin blog posts tagged Coordination." />
+<link rel="canonical" href="https://munderdiffl.in/blog/tags/coordination/" />
+
+<link rel="icon" type="image/png" href="https://munderdiffl.in/logo.png" />
+<link rel="apple-touch-icon" href="https://munderdiffl.in/logo.png" />
+<meta name="theme-color" content="#F5F2E8" />
+
+<!-- Open Graph -->
+<meta property="og:site_name" content="Munder Difflin Blog" />
+<meta property="og:type" content="website" />
+<meta property="og:title" content="Coordination — Munder Difflin Blog" />
+<meta property="og:description" content="Munder Difflin blog posts tagged Coordination." />
+<meta property="og:url" content="https://munderdiffl.in/blog/tags/coordination/" />
+<meta property="og:image" content="https://munderdiffl.in/media/og.png" />
+<meta property="og:locale" content="en_US" />
+
+
+<!-- Twitter -->
+<meta name="twitter:card" content="summary_large_image" />
+<meta name="twitter:title" content="Coordination — Munder Difflin Blog" />
+<meta name="twitter:description" content="Munder Difflin blog posts tagged Coordination." />
+<meta name="twitter:image" content="https://munderdiffl.in/media/og.png" />
+
+<link rel="alternate" type="application/atom+xml" title="Munder Difflin Blog" href="https://munderdiffl.in/blog/feed.xml" />
+<link rel="preconnect" href="https://fonts.googleapis.com" />
+<link rel="preconnect" href="https://fonts.gstatic.com" crossorigin />
+<link href="https://fonts.googleapis.com/css2?family=Geist:wght@400;500;600&family=JetBrains+Mono:wght@400;500;600;700&display=swap" rel="stylesheet" />
+<link rel="stylesheet" href="/blog/assets/blog.css" />
+
+</head>
+<body>
+<a class="skip-link" href="#main">Skip to content</a>
+<nav id="nav">
+ <a class="brand" href="/blog/" aria-label="Munder Difflin Blog home">
+ <span class="brand-mark">MD</span>
+ <span class="brand-word">MUNDER DIFFLIN<span class="sep">/</span><span class="blog">BLOG</span></span>
+ </a>
+ <span class="spacer"></span>
+ <div class="links">
+ <a href="/blog/">Latest</a>
+ <a href="/blog/topics/">Topics</a>
+ <a href="/blog/about/">About</a>
+ <a href="https://munderdiffl.in">↗ Product</a>
+ </div>
+ <div class="nav-actions">
+ <a class="btn sm" href="https://munderdiffl.in/blog/feed.xml" aria-label="RSS feed">⤵ RSS</a>
+ <a class="btn sm primary" href="https://munderdiffl.in/#install">⤓ Download</a>
+ </div>
+</nav>
+
+<main id="main">
+<header class="page-head wrap">
+ <p class="eyebrow">Tag</p>
+ <h1>#Coordination</h1>
+ <p class="lead">1 post tagged <strong>Coordination</strong>.</p>
+</header>
+<section class="wrap">
+ <div class="post-grid">
+ <article class="card">
+ <a class="thumb t-orchestration" href="/blog/coordinating-ai-coding-agents/" aria-hidden="true" tabindex="-1">
+ <span>ORCHESTRATION</span>
+ </a>
+ <div class="body">
+ <div class="meta">
+ <time datetime="2026-05-29">May 29, 2026</time>
+ <span class="dot" aria-hidden="true"></span>
+ <span>5 min</span>
+ </div>
+ <h3><a href="/blog/coordinating-ai-coding-agents/">The Best Way to Coordinate AI Coding Agents</a></h3>
+ <p class="dek">The best way to coordinate AI coding agents: single-writer files, a message router, a one-scribe plan, and an orchestrator — cooperate, not clobber.</p>
+ <div class="foot">
+ <span class="tag kind">Orchestration</span>
+ <a class="more" href="/blog/coordinating-ai-coding-agents/" aria-label="Read: The Best Way to Coordinate AI Coding Agents">Read →</a>
+ </div>
+ </div>
+</article>
+
+ </div>
+</section>
+
+
+</main>
+<footer>
+ <div class="wrap">
+ <div class="foot-top">
+ <a class="foot-brand brand" href="/blog/">
+ <span class="brand-mark">MD</span>
+ <span class="brand-word">MUNDER DIFFLIN<span class="sep">/</span><span class="blog">BLOG</span></span>
+ </a>
+ <div class="foot-links">
+ <a href="/blog/">Latest</a>
+ <a href="/blog/topics/">Topics</a>
+ <a href="/blog/about/">About</a>
+ <a href="https://munderdiffl.in/blog/feed.xml">RSS</a>
+ <a href="https://github.com/chaitanyagiri/munder-difflin">GitHub</a>
+ <a href="https://munderdiffl.in">munderdiffl.in ↗</a>
+ </div>
+ </div>
+ <div class="foot-meta">
+ © 2026 Munder Difflin · Local-first · MIT-licensed ·
+ Built on <a href="https://munderdiffl.in">Electron, React, Pixi.js, xterm.js &amp; node-pty</a>.
+ Run an office of agents while you sleep.
+ </div>
+ </div>
+</footer>
+
+<script>
+ // sticky-nav border on scroll
+ (function () {
+ var nav = document.getElementById('nav');
+ if (!nav) return;
+ var onScroll = function () { nav.classList.toggle('scrolled', window.scrollY > 8); };
+ onScroll(); window.addEventListener('scroll', onScroll, { passive: true });
+ })();
+</script>
+
+</body>
+</html>
diff --git a/docs/blog/tags/electron/index.html b/docs/blog/tags/electron/index.html
new file mode 100644
index 00000000..38d61e30
--- /dev/null
+++ b/docs/blog/tags/electron/index.html
@@ -0,0 +1,142 @@
+<!doctype html>
+<html lang="en">
+<head>
+<meta charset="UTF-8" />
+<meta name="viewport" content="width=device-width, initial-scale=1.0" />
+<title>Electron — Munder Difflin Blog</title>
+<meta name="description" content="Munder Difflin blog posts tagged Electron." />
+<link rel="canonical" href="https://munderdiffl.in/blog/tags/electron/" />
+
+<link rel="icon" type="image/png" href="https://munderdiffl.in/logo.png" />
+<link rel="apple-touch-icon" href="https://munderdiffl.in/logo.png" />
+<meta name="theme-color" content="#F5F2E8" />
+
+<!-- Open Graph -->
+<meta property="og:site_name" content="Munder Difflin Blog" />
+<meta property="og:type" content="website" />
+<meta property="og:title" content="Electron — Munder Difflin Blog" />
+<meta property="og:description" content="Munder Difflin blog posts tagged Electron." />
+<meta property="og:url" content="https://munderdiffl.in/blog/tags/electron/" />
+<meta property="og:image" content="https://munderdiffl.in/media/og.png" />
+<meta property="og:locale" content="en_US" />
+
+
+<!-- Twitter -->
+<meta name="twitter:card" content="summary_large_image" />
+<meta name="twitter:title" content="Electron — Munder Difflin Blog" />
+<meta name="twitter:description" content="Munder Difflin blog posts tagged Electron." />
+<meta name="twitter:image" content="https://munderdiffl.in/media/og.png" />
+
+<link rel="alternate" type="application/atom+xml" title="Munder Difflin Blog" href="https://munderdiffl.in/blog/feed.xml" />
+<link rel="preconnect" href="https://fonts.googleapis.com" />
+<link rel="preconnect" href="https://fonts.gstatic.com" crossorigin />
+<link href="https://fonts.googleapis.com/css2?family=Geist:wght@400;500;600&family=JetBrains+Mono:wght@400;500;600;700&display=swap" rel="stylesheet" />
+<link rel="stylesheet" href="/blog/assets/blog.css" />
+
+</head>
+<body>
+<a class="skip-link" href="#main">Skip to content</a>
+<nav id="nav">
+ <a class="brand" href="/blog/" aria-label="Munder Difflin Blog home">
+ <span class="brand-mark">MD</span>
+ <span class="brand-word">MUNDER DIFFLIN<span class="sep">/</span><span class="blog">BLOG</span></span>
+ </a>
+ <span class="spacer"></span>
+ <div class="links">
+ <a href="/blog/">Latest</a>
+ <a href="/blog/topics/">Topics</a>
+ <a href="/blog/about/">About</a>
+ <a href="https://munderdiffl.in">↗ Product</a>
+ </div>
+ <div class="nav-actions">
+ <a class="btn sm" href="https://munderdiffl.in/blog/feed.xml" aria-label="RSS feed">⤵ RSS</a>
+ <a class="btn sm primary" href="https://munderdiffl.in/#install">⤓ Download</a>
+ </div>
+</nav>
+
+<main id="main">
+<header class="page-head wrap">
+ <p class="eyebrow">Tag</p>
+ <h1>#Electron</h1>
+ <p class="lead">2 posts tagged <strong>Electron</strong>.</p>
+</header>
+<section class="wrap">
+ <div class="post-grid">
+ <article class="card">
+ <a class="thumb t-internals" href="/blog/building-a-terminal-ui-xterm-node-pty/" aria-hidden="true" tabindex="-1">
+ <span>INTERNALS</span>
+ </a>
+ <div class="body">
+ <div class="meta">
+ <time datetime="2026-06-03">Jun 3, 2026</time>
+ <span class="dot" aria-hidden="true"></span>
+ <span>8 min</span>
+ </div>
+ <h3><a href="/blog/building-a-terminal-ui-xterm-node-pty/">Building a Terminal UI with xterm.js and node-pty</a></h3>
+ <p class="dek">Wire xterm.js to a node-pty backend: stream output, write keystrokes back, handle resize, and keep many live terminals fast with a terminal pool.</p>
+ <div class="foot">
+ <span class="tag kind">Internals</span>
+ <a class="more" href="/blog/building-a-terminal-ui-xterm-node-pty/" aria-label="Read: Building a Terminal UI with xterm.js and node-pty">Read →</a>
+ </div>
+ </div>
+</article>
+<article class="card">
+ <a class="thumb t-internals" href="/blog/node-pty-electron-real-terminals/" aria-hidden="true" tabindex="-1">
+ <span>INTERNALS</span>
+ </a>
+ <div class="body">
+ <div class="meta">
+ <time datetime="2026-06-03">Jun 3, 2026</time>
+ <span class="dot" aria-hidden="true"></span>
+ <span>7 min</span>
+ </div>
+ <h3><a href="/blog/node-pty-electron-real-terminals/">Real Terminals in Electron with node-pty</a></h3>
+ <p class="dek">How to run byte-for-byte authentic shells inside Electron with node-pty: the native-rebuild gotcha, the macOS PATH trap, and streaming PTY output over IPC.</p>
+ <div class="foot">
+ <span class="tag kind">Internals</span>
+ <a class="more" href="/blog/node-pty-electron-real-terminals/" aria-label="Read: Real Terminals in Electron with node-pty">Read →</a>
+ </div>
+ </div>
+</article>
+
+ </div>
+</section>
+
+
+</main>
+<footer>
+ <div class="wrap">
+ <div class="foot-top">
+ <a class="foot-brand brand" href="/blog/">
+ <span class="brand-mark">MD</span>
+ <span class="brand-word">MUNDER DIFFLIN<span class="sep">/</span><span class="blog">BLOG</span></span>
+ </a>
+ <div class="foot-links">
+ <a href="/blog/">Latest</a>
+ <a href="/blog/topics/">Topics</a>
+ <a href="/blog/about/">About</a>
+ <a href="https://munderdiffl.in/blog/feed.xml">RSS</a>
+ <a href="https://github.com/chaitanyagiri/munder-difflin">GitHub</a>
+ <a href="https://munderdiffl.in">munderdiffl.in ↗</a>
+ </div>
+ </div>
+ <div class="foot-meta">
+ © 2026 Munder Difflin · Local-first · MIT-licensed ·
+ Built on <a href="https://munderdiffl.in">Electron, React, Pixi.js, xterm.js &amp; node-pty</a>.
+ Run an office of agents while you sleep.
+ </div>
+ </div>
+</footer>
+
+<script>
+ // sticky-nav border on scroll
+ (function () {
+ var nav = document.getElementById('nav');
+ if (!nav) return;
+ var onScroll = function () { nav.classList.toggle('scrolled', window.scrollY > 8); };
+ onScroll(); window.addEventListener('scroll', onScroll, { passive: true });
+ })();
+</script>
+
+</body>
+</html>
diff --git a/docs/blog/tags/faq/index.html b/docs/blog/tags/faq/index.html
new file mode 100644
index 00000000..6c7020dd
--- /dev/null
+++ b/docs/blog/tags/faq/index.html
@@ -0,0 +1,124 @@
+<!doctype html>
+<html lang="en">
+<head>
+<meta charset="UTF-8" />
+<meta name="viewport" content="width=device-width, initial-scale=1.0" />
+<title>FAQ — Munder Difflin Blog</title>
+<meta name="description" content="Munder Difflin blog posts tagged FAQ." />
+<link rel="canonical" href="https://munderdiffl.in/blog/tags/faq/" />
+
+<link rel="icon" type="image/png" href="https://munderdiffl.in/logo.png" />
+<link rel="apple-touch-icon" href="https://munderdiffl.in/logo.png" />
+<meta name="theme-color" content="#F5F2E8" />
+
+<!-- Open Graph -->
+<meta property="og:site_name" content="Munder Difflin Blog" />
+<meta property="og:type" content="website" />
+<meta property="og:title" content="FAQ — Munder Difflin Blog" />
+<meta property="og:description" content="Munder Difflin blog posts tagged FAQ." />
+<meta property="og:url" content="https://munderdiffl.in/blog/tags/faq/" />
+<meta property="og:image" content="https://munderdiffl.in/media/og.png" />
+<meta property="og:locale" content="en_US" />
+
+
+<!-- Twitter -->
+<meta name="twitter:card" content="summary_large_image" />
+<meta name="twitter:title" content="FAQ — Munder Difflin Blog" />
+<meta name="twitter:description" content="Munder Difflin blog posts tagged FAQ." />
+<meta name="twitter:image" content="https://munderdiffl.in/media/og.png" />
+
+<link rel="alternate" type="application/atom+xml" title="Munder Difflin Blog" href="https://munderdiffl.in/blog/feed.xml" />
+<link rel="preconnect" href="https://fonts.googleapis.com" />
+<link rel="preconnect" href="https://fonts.gstatic.com" crossorigin />
+<link href="https://fonts.googleapis.com/css2?family=Geist:wght@400;500;600&family=JetBrains+Mono:wght@400;500;600;700&display=swap" rel="stylesheet" />
+<link rel="stylesheet" href="/blog/assets/blog.css" />
+
+</head>
+<body>
+<a class="skip-link" href="#main">Skip to content</a>
+<nav id="nav">
+ <a class="brand" href="/blog/" aria-label="Munder Difflin Blog home">
+ <span class="brand-mark">MD</span>
+ <span class="brand-word">MUNDER DIFFLIN<span class="sep">/</span><span class="blog">BLOG</span></span>
+ </a>
+ <span class="spacer"></span>
+ <div class="links">
+ <a href="/blog/">Latest</a>
+ <a href="/blog/topics/">Topics</a>
+ <a href="/blog/about/">About</a>
+ <a href="https://munderdiffl.in">↗ Product</a>
+ </div>
+ <div class="nav-actions">
+ <a class="btn sm" href="https://munderdiffl.in/blog/feed.xml" aria-label="RSS feed">⤵ RSS</a>
+ <a class="btn sm primary" href="https://munderdiffl.in/#install">⤓ Download</a>
+ </div>
+</nav>
+
+<main id="main">
+<header class="page-head wrap">
+ <p class="eyebrow">Tag</p>
+ <h1>#FAQ</h1>
+ <p class="lead">1 post tagged <strong>FAQ</strong>.</p>
+</header>
+<section class="wrap">
+ <div class="post-grid">
+ <article class="card">
+ <a class="thumb t-concepts" href="/blog/munder-difflin-faq/" aria-hidden="true" tabindex="-1">
+ <span>CONCEPTS</span>
+ </a>
+ <div class="body">
+ <div class="meta">
+ <time datetime="2026-06-02">Jun 2, 2026</time>
+ <span class="dot" aria-hidden="true"></span>
+ <span>1 min</span>
+ </div>
+ <h3><a href="/blog/munder-difflin-faq/">Munder Difflin FAQ: Everything People Ask</a></h3>
+ <p class="dek">Answers to the top Munder Difflin questions — what it is, is it free, does it run locally, which platforms, and how it differs from many terminals.</p>
+ <div class="foot">
+ <span class="tag kind">Concepts</span>
+ <a class="more" href="/blog/munder-difflin-faq/" aria-label="Read: Munder Difflin FAQ: Everything People Ask">Read →</a>
+ </div>
+ </div>
+</article>
+
+ </div>
+</section>
+
+
+</main>
+<footer>
+ <div class="wrap">
+ <div class="foot-top">
+ <a class="foot-brand brand" href="/blog/">
+ <span class="brand-mark">MD</span>
+ <span class="brand-word">MUNDER DIFFLIN<span class="sep">/</span><span class="blog">BLOG</span></span>
+ </a>
+ <div class="foot-links">
+ <a href="/blog/">Latest</a>
+ <a href="/blog/topics/">Topics</a>
+ <a href="/blog/about/">About</a>
+ <a href="https://munderdiffl.in/blog/feed.xml">RSS</a>
+ <a href="https://github.com/chaitanyagiri/munder-difflin">GitHub</a>
+ <a href="https://munderdiffl.in">munderdiffl.in ↗</a>
+ </div>
+ </div>
+ <div class="foot-meta">
+ © 2026 Munder Difflin · Local-first · MIT-licensed ·
+ Built on <a href="https://munderdiffl.in">Electron, React, Pixi.js, xterm.js &amp; node-pty</a>.
+ Run an office of agents while you sleep.
+ </div>
+ </div>
+</footer>
+
+<script>
+ // sticky-nav border on scroll
+ (function () {
+ var nav = document.getElementById('nav');
+ if (!nav) return;
+ var onScroll = function () { nav.classList.toggle('scrolled', window.scrollY > 8); };
+ onScroll(); window.addEventListener('scroll', onScroll, { passive: true });
+ })();
+</script>
+
+</body>
+</html>
diff --git a/docs/blog/tags/getting-started/index.html b/docs/blog/tags/getting-started/index.html
index c544bd08..9f8cd3ca 100644
--- a/docs/blog/tags/getting-started/index.html
+++ b/docs/blog/tags/getting-started/index.html
@@ -58,11 +58,65 @@
<header class="page-head wrap">
<p class="eyebrow">Tag</p>
<h1>#Getting Started</h1>
- <p class="lead">1 post tagged <strong>Getting Started</strong>.</p>
+ <p class="lead">5 posts tagged <strong>Getting Started</strong>.</p>
</header>
<section class="wrap">
<div class="post-grid">
<article class="card">
+ <a class="thumb t-concepts" href="/blog/ai-agent-glossary/" aria-hidden="true" tabindex="-1">
+ <span>CONCEPTS</span>
+ </a>
+ <div class="body">
+ <div class="meta">
+ <time datetime="2026-06-02">Jun 2, 2026</time>
+ <span class="dot" aria-hidden="true"></span>
+ <span>3 min</span>
+ </div>
+ <h3><a href="/blog/ai-agent-glossary/">The AI Coding Agent Glossary: Harness, Orchestrator, Hive, Subagent</a></h3>
+ <p class="dek">Plain-English definitions of the AI coding agent terms everyone trips over — harness, orchestrator, hive, subagent, agent memory — each in one line.</p>
+ <div class="foot">
+ <span class="tag kind">Concepts</span>
+ <a class="more" href="/blog/ai-agent-glossary/" aria-label="Read: The AI Coding Agent Glossary: Harness, Orchestrator, Hive, Subagent">Read →</a>
+ </div>
+ </div>
+</article>
+<article class="card">
+ <a class="thumb t-comparisons" href="/blog/how-to-choose-a-multi-agent-tool/" aria-hidden="true" tabindex="-1">
+ <span>COMPARISONS</span>
+ </a>
+ <div class="body">
+ <div class="meta">
+ <time datetime="2026-06-02">Jun 2, 2026</time>
+ <span class="dot" aria-hidden="true"></span>
+ <span>3 min</span>
+ </div>
+ <h3><a href="/blog/how-to-choose-a-multi-agent-tool/">How to Choose a Multi-Agent Coding Tool: A Buyer&#39;s Checklist</a></h3>
+ <p class="dek">A decision framework for choosing a multi-agent coding tool — memory, control, visibility, cost, local-first — with a simple scoring rubric you can run.</p>
+ <div class="foot">
+ <span class="tag kind">Comparisons</span>
+ <a class="more" href="/blog/how-to-choose-a-multi-agent-tool/" aria-label="Read: How to Choose a Multi-Agent Coding Tool: A Buyer&#39;s Checklist">Read →</a>
+ </div>
+ </div>
+</article>
+<article class="card">
+ <a class="thumb t-concepts" href="/blog/what-are-claude-code-agents/" aria-hidden="true" tabindex="-1">
+ <span>CONCEPTS</span>
+ </a>
+ <div class="body">
+ <div class="meta">
+ <time datetime="2026-06-02">Jun 2, 2026</time>
+ <span class="dot" aria-hidden="true"></span>
+ <span>3 min</span>
+ </div>
+ <h3><a href="/blog/what-are-claude-code-agents/">What Are Claude Code Agents? And How to Use Many at Once</a></h3>
+ <p class="dek">Claude Code agents explained in plain English — what an agent actually is, how subagents differ, and the leap from one agent to a coordinated team.</p>
+ <div class="foot">
+ <span class="tag kind">Concepts</span>
+ <a class="more" href="/blog/what-are-claude-code-agents/" aria-label="Read: What Are Claude Code Agents? And How to Use Many at Once">Read →</a>
+ </div>
+ </div>
+</article>
+<article class="card">
<a class="thumb t-guides" href="/blog/how-to-run-multiple-claude-code-agents/" aria-hidden="true" tabindex="-1">
<span>GUIDES</span>
</a>
@@ -80,6 +134,24 @@
</div>
</div>
</article>
+<article class="card">
+ <a class="thumb t-guides" href="/blog/claude-code-multi-agent-setup-tutorial/" aria-hidden="true" tabindex="-1">
+ <span>GUIDES</span>
+ </a>
+ <div class="body">
+ <div class="meta">
+ <time datetime="2026-05-24">May 24, 2026</time>
+ <span class="dot" aria-hidden="true"></span>
+ <span>5 min</span>
+ </div>
+ <h3><a href="/blog/claude-code-multi-agent-setup-tutorial/">Set Up a Claude Code Multi-Agent Workflow in 10 Minutes</a></h3>
+ <p class="dek">A from-zero Claude Code multi-agent setup: install Munder Difflin, onboard, spawn a few agents, and watch the GOD orchestrator route your first task.</p>
+ <div class="foot">
+ <span class="tag kind">Guides</span>
+ <a class="more" href="/blog/claude-code-multi-agent-setup-tutorial/" aria-label="Read: Set Up a Claude Code Multi-Agent Workflow in 10 Minutes">Read →</a>
+ </div>
+ </div>
+</article>
</div>
</section>
diff --git a/docs/blog/tags/git/index.html b/docs/blog/tags/git/index.html
new file mode 100644
index 00000000..405bdb5b
--- /dev/null
+++ b/docs/blog/tags/git/index.html
@@ -0,0 +1,142 @@
+<!doctype html>
+<html lang="en">
+<head>
+<meta charset="UTF-8" />
+<meta name="viewport" content="width=device-width, initial-scale=1.0" />
+<title>Git — Munder Difflin Blog</title>
+<meta name="description" content="Munder Difflin blog posts tagged Git." />
+<link rel="canonical" href="https://munderdiffl.in/blog/tags/git/" />
+
+<link rel="icon" type="image/png" href="https://munderdiffl.in/logo.png" />
+<link rel="apple-touch-icon" href="https://munderdiffl.in/logo.png" />
+<meta name="theme-color" content="#F5F2E8" />
+
+<!-- Open Graph -->
+<meta property="og:site_name" content="Munder Difflin Blog" />
+<meta property="og:type" content="website" />
+<meta property="og:title" content="Git — Munder Difflin Blog" />
+<meta property="og:description" content="Munder Difflin blog posts tagged Git." />
+<meta property="og:url" content="https://munderdiffl.in/blog/tags/git/" />
+<meta property="og:image" content="https://munderdiffl.in/media/og.png" />
+<meta property="og:locale" content="en_US" />
+
+
+<!-- Twitter -->
+<meta name="twitter:card" content="summary_large_image" />
+<meta name="twitter:title" content="Git — Munder Difflin Blog" />
+<meta name="twitter:description" content="Munder Difflin blog posts tagged Git." />
+<meta name="twitter:image" content="https://munderdiffl.in/media/og.png" />
+
+<link rel="alternate" type="application/atom+xml" title="Munder Difflin Blog" href="https://munderdiffl.in/blog/feed.xml" />
+<link rel="preconnect" href="https://fonts.googleapis.com" />
+<link rel="preconnect" href="https://fonts.gstatic.com" crossorigin />
+<link href="https://fonts.googleapis.com/css2?family=Geist:wght@400;500;600&family=JetBrains+Mono:wght@400;500;600;700&display=swap" rel="stylesheet" />
+<link rel="stylesheet" href="/blog/assets/blog.css" />
+
+</head>
+<body>
+<a class="skip-link" href="#main">Skip to content</a>
+<nav id="nav">
+ <a class="brand" href="/blog/" aria-label="Munder Difflin Blog home">
+ <span class="brand-mark">MD</span>
+ <span class="brand-word">MUNDER DIFFLIN<span class="sep">/</span><span class="blog">BLOG</span></span>
+ </a>
+ <span class="spacer"></span>
+ <div class="links">
+ <a href="/blog/">Latest</a>
+ <a href="/blog/topics/">Topics</a>
+ <a href="/blog/about/">About</a>
+ <a href="https://munderdiffl.in">↗ Product</a>
+ </div>
+ <div class="nav-actions">
+ <a class="btn sm" href="https://munderdiffl.in/blog/feed.xml" aria-label="RSS feed">⤵ RSS</a>
+ <a class="btn sm primary" href="https://munderdiffl.in/#install">⤓ Download</a>
+ </div>
+</nav>
+
+<main id="main">
+<header class="page-head wrap">
+ <p class="eyebrow">Tag</p>
+ <h1>#Git</h1>
+ <p class="lead">2 posts tagged <strong>Git</strong>.</p>
+</header>
+<section class="wrap">
+ <div class="post-grid">
+ <article class="card">
+ <a class="thumb t-orchestration" href="/blog/claude-code-git-worktrees-vs-hive/" aria-hidden="true" tabindex="-1">
+ <span>ORCHESTRATION</span>
+ </a>
+ <div class="body">
+ <div class="meta">
+ <time datetime="2026-06-04">Jun 4, 2026</time>
+ <span class="dot" aria-hidden="true"></span>
+ <span>5 min</span>
+ </div>
+ <h3><a href="/blog/claude-code-git-worktrees-vs-hive/">Git Worktrees vs a Hive: Two Ways to Parallelize Claude Code</a></h3>
+ <p class="dek">Claude Code git worktrees vs a hive: when isolated worktrees suffice for parallel agents, and when you need memory, messaging, and an orchestrator on top.</p>
+ <div class="foot">
+ <span class="tag kind">Orchestration</span>
+ <a class="more" href="/blog/claude-code-git-worktrees-vs-hive/" aria-label="Read: Git Worktrees vs a Hive: Two Ways to Parallelize Claude Code">Read →</a>
+ </div>
+ </div>
+</article>
+<article class="card">
+ <a class="thumb t-internals" href="/blog/single-committer-git-pattern/" aria-hidden="true" tabindex="-1">
+ <span>INTERNALS</span>
+ </a>
+ <div class="body">
+ <div class="meta">
+ <time datetime="2026-06-02">Jun 2, 2026</time>
+ <span class="dot" aria-hidden="true"></span>
+ <span>5 min</span>
+ </div>
+ <h3><a href="/blog/single-committer-git-pattern/">The Single-Committer Pattern: Multi-Agent Git Without Corruption</a></h3>
+ <p class="dek">Parallel agents corrupt a repo with index.lock races. The single-committer pattern — agents write, one process commits — fixes concurrent git writes.</p>
+ <div class="foot">
+ <span class="tag kind">Internals</span>
+ <a class="more" href="/blog/single-committer-git-pattern/" aria-label="Read: The Single-Committer Pattern: Multi-Agent Git Without Corruption">Read →</a>
+ </div>
+ </div>
+</article>
+
+ </div>
+</section>
+
+
+</main>
+<footer>
+ <div class="wrap">
+ <div class="foot-top">
+ <a class="foot-brand brand" href="/blog/">
+ <span class="brand-mark">MD</span>
+ <span class="brand-word">MUNDER DIFFLIN<span class="sep">/</span><span class="blog">BLOG</span></span>
+ </a>
+ <div class="foot-links">
+ <a href="/blog/">Latest</a>
+ <a href="/blog/topics/">Topics</a>
+ <a href="/blog/about/">About</a>
+ <a href="https://munderdiffl.in/blog/feed.xml">RSS</a>
+ <a href="https://github.com/chaitanyagiri/munder-difflin">GitHub</a>
+ <a href="https://munderdiffl.in">munderdiffl.in ↗</a>
+ </div>
+ </div>
+ <div class="foot-meta">
+ © 2026 Munder Difflin · Local-first · MIT-licensed ·
+ Built on <a href="https://munderdiffl.in">Electron, React, Pixi.js, xterm.js &amp; node-pty</a>.
+ Run an office of agents while you sleep.
+ </div>
+ </div>
+</footer>
+
+<script>
+ // sticky-nav border on scroll
+ (function () {
+ var nav = document.getElementById('nav');
+ if (!nav) return;
+ var onScroll = function () { nav.classList.toggle('scrolled', window.scrollY > 8); };
+ onScroll(); window.addEventListener('scroll', onScroll, { passive: true });
+ })();
+</script>
+
+</body>
+</html>
diff --git a/docs/blog/tags/glossary/index.html b/docs/blog/tags/glossary/index.html
new file mode 100644
index 00000000..a631cc8f
--- /dev/null
+++ b/docs/blog/tags/glossary/index.html
@@ -0,0 +1,124 @@
+<!doctype html>
+<html lang="en">
+<head>
+<meta charset="UTF-8" />
+<meta name="viewport" content="width=device-width, initial-scale=1.0" />
+<title>Glossary — Munder Difflin Blog</title>
+<meta name="description" content="Munder Difflin blog posts tagged Glossary." />
+<link rel="canonical" href="https://munderdiffl.in/blog/tags/glossary/" />
+
+<link rel="icon" type="image/png" href="https://munderdiffl.in/logo.png" />
+<link rel="apple-touch-icon" href="https://munderdiffl.in/logo.png" />
+<meta name="theme-color" content="#F5F2E8" />
+
+<!-- Open Graph -->
+<meta property="og:site_name" content="Munder Difflin Blog" />
+<meta property="og:type" content="website" />
+<meta property="og:title" content="Glossary — Munder Difflin Blog" />
+<meta property="og:description" content="Munder Difflin blog posts tagged Glossary." />
+<meta property="og:url" content="https://munderdiffl.in/blog/tags/glossary/" />
+<meta property="og:image" content="https://munderdiffl.in/media/og.png" />
+<meta property="og:locale" content="en_US" />
+
+
+<!-- Twitter -->
+<meta name="twitter:card" content="summary_large_image" />
+<meta name="twitter:title" content="Glossary — Munder Difflin Blog" />
+<meta name="twitter:description" content="Munder Difflin blog posts tagged Glossary." />
+<meta name="twitter:image" content="https://munderdiffl.in/media/og.png" />
+
+<link rel="alternate" type="application/atom+xml" title="Munder Difflin Blog" href="https://munderdiffl.in/blog/feed.xml" />
+<link rel="preconnect" href="https://fonts.googleapis.com" />
+<link rel="preconnect" href="https://fonts.gstatic.com" crossorigin />
+<link href="https://fonts.googleapis.com/css2?family=Geist:wght@400;500;600&family=JetBrains+Mono:wght@400;500;600;700&display=swap" rel="stylesheet" />
+<link rel="stylesheet" href="/blog/assets/blog.css" />
+
+</head>
+<body>
+<a class="skip-link" href="#main">Skip to content</a>
+<nav id="nav">
+ <a class="brand" href="/blog/" aria-label="Munder Difflin Blog home">
+ <span class="brand-mark">MD</span>
+ <span class="brand-word">MUNDER DIFFLIN<span class="sep">/</span><span class="blog">BLOG</span></span>
+ </a>
+ <span class="spacer"></span>
+ <div class="links">
+ <a href="/blog/">Latest</a>
+ <a href="/blog/topics/">Topics</a>
+ <a href="/blog/about/">About</a>
+ <a href="https://munderdiffl.in">↗ Product</a>
+ </div>
+ <div class="nav-actions">
+ <a class="btn sm" href="https://munderdiffl.in/blog/feed.xml" aria-label="RSS feed">⤵ RSS</a>
+ <a class="btn sm primary" href="https://munderdiffl.in/#install">⤓ Download</a>
+ </div>
+</nav>
+
+<main id="main">
+<header class="page-head wrap">
+ <p class="eyebrow">Tag</p>
+ <h1>#Glossary</h1>
+ <p class="lead">1 post tagged <strong>Glossary</strong>.</p>
+</header>
+<section class="wrap">
+ <div class="post-grid">
+ <article class="card">
+ <a class="thumb t-concepts" href="/blog/ai-agent-glossary/" aria-hidden="true" tabindex="-1">
+ <span>CONCEPTS</span>
+ </a>
+ <div class="body">
+ <div class="meta">
+ <time datetime="2026-06-02">Jun 2, 2026</time>
+ <span class="dot" aria-hidden="true"></span>
+ <span>3 min</span>
+ </div>
+ <h3><a href="/blog/ai-agent-glossary/">The AI Coding Agent Glossary: Harness, Orchestrator, Hive, Subagent</a></h3>
+ <p class="dek">Plain-English definitions of the AI coding agent terms everyone trips over — harness, orchestrator, hive, subagent, agent memory — each in one line.</p>
+ <div class="foot">
+ <span class="tag kind">Concepts</span>
+ <a class="more" href="/blog/ai-agent-glossary/" aria-label="Read: The AI Coding Agent Glossary: Harness, Orchestrator, Hive, Subagent">Read →</a>
+ </div>
+ </div>
+</article>
+
+ </div>
+</section>
+
+
+</main>
+<footer>
+ <div class="wrap">
+ <div class="foot-top">
+ <a class="foot-brand brand" href="/blog/">
+ <span class="brand-mark">MD</span>
+ <span class="brand-word">MUNDER DIFFLIN<span class="sep">/</span><span class="blog">BLOG</span></span>
+ </a>
+ <div class="foot-links">
+ <a href="/blog/">Latest</a>
+ <a href="/blog/topics/">Topics</a>
+ <a href="/blog/about/">About</a>
+ <a href="https://munderdiffl.in/blog/feed.xml">RSS</a>
+ <a href="https://github.com/chaitanyagiri/munder-difflin">GitHub</a>
+ <a href="https://munderdiffl.in">munderdiffl.in ↗</a>
+ </div>
+ </div>
+ <div class="foot-meta">
+ © 2026 Munder Difflin · Local-first · MIT-licensed ·
+ Built on <a href="https://munderdiffl.in">Electron, React, Pixi.js, xterm.js &amp; node-pty</a>.
+ Run an office of agents while you sleep.
+ </div>
+ </div>
+</footer>
+
+<script>
+ // sticky-nav border on scroll
+ (function () {
+ var nav = document.getElementById('nav');
+ if (!nav) return;
+ var onScroll = function () { nav.classList.toggle('scrolled', window.scrollY > 8); };
+ onScroll(); window.addEventListener('scroll', onScroll, { passive: true });
+ })();
+</script>
+
+</body>
+</html>
diff --git a/docs/blog/tags/god/index.html b/docs/blog/tags/god/index.html
new file mode 100644
index 00000000..66c87da2
--- /dev/null
+++ b/docs/blog/tags/god/index.html
@@ -0,0 +1,142 @@
+<!doctype html>
+<html lang="en">
+<head>
+<meta charset="UTF-8" />
+<meta name="viewport" content="width=device-width, initial-scale=1.0" />
+<title>GOD — Munder Difflin Blog</title>
+<meta name="description" content="Munder Difflin blog posts tagged GOD." />
+<link rel="canonical" href="https://munderdiffl.in/blog/tags/god/" />
+
+<link rel="icon" type="image/png" href="https://munderdiffl.in/logo.png" />
+<link rel="apple-touch-icon" href="https://munderdiffl.in/logo.png" />
+<meta name="theme-color" content="#F5F2E8" />
+
+<!-- Open Graph -->
+<meta property="og:site_name" content="Munder Difflin Blog" />
+<meta property="og:type" content="website" />
+<meta property="og:title" content="GOD — Munder Difflin Blog" />
+<meta property="og:description" content="Munder Difflin blog posts tagged GOD." />
+<meta property="og:url" content="https://munderdiffl.in/blog/tags/god/" />
+<meta property="og:image" content="https://munderdiffl.in/media/og.png" />
+<meta property="og:locale" content="en_US" />
+
+
+<!-- Twitter -->
+<meta name="twitter:card" content="summary_large_image" />
+<meta name="twitter:title" content="GOD — Munder Difflin Blog" />
+<meta name="twitter:description" content="Munder Difflin blog posts tagged GOD." />
+<meta name="twitter:image" content="https://munderdiffl.in/media/og.png" />
+
+<link rel="alternate" type="application/atom+xml" title="Munder Difflin Blog" href="https://munderdiffl.in/blog/feed.xml" />
+<link rel="preconnect" href="https://fonts.googleapis.com" />
+<link rel="preconnect" href="https://fonts.gstatic.com" crossorigin />
+<link href="https://fonts.googleapis.com/css2?family=Geist:wght@400;500;600&family=JetBrains+Mono:wght@400;500;600;700&display=swap" rel="stylesheet" />
+<link rel="stylesheet" href="/blog/assets/blog.css" />
+
+</head>
+<body>
+<a class="skip-link" href="#main">Skip to content</a>
+<nav id="nav">
+ <a class="brand" href="/blog/" aria-label="Munder Difflin Blog home">
+ <span class="brand-mark">MD</span>
+ <span class="brand-word">MUNDER DIFFLIN<span class="sep">/</span><span class="blog">BLOG</span></span>
+ </a>
+ <span class="spacer"></span>
+ <div class="links">
+ <a href="/blog/">Latest</a>
+ <a href="/blog/topics/">Topics</a>
+ <a href="/blog/about/">About</a>
+ <a href="https://munderdiffl.in">↗ Product</a>
+ </div>
+ <div class="nav-actions">
+ <a class="btn sm" href="https://munderdiffl.in/blog/feed.xml" aria-label="RSS feed">⤵ RSS</a>
+ <a class="btn sm primary" href="https://munderdiffl.in/#install">⤓ Download</a>
+ </div>
+</nav>
+
+<main id="main">
+<header class="page-head wrap">
+ <p class="eyebrow">Tag</p>
+ <h1>#GOD</h1>
+ <p class="lead">2 posts tagged <strong>GOD</strong>.</p>
+</header>
+<section class="wrap">
+ <div class="post-grid">
+ <article class="card">
+ <a class="thumb t-orchestration" href="/blog/how-the-god-orchestrator-works/" aria-hidden="true" tabindex="-1">
+ <span>ORCHESTRATION</span>
+ </a>
+ <div class="body">
+ <div class="meta">
+ <time datetime="2026-05-30">May 30, 2026</time>
+ <span class="dot" aria-hidden="true"></span>
+ <span>6 min</span>
+ </div>
+ <h3><a href="/blog/how-the-god-orchestrator-works/">Inside the GOD Orchestrator: Routing, Adjudication, Escalation</a></h3>
+ <p class="dek">A deep dive into the Claude Code orchestrator: how a GOD agent reads requests, routes work, adjudicates routine traffic, and escalates the critical few.</p>
+ <div class="foot">
+ <span class="tag kind">Orchestration</span>
+ <a class="more" href="/blog/how-the-god-orchestrator-works/" aria-label="Read: Inside the GOD Orchestrator: Routing, Adjudication, Escalation">Read →</a>
+ </div>
+ </div>
+</article>
+<article class="card">
+ <a class="thumb t-orchestration" href="/blog/claude-code-orchestration-guide/" aria-hidden="true" tabindex="-1">
+ <span>ORCHESTRATION</span>
+ </a>
+ <div class="body">
+ <div class="meta">
+ <time datetime="2026-05-28">May 28, 2026</time>
+ <span class="dot" aria-hidden="true"></span>
+ <span>5 min</span>
+ </div>
+ <h3><a href="/blog/claude-code-orchestration-guide/">Orchestrating Claude Code Agents: A Practical Guide</a></h3>
+ <p class="dek">How to orchestrate Claude Code agents in practice: what orchestration means, how a GOD orchestrator routes and escalates work, and how to wire it up.</p>
+ <div class="foot">
+ <span class="tag kind">Orchestration</span>
+ <a class="more" href="/blog/claude-code-orchestration-guide/" aria-label="Read: Orchestrating Claude Code Agents: A Practical Guide">Read →</a>
+ </div>
+ </div>
+</article>
+
+ </div>
+</section>
+
+
+</main>
+<footer>
+ <div class="wrap">
+ <div class="foot-top">
+ <a class="foot-brand brand" href="/blog/">
+ <span class="brand-mark">MD</span>
+ <span class="brand-word">MUNDER DIFFLIN<span class="sep">/</span><span class="blog">BLOG</span></span>
+ </a>
+ <div class="foot-links">
+ <a href="/blog/">Latest</a>
+ <a href="/blog/topics/">Topics</a>
+ <a href="/blog/about/">About</a>
+ <a href="https://munderdiffl.in/blog/feed.xml">RSS</a>
+ <a href="https://github.com/chaitanyagiri/munder-difflin">GitHub</a>
+ <a href="https://munderdiffl.in">munderdiffl.in ↗</a>
+ </div>
+ </div>
+ <div class="foot-meta">
+ © 2026 Munder Difflin · Local-first · MIT-licensed ·
+ Built on <a href="https://munderdiffl.in">Electron, React, Pixi.js, xterm.js &amp; node-pty</a>.
+ Run an office of agents while you sleep.
+ </div>
+ </div>
+</footer>
+
+<script>
+ // sticky-nav border on scroll
+ (function () {
+ var nav = document.getElementById('nav');
+ if (!nav) return;
+ var onScroll = function () { nav.classList.toggle('scrolled', window.scrollY > 8); };
+ onScroll(); window.addEventListener('scroll', onScroll, { passive: true });
+ })();
+</script>
+
+</body>
+</html>
diff --git a/docs/blog/tags/guides/index.html b/docs/blog/tags/guides/index.html
index fe0eec5d..788786ec 100644
--- a/docs/blog/tags/guides/index.html
+++ b/docs/blog/tags/guides/index.html
@@ -58,11 +58,47 @@
<header class="page-head wrap">
<p class="eyebrow">Tag</p>
<h1>#Guides</h1>
- <p class="lead">1 post tagged <strong>Guides</strong>.</p>
+ <p class="lead">6 posts tagged <strong>Guides</strong>.</p>
</header>
<section class="wrap">
<div class="post-grid">
<article class="card">
+ <a class="thumb t-guides" href="/blog/claude-code-automation-while-you-sleep/" aria-hidden="true" tabindex="-1">
+ <span>GUIDES</span>
+ </a>
+ <div class="body">
+ <div class="meta">
+ <time datetime="2026-06-04">Jun 4, 2026</time>
+ <span class="dot" aria-hidden="true"></span>
+ <span>5 min</span>
+ </div>
+ <h3><a href="/blog/claude-code-automation-while-you-sleep/">Claude Code Automation: Let Agents Build While You Sleep</a></h3>
+ <p class="dek">Claude Code automation that runs overnight: an autonomous Stop-hook loop, safe permission bypass, and guardrails so you wake up to progress, not chaos.</p>
+ <div class="foot">
+ <span class="tag kind">Guides</span>
+ <a class="more" href="/blog/claude-code-automation-while-you-sleep/" aria-label="Read: Claude Code Automation: Let Agents Build While You Sleep">Read →</a>
+ </div>
+ </div>
+</article>
+<article class="card">
+ <a class="thumb t-guides" href="/blog/mcp-and-skills-in-a-hive/" aria-hidden="true" tabindex="-1">
+ <span>GUIDES</span>
+ </a>
+ <div class="body">
+ <div class="meta">
+ <time datetime="2026-06-03">Jun 3, 2026</time>
+ <span class="dot" aria-hidden="true"></span>
+ <span>6 min</span>
+ </div>
+ <h3><a href="/blog/mcp-and-skills-in-a-hive/">Bringing Your MCP Servers and Skills Into a Hive of Agents</a></h3>
+ <p class="dek">How agents in a hive inherit your existing Claude Code MCP servers, skills, and tools — and how to scope which agent gets which capability.</p>
+ <div class="foot">
+ <span class="tag kind">Guides</span>
+ <a class="more" href="/blog/mcp-and-skills-in-a-hive/" aria-label="Read: Bringing Your MCP Servers and Skills Into a Hive of Agents">Read →</a>
+ </div>
+ </div>
+</article>
+<article class="card">
<a class="thumb t-guides" href="/blog/how-to-run-multiple-claude-code-agents/" aria-hidden="true" tabindex="-1">
<span>GUIDES</span>
</a>
@@ -80,6 +116,60 @@
</div>
</div>
</article>
+<article class="card">
+ <a class="thumb t-guides" href="/blog/manage-multiple-claude-code-sessions/" aria-hidden="true" tabindex="-1">
+ <span>GUIDES</span>
+ </a>
+ <div class="body">
+ <div class="meta">
+ <time datetime="2026-05-25">May 25, 2026</time>
+ <span class="dot" aria-hidden="true"></span>
+ <span>4 min</span>
+ </div>
+ <h3><a href="/blog/manage-multiple-claude-code-sessions/">How to Manage Multiple Claude Code Sessions Like a Pro</a></h3>
+ <p class="dek">Tactics to manage multiple Claude Code sessions without losing track: naming, roles, context isolation, and when a harness beats juggling terminal tabs.</p>
+ <div class="foot">
+ <span class="tag kind">Guides</span>
+ <a class="more" href="/blog/manage-multiple-claude-code-sessions/" aria-label="Read: How to Manage Multiple Claude Code Sessions Like a Pro">Read →</a>
+ </div>
+ </div>
+</article>
+<article class="card">
+ <a class="thumb t-guides" href="/blog/claude-code-multi-agent-setup-tutorial/" aria-hidden="true" tabindex="-1">
+ <span>GUIDES</span>
+ </a>
+ <div class="body">
+ <div class="meta">
+ <time datetime="2026-05-24">May 24, 2026</time>
+ <span class="dot" aria-hidden="true"></span>
+ <span>5 min</span>
+ </div>
+ <h3><a href="/blog/claude-code-multi-agent-setup-tutorial/">Set Up a Claude Code Multi-Agent Workflow in 10 Minutes</a></h3>
+ <p class="dek">A from-zero Claude Code multi-agent setup: install Munder Difflin, onboard, spawn a few agents, and watch the GOD orchestrator route your first task.</p>
+ <div class="foot">
+ <span class="tag kind">Guides</span>
+ <a class="more" href="/blog/claude-code-multi-agent-setup-tutorial/" aria-label="Read: Set Up a Claude Code Multi-Agent Workflow in 10 Minutes">Read →</a>
+ </div>
+ </div>
+</article>
+<article class="card">
+ <a class="thumb t-guides" href="/blog/claude-code-subagents-vs-multi-agent-harness/" aria-hidden="true" tabindex="-1">
+ <span>GUIDES</span>
+ </a>
+ <div class="body">
+ <div class="meta">
+ <time datetime="2026-05-23">May 23, 2026</time>
+ <span class="dot" aria-hidden="true"></span>
+ <span>5 min</span>
+ </div>
+ <h3><a href="/blog/claude-code-subagents-vs-multi-agent-harness/">Claude Code Subagents vs a Multi-Agent Harness</a></h3>
+ <p class="dek">Claude Code subagents vs a multi-agent harness: where subagents stop and a harness with shared memory, messaging, and an orchestrator takes over.</p>
+ <div class="foot">
+ <span class="tag kind">Guides</span>
+ <a class="more" href="/blog/claude-code-subagents-vs-multi-agent-harness/" aria-label="Read: Claude Code Subagents vs a Multi-Agent Harness">Read →</a>
+ </div>
+ </div>
+</article>
</div>
</section>
diff --git a/docs/blog/tags/hooks/index.html b/docs/blog/tags/hooks/index.html
new file mode 100644
index 00000000..85876ab3
--- /dev/null
+++ b/docs/blog/tags/hooks/index.html
@@ -0,0 +1,124 @@
+<!doctype html>
+<html lang="en">
+<head>
+<meta charset="UTF-8" />
+<meta name="viewport" content="width=device-width, initial-scale=1.0" />
+<title>Hooks — Munder Difflin Blog</title>
+<meta name="description" content="Munder Difflin blog posts tagged Hooks." />
+<link rel="canonical" href="https://munderdiffl.in/blog/tags/hooks/" />
+
+<link rel="icon" type="image/png" href="https://munderdiffl.in/logo.png" />
+<link rel="apple-touch-icon" href="https://munderdiffl.in/logo.png" />
+<meta name="theme-color" content="#F5F2E8" />
+
+<!-- Open Graph -->
+<meta property="og:site_name" content="Munder Difflin Blog" />
+<meta property="og:type" content="website" />
+<meta property="og:title" content="Hooks — Munder Difflin Blog" />
+<meta property="og:description" content="Munder Difflin blog posts tagged Hooks." />
+<meta property="og:url" content="https://munderdiffl.in/blog/tags/hooks/" />
+<meta property="og:image" content="https://munderdiffl.in/media/og.png" />
+<meta property="og:locale" content="en_US" />
+
+
+<!-- Twitter -->
+<meta name="twitter:card" content="summary_large_image" />
+<meta name="twitter:title" content="Hooks — Munder Difflin Blog" />
+<meta name="twitter:description" content="Munder Difflin blog posts tagged Hooks." />
+<meta name="twitter:image" content="https://munderdiffl.in/media/og.png" />
+
+<link rel="alternate" type="application/atom+xml" title="Munder Difflin Blog" href="https://munderdiffl.in/blog/feed.xml" />
+<link rel="preconnect" href="https://fonts.googleapis.com" />
+<link rel="preconnect" href="https://fonts.gstatic.com" crossorigin />
+<link href="https://fonts.googleapis.com/css2?family=Geist:wght@400;500;600&family=JetBrains+Mono:wght@400;500;600;700&display=swap" rel="stylesheet" />
+<link rel="stylesheet" href="/blog/assets/blog.css" />
+
+</head>
+<body>
+<a class="skip-link" href="#main">Skip to content</a>
+<nav id="nav">
+ <a class="brand" href="/blog/" aria-label="Munder Difflin Blog home">
+ <span class="brand-mark">MD</span>
+ <span class="brand-word">MUNDER DIFFLIN<span class="sep">/</span><span class="blog">BLOG</span></span>
+ </a>
+ <span class="spacer"></span>
+ <div class="links">
+ <a href="/blog/">Latest</a>
+ <a href="/blog/topics/">Topics</a>
+ <a href="/blog/about/">About</a>
+ <a href="https://munderdiffl.in">↗ Product</a>
+ </div>
+ <div class="nav-actions">
+ <a class="btn sm" href="https://munderdiffl.in/blog/feed.xml" aria-label="RSS feed">⤵ RSS</a>
+ <a class="btn sm primary" href="https://munderdiffl.in/#install">⤓ Download</a>
+ </div>
+</nav>
+
+<main id="main">
+<header class="page-head wrap">
+ <p class="eyebrow">Tag</p>
+ <h1>#Hooks</h1>
+ <p class="lead">1 post tagged <strong>Hooks</strong>.</p>
+</header>
+<section class="wrap">
+ <div class="post-grid">
+ <article class="card">
+ <a class="thumb t-internals" href="/blog/claude-code-hooks-explained/" aria-hidden="true" tabindex="-1">
+ <span>INTERNALS</span>
+ </a>
+ <div class="body">
+ <div class="meta">
+ <time datetime="2026-06-03">Jun 3, 2026</time>
+ <span class="dot" aria-hidden="true"></span>
+ <span>6 min</span>
+ </div>
+ <h3><a href="/blog/claude-code-hooks-explained/">Claude Code Hooks, Explained (PreToolUse, PostToolUse, Stop)</a></h3>
+ <p class="dek">A practical tour of Claude Code hooks — the PreToolUse, PostToolUse, and Stop lifecycle — and how a Unix-socket hook shim drives a live office floor.</p>
+ <div class="foot">
+ <span class="tag kind">Internals</span>
+ <a class="more" href="/blog/claude-code-hooks-explained/" aria-label="Read: Claude Code Hooks, Explained (PreToolUse, PostToolUse, Stop)">Read →</a>
+ </div>
+ </div>
+</article>
+
+ </div>
+</section>
+
+
+</main>
+<footer>
+ <div class="wrap">
+ <div class="foot-top">
+ <a class="foot-brand brand" href="/blog/">
+ <span class="brand-mark">MD</span>
+ <span class="brand-word">MUNDER DIFFLIN<span class="sep">/</span><span class="blog">BLOG</span></span>
+ </a>
+ <div class="foot-links">
+ <a href="/blog/">Latest</a>
+ <a href="/blog/topics/">Topics</a>
+ <a href="/blog/about/">About</a>
+ <a href="https://munderdiffl.in/blog/feed.xml">RSS</a>
+ <a href="https://github.com/chaitanyagiri/munder-difflin">GitHub</a>
+ <a href="https://munderdiffl.in">munderdiffl.in ↗</a>
+ </div>
+ </div>
+ <div class="foot-meta">
+ © 2026 Munder Difflin · Local-first · MIT-licensed ·
+ Built on <a href="https://munderdiffl.in">Electron, React, Pixi.js, xterm.js &amp; node-pty</a>.
+ Run an office of agents while you sleep.
+ </div>
+ </div>
+</footer>
+
+<script>
+ // sticky-nav border on scroll
+ (function () {
+ var nav = document.getElementById('nav');
+ if (!nav) return;
+ var onScroll = function () { nav.classList.toggle('scrolled', window.scrollY > 8); };
+ onScroll(); window.addEventListener('scroll', onScroll, { passive: true });
+ })();
+</script>
+
+</body>
+</html>
diff --git a/docs/blog/tags/internals/index.html b/docs/blog/tags/internals/index.html
new file mode 100644
index 00000000..4d8899bf
--- /dev/null
+++ b/docs/blog/tags/internals/index.html
@@ -0,0 +1,214 @@
+<!doctype html>
+<html lang="en">
+<head>
+<meta charset="UTF-8" />
+<meta name="viewport" content="width=device-width, initial-scale=1.0" />
+<title>Internals — Munder Difflin Blog</title>
+<meta name="description" content="Munder Difflin blog posts tagged Internals." />
+<link rel="canonical" href="https://munderdiffl.in/blog/tags/internals/" />
+
+<link rel="icon" type="image/png" href="https://munderdiffl.in/logo.png" />
+<link rel="apple-touch-icon" href="https://munderdiffl.in/logo.png" />
+<meta name="theme-color" content="#F5F2E8" />
+
+<!-- Open Graph -->
+<meta property="og:site_name" content="Munder Difflin Blog" />
+<meta property="og:type" content="website" />
+<meta property="og:title" content="Internals — Munder Difflin Blog" />
+<meta property="og:description" content="Munder Difflin blog posts tagged Internals." />
+<meta property="og:url" content="https://munderdiffl.in/blog/tags/internals/" />
+<meta property="og:image" content="https://munderdiffl.in/media/og.png" />
+<meta property="og:locale" content="en_US" />
+
+
+<!-- Twitter -->
+<meta name="twitter:card" content="summary_large_image" />
+<meta name="twitter:title" content="Internals — Munder Difflin Blog" />
+<meta name="twitter:description" content="Munder Difflin blog posts tagged Internals." />
+<meta name="twitter:image" content="https://munderdiffl.in/media/og.png" />
+
+<link rel="alternate" type="application/atom+xml" title="Munder Difflin Blog" href="https://munderdiffl.in/blog/feed.xml" />
+<link rel="preconnect" href="https://fonts.googleapis.com" />
+<link rel="preconnect" href="https://fonts.gstatic.com" crossorigin />
+<link href="https://fonts.googleapis.com/css2?family=Geist:wght@400;500;600&family=JetBrains+Mono:wght@400;500;600;700&display=swap" rel="stylesheet" />
+<link rel="stylesheet" href="/blog/assets/blog.css" />
+
+</head>
+<body>
+<a class="skip-link" href="#main">Skip to content</a>
+<nav id="nav">
+ <a class="brand" href="/blog/" aria-label="Munder Difflin Blog home">
+ <span class="brand-mark">MD</span>
+ <span class="brand-word">MUNDER DIFFLIN<span class="sep">/</span><span class="blog">BLOG</span></span>
+ </a>
+ <span class="spacer"></span>
+ <div class="links">
+ <a href="/blog/">Latest</a>
+ <a href="/blog/topics/">Topics</a>
+ <a href="/blog/about/">About</a>
+ <a href="https://munderdiffl.in">↗ Product</a>
+ </div>
+ <div class="nav-actions">
+ <a class="btn sm" href="https://munderdiffl.in/blog/feed.xml" aria-label="RSS feed">⤵ RSS</a>
+ <a class="btn sm primary" href="https://munderdiffl.in/#install">⤓ Download</a>
+ </div>
+</nav>
+
+<main id="main">
+<header class="page-head wrap">
+ <p class="eyebrow">Tag</p>
+ <h1>#Internals</h1>
+ <p class="lead">6 posts tagged <strong>Internals</strong>.</p>
+</header>
+<section class="wrap">
+ <div class="post-grid">
+ <article class="card">
+ <a class="thumb t-internals" href="/blog/building-a-terminal-ui-xterm-node-pty/" aria-hidden="true" tabindex="-1">
+ <span>INTERNALS</span>
+ </a>
+ <div class="body">
+ <div class="meta">
+ <time datetime="2026-06-03">Jun 3, 2026</time>
+ <span class="dot" aria-hidden="true"></span>
+ <span>8 min</span>
+ </div>
+ <h3><a href="/blog/building-a-terminal-ui-xterm-node-pty/">Building a Terminal UI with xterm.js and node-pty</a></h3>
+ <p class="dek">Wire xterm.js to a node-pty backend: stream output, write keystrokes back, handle resize, and keep many live terminals fast with a terminal pool.</p>
+ <div class="foot">
+ <span class="tag kind">Internals</span>
+ <a class="more" href="/blog/building-a-terminal-ui-xterm-node-pty/" aria-label="Read: Building a Terminal UI with xterm.js and node-pty">Read →</a>
+ </div>
+ </div>
+</article>
+<article class="card">
+ <a class="thumb t-internals" href="/blog/claude-code-hooks-explained/" aria-hidden="true" tabindex="-1">
+ <span>INTERNALS</span>
+ </a>
+ <div class="body">
+ <div class="meta">
+ <time datetime="2026-06-03">Jun 3, 2026</time>
+ <span class="dot" aria-hidden="true"></span>
+ <span>6 min</span>
+ </div>
+ <h3><a href="/blog/claude-code-hooks-explained/">Claude Code Hooks, Explained (PreToolUse, PostToolUse, Stop)</a></h3>
+ <p class="dek">A practical tour of Claude Code hooks — the PreToolUse, PostToolUse, and Stop lifecycle — and how a Unix-socket hook shim drives a live office floor.</p>
+ <div class="foot">
+ <span class="tag kind">Internals</span>
+ <a class="more" href="/blog/claude-code-hooks-explained/" aria-label="Read: Claude Code Hooks, Explained (PreToolUse, PostToolUse, Stop)">Read →</a>
+ </div>
+ </div>
+</article>
+<article class="card">
+ <a class="thumb t-internals" href="/blog/node-pty-electron-real-terminals/" aria-hidden="true" tabindex="-1">
+ <span>INTERNALS</span>
+ </a>
+ <div class="body">
+ <div class="meta">
+ <time datetime="2026-06-03">Jun 3, 2026</time>
+ <span class="dot" aria-hidden="true"></span>
+ <span>7 min</span>
+ </div>
+ <h3><a href="/blog/node-pty-electron-real-terminals/">Real Terminals in Electron with node-pty</a></h3>
+ <p class="dek">How to run byte-for-byte authentic shells inside Electron with node-pty: the native-rebuild gotcha, the macOS PATH trap, and streaming PTY output over IPC.</p>
+ <div class="foot">
+ <span class="tag kind">Internals</span>
+ <a class="more" href="/blog/node-pty-electron-real-terminals/" aria-label="Read: Real Terminals in Electron with node-pty">Read →</a>
+ </div>
+ </div>
+</article>
+<article class="card">
+ <a class="thumb t-internals" href="/blog/single-committer-git-pattern/" aria-hidden="true" tabindex="-1">
+ <span>INTERNALS</span>
+ </a>
+ <div class="body">
+ <div class="meta">
+ <time datetime="2026-06-02">Jun 2, 2026</time>
+ <span class="dot" aria-hidden="true"></span>
+ <span>5 min</span>
+ </div>
+ <h3><a href="/blog/single-committer-git-pattern/">The Single-Committer Pattern: Multi-Agent Git Without Corruption</a></h3>
+ <p class="dek">Parallel agents corrupt a repo with index.lock races. The single-committer pattern — agents write, one process commits — fixes concurrent git writes.</p>
+ <div class="foot">
+ <span class="tag kind">Internals</span>
+ <a class="more" href="/blog/single-committer-git-pattern/" aria-label="Read: The Single-Committer Pattern: Multi-Agent Git Without Corruption">Read →</a>
+ </div>
+ </div>
+</article>
+<article class="card">
+ <a class="thumb t-internals" href="/blog/atomic-file-mailboxes-for-agents/" aria-hidden="true" tabindex="-1">
+ <span>INTERNALS</span>
+ </a>
+ <div class="body">
+ <div class="meta">
+ <time datetime="2026-05-31">May 31, 2026</time>
+ <span class="dot" aria-hidden="true"></span>
+ <span>5 min</span>
+ </div>
+ <h3><a href="/blog/atomic-file-mailboxes-for-agents/">Atomic File Mailboxes: How Agents Message Each Other</a></h3>
+ <p class="dek">Can Claude Code agents talk to each other? Yes — the outbox-router-inbox design that lets agents message safely using plain files and atomic renames.</p>
+ <div class="foot">
+ <span class="tag kind">Internals</span>
+ <a class="more" href="/blog/atomic-file-mailboxes-for-agents/" aria-label="Read: Atomic File Mailboxes: How Agents Message Each Other">Read →</a>
+ </div>
+ </div>
+</article>
+<article class="card">
+ <a class="thumb t-orchestration" href="/blog/how-the-god-orchestrator-works/" aria-hidden="true" tabindex="-1">
+ <span>ORCHESTRATION</span>
+ </a>
+ <div class="body">
+ <div class="meta">
+ <time datetime="2026-05-30">May 30, 2026</time>
+ <span class="dot" aria-hidden="true"></span>
+ <span>6 min</span>
+ </div>
+ <h3><a href="/blog/how-the-god-orchestrator-works/">Inside the GOD Orchestrator: Routing, Adjudication, Escalation</a></h3>
+ <p class="dek">A deep dive into the Claude Code orchestrator: how a GOD agent reads requests, routes work, adjudicates routine traffic, and escalates the critical few.</p>
+ <div class="foot">
+ <span class="tag kind">Orchestration</span>
+ <a class="more" href="/blog/how-the-god-orchestrator-works/" aria-label="Read: Inside the GOD Orchestrator: Routing, Adjudication, Escalation">Read →</a>
+ </div>
+ </div>
+</article>
+
+ </div>
+</section>
+
+
+</main>
+<footer>
+ <div class="wrap">
+ <div class="foot-top">
+ <a class="foot-brand brand" href="/blog/">
+ <span class="brand-mark">MD</span>
+ <span class="brand-word">MUNDER DIFFLIN<span class="sep">/</span><span class="blog">BLOG</span></span>
+ </a>
+ <div class="foot-links">
+ <a href="/blog/">Latest</a>
+ <a href="/blog/topics/">Topics</a>
+ <a href="/blog/about/">About</a>
+ <a href="https://munderdiffl.in/blog/feed.xml">RSS</a>
+ <a href="https://github.com/chaitanyagiri/munder-difflin">GitHub</a>
+ <a href="https://munderdiffl.in">munderdiffl.in ↗</a>
+ </div>
+ </div>
+ <div class="foot-meta">
+ © 2026 Munder Difflin · Local-first · MIT-licensed ·
+ Built on <a href="https://munderdiffl.in">Electron, React, Pixi.js, xterm.js &amp; node-pty</a>.
+ Run an office of agents while you sleep.
+ </div>
+ </div>
+</footer>
+
+<script>
+ // sticky-nav border on scroll
+ (function () {
+ var nav = document.getElementById('nav');
+ if (!nav) return;
+ var onScroll = function () { nav.classList.toggle('scrolled', window.scrollY > 8); };
+ onScroll(); window.addEventListener('scroll', onScroll, { passive: true });
+ })();
+</script>
+
+</body>
+</html>
diff --git a/docs/blog/tags/local-first/index.html b/docs/blog/tags/local-first/index.html
new file mode 100644
index 00000000..9fc6b218
--- /dev/null
+++ b/docs/blog/tags/local-first/index.html
@@ -0,0 +1,124 @@
+<!doctype html>
+<html lang="en">
+<head>
+<meta charset="UTF-8" />
+<meta name="viewport" content="width=device-width, initial-scale=1.0" />
+<title>Local-First — Munder Difflin Blog</title>
+<meta name="description" content="Munder Difflin blog posts tagged Local-First." />
+<link rel="canonical" href="https://munderdiffl.in/blog/tags/local-first/" />
+
+<link rel="icon" type="image/png" href="https://munderdiffl.in/logo.png" />
+<link rel="apple-touch-icon" href="https://munderdiffl.in/logo.png" />
+<meta name="theme-color" content="#F5F2E8" />
+
+<!-- Open Graph -->
+<meta property="og:site_name" content="Munder Difflin Blog" />
+<meta property="og:type" content="website" />
+<meta property="og:title" content="Local-First — Munder Difflin Blog" />
+<meta property="og:description" content="Munder Difflin blog posts tagged Local-First." />
+<meta property="og:url" content="https://munderdiffl.in/blog/tags/local-first/" />
+<meta property="og:image" content="https://munderdiffl.in/media/og.png" />
+<meta property="og:locale" content="en_US" />
+
+
+<!-- Twitter -->
+<meta name="twitter:card" content="summary_large_image" />
+<meta name="twitter:title" content="Local-First — Munder Difflin Blog" />
+<meta name="twitter:description" content="Munder Difflin blog posts tagged Local-First." />
+<meta name="twitter:image" content="https://munderdiffl.in/media/og.png" />
+
+<link rel="alternate" type="application/atom+xml" title="Munder Difflin Blog" href="https://munderdiffl.in/blog/feed.xml" />
+<link rel="preconnect" href="https://fonts.googleapis.com" />
+<link rel="preconnect" href="https://fonts.gstatic.com" crossorigin />
+<link href="https://fonts.googleapis.com/css2?family=Geist:wght@400;500;600&family=JetBrains+Mono:wght@400;500;600;700&display=swap" rel="stylesheet" />
+<link rel="stylesheet" href="/blog/assets/blog.css" />
+
+</head>
+<body>
+<a class="skip-link" href="#main">Skip to content</a>
+<nav id="nav">
+ <a class="brand" href="/blog/" aria-label="Munder Difflin Blog home">
+ <span class="brand-mark">MD</span>
+ <span class="brand-word">MUNDER DIFFLIN<span class="sep">/</span><span class="blog">BLOG</span></span>
+ </a>
+ <span class="spacer"></span>
+ <div class="links">
+ <a href="/blog/">Latest</a>
+ <a href="/blog/topics/">Topics</a>
+ <a href="/blog/about/">About</a>
+ <a href="https://munderdiffl.in">↗ Product</a>
+ </div>
+ <div class="nav-actions">
+ <a class="btn sm" href="https://munderdiffl.in/blog/feed.xml" aria-label="RSS feed">⤵ RSS</a>
+ <a class="btn sm primary" href="https://munderdiffl.in/#install">⤓ Download</a>
+ </div>
+</nav>
+
+<main id="main">
+<header class="page-head wrap">
+ <p class="eyebrow">Tag</p>
+ <h1>#Local-First</h1>
+ <p class="lead">1 post tagged <strong>Local-First</strong>.</p>
+</header>
+<section class="wrap">
+ <div class="post-grid">
+ <article class="card">
+ <a class="thumb t-use-cases" href="/blog/why-local-first-matters-for-ai-agents/" aria-hidden="true" tabindex="-1">
+ <span>USE CASES</span>
+ </a>
+ <div class="body">
+ <div class="meta">
+ <time datetime="2026-06-02">Jun 2, 2026</time>
+ <span class="dot" aria-hidden="true"></span>
+ <span>3 min</span>
+ </div>
+ <h3><a href="/blog/why-local-first-matters-for-ai-agents/">Why Local-First Matters for Your AI Agents</a></h3>
+ <p class="dek">The control, privacy, and cost case for keeping your AI agents and their memory on your own machine — and what cloud orchestration quietly costs.</p>
+ <div class="foot">
+ <span class="tag kind">Use Cases</span>
+ <a class="more" href="/blog/why-local-first-matters-for-ai-agents/" aria-label="Read: Why Local-First Matters for Your AI Agents">Read →</a>
+ </div>
+ </div>
+</article>
+
+ </div>
+</section>
+
+
+</main>
+<footer>
+ <div class="wrap">
+ <div class="foot-top">
+ <a class="foot-brand brand" href="/blog/">
+ <span class="brand-mark">MD</span>
+ <span class="brand-word">MUNDER DIFFLIN<span class="sep">/</span><span class="blog">BLOG</span></span>
+ </a>
+ <div class="foot-links">
+ <a href="/blog/">Latest</a>
+ <a href="/blog/topics/">Topics</a>
+ <a href="/blog/about/">About</a>
+ <a href="https://munderdiffl.in/blog/feed.xml">RSS</a>
+ <a href="https://github.com/chaitanyagiri/munder-difflin">GitHub</a>
+ <a href="https://munderdiffl.in">munderdiffl.in ↗</a>
+ </div>
+ </div>
+ <div class="foot-meta">
+ © 2026 Munder Difflin · Local-first · MIT-licensed ·
+ Built on <a href="https://munderdiffl.in">Electron, React, Pixi.js, xterm.js &amp; node-pty</a>.
+ Run an office of agents while you sleep.
+ </div>
+ </div>
+</footer>
+
+<script>
+ // sticky-nav border on scroll
+ (function () {
+ var nav = document.getElementById('nav');
+ if (!nav) return;
+ var onScroll = function () { nav.classList.toggle('scrolled', window.scrollY > 8); };
+ onScroll(); window.addEventListener('scroll', onScroll, { passive: true });
+ })();
+</script>
+
+</body>
+</html>
diff --git a/docs/blog/tags/mcp/index.html b/docs/blog/tags/mcp/index.html
new file mode 100644
index 00000000..85a53154
--- /dev/null
+++ b/docs/blog/tags/mcp/index.html
@@ -0,0 +1,124 @@
+<!doctype html>
+<html lang="en">
+<head>
+<meta charset="UTF-8" />
+<meta name="viewport" content="width=device-width, initial-scale=1.0" />
+<title>MCP — Munder Difflin Blog</title>
+<meta name="description" content="Munder Difflin blog posts tagged MCP." />
+<link rel="canonical" href="https://munderdiffl.in/blog/tags/mcp/" />
+
+<link rel="icon" type="image/png" href="https://munderdiffl.in/logo.png" />
+<link rel="apple-touch-icon" href="https://munderdiffl.in/logo.png" />
+<meta name="theme-color" content="#F5F2E8" />
+
+<!-- Open Graph -->
+<meta property="og:site_name" content="Munder Difflin Blog" />
+<meta property="og:type" content="website" />
+<meta property="og:title" content="MCP — Munder Difflin Blog" />
+<meta property="og:description" content="Munder Difflin blog posts tagged MCP." />
+<meta property="og:url" content="https://munderdiffl.in/blog/tags/mcp/" />
+<meta property="og:image" content="https://munderdiffl.in/media/og.png" />
+<meta property="og:locale" content="en_US" />
+
+
+<!-- Twitter -->
+<meta name="twitter:card" content="summary_large_image" />
+<meta name="twitter:title" content="MCP — Munder Difflin Blog" />
+<meta name="twitter:description" content="Munder Difflin blog posts tagged MCP." />
+<meta name="twitter:image" content="https://munderdiffl.in/media/og.png" />
+
+<link rel="alternate" type="application/atom+xml" title="Munder Difflin Blog" href="https://munderdiffl.in/blog/feed.xml" />
+<link rel="preconnect" href="https://fonts.googleapis.com" />
+<link rel="preconnect" href="https://fonts.gstatic.com" crossorigin />
+<link href="https://fonts.googleapis.com/css2?family=Geist:wght@400;500;600&family=JetBrains+Mono:wght@400;500;600;700&display=swap" rel="stylesheet" />
+<link rel="stylesheet" href="/blog/assets/blog.css" />
+
+</head>
+<body>
+<a class="skip-link" href="#main">Skip to content</a>
+<nav id="nav">
+ <a class="brand" href="/blog/" aria-label="Munder Difflin Blog home">
+ <span class="brand-mark">MD</span>
+ <span class="brand-word">MUNDER DIFFLIN<span class="sep">/</span><span class="blog">BLOG</span></span>
+ </a>
+ <span class="spacer"></span>
+ <div class="links">
+ <a href="/blog/">Latest</a>
+ <a href="/blog/topics/">Topics</a>
+ <a href="/blog/about/">About</a>
+ <a href="https://munderdiffl.in">↗ Product</a>
+ </div>
+ <div class="nav-actions">
+ <a class="btn sm" href="https://munderdiffl.in/blog/feed.xml" aria-label="RSS feed">⤵ RSS</a>
+ <a class="btn sm primary" href="https://munderdiffl.in/#install">⤓ Download</a>
+ </div>
+</nav>
+
+<main id="main">
+<header class="page-head wrap">
+ <p class="eyebrow">Tag</p>
+ <h1>#MCP</h1>
+ <p class="lead">1 post tagged <strong>MCP</strong>.</p>
+</header>
+<section class="wrap">
+ <div class="post-grid">
+ <article class="card">
+ <a class="thumb t-guides" href="/blog/mcp-and-skills-in-a-hive/" aria-hidden="true" tabindex="-1">
+ <span>GUIDES</span>
+ </a>
+ <div class="body">
+ <div class="meta">
+ <time datetime="2026-06-03">Jun 3, 2026</time>
+ <span class="dot" aria-hidden="true"></span>
+ <span>6 min</span>
+ </div>
+ <h3><a href="/blog/mcp-and-skills-in-a-hive/">Bringing Your MCP Servers and Skills Into a Hive of Agents</a></h3>
+ <p class="dek">How agents in a hive inherit your existing Claude Code MCP servers, skills, and tools — and how to scope which agent gets which capability.</p>
+ <div class="foot">
+ <span class="tag kind">Guides</span>
+ <a class="more" href="/blog/mcp-and-skills-in-a-hive/" aria-label="Read: Bringing Your MCP Servers and Skills Into a Hive of Agents">Read →</a>
+ </div>
+ </div>
+</article>
+
+ </div>
+</section>
+
+
+</main>
+<footer>
+ <div class="wrap">
+ <div class="foot-top">
+ <a class="foot-brand brand" href="/blog/">
+ <span class="brand-mark">MD</span>
+ <span class="brand-word">MUNDER DIFFLIN<span class="sep">/</span><span class="blog">BLOG</span></span>
+ </a>
+ <div class="foot-links">
+ <a href="/blog/">Latest</a>
+ <a href="/blog/topics/">Topics</a>
+ <a href="/blog/about/">About</a>
+ <a href="https://munderdiffl.in/blog/feed.xml">RSS</a>
+ <a href="https://github.com/chaitanyagiri/munder-difflin">GitHub</a>
+ <a href="https://munderdiffl.in">munderdiffl.in ↗</a>
+ </div>
+ </div>
+ <div class="foot-meta">
+ © 2026 Munder Difflin · Local-first · MIT-licensed ·
+ Built on <a href="https://munderdiffl.in">Electron, React, Pixi.js, xterm.js &amp; node-pty</a>.
+ Run an office of agents while you sleep.
+ </div>
+ </div>
+</footer>
+
+<script>
+ // sticky-nav border on scroll
+ (function () {
+ var nav = document.getElementById('nav');
+ if (!nav) return;
+ var onScroll = function () { nav.classList.toggle('scrolled', window.scrollY > 8); };
+ onScroll(); window.addEventListener('scroll', onScroll, { passive: true });
+ })();
+</script>
+
+</body>
+</html>
diff --git a/docs/blog/tags/memory/index.html b/docs/blog/tags/memory/index.html
index 87543aac..f30a5565 100644
--- a/docs/blog/tags/memory/index.html
+++ b/docs/blog/tags/memory/index.html
@@ -58,11 +58,29 @@
<header class="page-head wrap">
<p class="eyebrow">Tag</p>
<h1>#Memory</h1>
- <p class="lead">1 post tagged <strong>Memory</strong>.</p>
+ <p class="lead">3 posts tagged <strong>Memory</strong>.</p>
</header>
<section class="wrap">
<div class="post-grid">
<article class="card">
+ <a class="thumb t-comparisons" href="/blog/crystal-claude-code-alternative/" aria-hidden="true" tabindex="-1">
+ <span>COMPARISONS</span>
+ </a>
+ <div class="body">
+ <div class="meta">
+ <time datetime="2026-06-03">Jun 3, 2026</time>
+ <span class="dot" aria-hidden="true"></span>
+ <span>3 min</span>
+ </div>
+ <h3><a href="/blog/crystal-claude-code-alternative/">A Crystal Alternative: Multi-Agent Claude Code with Memory</a></h3>
+ <p class="dek">Crystal runs parallel Claude Code worktrees well. Where a memory-backed, orchestrated hive changes the workflow — and when to stick with Crystal.</p>
+ <div class="foot">
+ <span class="tag kind">Comparisons</span>
+ <a class="more" href="/blog/crystal-claude-code-alternative/" aria-label="Read: A Crystal Alternative: Multi-Agent Claude Code with Memory">Read →</a>
+ </div>
+ </div>
+</article>
+<article class="card">
<a class="thumb t-memory" href="/blog/give-claude-code-long-term-memory/" aria-hidden="true" tabindex="-1">
<span>MEMORY</span>
</a>
@@ -80,6 +98,24 @@
</div>
</div>
</article>
+<article class="card">
+ <a class="thumb t-memory" href="/blog/semantic-memory-for-ai-agents/" aria-hidden="true" tabindex="-1">
+ <span>MEMORY</span>
+ </a>
+ <div class="body">
+ <div class="meta">
+ <time datetime="2026-05-26">May 26, 2026</time>
+ <span class="dot" aria-hidden="true"></span>
+ <span>6 min</span>
+ </div>
+ <h3><a href="/blog/semantic-memory-for-ai-agents/">Semantic Memory for AI Agents: Recall in Milliseconds</a></h3>
+ <p class="dek">What semantic memory for AI agents is, why a markdown-first store beats a heavy DB, and how a shared palace lets a hive recall a note by meaning, fast.</p>
+ <div class="foot">
+ <span class="tag kind">Memory</span>
+ <a class="more" href="/blog/semantic-memory-for-ai-agents/" aria-label="Read: Semantic Memory for AI Agents: Recall in Milliseconds">Read →</a>
+ </div>
+ </div>
+</article>
</div>
</section>
diff --git a/docs/blog/tags/mempalace/index.html b/docs/blog/tags/mempalace/index.html
index 03e51f1f..339754df 100644
--- a/docs/blog/tags/mempalace/index.html
+++ b/docs/blog/tags/mempalace/index.html
@@ -58,7 +58,7 @@
<header class="page-head wrap">
<p class="eyebrow">Tag</p>
<h1>#MemPalace</h1>
- <p class="lead">1 post tagged <strong>MemPalace</strong>.</p>
+ <p class="lead">2 posts tagged <strong>MemPalace</strong>.</p>
</header>
<section class="wrap">
<div class="post-grid">
@@ -80,6 +80,24 @@
</div>
</div>
</article>
+<article class="card">
+ <a class="thumb t-memory" href="/blog/semantic-memory-for-ai-agents/" aria-hidden="true" tabindex="-1">
+ <span>MEMORY</span>
+ </a>
+ <div class="body">
+ <div class="meta">
+ <time datetime="2026-05-26">May 26, 2026</time>
+ <span class="dot" aria-hidden="true"></span>
+ <span>6 min</span>
+ </div>
+ <h3><a href="/blog/semantic-memory-for-ai-agents/">Semantic Memory for AI Agents: Recall in Milliseconds</a></h3>
+ <p class="dek">What semantic memory for AI agents is, why a markdown-first store beats a heavy DB, and how a shared palace lets a hive recall a note by meaning, fast.</p>
+ <div class="foot">
+ <span class="tag kind">Memory</span>
+ <a class="more" href="/blog/semantic-memory-for-ai-agents/" aria-label="Read: Semantic Memory for AI Agents: Recall in Milliseconds">Read →</a>
+ </div>
+ </div>
+</article>
</div>
</section>
diff --git a/docs/blog/tags/messaging/index.html b/docs/blog/tags/messaging/index.html
new file mode 100644
index 00000000..2ff91637
--- /dev/null
+++ b/docs/blog/tags/messaging/index.html
@@ -0,0 +1,124 @@
+<!doctype html>
+<html lang="en">
+<head>
+<meta charset="UTF-8" />
+<meta name="viewport" content="width=device-width, initial-scale=1.0" />
+<title>Messaging — Munder Difflin Blog</title>
+<meta name="description" content="Munder Difflin blog posts tagged Messaging." />
+<link rel="canonical" href="https://munderdiffl.in/blog/tags/messaging/" />
+
+<link rel="icon" type="image/png" href="https://munderdiffl.in/logo.png" />
+<link rel="apple-touch-icon" href="https://munderdiffl.in/logo.png" />
+<meta name="theme-color" content="#F5F2E8" />
+
+<!-- Open Graph -->
+<meta property="og:site_name" content="Munder Difflin Blog" />
+<meta property="og:type" content="website" />
+<meta property="og:title" content="Messaging — Munder Difflin Blog" />
+<meta property="og:description" content="Munder Difflin blog posts tagged Messaging." />
+<meta property="og:url" content="https://munderdiffl.in/blog/tags/messaging/" />
+<meta property="og:image" content="https://munderdiffl.in/media/og.png" />
+<meta property="og:locale" content="en_US" />
+
+
+<!-- Twitter -->
+<meta name="twitter:card" content="summary_large_image" />
+<meta name="twitter:title" content="Messaging — Munder Difflin Blog" />
+<meta name="twitter:description" content="Munder Difflin blog posts tagged Messaging." />
+<meta name="twitter:image" content="https://munderdiffl.in/media/og.png" />
+
+<link rel="alternate" type="application/atom+xml" title="Munder Difflin Blog" href="https://munderdiffl.in/blog/feed.xml" />
+<link rel="preconnect" href="https://fonts.googleapis.com" />
+<link rel="preconnect" href="https://fonts.gstatic.com" crossorigin />
+<link href="https://fonts.googleapis.com/css2?family=Geist:wght@400;500;600&family=JetBrains+Mono:wght@400;500;600;700&display=swap" rel="stylesheet" />
+<link rel="stylesheet" href="/blog/assets/blog.css" />
+
+</head>
+<body>
+<a class="skip-link" href="#main">Skip to content</a>
+<nav id="nav">
+ <a class="brand" href="/blog/" aria-label="Munder Difflin Blog home">
+ <span class="brand-mark">MD</span>
+ <span class="brand-word">MUNDER DIFFLIN<span class="sep">/</span><span class="blog">BLOG</span></span>
+ </a>
+ <span class="spacer"></span>
+ <div class="links">
+ <a href="/blog/">Latest</a>
+ <a href="/blog/topics/">Topics</a>
+ <a href="/blog/about/">About</a>
+ <a href="https://munderdiffl.in">↗ Product</a>
+ </div>
+ <div class="nav-actions">
+ <a class="btn sm" href="https://munderdiffl.in/blog/feed.xml" aria-label="RSS feed">⤵ RSS</a>
+ <a class="btn sm primary" href="https://munderdiffl.in/#install">⤓ Download</a>
+ </div>
+</nav>
+
+<main id="main">
+<header class="page-head wrap">
+ <p class="eyebrow">Tag</p>
+ <h1>#Messaging</h1>
+ <p class="lead">1 post tagged <strong>Messaging</strong>.</p>
+</header>
+<section class="wrap">
+ <div class="post-grid">
+ <article class="card">
+ <a class="thumb t-internals" href="/blog/atomic-file-mailboxes-for-agents/" aria-hidden="true" tabindex="-1">
+ <span>INTERNALS</span>
+ </a>
+ <div class="body">
+ <div class="meta">
+ <time datetime="2026-05-31">May 31, 2026</time>
+ <span class="dot" aria-hidden="true"></span>
+ <span>5 min</span>
+ </div>
+ <h3><a href="/blog/atomic-file-mailboxes-for-agents/">Atomic File Mailboxes: How Agents Message Each Other</a></h3>
+ <p class="dek">Can Claude Code agents talk to each other? Yes — the outbox-router-inbox design that lets agents message safely using plain files and atomic renames.</p>
+ <div class="foot">
+ <span class="tag kind">Internals</span>
+ <a class="more" href="/blog/atomic-file-mailboxes-for-agents/" aria-label="Read: Atomic File Mailboxes: How Agents Message Each Other">Read →</a>
+ </div>
+ </div>
+</article>
+
+ </div>
+</section>
+
+
+</main>
+<footer>
+ <div class="wrap">
+ <div class="foot-top">
+ <a class="foot-brand brand" href="/blog/">
+ <span class="brand-mark">MD</span>
+ <span class="brand-word">MUNDER DIFFLIN<span class="sep">/</span><span class="blog">BLOG</span></span>
+ </a>
+ <div class="foot-links">
+ <a href="/blog/">Latest</a>
+ <a href="/blog/topics/">Topics</a>
+ <a href="/blog/about/">About</a>
+ <a href="https://munderdiffl.in/blog/feed.xml">RSS</a>
+ <a href="https://github.com/chaitanyagiri/munder-difflin">GitHub</a>
+ <a href="https://munderdiffl.in">munderdiffl.in ↗</a>
+ </div>
+ </div>
+ <div class="foot-meta">
+ © 2026 Munder Difflin · Local-first · MIT-licensed ·
+ Built on <a href="https://munderdiffl.in">Electron, React, Pixi.js, xterm.js &amp; node-pty</a>.
+ Run an office of agents while you sleep.
+ </div>
+ </div>
+</footer>
+
+<script>
+ // sticky-nav border on scroll
+ (function () {
+ var nav = document.getElementById('nav');
+ if (!nav) return;
+ var onScroll = function () { nav.classList.toggle('scrolled', window.scrollY > 8); };
+ onScroll(); window.addEventListener('scroll', onScroll, { passive: true });
+ })();
+</script>
+
+</body>
+</html>
diff --git a/docs/blog/tags/multi-agent/index.html b/docs/blog/tags/multi-agent/index.html
index 26a23d92..3755d15b 100644
--- a/docs/blog/tags/multi-agent/index.html
+++ b/docs/blog/tags/multi-agent/index.html
@@ -58,11 +58,263 @@
<header class="page-head wrap">
<p class="eyebrow">Tag</p>
<h1>#Multi-Agent</h1>
- <p class="lead">2 posts tagged <strong>Multi-Agent</strong>.</p>
+ <p class="lead">24 posts tagged <strong>Multi-Agent</strong>.</p>
</header>
<section class="wrap">
<div class="post-grid">
<article class="card">
+ <a class="thumb t-comparisons" href="/blog/best-claude-code-multi-agent-tools/" aria-hidden="true" tabindex="-1">
+ <span>COMPARISONS</span>
+ </a>
+ <div class="body">
+ <div class="meta">
+ <time datetime="2026-06-04">Jun 4, 2026</time>
+ <span class="dot" aria-hidden="true"></span>
+ <span>6 min</span>
+ </div>
+ <h3><a href="/blog/best-claude-code-multi-agent-tools/">The Best Tools to Run Multiple Claude Code Agents (2026)</a></h3>
+ <p class="dek">An honest 2026 roundup of tools to run multiple Claude Code agents — Claude Squad, Conductor, Crystal, vibe-kanban, and Munder Difflin — compared.</p>
+ <div class="foot">
+ <span class="tag kind">Comparisons</span>
+ <a class="more" href="/blog/best-claude-code-multi-agent-tools/" aria-label="Read: The Best Tools to Run Multiple Claude Code Agents (2026)">Read →</a>
+ </div>
+ </div>
+</article>
+<article class="card">
+ <a class="thumb t-orchestration" href="/blog/claude-code-git-worktrees-vs-hive/" aria-hidden="true" tabindex="-1">
+ <span>ORCHESTRATION</span>
+ </a>
+ <div class="body">
+ <div class="meta">
+ <time datetime="2026-06-04">Jun 4, 2026</time>
+ <span class="dot" aria-hidden="true"></span>
+ <span>5 min</span>
+ </div>
+ <h3><a href="/blog/claude-code-git-worktrees-vs-hive/">Git Worktrees vs a Hive: Two Ways to Parallelize Claude Code</a></h3>
+ <p class="dek">Claude Code git worktrees vs a hive: when isolated worktrees suffice for parallel agents, and when you need memory, messaging, and an orchestrator on top.</p>
+ <div class="foot">
+ <span class="tag kind">Orchestration</span>
+ <a class="more" href="/blog/claude-code-git-worktrees-vs-hive/" aria-label="Read: Git Worktrees vs a Hive: Two Ways to Parallelize Claude Code">Read →</a>
+ </div>
+ </div>
+</article>
+<article class="card">
+ <a class="thumb t-comparisons" href="/blog/claude-squad-vs-munder-difflin/" aria-hidden="true" tabindex="-1">
+ <span>COMPARISONS</span>
+ </a>
+ <div class="body">
+ <div class="meta">
+ <time datetime="2026-06-04">Jun 4, 2026</time>
+ <span class="dot" aria-hidden="true"></span>
+ <span>3 min</span>
+ </div>
+ <h3><a href="/blog/claude-squad-vs-munder-difflin/">Claude Squad vs Munder Difflin: Which Should You Use?</a></h3>
+ <p class="dek">Claude Squad vs Munder Difflin: a lean terminal session manager against a memory-backed, orchestrated, visual hive. Feature table and an honest verdict.</p>
+ <div class="foot">
+ <span class="tag kind">Comparisons</span>
+ <a class="more" href="/blog/claude-squad-vs-munder-difflin/" aria-label="Read: Claude Squad vs Munder Difflin: Which Should You Use?">Read →</a>
+ </div>
+ </div>
+</article>
+<article class="card">
+ <a class="thumb t-comparisons" href="/blog/claude-squad-alternative/" aria-hidden="true" tabindex="-1">
+ <span>COMPARISONS</span>
+ </a>
+ <div class="body">
+ <div class="meta">
+ <time datetime="2026-06-03">Jun 3, 2026</time>
+ <span class="dot" aria-hidden="true"></span>
+ <span>3 min</span>
+ </div>
+ <h3><a href="/blog/claude-squad-alternative/">Looking for a Claude Squad Alternative?</a></h3>
+ <p class="dek">What Claude Squad does well, where it stops, and why a memory-backed, orchestrated hive may be the Claude Squad alternative you&#39;re after.</p>
+ <div class="foot">
+ <span class="tag kind">Comparisons</span>
+ <a class="more" href="/blog/claude-squad-alternative/" aria-label="Read: Looking for a Claude Squad Alternative?">Read →</a>
+ </div>
+ </div>
+</article>
+<article class="card">
+ <a class="thumb t-comparisons" href="/blog/vibe-kanban-alternative/" aria-hidden="true" tabindex="-1">
+ <span>COMPARISONS</span>
+ </a>
+ <div class="body">
+ <div class="meta">
+ <time datetime="2026-06-03">Jun 3, 2026</time>
+ <span class="dot" aria-hidden="true"></span>
+ <span>3 min</span>
+ </div>
+ <h3><a href="/blog/vibe-kanban-alternative/">A vibe-kanban Alternative for Coordinating AI Agents</a></h3>
+ <p class="dek">vibe-kanban gives you a board to assign tasks to coding agents. When a self-routing hive is the better vibe-kanban alternative — and when a board wins.</p>
+ <div class="foot">
+ <span class="tag kind">Comparisons</span>
+ <a class="more" href="/blog/vibe-kanban-alternative/" aria-label="Read: A vibe-kanban Alternative for Coordinating AI Agents">Read →</a>
+ </div>
+ </div>
+</article>
+<article class="card">
+ <a class="thumb t-concepts" href="/blog/ai-agent-glossary/" aria-hidden="true" tabindex="-1">
+ <span>CONCEPTS</span>
+ </a>
+ <div class="body">
+ <div class="meta">
+ <time datetime="2026-06-02">Jun 2, 2026</time>
+ <span class="dot" aria-hidden="true"></span>
+ <span>3 min</span>
+ </div>
+ <h3><a href="/blog/ai-agent-glossary/">The AI Coding Agent Glossary: Harness, Orchestrator, Hive, Subagent</a></h3>
+ <p class="dek">Plain-English definitions of the AI coding agent terms everyone trips over — harness, orchestrator, hive, subagent, agent memory — each in one line.</p>
+ <div class="foot">
+ <span class="tag kind">Concepts</span>
+ <a class="more" href="/blog/ai-agent-glossary/" aria-label="Read: The AI Coding Agent Glossary: Harness, Orchestrator, Hive, Subagent">Read →</a>
+ </div>
+ </div>
+</article>
+<article class="card">
+ <a class="thumb t-use-cases" href="/blog/from-one-terminal-to-a-team/" aria-hidden="true" tabindex="-1">
+ <span>USE CASES</span>
+ </a>
+ <div class="body">
+ <div class="meta">
+ <time datetime="2026-06-02">Jun 2, 2026</time>
+ <span class="dot" aria-hidden="true"></span>
+ <span>3 min</span>
+ </div>
+ <h3><a href="/blog/from-one-terminal-to-a-team/">From One Terminal to a Team: Scaling Your Claude Code Workflow</a></h3>
+ <p class="dek">The workflow shift from a single Claude Code session to a coordinated team of agents — what changes, where it breaks, and the concrete before-and-after.</p>
+ <div class="foot">
+ <span class="tag kind">Use Cases</span>
+ <a class="more" href="/blog/from-one-terminal-to-a-team/" aria-label="Read: From One Terminal to a Team: Scaling Your Claude Code Workflow">Read →</a>
+ </div>
+ </div>
+</article>
+<article class="card">
+ <a class="thumb t-comparisons" href="/blog/how-to-choose-a-multi-agent-tool/" aria-hidden="true" tabindex="-1">
+ <span>COMPARISONS</span>
+ </a>
+ <div class="body">
+ <div class="meta">
+ <time datetime="2026-06-02">Jun 2, 2026</time>
+ <span class="dot" aria-hidden="true"></span>
+ <span>3 min</span>
+ </div>
+ <h3><a href="/blog/how-to-choose-a-multi-agent-tool/">How to Choose a Multi-Agent Coding Tool: A Buyer&#39;s Checklist</a></h3>
+ <p class="dek">A decision framework for choosing a multi-agent coding tool — memory, control, visibility, cost, local-first — with a simple scoring rubric you can run.</p>
+ <div class="foot">
+ <span class="tag kind">Comparisons</span>
+ <a class="more" href="/blog/how-to-choose-a-multi-agent-tool/" aria-label="Read: How to Choose a Multi-Agent Coding Tool: A Buyer&#39;s Checklist">Read →</a>
+ </div>
+ </div>
+</article>
+<article class="card">
+ <a class="thumb t-concepts" href="/blog/munder-difflin-faq/" aria-hidden="true" tabindex="-1">
+ <span>CONCEPTS</span>
+ </a>
+ <div class="body">
+ <div class="meta">
+ <time datetime="2026-06-02">Jun 2, 2026</time>
+ <span class="dot" aria-hidden="true"></span>
+ <span>1 min</span>
+ </div>
+ <h3><a href="/blog/munder-difflin-faq/">Munder Difflin FAQ: Everything People Ask</a></h3>
+ <p class="dek">Answers to the top Munder Difflin questions — what it is, is it free, does it run locally, which platforms, and how it differs from many terminals.</p>
+ <div class="foot">
+ <span class="tag kind">Concepts</span>
+ <a class="more" href="/blog/munder-difflin-faq/" aria-label="Read: Munder Difflin FAQ: Everything People Ask">Read →</a>
+ </div>
+ </div>
+</article>
+<article class="card">
+ <a class="thumb t-use-cases" href="/blog/run-an-office-of-ai-agents/" aria-hidden="true" tabindex="-1">
+ <span>USE CASES</span>
+ </a>
+ <div class="body">
+ <div class="meta">
+ <time datetime="2026-06-02">Jun 2, 2026</time>
+ <span class="dot" aria-hidden="true"></span>
+ <span>3 min</span>
+ </div>
+ <h3><a href="/blog/run-an-office-of-ai-agents/">Run an Office of AI Agents While You Sleep</a></h3>
+ <p class="dek">What it takes to run a self-coordinating office of AI coding agents that keeps shipping after you log off — and the guardrails that keep it sane.</p>
+ <div class="foot">
+ <span class="tag kind">Use Cases</span>
+ <a class="more" href="/blog/run-an-office-of-ai-agents/" aria-label="Read: Run an Office of AI Agents While You Sleep">Read →</a>
+ </div>
+ </div>
+</article>
+<article class="card">
+ <a class="thumb t-internals" href="/blog/single-committer-git-pattern/" aria-hidden="true" tabindex="-1">
+ <span>INTERNALS</span>
+ </a>
+ <div class="body">
+ <div class="meta">
+ <time datetime="2026-06-02">Jun 2, 2026</time>
+ <span class="dot" aria-hidden="true"></span>
+ <span>5 min</span>
+ </div>
+ <h3><a href="/blog/single-committer-git-pattern/">The Single-Committer Pattern: Multi-Agent Git Without Corruption</a></h3>
+ <p class="dek">Parallel agents corrupt a repo with index.lock races. The single-committer pattern — agents write, one process commits — fixes concurrent git writes.</p>
+ <div class="foot">
+ <span class="tag kind">Internals</span>
+ <a class="more" href="/blog/single-committer-git-pattern/" aria-label="Read: The Single-Committer Pattern: Multi-Agent Git Without Corruption">Read →</a>
+ </div>
+ </div>
+</article>
+<article class="card">
+ <a class="thumb t-concepts" href="/blog/what-are-claude-code-agents/" aria-hidden="true" tabindex="-1">
+ <span>CONCEPTS</span>
+ </a>
+ <div class="body">
+ <div class="meta">
+ <time datetime="2026-06-02">Jun 2, 2026</time>
+ <span class="dot" aria-hidden="true"></span>
+ <span>3 min</span>
+ </div>
+ <h3><a href="/blog/what-are-claude-code-agents/">What Are Claude Code Agents? And How to Use Many at Once</a></h3>
+ <p class="dek">Claude Code agents explained in plain English — what an agent actually is, how subagents differ, and the leap from one agent to a coordinated team.</p>
+ <div class="foot">
+ <span class="tag kind">Concepts</span>
+ <a class="more" href="/blog/what-are-claude-code-agents/" aria-label="Read: What Are Claude Code Agents? And How to Use Many at Once">Read →</a>
+ </div>
+ </div>
+</article>
+<article class="card">
+ <a class="thumb t-use-cases" href="/blog/why-local-first-matters-for-ai-agents/" aria-hidden="true" tabindex="-1">
+ <span>USE CASES</span>
+ </a>
+ <div class="body">
+ <div class="meta">
+ <time datetime="2026-06-02">Jun 2, 2026</time>
+ <span class="dot" aria-hidden="true"></span>
+ <span>3 min</span>
+ </div>
+ <h3><a href="/blog/why-local-first-matters-for-ai-agents/">Why Local-First Matters for Your AI Agents</a></h3>
+ <p class="dek">The control, privacy, and cost case for keeping your AI agents and their memory on your own machine — and what cloud orchestration quietly costs.</p>
+ <div class="foot">
+ <span class="tag kind">Use Cases</span>
+ <a class="more" href="/blog/why-local-first-matters-for-ai-agents/" aria-label="Read: Why Local-First Matters for Your AI Agents">Read →</a>
+ </div>
+ </div>
+</article>
+<article class="card">
+ <a class="thumb t-story" href="/blog/why-we-built-munder-difflin/" aria-hidden="true" tabindex="-1">
+ <span>STORY</span>
+ </a>
+ <div class="body">
+ <div class="meta">
+ <time datetime="2026-06-02">Jun 2, 2026</time>
+ <span class="dot" aria-hidden="true"></span>
+ <span>3 min</span>
+ </div>
+ <h3><a href="/blog/why-we-built-munder-difflin/">Why We Built Munder Difflin</a></h3>
+ <p class="dek">The origin story of Munder Difflin — how the pain of juggling Claude Code terminals led to a coordinated, memory-backed hive of agents you can watch.</p>
+ <div class="foot">
+ <span class="tag kind">Story</span>
+ <a class="more" href="/blog/why-we-built-munder-difflin/" aria-label="Read: Why We Built Munder Difflin">Read →</a>
+ </div>
+ </div>
+</article>
+<article class="card">
<a class="thumb t-guides" href="/blog/how-to-run-multiple-claude-code-agents/" aria-hidden="true" tabindex="-1">
<span>GUIDES</span>
</a>
@@ -80,6 +332,150 @@
</div>
</div>
</article>
+<article class="card">
+ <a class="thumb t-internals" href="/blog/atomic-file-mailboxes-for-agents/" aria-hidden="true" tabindex="-1">
+ <span>INTERNALS</span>
+ </a>
+ <div class="body">
+ <div class="meta">
+ <time datetime="2026-05-31">May 31, 2026</time>
+ <span class="dot" aria-hidden="true"></span>
+ <span>5 min</span>
+ </div>
+ <h3><a href="/blog/atomic-file-mailboxes-for-agents/">Atomic File Mailboxes: How Agents Message Each Other</a></h3>
+ <p class="dek">Can Claude Code agents talk to each other? Yes — the outbox-router-inbox design that lets agents message safely using plain files and atomic renames.</p>
+ <div class="foot">
+ <span class="tag kind">Internals</span>
+ <a class="more" href="/blog/atomic-file-mailboxes-for-agents/" aria-label="Read: Atomic File Mailboxes: How Agents Message Each Other">Read →</a>
+ </div>
+ </div>
+</article>
+<article class="card">
+ <a class="thumb t-orchestration" href="/blog/how-the-god-orchestrator-works/" aria-hidden="true" tabindex="-1">
+ <span>ORCHESTRATION</span>
+ </a>
+ <div class="body">
+ <div class="meta">
+ <time datetime="2026-05-30">May 30, 2026</time>
+ <span class="dot" aria-hidden="true"></span>
+ <span>6 min</span>
+ </div>
+ <h3><a href="/blog/how-the-god-orchestrator-works/">Inside the GOD Orchestrator: Routing, Adjudication, Escalation</a></h3>
+ <p class="dek">A deep dive into the Claude Code orchestrator: how a GOD agent reads requests, routes work, adjudicates routine traffic, and escalates the critical few.</p>
+ <div class="foot">
+ <span class="tag kind">Orchestration</span>
+ <a class="more" href="/blog/how-the-god-orchestrator-works/" aria-label="Read: Inside the GOD Orchestrator: Routing, Adjudication, Escalation">Read →</a>
+ </div>
+ </div>
+</article>
+<article class="card">
+ <a class="thumb t-orchestration" href="/blog/coordinating-ai-coding-agents/" aria-hidden="true" tabindex="-1">
+ <span>ORCHESTRATION</span>
+ </a>
+ <div class="body">
+ <div class="meta">
+ <time datetime="2026-05-29">May 29, 2026</time>
+ <span class="dot" aria-hidden="true"></span>
+ <span>5 min</span>
+ </div>
+ <h3><a href="/blog/coordinating-ai-coding-agents/">The Best Way to Coordinate AI Coding Agents</a></h3>
+ <p class="dek">The best way to coordinate AI coding agents: single-writer files, a message router, a one-scribe plan, and an orchestrator — cooperate, not clobber.</p>
+ <div class="foot">
+ <span class="tag kind">Orchestration</span>
+ <a class="more" href="/blog/coordinating-ai-coding-agents/" aria-label="Read: The Best Way to Coordinate AI Coding Agents">Read →</a>
+ </div>
+ </div>
+</article>
+<article class="card">
+ <a class="thumb t-orchestration" href="/blog/claude-code-orchestration-guide/" aria-hidden="true" tabindex="-1">
+ <span>ORCHESTRATION</span>
+ </a>
+ <div class="body">
+ <div class="meta">
+ <time datetime="2026-05-28">May 28, 2026</time>
+ <span class="dot" aria-hidden="true"></span>
+ <span>5 min</span>
+ </div>
+ <h3><a href="/blog/claude-code-orchestration-guide/">Orchestrating Claude Code Agents: A Practical Guide</a></h3>
+ <p class="dek">How to orchestrate Claude Code agents in practice: what orchestration means, how a GOD orchestrator routes and escalates work, and how to wire it up.</p>
+ <div class="foot">
+ <span class="tag kind">Orchestration</span>
+ <a class="more" href="/blog/claude-code-orchestration-guide/" aria-label="Read: Orchestrating Claude Code Agents: A Practical Guide">Read →</a>
+ </div>
+ </div>
+</article>
+<article class="card">
+ <a class="thumb t-memory" href="/blog/semantic-memory-for-ai-agents/" aria-hidden="true" tabindex="-1">
+ <span>MEMORY</span>
+ </a>
+ <div class="body">
+ <div class="meta">
+ <time datetime="2026-05-26">May 26, 2026</time>
+ <span class="dot" aria-hidden="true"></span>
+ <span>6 min</span>
+ </div>
+ <h3><a href="/blog/semantic-memory-for-ai-agents/">Semantic Memory for AI Agents: Recall in Milliseconds</a></h3>
+ <p class="dek">What semantic memory for AI agents is, why a markdown-first store beats a heavy DB, and how a shared palace lets a hive recall a note by meaning, fast.</p>
+ <div class="foot">
+ <span class="tag kind">Memory</span>
+ <a class="more" href="/blog/semantic-memory-for-ai-agents/" aria-label="Read: Semantic Memory for AI Agents: Recall in Milliseconds">Read →</a>
+ </div>
+ </div>
+</article>
+<article class="card">
+ <a class="thumb t-guides" href="/blog/manage-multiple-claude-code-sessions/" aria-hidden="true" tabindex="-1">
+ <span>GUIDES</span>
+ </a>
+ <div class="body">
+ <div class="meta">
+ <time datetime="2026-05-25">May 25, 2026</time>
+ <span class="dot" aria-hidden="true"></span>
+ <span>4 min</span>
+ </div>
+ <h3><a href="/blog/manage-multiple-claude-code-sessions/">How to Manage Multiple Claude Code Sessions Like a Pro</a></h3>
+ <p class="dek">Tactics to manage multiple Claude Code sessions without losing track: naming, roles, context isolation, and when a harness beats juggling terminal tabs.</p>
+ <div class="foot">
+ <span class="tag kind">Guides</span>
+ <a class="more" href="/blog/manage-multiple-claude-code-sessions/" aria-label="Read: How to Manage Multiple Claude Code Sessions Like a Pro">Read →</a>
+ </div>
+ </div>
+</article>
+<article class="card">
+ <a class="thumb t-guides" href="/blog/claude-code-multi-agent-setup-tutorial/" aria-hidden="true" tabindex="-1">
+ <span>GUIDES</span>
+ </a>
+ <div class="body">
+ <div class="meta">
+ <time datetime="2026-05-24">May 24, 2026</time>
+ <span class="dot" aria-hidden="true"></span>
+ <span>5 min</span>
+ </div>
+ <h3><a href="/blog/claude-code-multi-agent-setup-tutorial/">Set Up a Claude Code Multi-Agent Workflow in 10 Minutes</a></h3>
+ <p class="dek">A from-zero Claude Code multi-agent setup: install Munder Difflin, onboard, spawn a few agents, and watch the GOD orchestrator route your first task.</p>
+ <div class="foot">
+ <span class="tag kind">Guides</span>
+ <a class="more" href="/blog/claude-code-multi-agent-setup-tutorial/" aria-label="Read: Set Up a Claude Code Multi-Agent Workflow in 10 Minutes">Read →</a>
+ </div>
+ </div>
+</article>
+<article class="card">
+ <a class="thumb t-guides" href="/blog/claude-code-subagents-vs-multi-agent-harness/" aria-hidden="true" tabindex="-1">
+ <span>GUIDES</span>
+ </a>
+ <div class="body">
+ <div class="meta">
+ <time datetime="2026-05-23">May 23, 2026</time>
+ <span class="dot" aria-hidden="true"></span>
+ <span>5 min</span>
+ </div>
+ <h3><a href="/blog/claude-code-subagents-vs-multi-agent-harness/">Claude Code Subagents vs a Multi-Agent Harness</a></h3>
+ <p class="dek">Claude Code subagents vs a multi-agent harness: where subagents stop and a harness with shared memory, messaging, and an orchestrator takes over.</p>
+ <div class="foot">
+ <span class="tag kind">Guides</span>
+ <a class="more" href="/blog/claude-code-subagents-vs-multi-agent-harness/" aria-label="Read: Claude Code Subagents vs a Multi-Agent Harness">Read →</a>
+ </div>
+ </div>
+</article>
<article class="card">
<a class="thumb t-concepts" href="/blog/what-is-a-multi-agent-harness/" aria-hidden="true" tabindex="-1">
<span>CONCEPTS</span>
diff --git a/docs/blog/tags/node-pty/index.html b/docs/blog/tags/node-pty/index.html
new file mode 100644
index 00000000..a6e80d5c
--- /dev/null
+++ b/docs/blog/tags/node-pty/index.html
@@ -0,0 +1,124 @@
+<!doctype html>
+<html lang="en">
+<head>
+<meta charset="UTF-8" />
+<meta name="viewport" content="width=device-width, initial-scale=1.0" />
+<title>node-pty — Munder Difflin Blog</title>
+<meta name="description" content="Munder Difflin blog posts tagged node-pty." />
+<link rel="canonical" href="https://munderdiffl.in/blog/tags/node-pty/" />
+
+<link rel="icon" type="image/png" href="https://munderdiffl.in/logo.png" />
+<link rel="apple-touch-icon" href="https://munderdiffl.in/logo.png" />
+<meta name="theme-color" content="#F5F2E8" />
+
+<!-- Open Graph -->
+<meta property="og:site_name" content="Munder Difflin Blog" />
+<meta property="og:type" content="website" />
+<meta property="og:title" content="node-pty — Munder Difflin Blog" />
+<meta property="og:description" content="Munder Difflin blog posts tagged node-pty." />
+<meta property="og:url" content="https://munderdiffl.in/blog/tags/node-pty/" />
+<meta property="og:image" content="https://munderdiffl.in/media/og.png" />
+<meta property="og:locale" content="en_US" />
+
+
+<!-- Twitter -->
+<meta name="twitter:card" content="summary_large_image" />
+<meta name="twitter:title" content="node-pty — Munder Difflin Blog" />
+<meta name="twitter:description" content="Munder Difflin blog posts tagged node-pty." />
+<meta name="twitter:image" content="https://munderdiffl.in/media/og.png" />
+
+<link rel="alternate" type="application/atom+xml" title="Munder Difflin Blog" href="https://munderdiffl.in/blog/feed.xml" />
+<link rel="preconnect" href="https://fonts.googleapis.com" />
+<link rel="preconnect" href="https://fonts.gstatic.com" crossorigin />
+<link href="https://fonts.googleapis.com/css2?family=Geist:wght@400;500;600&family=JetBrains+Mono:wght@400;500;600;700&display=swap" rel="stylesheet" />
+<link rel="stylesheet" href="/blog/assets/blog.css" />
+
+</head>
+<body>
+<a class="skip-link" href="#main">Skip to content</a>
+<nav id="nav">
+ <a class="brand" href="/blog/" aria-label="Munder Difflin Blog home">
+ <span class="brand-mark">MD</span>
+ <span class="brand-word">MUNDER DIFFLIN<span class="sep">/</span><span class="blog">BLOG</span></span>
+ </a>
+ <span class="spacer"></span>
+ <div class="links">
+ <a href="/blog/">Latest</a>
+ <a href="/blog/topics/">Topics</a>
+ <a href="/blog/about/">About</a>
+ <a href="https://munderdiffl.in">↗ Product</a>
+ </div>
+ <div class="nav-actions">
+ <a class="btn sm" href="https://munderdiffl.in/blog/feed.xml" aria-label="RSS feed">⤵ RSS</a>
+ <a class="btn sm primary" href="https://munderdiffl.in/#install">⤓ Download</a>
+ </div>
+</nav>
+
+<main id="main">
+<header class="page-head wrap">
+ <p class="eyebrow">Tag</p>
+ <h1>#node-pty</h1>
+ <p class="lead">1 post tagged <strong>node-pty</strong>.</p>
+</header>
+<section class="wrap">
+ <div class="post-grid">
+ <article class="card">
+ <a class="thumb t-internals" href="/blog/node-pty-electron-real-terminals/" aria-hidden="true" tabindex="-1">
+ <span>INTERNALS</span>
+ </a>
+ <div class="body">
+ <div class="meta">
+ <time datetime="2026-06-03">Jun 3, 2026</time>
+ <span class="dot" aria-hidden="true"></span>
+ <span>7 min</span>
+ </div>
+ <h3><a href="/blog/node-pty-electron-real-terminals/">Real Terminals in Electron with node-pty</a></h3>
+ <p class="dek">How to run byte-for-byte authentic shells inside Electron with node-pty: the native-rebuild gotcha, the macOS PATH trap, and streaming PTY output over IPC.</p>
+ <div class="foot">
+ <span class="tag kind">Internals</span>
+ <a class="more" href="/blog/node-pty-electron-real-terminals/" aria-label="Read: Real Terminals in Electron with node-pty">Read →</a>
+ </div>
+ </div>
+</article>
+
+ </div>
+</section>
+
+
+</main>
+<footer>
+ <div class="wrap">
+ <div class="foot-top">
+ <a class="foot-brand brand" href="/blog/">
+ <span class="brand-mark">MD</span>
+ <span class="brand-word">MUNDER DIFFLIN<span class="sep">/</span><span class="blog">BLOG</span></span>
+ </a>
+ <div class="foot-links">
+ <a href="/blog/">Latest</a>
+ <a href="/blog/topics/">Topics</a>
+ <a href="/blog/about/">About</a>
+ <a href="https://munderdiffl.in/blog/feed.xml">RSS</a>
+ <a href="https://github.com/chaitanyagiri/munder-difflin">GitHub</a>
+ <a href="https://munderdiffl.in">munderdiffl.in ↗</a>
+ </div>
+ </div>
+ <div class="foot-meta">
+ © 2026 Munder Difflin · Local-first · MIT-licensed ·
+ Built on <a href="https://munderdiffl.in">Electron, React, Pixi.js, xterm.js &amp; node-pty</a>.
+ Run an office of agents while you sleep.
+ </div>
+ </div>
+</footer>
+
+<script>
+ // sticky-nav border on scroll
+ (function () {
+ var nav = document.getElementById('nav');
+ if (!nav) return;
+ var onScroll = function () { nav.classList.toggle('scrolled', window.scrollY > 8); };
+ onScroll(); window.addEventListener('scroll', onScroll, { passive: true });
+ })();
+</script>
+
+</body>
+</html>
diff --git a/docs/blog/tags/open-source/index.html b/docs/blog/tags/open-source/index.html
new file mode 100644
index 00000000..e356cf2b
--- /dev/null
+++ b/docs/blog/tags/open-source/index.html
@@ -0,0 +1,124 @@
+<!doctype html>
+<html lang="en">
+<head>
+<meta charset="UTF-8" />
+<meta name="viewport" content="width=device-width, initial-scale=1.0" />
+<title>Open Source — Munder Difflin Blog</title>
+<meta name="description" content="Munder Difflin blog posts tagged Open Source." />
+<link rel="canonical" href="https://munderdiffl.in/blog/tags/open-source/" />
+
+<link rel="icon" type="image/png" href="https://munderdiffl.in/logo.png" />
+<link rel="apple-touch-icon" href="https://munderdiffl.in/logo.png" />
+<meta name="theme-color" content="#F5F2E8" />
+
+<!-- Open Graph -->
+<meta property="og:site_name" content="Munder Difflin Blog" />
+<meta property="og:type" content="website" />
+<meta property="og:title" content="Open Source — Munder Difflin Blog" />
+<meta property="og:description" content="Munder Difflin blog posts tagged Open Source." />
+<meta property="og:url" content="https://munderdiffl.in/blog/tags/open-source/" />
+<meta property="og:image" content="https://munderdiffl.in/media/og.png" />
+<meta property="og:locale" content="en_US" />
+
+
+<!-- Twitter -->
+<meta name="twitter:card" content="summary_large_image" />
+<meta name="twitter:title" content="Open Source — Munder Difflin Blog" />
+<meta name="twitter:description" content="Munder Difflin blog posts tagged Open Source." />
+<meta name="twitter:image" content="https://munderdiffl.in/media/og.png" />
+
+<link rel="alternate" type="application/atom+xml" title="Munder Difflin Blog" href="https://munderdiffl.in/blog/feed.xml" />
+<link rel="preconnect" href="https://fonts.googleapis.com" />
+<link rel="preconnect" href="https://fonts.gstatic.com" crossorigin />
+<link href="https://fonts.googleapis.com/css2?family=Geist:wght@400;500;600&family=JetBrains+Mono:wght@400;500;600;700&display=swap" rel="stylesheet" />
+<link rel="stylesheet" href="/blog/assets/blog.css" />
+
+</head>
+<body>
+<a class="skip-link" href="#main">Skip to content</a>
+<nav id="nav">
+ <a class="brand" href="/blog/" aria-label="Munder Difflin Blog home">
+ <span class="brand-mark">MD</span>
+ <span class="brand-word">MUNDER DIFFLIN<span class="sep">/</span><span class="blog">BLOG</span></span>
+ </a>
+ <span class="spacer"></span>
+ <div class="links">
+ <a href="/blog/">Latest</a>
+ <a href="/blog/topics/">Topics</a>
+ <a href="/blog/about/">About</a>
+ <a href="https://munderdiffl.in">↗ Product</a>
+ </div>
+ <div class="nav-actions">
+ <a class="btn sm" href="https://munderdiffl.in/blog/feed.xml" aria-label="RSS feed">⤵ RSS</a>
+ <a class="btn sm primary" href="https://munderdiffl.in/#install">⤓ Download</a>
+ </div>
+</nav>
+
+<main id="main">
+<header class="page-head wrap">
+ <p class="eyebrow">Tag</p>
+ <h1>#Open Source</h1>
+ <p class="lead">1 post tagged <strong>Open Source</strong>.</p>
+</header>
+<section class="wrap">
+ <div class="post-grid">
+ <article class="card">
+ <a class="thumb t-story" href="/blog/why-we-built-munder-difflin/" aria-hidden="true" tabindex="-1">
+ <span>STORY</span>
+ </a>
+ <div class="body">
+ <div class="meta">
+ <time datetime="2026-06-02">Jun 2, 2026</time>
+ <span class="dot" aria-hidden="true"></span>
+ <span>3 min</span>
+ </div>
+ <h3><a href="/blog/why-we-built-munder-difflin/">Why We Built Munder Difflin</a></h3>
+ <p class="dek">The origin story of Munder Difflin — how the pain of juggling Claude Code terminals led to a coordinated, memory-backed hive of agents you can watch.</p>
+ <div class="foot">
+ <span class="tag kind">Story</span>
+ <a class="more" href="/blog/why-we-built-munder-difflin/" aria-label="Read: Why We Built Munder Difflin">Read →</a>
+ </div>
+ </div>
+</article>
+
+ </div>
+</section>
+
+
+</main>
+<footer>
+ <div class="wrap">
+ <div class="foot-top">
+ <a class="foot-brand brand" href="/blog/">
+ <span class="brand-mark">MD</span>
+ <span class="brand-word">MUNDER DIFFLIN<span class="sep">/</span><span class="blog">BLOG</span></span>
+ </a>
+ <div class="foot-links">
+ <a href="/blog/">Latest</a>
+ <a href="/blog/topics/">Topics</a>
+ <a href="/blog/about/">About</a>
+ <a href="https://munderdiffl.in/blog/feed.xml">RSS</a>
+ <a href="https://github.com/chaitanyagiri/munder-difflin">GitHub</a>
+ <a href="https://munderdiffl.in">munderdiffl.in ↗</a>
+ </div>
+ </div>
+ <div class="foot-meta">
+ © 2026 Munder Difflin · Local-first · MIT-licensed ·
+ Built on <a href="https://munderdiffl.in">Electron, React, Pixi.js, xterm.js &amp; node-pty</a>.
+ Run an office of agents while you sleep.
+ </div>
+ </div>
+</footer>
+
+<script>
+ // sticky-nav border on scroll
+ (function () {
+ var nav = document.getElementById('nav');
+ if (!nav) return;
+ var onScroll = function () { nav.classList.toggle('scrolled', window.scrollY > 8); };
+ onScroll(); window.addEventListener('scroll', onScroll, { passive: true });
+ })();
+</script>
+
+</body>
+</html>
diff --git a/docs/blog/tags/orchestration/index.html b/docs/blog/tags/orchestration/index.html
new file mode 100644
index 00000000..848ab495
--- /dev/null
+++ b/docs/blog/tags/orchestration/index.html
@@ -0,0 +1,232 @@
+<!doctype html>
+<html lang="en">
+<head>
+<meta charset="UTF-8" />
+<meta name="viewport" content="width=device-width, initial-scale=1.0" />
+<title>Orchestration — Munder Difflin Blog</title>
+<meta name="description" content="Munder Difflin blog posts tagged Orchestration." />
+<link rel="canonical" href="https://munderdiffl.in/blog/tags/orchestration/" />
+
+<link rel="icon" type="image/png" href="https://munderdiffl.in/logo.png" />
+<link rel="apple-touch-icon" href="https://munderdiffl.in/logo.png" />
+<meta name="theme-color" content="#F5F2E8" />
+
+<!-- Open Graph -->
+<meta property="og:site_name" content="Munder Difflin Blog" />
+<meta property="og:type" content="website" />
+<meta property="og:title" content="Orchestration — Munder Difflin Blog" />
+<meta property="og:description" content="Munder Difflin blog posts tagged Orchestration." />
+<meta property="og:url" content="https://munderdiffl.in/blog/tags/orchestration/" />
+<meta property="og:image" content="https://munderdiffl.in/media/og.png" />
+<meta property="og:locale" content="en_US" />
+
+
+<!-- Twitter -->
+<meta name="twitter:card" content="summary_large_image" />
+<meta name="twitter:title" content="Orchestration — Munder Difflin Blog" />
+<meta name="twitter:description" content="Munder Difflin blog posts tagged Orchestration." />
+<meta name="twitter:image" content="https://munderdiffl.in/media/og.png" />
+
+<link rel="alternate" type="application/atom+xml" title="Munder Difflin Blog" href="https://munderdiffl.in/blog/feed.xml" />
+<link rel="preconnect" href="https://fonts.googleapis.com" />
+<link rel="preconnect" href="https://fonts.gstatic.com" crossorigin />
+<link href="https://fonts.googleapis.com/css2?family=Geist:wght@400;500;600&family=JetBrains+Mono:wght@400;500;600;700&display=swap" rel="stylesheet" />
+<link rel="stylesheet" href="/blog/assets/blog.css" />
+
+</head>
+<body>
+<a class="skip-link" href="#main">Skip to content</a>
+<nav id="nav">
+ <a class="brand" href="/blog/" aria-label="Munder Difflin Blog home">
+ <span class="brand-mark">MD</span>
+ <span class="brand-word">MUNDER DIFFLIN<span class="sep">/</span><span class="blog">BLOG</span></span>
+ </a>
+ <span class="spacer"></span>
+ <div class="links">
+ <a href="/blog/">Latest</a>
+ <a href="/blog/topics/">Topics</a>
+ <a href="/blog/about/">About</a>
+ <a href="https://munderdiffl.in">↗ Product</a>
+ </div>
+ <div class="nav-actions">
+ <a class="btn sm" href="https://munderdiffl.in/blog/feed.xml" aria-label="RSS feed">⤵ RSS</a>
+ <a class="btn sm primary" href="https://munderdiffl.in/#install">⤓ Download</a>
+ </div>
+</nav>
+
+<main id="main">
+<header class="page-head wrap">
+ <p class="eyebrow">Tag</p>
+ <h1>#Orchestration</h1>
+ <p class="lead">7 posts tagged <strong>Orchestration</strong>.</p>
+</header>
+<section class="wrap">
+ <div class="post-grid">
+ <article class="card">
+ <a class="thumb t-orchestration" href="/blog/claude-code-git-worktrees-vs-hive/" aria-hidden="true" tabindex="-1">
+ <span>ORCHESTRATION</span>
+ </a>
+ <div class="body">
+ <div class="meta">
+ <time datetime="2026-06-04">Jun 4, 2026</time>
+ <span class="dot" aria-hidden="true"></span>
+ <span>5 min</span>
+ </div>
+ <h3><a href="/blog/claude-code-git-worktrees-vs-hive/">Git Worktrees vs a Hive: Two Ways to Parallelize Claude Code</a></h3>
+ <p class="dek">Claude Code git worktrees vs a hive: when isolated worktrees suffice for parallel agents, and when you need memory, messaging, and an orchestrator on top.</p>
+ <div class="foot">
+ <span class="tag kind">Orchestration</span>
+ <a class="more" href="/blog/claude-code-git-worktrees-vs-hive/" aria-label="Read: Git Worktrees vs a Hive: Two Ways to Parallelize Claude Code">Read →</a>
+ </div>
+ </div>
+</article>
+<article class="card">
+ <a class="thumb t-comparisons" href="/blog/claude-code-orchestration-tools-compared/" aria-hidden="true" tabindex="-1">
+ <span>COMPARISONS</span>
+ </a>
+ <div class="body">
+ <div class="meta">
+ <time datetime="2026-06-04">Jun 4, 2026</time>
+ <span class="dot" aria-hidden="true"></span>
+ <span>3 min</span>
+ </div>
+ <h3><a href="/blog/claude-code-orchestration-tools-compared/">Claude Code Orchestration Tools, Compared</a></h3>
+ <p class="dek">Claude Code orchestration tools compared on memory, messaging, visibility, control, and local-first — across Claude Squad, Conductor, Crystal, and more.</p>
+ <div class="foot">
+ <span class="tag kind">Comparisons</span>
+ <a class="more" href="/blog/claude-code-orchestration-tools-compared/" aria-label="Read: Claude Code Orchestration Tools, Compared">Read →</a>
+ </div>
+ </div>
+</article>
+<article class="card">
+ <a class="thumb t-comparisons" href="/blog/conductor-claude-code-alternative/" aria-hidden="true" tabindex="-1">
+ <span>COMPARISONS</span>
+ </a>
+ <div class="body">
+ <div class="meta">
+ <time datetime="2026-06-03">Jun 3, 2026</time>
+ <span class="dot" aria-hidden="true"></span>
+ <span>3 min</span>
+ </div>
+ <h3><a href="/blog/conductor-claude-code-alternative/">A Conductor Alternative for Orchestrating Claude Code</a></h3>
+ <p class="dek">Conductor is a polished macOS app for parallel Claude Code worktrees. When to pick a cross-platform, orchestrated hive as your Conductor alternative.</p>
+ <div class="foot">
+ <span class="tag kind">Comparisons</span>
+ <a class="more" href="/blog/conductor-claude-code-alternative/" aria-label="Read: A Conductor Alternative for Orchestrating Claude Code">Read →</a>
+ </div>
+ </div>
+</article>
+<article class="card">
+ <a class="thumb t-comparisons" href="/blog/vibe-kanban-alternative/" aria-hidden="true" tabindex="-1">
+ <span>COMPARISONS</span>
+ </a>
+ <div class="body">
+ <div class="meta">
+ <time datetime="2026-06-03">Jun 3, 2026</time>
+ <span class="dot" aria-hidden="true"></span>
+ <span>3 min</span>
+ </div>
+ <h3><a href="/blog/vibe-kanban-alternative/">A vibe-kanban Alternative for Coordinating AI Agents</a></h3>
+ <p class="dek">vibe-kanban gives you a board to assign tasks to coding agents. When a self-routing hive is the better vibe-kanban alternative — and when a board wins.</p>
+ <div class="foot">
+ <span class="tag kind">Comparisons</span>
+ <a class="more" href="/blog/vibe-kanban-alternative/" aria-label="Read: A vibe-kanban Alternative for Coordinating AI Agents">Read →</a>
+ </div>
+ </div>
+</article>
+<article class="card">
+ <a class="thumb t-orchestration" href="/blog/how-the-god-orchestrator-works/" aria-hidden="true" tabindex="-1">
+ <span>ORCHESTRATION</span>
+ </a>
+ <div class="body">
+ <div class="meta">
+ <time datetime="2026-05-30">May 30, 2026</time>
+ <span class="dot" aria-hidden="true"></span>
+ <span>6 min</span>
+ </div>
+ <h3><a href="/blog/how-the-god-orchestrator-works/">Inside the GOD Orchestrator: Routing, Adjudication, Escalation</a></h3>
+ <p class="dek">A deep dive into the Claude Code orchestrator: how a GOD agent reads requests, routes work, adjudicates routine traffic, and escalates the critical few.</p>
+ <div class="foot">
+ <span class="tag kind">Orchestration</span>
+ <a class="more" href="/blog/how-the-god-orchestrator-works/" aria-label="Read: Inside the GOD Orchestrator: Routing, Adjudication, Escalation">Read →</a>
+ </div>
+ </div>
+</article>
+<article class="card">
+ <a class="thumb t-orchestration" href="/blog/coordinating-ai-coding-agents/" aria-hidden="true" tabindex="-1">
+ <span>ORCHESTRATION</span>
+ </a>
+ <div class="body">
+ <div class="meta">
+ <time datetime="2026-05-29">May 29, 2026</time>
+ <span class="dot" aria-hidden="true"></span>
+ <span>5 min</span>
+ </div>
+ <h3><a href="/blog/coordinating-ai-coding-agents/">The Best Way to Coordinate AI Coding Agents</a></h3>
+ <p class="dek">The best way to coordinate AI coding agents: single-writer files, a message router, a one-scribe plan, and an orchestrator — cooperate, not clobber.</p>
+ <div class="foot">
+ <span class="tag kind">Orchestration</span>
+ <a class="more" href="/blog/coordinating-ai-coding-agents/" aria-label="Read: The Best Way to Coordinate AI Coding Agents">Read →</a>
+ </div>
+ </div>
+</article>
+<article class="card">
+ <a class="thumb t-orchestration" href="/blog/claude-code-orchestration-guide/" aria-hidden="true" tabindex="-1">
+ <span>ORCHESTRATION</span>
+ </a>
+ <div class="body">
+ <div class="meta">
+ <time datetime="2026-05-28">May 28, 2026</time>
+ <span class="dot" aria-hidden="true"></span>
+ <span>5 min</span>
+ </div>
+ <h3><a href="/blog/claude-code-orchestration-guide/">Orchestrating Claude Code Agents: A Practical Guide</a></h3>
+ <p class="dek">How to orchestrate Claude Code agents in practice: what orchestration means, how a GOD orchestrator routes and escalates work, and how to wire it up.</p>
+ <div class="foot">
+ <span class="tag kind">Orchestration</span>
+ <a class="more" href="/blog/claude-code-orchestration-guide/" aria-label="Read: Orchestrating Claude Code Agents: A Practical Guide">Read →</a>
+ </div>
+ </div>
+</article>
+
+ </div>
+</section>
+
+
+</main>
+<footer>
+ <div class="wrap">
+ <div class="foot-top">
+ <a class="foot-brand brand" href="/blog/">
+ <span class="brand-mark">MD</span>
+ <span class="brand-word">MUNDER DIFFLIN<span class="sep">/</span><span class="blog">BLOG</span></span>
+ </a>
+ <div class="foot-links">
+ <a href="/blog/">Latest</a>
+ <a href="/blog/topics/">Topics</a>
+ <a href="/blog/about/">About</a>
+ <a href="https://munderdiffl.in/blog/feed.xml">RSS</a>
+ <a href="https://github.com/chaitanyagiri/munder-difflin">GitHub</a>
+ <a href="https://munderdiffl.in">munderdiffl.in ↗</a>
+ </div>
+ </div>
+ <div class="foot-meta">
+ © 2026 Munder Difflin · Local-first · MIT-licensed ·
+ Built on <a href="https://munderdiffl.in">Electron, React, Pixi.js, xterm.js &amp; node-pty</a>.
+ Run an office of agents while you sleep.
+ </div>
+ </div>
+</footer>
+
+<script>
+ // sticky-nav border on scroll
+ (function () {
+ var nav = document.getElementById('nav');
+ if (!nav) return;
+ var onScroll = function () { nav.classList.toggle('scrolled', window.scrollY > 8); };
+ onScroll(); window.addEventListener('scroll', onScroll, { passive: true });
+ })();
+</script>
+
+</body>
+</html>
diff --git a/docs/blog/tags/privacy/index.html b/docs/blog/tags/privacy/index.html
new file mode 100644
index 00000000..6abd5ef7
--- /dev/null
+++ b/docs/blog/tags/privacy/index.html
@@ -0,0 +1,124 @@
+<!doctype html>
+<html lang="en">
+<head>
+<meta charset="UTF-8" />
+<meta name="viewport" content="width=device-width, initial-scale=1.0" />
+<title>Privacy — Munder Difflin Blog</title>
+<meta name="description" content="Munder Difflin blog posts tagged Privacy." />
+<link rel="canonical" href="https://munderdiffl.in/blog/tags/privacy/" />
+
+<link rel="icon" type="image/png" href="https://munderdiffl.in/logo.png" />
+<link rel="apple-touch-icon" href="https://munderdiffl.in/logo.png" />
+<meta name="theme-color" content="#F5F2E8" />
+
+<!-- Open Graph -->
+<meta property="og:site_name" content="Munder Difflin Blog" />
+<meta property="og:type" content="website" />
+<meta property="og:title" content="Privacy — Munder Difflin Blog" />
+<meta property="og:description" content="Munder Difflin blog posts tagged Privacy." />
+<meta property="og:url" content="https://munderdiffl.in/blog/tags/privacy/" />
+<meta property="og:image" content="https://munderdiffl.in/media/og.png" />
+<meta property="og:locale" content="en_US" />
+
+
+<!-- Twitter -->
+<meta name="twitter:card" content="summary_large_image" />
+<meta name="twitter:title" content="Privacy — Munder Difflin Blog" />
+<meta name="twitter:description" content="Munder Difflin blog posts tagged Privacy." />
+<meta name="twitter:image" content="https://munderdiffl.in/media/og.png" />
+
+<link rel="alternate" type="application/atom+xml" title="Munder Difflin Blog" href="https://munderdiffl.in/blog/feed.xml" />
+<link rel="preconnect" href="https://fonts.googleapis.com" />
+<link rel="preconnect" href="https://fonts.gstatic.com" crossorigin />
+<link href="https://fonts.googleapis.com/css2?family=Geist:wght@400;500;600&family=JetBrains+Mono:wght@400;500;600;700&display=swap" rel="stylesheet" />
+<link rel="stylesheet" href="/blog/assets/blog.css" />
+
+</head>
+<body>
+<a class="skip-link" href="#main">Skip to content</a>
+<nav id="nav">
+ <a class="brand" href="/blog/" aria-label="Munder Difflin Blog home">
+ <span class="brand-mark">MD</span>
+ <span class="brand-word">MUNDER DIFFLIN<span class="sep">/</span><span class="blog">BLOG</span></span>
+ </a>
+ <span class="spacer"></span>
+ <div class="links">
+ <a href="/blog/">Latest</a>
+ <a href="/blog/topics/">Topics</a>
+ <a href="/blog/about/">About</a>
+ <a href="https://munderdiffl.in">↗ Product</a>
+ </div>
+ <div class="nav-actions">
+ <a class="btn sm" href="https://munderdiffl.in/blog/feed.xml" aria-label="RSS feed">⤵ RSS</a>
+ <a class="btn sm primary" href="https://munderdiffl.in/#install">⤓ Download</a>
+ </div>
+</nav>
+
+<main id="main">
+<header class="page-head wrap">
+ <p class="eyebrow">Tag</p>
+ <h1>#Privacy</h1>
+ <p class="lead">1 post tagged <strong>Privacy</strong>.</p>
+</header>
+<section class="wrap">
+ <div class="post-grid">
+ <article class="card">
+ <a class="thumb t-use-cases" href="/blog/why-local-first-matters-for-ai-agents/" aria-hidden="true" tabindex="-1">
+ <span>USE CASES</span>
+ </a>
+ <div class="body">
+ <div class="meta">
+ <time datetime="2026-06-02">Jun 2, 2026</time>
+ <span class="dot" aria-hidden="true"></span>
+ <span>3 min</span>
+ </div>
+ <h3><a href="/blog/why-local-first-matters-for-ai-agents/">Why Local-First Matters for Your AI Agents</a></h3>
+ <p class="dek">The control, privacy, and cost case for keeping your AI agents and their memory on your own machine — and what cloud orchestration quietly costs.</p>
+ <div class="foot">
+ <span class="tag kind">Use Cases</span>
+ <a class="more" href="/blog/why-local-first-matters-for-ai-agents/" aria-label="Read: Why Local-First Matters for Your AI Agents">Read →</a>
+ </div>
+ </div>
+</article>
+
+ </div>
+</section>
+
+
+</main>
+<footer>
+ <div class="wrap">
+ <div class="foot-top">
+ <a class="foot-brand brand" href="/blog/">
+ <span class="brand-mark">MD</span>
+ <span class="brand-word">MUNDER DIFFLIN<span class="sep">/</span><span class="blog">BLOG</span></span>
+ </a>
+ <div class="foot-links">
+ <a href="/blog/">Latest</a>
+ <a href="/blog/topics/">Topics</a>
+ <a href="/blog/about/">About</a>
+ <a href="https://munderdiffl.in/blog/feed.xml">RSS</a>
+ <a href="https://github.com/chaitanyagiri/munder-difflin">GitHub</a>
+ <a href="https://munderdiffl.in">munderdiffl.in ↗</a>
+ </div>
+ </div>
+ <div class="foot-meta">
+ © 2026 Munder Difflin · Local-first · MIT-licensed ·
+ Built on <a href="https://munderdiffl.in">Electron, React, Pixi.js, xterm.js &amp; node-pty</a>.
+ Run an office of agents while you sleep.
+ </div>
+ </div>
+</footer>
+
+<script>
+ // sticky-nav border on scroll
+ (function () {
+ var nav = document.getElementById('nav');
+ if (!nav) return;
+ var onScroll = function () { nav.classList.toggle('scrolled', window.scrollY > 8); };
+ onScroll(); window.addEventListener('scroll', onScroll, { passive: true });
+ })();
+</script>
+
+</body>
+</html>
diff --git a/docs/blog/tags/skills/index.html b/docs/blog/tags/skills/index.html
new file mode 100644
index 00000000..7966510f
--- /dev/null
+++ b/docs/blog/tags/skills/index.html
@@ -0,0 +1,124 @@
+<!doctype html>
+<html lang="en">
+<head>
+<meta charset="UTF-8" />
+<meta name="viewport" content="width=device-width, initial-scale=1.0" />
+<title>Skills — Munder Difflin Blog</title>
+<meta name="description" content="Munder Difflin blog posts tagged Skills." />
+<link rel="canonical" href="https://munderdiffl.in/blog/tags/skills/" />
+
+<link rel="icon" type="image/png" href="https://munderdiffl.in/logo.png" />
+<link rel="apple-touch-icon" href="https://munderdiffl.in/logo.png" />
+<meta name="theme-color" content="#F5F2E8" />
+
+<!-- Open Graph -->
+<meta property="og:site_name" content="Munder Difflin Blog" />
+<meta property="og:type" content="website" />
+<meta property="og:title" content="Skills — Munder Difflin Blog" />
+<meta property="og:description" content="Munder Difflin blog posts tagged Skills." />
+<meta property="og:url" content="https://munderdiffl.in/blog/tags/skills/" />
+<meta property="og:image" content="https://munderdiffl.in/media/og.png" />
+<meta property="og:locale" content="en_US" />
+
+
+<!-- Twitter -->
+<meta name="twitter:card" content="summary_large_image" />
+<meta name="twitter:title" content="Skills — Munder Difflin Blog" />
+<meta name="twitter:description" content="Munder Difflin blog posts tagged Skills." />
+<meta name="twitter:image" content="https://munderdiffl.in/media/og.png" />
+
+<link rel="alternate" type="application/atom+xml" title="Munder Difflin Blog" href="https://munderdiffl.in/blog/feed.xml" />
+<link rel="preconnect" href="https://fonts.googleapis.com" />
+<link rel="preconnect" href="https://fonts.gstatic.com" crossorigin />
+<link href="https://fonts.googleapis.com/css2?family=Geist:wght@400;500;600&family=JetBrains+Mono:wght@400;500;600;700&display=swap" rel="stylesheet" />
+<link rel="stylesheet" href="/blog/assets/blog.css" />
+
+</head>
+<body>
+<a class="skip-link" href="#main">Skip to content</a>
+<nav id="nav">
+ <a class="brand" href="/blog/" aria-label="Munder Difflin Blog home">
+ <span class="brand-mark">MD</span>
+ <span class="brand-word">MUNDER DIFFLIN<span class="sep">/</span><span class="blog">BLOG</span></span>
+ </a>
+ <span class="spacer"></span>
+ <div class="links">
+ <a href="/blog/">Latest</a>
+ <a href="/blog/topics/">Topics</a>
+ <a href="/blog/about/">About</a>
+ <a href="https://munderdiffl.in">↗ Product</a>
+ </div>
+ <div class="nav-actions">
+ <a class="btn sm" href="https://munderdiffl.in/blog/feed.xml" aria-label="RSS feed">⤵ RSS</a>
+ <a class="btn sm primary" href="https://munderdiffl.in/#install">⤓ Download</a>
+ </div>
+</nav>
+
+<main id="main">
+<header class="page-head wrap">
+ <p class="eyebrow">Tag</p>
+ <h1>#Skills</h1>
+ <p class="lead">1 post tagged <strong>Skills</strong>.</p>
+</header>
+<section class="wrap">
+ <div class="post-grid">
+ <article class="card">
+ <a class="thumb t-guides" href="/blog/mcp-and-skills-in-a-hive/" aria-hidden="true" tabindex="-1">
+ <span>GUIDES</span>
+ </a>
+ <div class="body">
+ <div class="meta">
+ <time datetime="2026-06-03">Jun 3, 2026</time>
+ <span class="dot" aria-hidden="true"></span>
+ <span>6 min</span>
+ </div>
+ <h3><a href="/blog/mcp-and-skills-in-a-hive/">Bringing Your MCP Servers and Skills Into a Hive of Agents</a></h3>
+ <p class="dek">How agents in a hive inherit your existing Claude Code MCP servers, skills, and tools — and how to scope which agent gets which capability.</p>
+ <div class="foot">
+ <span class="tag kind">Guides</span>
+ <a class="more" href="/blog/mcp-and-skills-in-a-hive/" aria-label="Read: Bringing Your MCP Servers and Skills Into a Hive of Agents">Read →</a>
+ </div>
+ </div>
+</article>
+
+ </div>
+</section>
+
+
+</main>
+<footer>
+ <div class="wrap">
+ <div class="foot-top">
+ <a class="foot-brand brand" href="/blog/">
+ <span class="brand-mark">MD</span>
+ <span class="brand-word">MUNDER DIFFLIN<span class="sep">/</span><span class="blog">BLOG</span></span>
+ </a>
+ <div class="foot-links">
+ <a href="/blog/">Latest</a>
+ <a href="/blog/topics/">Topics</a>
+ <a href="/blog/about/">About</a>
+ <a href="https://munderdiffl.in/blog/feed.xml">RSS</a>
+ <a href="https://github.com/chaitanyagiri/munder-difflin">GitHub</a>
+ <a href="https://munderdiffl.in">munderdiffl.in ↗</a>
+ </div>
+ </div>
+ <div class="foot-meta">
+ © 2026 Munder Difflin · Local-first · MIT-licensed ·
+ Built on <a href="https://munderdiffl.in">Electron, React, Pixi.js, xterm.js &amp; node-pty</a>.
+ Run an office of agents while you sleep.
+ </div>
+ </div>
+</footer>
+
+<script>
+ // sticky-nav border on scroll
+ (function () {
+ var nav = document.getElementById('nav');
+ if (!nav) return;
+ var onScroll = function () { nav.classList.toggle('scrolled', window.scrollY > 8); };
+ onScroll(); window.addEventListener('scroll', onScroll, { passive: true });
+ })();
+</script>
+
+</body>
+</html>
diff --git a/docs/blog/tags/story/index.html b/docs/blog/tags/story/index.html
new file mode 100644
index 00000000..e027906f
--- /dev/null
+++ b/docs/blog/tags/story/index.html
@@ -0,0 +1,142 @@
+<!doctype html>
+<html lang="en">
+<head>
+<meta charset="UTF-8" />
+<meta name="viewport" content="width=device-width, initial-scale=1.0" />
+<title>Story — Munder Difflin Blog</title>
+<meta name="description" content="Munder Difflin blog posts tagged Story." />
+<link rel="canonical" href="https://munderdiffl.in/blog/tags/story/" />
+
+<link rel="icon" type="image/png" href="https://munderdiffl.in/logo.png" />
+<link rel="apple-touch-icon" href="https://munderdiffl.in/logo.png" />
+<meta name="theme-color" content="#F5F2E8" />
+
+<!-- Open Graph -->
+<meta property="og:site_name" content="Munder Difflin Blog" />
+<meta property="og:type" content="website" />
+<meta property="og:title" content="Story — Munder Difflin Blog" />
+<meta property="og:description" content="Munder Difflin blog posts tagged Story." />
+<meta property="og:url" content="https://munderdiffl.in/blog/tags/story/" />
+<meta property="og:image" content="https://munderdiffl.in/media/og.png" />
+<meta property="og:locale" content="en_US" />
+
+
+<!-- Twitter -->
+<meta name="twitter:card" content="summary_large_image" />
+<meta name="twitter:title" content="Story — Munder Difflin Blog" />
+<meta name="twitter:description" content="Munder Difflin blog posts tagged Story." />
+<meta name="twitter:image" content="https://munderdiffl.in/media/og.png" />
+
+<link rel="alternate" type="application/atom+xml" title="Munder Difflin Blog" href="https://munderdiffl.in/blog/feed.xml" />
+<link rel="preconnect" href="https://fonts.googleapis.com" />
+<link rel="preconnect" href="https://fonts.gstatic.com" crossorigin />
+<link href="https://fonts.googleapis.com/css2?family=Geist:wght@400;500;600&family=JetBrains+Mono:wght@400;500;600;700&display=swap" rel="stylesheet" />
+<link rel="stylesheet" href="/blog/assets/blog.css" />
+
+</head>
+<body>
+<a class="skip-link" href="#main">Skip to content</a>
+<nav id="nav">
+ <a class="brand" href="/blog/" aria-label="Munder Difflin Blog home">
+ <span class="brand-mark">MD</span>
+ <span class="brand-word">MUNDER DIFFLIN<span class="sep">/</span><span class="blog">BLOG</span></span>
+ </a>
+ <span class="spacer"></span>
+ <div class="links">
+ <a href="/blog/">Latest</a>
+ <a href="/blog/topics/">Topics</a>
+ <a href="/blog/about/">About</a>
+ <a href="https://munderdiffl.in">↗ Product</a>
+ </div>
+ <div class="nav-actions">
+ <a class="btn sm" href="https://munderdiffl.in/blog/feed.xml" aria-label="RSS feed">⤵ RSS</a>
+ <a class="btn sm primary" href="https://munderdiffl.in/#install">⤓ Download</a>
+ </div>
+</nav>
+
+<main id="main">
+<header class="page-head wrap">
+ <p class="eyebrow">Tag</p>
+ <h1>#Story</h1>
+ <p class="lead">2 posts tagged <strong>Story</strong>.</p>
+</header>
+<section class="wrap">
+ <div class="post-grid">
+ <article class="card">
+ <a class="thumb t-use-cases" href="/blog/run-an-office-of-ai-agents/" aria-hidden="true" tabindex="-1">
+ <span>USE CASES</span>
+ </a>
+ <div class="body">
+ <div class="meta">
+ <time datetime="2026-06-02">Jun 2, 2026</time>
+ <span class="dot" aria-hidden="true"></span>
+ <span>3 min</span>
+ </div>
+ <h3><a href="/blog/run-an-office-of-ai-agents/">Run an Office of AI Agents While You Sleep</a></h3>
+ <p class="dek">What it takes to run a self-coordinating office of AI coding agents that keeps shipping after you log off — and the guardrails that keep it sane.</p>
+ <div class="foot">
+ <span class="tag kind">Use Cases</span>
+ <a class="more" href="/blog/run-an-office-of-ai-agents/" aria-label="Read: Run an Office of AI Agents While You Sleep">Read →</a>
+ </div>
+ </div>
+</article>
+<article class="card">
+ <a class="thumb t-story" href="/blog/why-we-built-munder-difflin/" aria-hidden="true" tabindex="-1">
+ <span>STORY</span>
+ </a>
+ <div class="body">
+ <div class="meta">
+ <time datetime="2026-06-02">Jun 2, 2026</time>
+ <span class="dot" aria-hidden="true"></span>
+ <span>3 min</span>
+ </div>
+ <h3><a href="/blog/why-we-built-munder-difflin/">Why We Built Munder Difflin</a></h3>
+ <p class="dek">The origin story of Munder Difflin — how the pain of juggling Claude Code terminals led to a coordinated, memory-backed hive of agents you can watch.</p>
+ <div class="foot">
+ <span class="tag kind">Story</span>
+ <a class="more" href="/blog/why-we-built-munder-difflin/" aria-label="Read: Why We Built Munder Difflin">Read →</a>
+ </div>
+ </div>
+</article>
+
+ </div>
+</section>
+
+
+</main>
+<footer>
+ <div class="wrap">
+ <div class="foot-top">
+ <a class="foot-brand brand" href="/blog/">
+ <span class="brand-mark">MD</span>
+ <span class="brand-word">MUNDER DIFFLIN<span class="sep">/</span><span class="blog">BLOG</span></span>
+ </a>
+ <div class="foot-links">
+ <a href="/blog/">Latest</a>
+ <a href="/blog/topics/">Topics</a>
+ <a href="/blog/about/">About</a>
+ <a href="https://munderdiffl.in/blog/feed.xml">RSS</a>
+ <a href="https://github.com/chaitanyagiri/munder-difflin">GitHub</a>
+ <a href="https://munderdiffl.in">munderdiffl.in ↗</a>
+ </div>
+ </div>
+ <div class="foot-meta">
+ © 2026 Munder Difflin · Local-first · MIT-licensed ·
+ Built on <a href="https://munderdiffl.in">Electron, React, Pixi.js, xterm.js &amp; node-pty</a>.
+ Run an office of agents while you sleep.
+ </div>
+ </div>
+</footer>
+
+<script>
+ // sticky-nav border on scroll
+ (function () {
+ var nav = document.getElementById('nav');
+ if (!nav) return;
+ var onScroll = function () { nav.classList.toggle('scrolled', window.scrollY > 8); };
+ onScroll(); window.addEventListener('scroll', onScroll, { passive: true });
+ })();
+</script>
+
+</body>
+</html>
diff --git a/docs/blog/tags/subagents/index.html b/docs/blog/tags/subagents/index.html
new file mode 100644
index 00000000..2de4858d
--- /dev/null
+++ b/docs/blog/tags/subagents/index.html
@@ -0,0 +1,124 @@
+<!doctype html>
+<html lang="en">
+<head>
+<meta charset="UTF-8" />
+<meta name="viewport" content="width=device-width, initial-scale=1.0" />
+<title>Subagents — Munder Difflin Blog</title>
+<meta name="description" content="Munder Difflin blog posts tagged Subagents." />
+<link rel="canonical" href="https://munderdiffl.in/blog/tags/subagents/" />
+
+<link rel="icon" type="image/png" href="https://munderdiffl.in/logo.png" />
+<link rel="apple-touch-icon" href="https://munderdiffl.in/logo.png" />
+<meta name="theme-color" content="#F5F2E8" />
+
+<!-- Open Graph -->
+<meta property="og:site_name" content="Munder Difflin Blog" />
+<meta property="og:type" content="website" />
+<meta property="og:title" content="Subagents — Munder Difflin Blog" />
+<meta property="og:description" content="Munder Difflin blog posts tagged Subagents." />
+<meta property="og:url" content="https://munderdiffl.in/blog/tags/subagents/" />
+<meta property="og:image" content="https://munderdiffl.in/media/og.png" />
+<meta property="og:locale" content="en_US" />
+
+
+<!-- Twitter -->
+<meta name="twitter:card" content="summary_large_image" />
+<meta name="twitter:title" content="Subagents — Munder Difflin Blog" />
+<meta name="twitter:description" content="Munder Difflin blog posts tagged Subagents." />
+<meta name="twitter:image" content="https://munderdiffl.in/media/og.png" />
+
+<link rel="alternate" type="application/atom+xml" title="Munder Difflin Blog" href="https://munderdiffl.in/blog/feed.xml" />
+<link rel="preconnect" href="https://fonts.googleapis.com" />
+<link rel="preconnect" href="https://fonts.gstatic.com" crossorigin />
+<link href="https://fonts.googleapis.com/css2?family=Geist:wght@400;500;600&family=JetBrains+Mono:wght@400;500;600;700&display=swap" rel="stylesheet" />
+<link rel="stylesheet" href="/blog/assets/blog.css" />
+
+</head>
+<body>
+<a class="skip-link" href="#main">Skip to content</a>
+<nav id="nav">
+ <a class="brand" href="/blog/" aria-label="Munder Difflin Blog home">
+ <span class="brand-mark">MD</span>
+ <span class="brand-word">MUNDER DIFFLIN<span class="sep">/</span><span class="blog">BLOG</span></span>
+ </a>
+ <span class="spacer"></span>
+ <div class="links">
+ <a href="/blog/">Latest</a>
+ <a href="/blog/topics/">Topics</a>
+ <a href="/blog/about/">About</a>
+ <a href="https://munderdiffl.in">↗ Product</a>
+ </div>
+ <div class="nav-actions">
+ <a class="btn sm" href="https://munderdiffl.in/blog/feed.xml" aria-label="RSS feed">⤵ RSS</a>
+ <a class="btn sm primary" href="https://munderdiffl.in/#install">⤓ Download</a>
+ </div>
+</nav>
+
+<main id="main">
+<header class="page-head wrap">
+ <p class="eyebrow">Tag</p>
+ <h1>#Subagents</h1>
+ <p class="lead">1 post tagged <strong>Subagents</strong>.</p>
+</header>
+<section class="wrap">
+ <div class="post-grid">
+ <article class="card">
+ <a class="thumb t-guides" href="/blog/claude-code-subagents-vs-multi-agent-harness/" aria-hidden="true" tabindex="-1">
+ <span>GUIDES</span>
+ </a>
+ <div class="body">
+ <div class="meta">
+ <time datetime="2026-05-23">May 23, 2026</time>
+ <span class="dot" aria-hidden="true"></span>
+ <span>5 min</span>
+ </div>
+ <h3><a href="/blog/claude-code-subagents-vs-multi-agent-harness/">Claude Code Subagents vs a Multi-Agent Harness</a></h3>
+ <p class="dek">Claude Code subagents vs a multi-agent harness: where subagents stop and a harness with shared memory, messaging, and an orchestrator takes over.</p>
+ <div class="foot">
+ <span class="tag kind">Guides</span>
+ <a class="more" href="/blog/claude-code-subagents-vs-multi-agent-harness/" aria-label="Read: Claude Code Subagents vs a Multi-Agent Harness">Read →</a>
+ </div>
+ </div>
+</article>
+
+ </div>
+</section>
+
+
+</main>
+<footer>
+ <div class="wrap">
+ <div class="foot-top">
+ <a class="foot-brand brand" href="/blog/">
+ <span class="brand-mark">MD</span>
+ <span class="brand-word">MUNDER DIFFLIN<span class="sep">/</span><span class="blog">BLOG</span></span>
+ </a>
+ <div class="foot-links">
+ <a href="/blog/">Latest</a>
+ <a href="/blog/topics/">Topics</a>
+ <a href="/blog/about/">About</a>
+ <a href="https://munderdiffl.in/blog/feed.xml">RSS</a>
+ <a href="https://github.com/chaitanyagiri/munder-difflin">GitHub</a>
+ <a href="https://munderdiffl.in">munderdiffl.in ↗</a>
+ </div>
+ </div>
+ <div class="foot-meta">
+ © 2026 Munder Difflin · Local-first · MIT-licensed ·
+ Built on <a href="https://munderdiffl.in">Electron, React, Pixi.js, xterm.js &amp; node-pty</a>.
+ Run an office of agents while you sleep.
+ </div>
+ </div>
+</footer>
+
+<script>
+ // sticky-nav border on scroll
+ (function () {
+ var nav = document.getElementById('nav');
+ if (!nav) return;
+ var onScroll = function () { nav.classList.toggle('scrolled', window.scrollY > 8); };
+ onScroll(); window.addEventListener('scroll', onScroll, { passive: true });
+ })();
+</script>
+
+</body>
+</html>
diff --git a/docs/blog/tags/terminals/index.html b/docs/blog/tags/terminals/index.html
new file mode 100644
index 00000000..cc808e7b
--- /dev/null
+++ b/docs/blog/tags/terminals/index.html
@@ -0,0 +1,142 @@
+<!doctype html>
+<html lang="en">
+<head>
+<meta charset="UTF-8" />
+<meta name="viewport" content="width=device-width, initial-scale=1.0" />
+<title>Terminals — Munder Difflin Blog</title>
+<meta name="description" content="Munder Difflin blog posts tagged Terminals." />
+<link rel="canonical" href="https://munderdiffl.in/blog/tags/terminals/" />
+
+<link rel="icon" type="image/png" href="https://munderdiffl.in/logo.png" />
+<link rel="apple-touch-icon" href="https://munderdiffl.in/logo.png" />
+<meta name="theme-color" content="#F5F2E8" />
+
+<!-- Open Graph -->
+<meta property="og:site_name" content="Munder Difflin Blog" />
+<meta property="og:type" content="website" />
+<meta property="og:title" content="Terminals — Munder Difflin Blog" />
+<meta property="og:description" content="Munder Difflin blog posts tagged Terminals." />
+<meta property="og:url" content="https://munderdiffl.in/blog/tags/terminals/" />
+<meta property="og:image" content="https://munderdiffl.in/media/og.png" />
+<meta property="og:locale" content="en_US" />
+
+
+<!-- Twitter -->
+<meta name="twitter:card" content="summary_large_image" />
+<meta name="twitter:title" content="Terminals — Munder Difflin Blog" />
+<meta name="twitter:description" content="Munder Difflin blog posts tagged Terminals." />
+<meta name="twitter:image" content="https://munderdiffl.in/media/og.png" />
+
+<link rel="alternate" type="application/atom+xml" title="Munder Difflin Blog" href="https://munderdiffl.in/blog/feed.xml" />
+<link rel="preconnect" href="https://fonts.googleapis.com" />
+<link rel="preconnect" href="https://fonts.gstatic.com" crossorigin />
+<link href="https://fonts.googleapis.com/css2?family=Geist:wght@400;500;600&family=JetBrains+Mono:wght@400;500;600;700&display=swap" rel="stylesheet" />
+<link rel="stylesheet" href="/blog/assets/blog.css" />
+
+</head>
+<body>
+<a class="skip-link" href="#main">Skip to content</a>
+<nav id="nav">
+ <a class="brand" href="/blog/" aria-label="Munder Difflin Blog home">
+ <span class="brand-mark">MD</span>
+ <span class="brand-word">MUNDER DIFFLIN<span class="sep">/</span><span class="blog">BLOG</span></span>
+ </a>
+ <span class="spacer"></span>
+ <div class="links">
+ <a href="/blog/">Latest</a>
+ <a href="/blog/topics/">Topics</a>
+ <a href="/blog/about/">About</a>
+ <a href="https://munderdiffl.in">↗ Product</a>
+ </div>
+ <div class="nav-actions">
+ <a class="btn sm" href="https://munderdiffl.in/blog/feed.xml" aria-label="RSS feed">⤵ RSS</a>
+ <a class="btn sm primary" href="https://munderdiffl.in/#install">⤓ Download</a>
+ </div>
+</nav>
+
+<main id="main">
+<header class="page-head wrap">
+ <p class="eyebrow">Tag</p>
+ <h1>#Terminals</h1>
+ <p class="lead">2 posts tagged <strong>Terminals</strong>.</p>
+</header>
+<section class="wrap">
+ <div class="post-grid">
+ <article class="card">
+ <a class="thumb t-internals" href="/blog/building-a-terminal-ui-xterm-node-pty/" aria-hidden="true" tabindex="-1">
+ <span>INTERNALS</span>
+ </a>
+ <div class="body">
+ <div class="meta">
+ <time datetime="2026-06-03">Jun 3, 2026</time>
+ <span class="dot" aria-hidden="true"></span>
+ <span>8 min</span>
+ </div>
+ <h3><a href="/blog/building-a-terminal-ui-xterm-node-pty/">Building a Terminal UI with xterm.js and node-pty</a></h3>
+ <p class="dek">Wire xterm.js to a node-pty backend: stream output, write keystrokes back, handle resize, and keep many live terminals fast with a terminal pool.</p>
+ <div class="foot">
+ <span class="tag kind">Internals</span>
+ <a class="more" href="/blog/building-a-terminal-ui-xterm-node-pty/" aria-label="Read: Building a Terminal UI with xterm.js and node-pty">Read →</a>
+ </div>
+ </div>
+</article>
+<article class="card">
+ <a class="thumb t-internals" href="/blog/node-pty-electron-real-terminals/" aria-hidden="true" tabindex="-1">
+ <span>INTERNALS</span>
+ </a>
+ <div class="body">
+ <div class="meta">
+ <time datetime="2026-06-03">Jun 3, 2026</time>
+ <span class="dot" aria-hidden="true"></span>
+ <span>7 min</span>
+ </div>
+ <h3><a href="/blog/node-pty-electron-real-terminals/">Real Terminals in Electron with node-pty</a></h3>
+ <p class="dek">How to run byte-for-byte authentic shells inside Electron with node-pty: the native-rebuild gotcha, the macOS PATH trap, and streaming PTY output over IPC.</p>
+ <div class="foot">
+ <span class="tag kind">Internals</span>
+ <a class="more" href="/blog/node-pty-electron-real-terminals/" aria-label="Read: Real Terminals in Electron with node-pty">Read →</a>
+ </div>
+ </div>
+</article>
+
+ </div>
+</section>
+
+
+</main>
+<footer>
+ <div class="wrap">
+ <div class="foot-top">
+ <a class="foot-brand brand" href="/blog/">
+ <span class="brand-mark">MD</span>
+ <span class="brand-word">MUNDER DIFFLIN<span class="sep">/</span><span class="blog">BLOG</span></span>
+ </a>
+ <div class="foot-links">
+ <a href="/blog/">Latest</a>
+ <a href="/blog/topics/">Topics</a>
+ <a href="/blog/about/">About</a>
+ <a href="https://munderdiffl.in/blog/feed.xml">RSS</a>
+ <a href="https://github.com/chaitanyagiri/munder-difflin">GitHub</a>
+ <a href="https://munderdiffl.in">munderdiffl.in ↗</a>
+ </div>
+ </div>
+ <div class="foot-meta">
+ © 2026 Munder Difflin · Local-first · MIT-licensed ·
+ Built on <a href="https://munderdiffl.in">Electron, React, Pixi.js, xterm.js &amp; node-pty</a>.
+ Run an office of agents while you sleep.
+ </div>
+ </div>
+</footer>
+
+<script>
+ // sticky-nav border on scroll
+ (function () {
+ var nav = document.getElementById('nav');
+ if (!nav) return;
+ var onScroll = function () { nav.classList.toggle('scrolled', window.scrollY > 8); };
+ onScroll(); window.addEventListener('scroll', onScroll, { passive: true });
+ })();
+</script>
+
+</body>
+</html>
diff --git a/docs/blog/tags/tools/index.html b/docs/blog/tags/tools/index.html
new file mode 100644
index 00000000..f3d9ad39
--- /dev/null
+++ b/docs/blog/tags/tools/index.html
@@ -0,0 +1,250 @@
+<!doctype html>
+<html lang="en">
+<head>
+<meta charset="UTF-8" />
+<meta name="viewport" content="width=device-width, initial-scale=1.0" />
+<title>Tools — Munder Difflin Blog</title>
+<meta name="description" content="Munder Difflin blog posts tagged Tools." />
+<link rel="canonical" href="https://munderdiffl.in/blog/tags/tools/" />
+
+<link rel="icon" type="image/png" href="https://munderdiffl.in/logo.png" />
+<link rel="apple-touch-icon" href="https://munderdiffl.in/logo.png" />
+<meta name="theme-color" content="#F5F2E8" />
+
+<!-- Open Graph -->
+<meta property="og:site_name" content="Munder Difflin Blog" />
+<meta property="og:type" content="website" />
+<meta property="og:title" content="Tools — Munder Difflin Blog" />
+<meta property="og:description" content="Munder Difflin blog posts tagged Tools." />
+<meta property="og:url" content="https://munderdiffl.in/blog/tags/tools/" />
+<meta property="og:image" content="https://munderdiffl.in/media/og.png" />
+<meta property="og:locale" content="en_US" />
+
+
+<!-- Twitter -->
+<meta name="twitter:card" content="summary_large_image" />
+<meta name="twitter:title" content="Tools — Munder Difflin Blog" />
+<meta name="twitter:description" content="Munder Difflin blog posts tagged Tools." />
+<meta name="twitter:image" content="https://munderdiffl.in/media/og.png" />
+
+<link rel="alternate" type="application/atom+xml" title="Munder Difflin Blog" href="https://munderdiffl.in/blog/feed.xml" />
+<link rel="preconnect" href="https://fonts.googleapis.com" />
+<link rel="preconnect" href="https://fonts.gstatic.com" crossorigin />
+<link href="https://fonts.googleapis.com/css2?family=Geist:wght@400;500;600&family=JetBrains+Mono:wght@400;500;600;700&display=swap" rel="stylesheet" />
+<link rel="stylesheet" href="/blog/assets/blog.css" />
+
+</head>
+<body>
+<a class="skip-link" href="#main">Skip to content</a>
+<nav id="nav">
+ <a class="brand" href="/blog/" aria-label="Munder Difflin Blog home">
+ <span class="brand-mark">MD</span>
+ <span class="brand-word">MUNDER DIFFLIN<span class="sep">/</span><span class="blog">BLOG</span></span>
+ </a>
+ <span class="spacer"></span>
+ <div class="links">
+ <a href="/blog/">Latest</a>
+ <a href="/blog/topics/">Topics</a>
+ <a href="/blog/about/">About</a>
+ <a href="https://munderdiffl.in">↗ Product</a>
+ </div>
+ <div class="nav-actions">
+ <a class="btn sm" href="https://munderdiffl.in/blog/feed.xml" aria-label="RSS feed">⤵ RSS</a>
+ <a class="btn sm primary" href="https://munderdiffl.in/#install">⤓ Download</a>
+ </div>
+</nav>
+
+<main id="main">
+<header class="page-head wrap">
+ <p class="eyebrow">Tag</p>
+ <h1>#Tools</h1>
+ <p class="lead">8 posts tagged <strong>Tools</strong>.</p>
+</header>
+<section class="wrap">
+ <div class="post-grid">
+ <article class="card">
+ <a class="thumb t-comparisons" href="/blog/best-claude-code-multi-agent-tools/" aria-hidden="true" tabindex="-1">
+ <span>COMPARISONS</span>
+ </a>
+ <div class="body">
+ <div class="meta">
+ <time datetime="2026-06-04">Jun 4, 2026</time>
+ <span class="dot" aria-hidden="true"></span>
+ <span>6 min</span>
+ </div>
+ <h3><a href="/blog/best-claude-code-multi-agent-tools/">The Best Tools to Run Multiple Claude Code Agents (2026)</a></h3>
+ <p class="dek">An honest 2026 roundup of tools to run multiple Claude Code agents — Claude Squad, Conductor, Crystal, vibe-kanban, and Munder Difflin — compared.</p>
+ <div class="foot">
+ <span class="tag kind">Comparisons</span>
+ <a class="more" href="/blog/best-claude-code-multi-agent-tools/" aria-label="Read: The Best Tools to Run Multiple Claude Code Agents (2026)">Read →</a>
+ </div>
+ </div>
+</article>
+<article class="card">
+ <a class="thumb t-comparisons" href="/blog/claude-code-orchestration-tools-compared/" aria-hidden="true" tabindex="-1">
+ <span>COMPARISONS</span>
+ </a>
+ <div class="body">
+ <div class="meta">
+ <time datetime="2026-06-04">Jun 4, 2026</time>
+ <span class="dot" aria-hidden="true"></span>
+ <span>3 min</span>
+ </div>
+ <h3><a href="/blog/claude-code-orchestration-tools-compared/">Claude Code Orchestration Tools, Compared</a></h3>
+ <p class="dek">Claude Code orchestration tools compared on memory, messaging, visibility, control, and local-first — across Claude Squad, Conductor, Crystal, and more.</p>
+ <div class="foot">
+ <span class="tag kind">Comparisons</span>
+ <a class="more" href="/blog/claude-code-orchestration-tools-compared/" aria-label="Read: Claude Code Orchestration Tools, Compared">Read →</a>
+ </div>
+ </div>
+</article>
+<article class="card">
+ <a class="thumb t-comparisons" href="/blog/claude-squad-vs-munder-difflin/" aria-hidden="true" tabindex="-1">
+ <span>COMPARISONS</span>
+ </a>
+ <div class="body">
+ <div class="meta">
+ <time datetime="2026-06-04">Jun 4, 2026</time>
+ <span class="dot" aria-hidden="true"></span>
+ <span>3 min</span>
+ </div>
+ <h3><a href="/blog/claude-squad-vs-munder-difflin/">Claude Squad vs Munder Difflin: Which Should You Use?</a></h3>
+ <p class="dek">Claude Squad vs Munder Difflin: a lean terminal session manager against a memory-backed, orchestrated, visual hive. Feature table and an honest verdict.</p>
+ <div class="foot">
+ <span class="tag kind">Comparisons</span>
+ <a class="more" href="/blog/claude-squad-vs-munder-difflin/" aria-label="Read: Claude Squad vs Munder Difflin: Which Should You Use?">Read →</a>
+ </div>
+ </div>
+</article>
+<article class="card">
+ <a class="thumb t-comparisons" href="/blog/claude-squad-alternative/" aria-hidden="true" tabindex="-1">
+ <span>COMPARISONS</span>
+ </a>
+ <div class="body">
+ <div class="meta">
+ <time datetime="2026-06-03">Jun 3, 2026</time>
+ <span class="dot" aria-hidden="true"></span>
+ <span>3 min</span>
+ </div>
+ <h3><a href="/blog/claude-squad-alternative/">Looking for a Claude Squad Alternative?</a></h3>
+ <p class="dek">What Claude Squad does well, where it stops, and why a memory-backed, orchestrated hive may be the Claude Squad alternative you&#39;re after.</p>
+ <div class="foot">
+ <span class="tag kind">Comparisons</span>
+ <a class="more" href="/blog/claude-squad-alternative/" aria-label="Read: Looking for a Claude Squad Alternative?">Read →</a>
+ </div>
+ </div>
+</article>
+<article class="card">
+ <a class="thumb t-comparisons" href="/blog/conductor-claude-code-alternative/" aria-hidden="true" tabindex="-1">
+ <span>COMPARISONS</span>
+ </a>
+ <div class="body">
+ <div class="meta">
+ <time datetime="2026-06-03">Jun 3, 2026</time>
+ <span class="dot" aria-hidden="true"></span>
+ <span>3 min</span>
+ </div>
+ <h3><a href="/blog/conductor-claude-code-alternative/">A Conductor Alternative for Orchestrating Claude Code</a></h3>
+ <p class="dek">Conductor is a polished macOS app for parallel Claude Code worktrees. When to pick a cross-platform, orchestrated hive as your Conductor alternative.</p>
+ <div class="foot">
+ <span class="tag kind">Comparisons</span>
+ <a class="more" href="/blog/conductor-claude-code-alternative/" aria-label="Read: A Conductor Alternative for Orchestrating Claude Code">Read →</a>
+ </div>
+ </div>
+</article>
+<article class="card">
+ <a class="thumb t-comparisons" href="/blog/crystal-claude-code-alternative/" aria-hidden="true" tabindex="-1">
+ <span>COMPARISONS</span>
+ </a>
+ <div class="body">
+ <div class="meta">
+ <time datetime="2026-06-03">Jun 3, 2026</time>
+ <span class="dot" aria-hidden="true"></span>
+ <span>3 min</span>
+ </div>
+ <h3><a href="/blog/crystal-claude-code-alternative/">A Crystal Alternative: Multi-Agent Claude Code with Memory</a></h3>
+ <p class="dek">Crystal runs parallel Claude Code worktrees well. Where a memory-backed, orchestrated hive changes the workflow — and when to stick with Crystal.</p>
+ <div class="foot">
+ <span class="tag kind">Comparisons</span>
+ <a class="more" href="/blog/crystal-claude-code-alternative/" aria-label="Read: A Crystal Alternative: Multi-Agent Claude Code with Memory">Read →</a>
+ </div>
+ </div>
+</article>
+<article class="card">
+ <a class="thumb t-comparisons" href="/blog/vibe-kanban-alternative/" aria-hidden="true" tabindex="-1">
+ <span>COMPARISONS</span>
+ </a>
+ <div class="body">
+ <div class="meta">
+ <time datetime="2026-06-03">Jun 3, 2026</time>
+ <span class="dot" aria-hidden="true"></span>
+ <span>3 min</span>
+ </div>
+ <h3><a href="/blog/vibe-kanban-alternative/">A vibe-kanban Alternative for Coordinating AI Agents</a></h3>
+ <p class="dek">vibe-kanban gives you a board to assign tasks to coding agents. When a self-routing hive is the better vibe-kanban alternative — and when a board wins.</p>
+ <div class="foot">
+ <span class="tag kind">Comparisons</span>
+ <a class="more" href="/blog/vibe-kanban-alternative/" aria-label="Read: A vibe-kanban Alternative for Coordinating AI Agents">Read →</a>
+ </div>
+ </div>
+</article>
+<article class="card">
+ <a class="thumb t-comparisons" href="/blog/how-to-choose-a-multi-agent-tool/" aria-hidden="true" tabindex="-1">
+ <span>COMPARISONS</span>
+ </a>
+ <div class="body">
+ <div class="meta">
+ <time datetime="2026-06-02">Jun 2, 2026</time>
+ <span class="dot" aria-hidden="true"></span>
+ <span>3 min</span>
+ </div>
+ <h3><a href="/blog/how-to-choose-a-multi-agent-tool/">How to Choose a Multi-Agent Coding Tool: A Buyer&#39;s Checklist</a></h3>
+ <p class="dek">A decision framework for choosing a multi-agent coding tool — memory, control, visibility, cost, local-first — with a simple scoring rubric you can run.</p>
+ <div class="foot">
+ <span class="tag kind">Comparisons</span>
+ <a class="more" href="/blog/how-to-choose-a-multi-agent-tool/" aria-label="Read: How to Choose a Multi-Agent Coding Tool: A Buyer&#39;s Checklist">Read →</a>
+ </div>
+ </div>
+</article>
+
+ </div>
+</section>
+
+
+</main>
+<footer>
+ <div class="wrap">
+ <div class="foot-top">
+ <a class="foot-brand brand" href="/blog/">
+ <span class="brand-mark">MD</span>
+ <span class="brand-word">MUNDER DIFFLIN<span class="sep">/</span><span class="blog">BLOG</span></span>
+ </a>
+ <div class="foot-links">
+ <a href="/blog/">Latest</a>
+ <a href="/blog/topics/">Topics</a>
+ <a href="/blog/about/">About</a>
+ <a href="https://munderdiffl.in/blog/feed.xml">RSS</a>
+ <a href="https://github.com/chaitanyagiri/munder-difflin">GitHub</a>
+ <a href="https://munderdiffl.in">munderdiffl.in ↗</a>
+ </div>
+ </div>
+ <div class="foot-meta">
+ © 2026 Munder Difflin · Local-first · MIT-licensed ·
+ Built on <a href="https://munderdiffl.in">Electron, React, Pixi.js, xterm.js &amp; node-pty</a>.
+ Run an office of agents while you sleep.
+ </div>
+ </div>
+</footer>
+
+<script>
+ // sticky-nav border on scroll
+ (function () {
+ var nav = document.getElementById('nav');
+ if (!nav) return;
+ var onScroll = function () { nav.classList.toggle('scrolled', window.scrollY > 8); };
+ onScroll(); window.addEventListener('scroll', onScroll, { passive: true });
+ })();
+</script>
+
+</body>
+</html>
diff --git a/docs/blog/tags/use-cases/index.html b/docs/blog/tags/use-cases/index.html
new file mode 100644
index 00000000..567ce092
--- /dev/null
+++ b/docs/blog/tags/use-cases/index.html
@@ -0,0 +1,160 @@
+<!doctype html>
+<html lang="en">
+<head>
+<meta charset="UTF-8" />
+<meta name="viewport" content="width=device-width, initial-scale=1.0" />
+<title>Use Cases — Munder Difflin Blog</title>
+<meta name="description" content="Munder Difflin blog posts tagged Use Cases." />
+<link rel="canonical" href="https://munderdiffl.in/blog/tags/use-cases/" />
+
+<link rel="icon" type="image/png" href="https://munderdiffl.in/logo.png" />
+<link rel="apple-touch-icon" href="https://munderdiffl.in/logo.png" />
+<meta name="theme-color" content="#F5F2E8" />
+
+<!-- Open Graph -->
+<meta property="og:site_name" content="Munder Difflin Blog" />
+<meta property="og:type" content="website" />
+<meta property="og:title" content="Use Cases — Munder Difflin Blog" />
+<meta property="og:description" content="Munder Difflin blog posts tagged Use Cases." />
+<meta property="og:url" content="https://munderdiffl.in/blog/tags/use-cases/" />
+<meta property="og:image" content="https://munderdiffl.in/media/og.png" />
+<meta property="og:locale" content="en_US" />
+
+
+<!-- Twitter -->
+<meta name="twitter:card" content="summary_large_image" />
+<meta name="twitter:title" content="Use Cases — Munder Difflin Blog" />
+<meta name="twitter:description" content="Munder Difflin blog posts tagged Use Cases." />
+<meta name="twitter:image" content="https://munderdiffl.in/media/og.png" />
+
+<link rel="alternate" type="application/atom+xml" title="Munder Difflin Blog" href="https://munderdiffl.in/blog/feed.xml" />
+<link rel="preconnect" href="https://fonts.googleapis.com" />
+<link rel="preconnect" href="https://fonts.gstatic.com" crossorigin />
+<link href="https://fonts.googleapis.com/css2?family=Geist:wght@400;500;600&family=JetBrains+Mono:wght@400;500;600;700&display=swap" rel="stylesheet" />
+<link rel="stylesheet" href="/blog/assets/blog.css" />
+
+</head>
+<body>
+<a class="skip-link" href="#main">Skip to content</a>
+<nav id="nav">
+ <a class="brand" href="/blog/" aria-label="Munder Difflin Blog home">
+ <span class="brand-mark">MD</span>
+ <span class="brand-word">MUNDER DIFFLIN<span class="sep">/</span><span class="blog">BLOG</span></span>
+ </a>
+ <span class="spacer"></span>
+ <div class="links">
+ <a href="/blog/">Latest</a>
+ <a href="/blog/topics/">Topics</a>
+ <a href="/blog/about/">About</a>
+ <a href="https://munderdiffl.in">↗ Product</a>
+ </div>
+ <div class="nav-actions">
+ <a class="btn sm" href="https://munderdiffl.in/blog/feed.xml" aria-label="RSS feed">⤵ RSS</a>
+ <a class="btn sm primary" href="https://munderdiffl.in/#install">⤓ Download</a>
+ </div>
+</nav>
+
+<main id="main">
+<header class="page-head wrap">
+ <p class="eyebrow">Tag</p>
+ <h1>#Use Cases</h1>
+ <p class="lead">3 posts tagged <strong>Use Cases</strong>.</p>
+</header>
+<section class="wrap">
+ <div class="post-grid">
+ <article class="card">
+ <a class="thumb t-use-cases" href="/blog/from-one-terminal-to-a-team/" aria-hidden="true" tabindex="-1">
+ <span>USE CASES</span>
+ </a>
+ <div class="body">
+ <div class="meta">
+ <time datetime="2026-06-02">Jun 2, 2026</time>
+ <span class="dot" aria-hidden="true"></span>
+ <span>3 min</span>
+ </div>
+ <h3><a href="/blog/from-one-terminal-to-a-team/">From One Terminal to a Team: Scaling Your Claude Code Workflow</a></h3>
+ <p class="dek">The workflow shift from a single Claude Code session to a coordinated team of agents — what changes, where it breaks, and the concrete before-and-after.</p>
+ <div class="foot">
+ <span class="tag kind">Use Cases</span>
+ <a class="more" href="/blog/from-one-terminal-to-a-team/" aria-label="Read: From One Terminal to a Team: Scaling Your Claude Code Workflow">Read →</a>
+ </div>
+ </div>
+</article>
+<article class="card">
+ <a class="thumb t-use-cases" href="/blog/run-an-office-of-ai-agents/" aria-hidden="true" tabindex="-1">
+ <span>USE CASES</span>
+ </a>
+ <div class="body">
+ <div class="meta">
+ <time datetime="2026-06-02">Jun 2, 2026</time>
+ <span class="dot" aria-hidden="true"></span>
+ <span>3 min</span>
+ </div>
+ <h3><a href="/blog/run-an-office-of-ai-agents/">Run an Office of AI Agents While You Sleep</a></h3>
+ <p class="dek">What it takes to run a self-coordinating office of AI coding agents that keeps shipping after you log off — and the guardrails that keep it sane.</p>
+ <div class="foot">
+ <span class="tag kind">Use Cases</span>
+ <a class="more" href="/blog/run-an-office-of-ai-agents/" aria-label="Read: Run an Office of AI Agents While You Sleep">Read →</a>
+ </div>
+ </div>
+</article>
+<article class="card">
+ <a class="thumb t-use-cases" href="/blog/why-local-first-matters-for-ai-agents/" aria-hidden="true" tabindex="-1">
+ <span>USE CASES</span>
+ </a>
+ <div class="body">
+ <div class="meta">
+ <time datetime="2026-06-02">Jun 2, 2026</time>
+ <span class="dot" aria-hidden="true"></span>
+ <span>3 min</span>
+ </div>
+ <h3><a href="/blog/why-local-first-matters-for-ai-agents/">Why Local-First Matters for Your AI Agents</a></h3>
+ <p class="dek">The control, privacy, and cost case for keeping your AI agents and their memory on your own machine — and what cloud orchestration quietly costs.</p>
+ <div class="foot">
+ <span class="tag kind">Use Cases</span>
+ <a class="more" href="/blog/why-local-first-matters-for-ai-agents/" aria-label="Read: Why Local-First Matters for Your AI Agents">Read →</a>
+ </div>
+ </div>
+</article>
+
+ </div>
+</section>
+
+
+</main>
+<footer>
+ <div class="wrap">
+ <div class="foot-top">
+ <a class="foot-brand brand" href="/blog/">
+ <span class="brand-mark">MD</span>
+ <span class="brand-word">MUNDER DIFFLIN<span class="sep">/</span><span class="blog">BLOG</span></span>
+ </a>
+ <div class="foot-links">
+ <a href="/blog/">Latest</a>
+ <a href="/blog/topics/">Topics</a>
+ <a href="/blog/about/">About</a>
+ <a href="https://munderdiffl.in/blog/feed.xml">RSS</a>
+ <a href="https://github.com/chaitanyagiri/munder-difflin">GitHub</a>
+ <a href="https://munderdiffl.in">munderdiffl.in ↗</a>
+ </div>
+ </div>
+ <div class="foot-meta">
+ © 2026 Munder Difflin · Local-first · MIT-licensed ·
+ Built on <a href="https://munderdiffl.in">Electron, React, Pixi.js, xterm.js &amp; node-pty</a>.
+ Run an office of agents while you sleep.
+ </div>
+ </div>
+</footer>
+
+<script>
+ // sticky-nav border on scroll
+ (function () {
+ var nav = document.getElementById('nav');
+ if (!nav) return;
+ var onScroll = function () { nav.classList.toggle('scrolled', window.scrollY > 8); };
+ onScroll(); window.addEventListener('scroll', onScroll, { passive: true });
+ })();
+</script>
+
+</body>
+</html>
diff --git a/docs/blog/tags/workflow/index.html b/docs/blog/tags/workflow/index.html
new file mode 100644
index 00000000..feecc920
--- /dev/null
+++ b/docs/blog/tags/workflow/index.html
@@ -0,0 +1,142 @@
+<!doctype html>
+<html lang="en">
+<head>
+<meta charset="UTF-8" />
+<meta name="viewport" content="width=device-width, initial-scale=1.0" />
+<title>Workflow — Munder Difflin Blog</title>
+<meta name="description" content="Munder Difflin blog posts tagged Workflow." />
+<link rel="canonical" href="https://munderdiffl.in/blog/tags/workflow/" />
+
+<link rel="icon" type="image/png" href="https://munderdiffl.in/logo.png" />
+<link rel="apple-touch-icon" href="https://munderdiffl.in/logo.png" />
+<meta name="theme-color" content="#F5F2E8" />
+
+<!-- Open Graph -->
+<meta property="og:site_name" content="Munder Difflin Blog" />
+<meta property="og:type" content="website" />
+<meta property="og:title" content="Workflow — Munder Difflin Blog" />
+<meta property="og:description" content="Munder Difflin blog posts tagged Workflow." />
+<meta property="og:url" content="https://munderdiffl.in/blog/tags/workflow/" />
+<meta property="og:image" content="https://munderdiffl.in/media/og.png" />
+<meta property="og:locale" content="en_US" />
+
+
+<!-- Twitter -->
+<meta name="twitter:card" content="summary_large_image" />
+<meta name="twitter:title" content="Workflow — Munder Difflin Blog" />
+<meta name="twitter:description" content="Munder Difflin blog posts tagged Workflow." />
+<meta name="twitter:image" content="https://munderdiffl.in/media/og.png" />
+
+<link rel="alternate" type="application/atom+xml" title="Munder Difflin Blog" href="https://munderdiffl.in/blog/feed.xml" />
+<link rel="preconnect" href="https://fonts.googleapis.com" />
+<link rel="preconnect" href="https://fonts.gstatic.com" crossorigin />
+<link href="https://fonts.googleapis.com/css2?family=Geist:wght@400;500;600&family=JetBrains+Mono:wght@400;500;600;700&display=swap" rel="stylesheet" />
+<link rel="stylesheet" href="/blog/assets/blog.css" />
+
+</head>
+<body>
+<a class="skip-link" href="#main">Skip to content</a>
+<nav id="nav">
+ <a class="brand" href="/blog/" aria-label="Munder Difflin Blog home">
+ <span class="brand-mark">MD</span>
+ <span class="brand-word">MUNDER DIFFLIN<span class="sep">/</span><span class="blog">BLOG</span></span>
+ </a>
+ <span class="spacer"></span>
+ <div class="links">
+ <a href="/blog/">Latest</a>
+ <a href="/blog/topics/">Topics</a>
+ <a href="/blog/about/">About</a>
+ <a href="https://munderdiffl.in">↗ Product</a>
+ </div>
+ <div class="nav-actions">
+ <a class="btn sm" href="https://munderdiffl.in/blog/feed.xml" aria-label="RSS feed">⤵ RSS</a>
+ <a class="btn sm primary" href="https://munderdiffl.in/#install">⤓ Download</a>
+ </div>
+</nav>
+
+<main id="main">
+<header class="page-head wrap">
+ <p class="eyebrow">Tag</p>
+ <h1>#Workflow</h1>
+ <p class="lead">2 posts tagged <strong>Workflow</strong>.</p>
+</header>
+<section class="wrap">
+ <div class="post-grid">
+ <article class="card">
+ <a class="thumb t-use-cases" href="/blog/from-one-terminal-to-a-team/" aria-hidden="true" tabindex="-1">
+ <span>USE CASES</span>
+ </a>
+ <div class="body">
+ <div class="meta">
+ <time datetime="2026-06-02">Jun 2, 2026</time>
+ <span class="dot" aria-hidden="true"></span>
+ <span>3 min</span>
+ </div>
+ <h3><a href="/blog/from-one-terminal-to-a-team/">From One Terminal to a Team: Scaling Your Claude Code Workflow</a></h3>
+ <p class="dek">The workflow shift from a single Claude Code session to a coordinated team of agents — what changes, where it breaks, and the concrete before-and-after.</p>
+ <div class="foot">
+ <span class="tag kind">Use Cases</span>
+ <a class="more" href="/blog/from-one-terminal-to-a-team/" aria-label="Read: From One Terminal to a Team: Scaling Your Claude Code Workflow">Read →</a>
+ </div>
+ </div>
+</article>
+<article class="card">
+ <a class="thumb t-guides" href="/blog/manage-multiple-claude-code-sessions/" aria-hidden="true" tabindex="-1">
+ <span>GUIDES</span>
+ </a>
+ <div class="body">
+ <div class="meta">
+ <time datetime="2026-05-25">May 25, 2026</time>
+ <span class="dot" aria-hidden="true"></span>
+ <span>4 min</span>
+ </div>
+ <h3><a href="/blog/manage-multiple-claude-code-sessions/">How to Manage Multiple Claude Code Sessions Like a Pro</a></h3>
+ <p class="dek">Tactics to manage multiple Claude Code sessions without losing track: naming, roles, context isolation, and when a harness beats juggling terminal tabs.</p>
+ <div class="foot">
+ <span class="tag kind">Guides</span>
+ <a class="more" href="/blog/manage-multiple-claude-code-sessions/" aria-label="Read: How to Manage Multiple Claude Code Sessions Like a Pro">Read →</a>
+ </div>
+ </div>
+</article>
+
+ </div>
+</section>
+
+
+</main>
+<footer>
+ <div class="wrap">
+ <div class="foot-top">
+ <a class="foot-brand brand" href="/blog/">
+ <span class="brand-mark">MD</span>
+ <span class="brand-word">MUNDER DIFFLIN<span class="sep">/</span><span class="blog">BLOG</span></span>
+ </a>
+ <div class="foot-links">
+ <a href="/blog/">Latest</a>
+ <a href="/blog/topics/">Topics</a>
+ <a href="/blog/about/">About</a>
+ <a href="https://munderdiffl.in/blog/feed.xml">RSS</a>
+ <a href="https://github.com/chaitanyagiri/munder-difflin">GitHub</a>
+ <a href="https://munderdiffl.in">munderdiffl.in ↗</a>
+ </div>
+ </div>
+ <div class="foot-meta">
+ © 2026 Munder Difflin · Local-first · MIT-licensed ·
+ Built on <a href="https://munderdiffl.in">Electron, React, Pixi.js, xterm.js &amp; node-pty</a>.
+ Run an office of agents while you sleep.
+ </div>
+ </div>
+</footer>
+
+<script>
+ // sticky-nav border on scroll
+ (function () {
+ var nav = document.getElementById('nav');
+ if (!nav) return;
+ var onScroll = function () { nav.classList.toggle('scrolled', window.scrollY > 8); };
+ onScroll(); window.addEventListener('scroll', onScroll, { passive: true });
+ })();
+</script>
+
+</body>
+</html>
diff --git a/docs/blog/tags/xtermjs/index.html b/docs/blog/tags/xtermjs/index.html
new file mode 100644
index 00000000..b3663a71
--- /dev/null
+++ b/docs/blog/tags/xtermjs/index.html
@@ -0,0 +1,124 @@
+<!doctype html>
+<html lang="en">
+<head>
+<meta charset="UTF-8" />
+<meta name="viewport" content="width=device-width, initial-scale=1.0" />
+<title>xterm.js — Munder Difflin Blog</title>
+<meta name="description" content="Munder Difflin blog posts tagged xterm.js." />
+<link rel="canonical" href="https://munderdiffl.in/blog/tags/xtermjs/" />
+
+<link rel="icon" type="image/png" href="https://munderdiffl.in/logo.png" />
+<link rel="apple-touch-icon" href="https://munderdiffl.in/logo.png" />
+<meta name="theme-color" content="#F5F2E8" />
+
+<!-- Open Graph -->
+<meta property="og:site_name" content="Munder Difflin Blog" />
+<meta property="og:type" content="website" />
+<meta property="og:title" content="xterm.js — Munder Difflin Blog" />
+<meta property="og:description" content="Munder Difflin blog posts tagged xterm.js." />
+<meta property="og:url" content="https://munderdiffl.in/blog/tags/xtermjs/" />
+<meta property="og:image" content="https://munderdiffl.in/media/og.png" />
+<meta property="og:locale" content="en_US" />
+
+
+<!-- Twitter -->
+<meta name="twitter:card" content="summary_large_image" />
+<meta name="twitter:title" content="xterm.js — Munder Difflin Blog" />
+<meta name="twitter:description" content="Munder Difflin blog posts tagged xterm.js." />
+<meta name="twitter:image" content="https://munderdiffl.in/media/og.png" />
+
+<link rel="alternate" type="application/atom+xml" title="Munder Difflin Blog" href="https://munderdiffl.in/blog/feed.xml" />
+<link rel="preconnect" href="https://fonts.googleapis.com" />
+<link rel="preconnect" href="https://fonts.gstatic.com" crossorigin />
+<link href="https://fonts.googleapis.com/css2?family=Geist:wght@400;500;600&family=JetBrains+Mono:wght@400;500;600;700&display=swap" rel="stylesheet" />
+<link rel="stylesheet" href="/blog/assets/blog.css" />
+
+</head>
+<body>
+<a class="skip-link" href="#main">Skip to content</a>
+<nav id="nav">
+ <a class="brand" href="/blog/" aria-label="Munder Difflin Blog home">
+ <span class="brand-mark">MD</span>
+ <span class="brand-word">MUNDER DIFFLIN<span class="sep">/</span><span class="blog">BLOG</span></span>
+ </a>
+ <span class="spacer"></span>
+ <div class="links">
+ <a href="/blog/">Latest</a>
+ <a href="/blog/topics/">Topics</a>
+ <a href="/blog/about/">About</a>
+ <a href="https://munderdiffl.in">↗ Product</a>
+ </div>
+ <div class="nav-actions">
+ <a class="btn sm" href="https://munderdiffl.in/blog/feed.xml" aria-label="RSS feed">⤵ RSS</a>
+ <a class="btn sm primary" href="https://munderdiffl.in/#install">⤓ Download</a>
+ </div>
+</nav>
+
+<main id="main">
+<header class="page-head wrap">
+ <p class="eyebrow">Tag</p>
+ <h1>#xterm.js</h1>
+ <p class="lead">1 post tagged <strong>xterm.js</strong>.</p>
+</header>
+<section class="wrap">
+ <div class="post-grid">
+ <article class="card">
+ <a class="thumb t-internals" href="/blog/building-a-terminal-ui-xterm-node-pty/" aria-hidden="true" tabindex="-1">
+ <span>INTERNALS</span>
+ </a>
+ <div class="body">
+ <div class="meta">
+ <time datetime="2026-06-03">Jun 3, 2026</time>
+ <span class="dot" aria-hidden="true"></span>
+ <span>8 min</span>
+ </div>
+ <h3><a href="/blog/building-a-terminal-ui-xterm-node-pty/">Building a Terminal UI with xterm.js and node-pty</a></h3>
+ <p class="dek">Wire xterm.js to a node-pty backend: stream output, write keystrokes back, handle resize, and keep many live terminals fast with a terminal pool.</p>
+ <div class="foot">
+ <span class="tag kind">Internals</span>
+ <a class="more" href="/blog/building-a-terminal-ui-xterm-node-pty/" aria-label="Read: Building a Terminal UI with xterm.js and node-pty">Read →</a>
+ </div>
+ </div>
+</article>
+
+ </div>
+</section>
+
+
+</main>
+<footer>
+ <div class="wrap">
+ <div class="foot-top">
+ <a class="foot-brand brand" href="/blog/">
+ <span class="brand-mark">MD</span>
+ <span class="brand-word">MUNDER DIFFLIN<span class="sep">/</span><span class="blog">BLOG</span></span>
+ </a>
+ <div class="foot-links">
+ <a href="/blog/">Latest</a>
+ <a href="/blog/topics/">Topics</a>
+ <a href="/blog/about/">About</a>
+ <a href="https://munderdiffl.in/blog/feed.xml">RSS</a>
+ <a href="https://github.com/chaitanyagiri/munder-difflin">GitHub</a>
+ <a href="https://munderdiffl.in">munderdiffl.in ↗</a>
+ </div>
+ </div>
+ <div class="foot-meta">
+ © 2026 Munder Difflin · Local-first · MIT-licensed ·
+ Built on <a href="https://munderdiffl.in">Electron, React, Pixi.js, xterm.js &amp; node-pty</a>.
+ Run an office of agents while you sleep.
+ </div>
+ </div>
+</footer>
+
+<script>
+ // sticky-nav border on scroll
+ (function () {
+ var nav = document.getElementById('nav');
+ if (!nav) return;
+ var onScroll = function () { nav.classList.toggle('scrolled', window.scrollY > 8); };
+ onScroll(); window.addEventListener('scroll', onScroll, { passive: true });
+ })();
+</script>
+
+</body>
+</html>
diff --git a/docs/blog/topics/comparisons/index.html b/docs/blog/topics/comparisons/index.html
new file mode 100644
index 00000000..4f98744e
--- /dev/null
+++ b/docs/blog/topics/comparisons/index.html
@@ -0,0 +1,277 @@
+<!doctype html>
+<html lang="en">
+<head>
+<meta charset="UTF-8" />
+<meta name="viewport" content="width=device-width, initial-scale=1.0" />
+<title>comparisons — Munder Difflin Blog</title>
+<meta name="description" content="Munder Difflin blog posts on comparisons — agentic coding with Claude Code, the hive, GOD orchestrator, and long-term memory." />
+<link rel="canonical" href="https://munderdiffl.in/blog/topics/comparisons/" />
+
+<link rel="icon" type="image/png" href="https://munderdiffl.in/logo.png" />
+<link rel="apple-touch-icon" href="https://munderdiffl.in/logo.png" />
+<meta name="theme-color" content="#F5F2E8" />
+
+<!-- Open Graph -->
+<meta property="og:site_name" content="Munder Difflin Blog" />
+<meta property="og:type" content="website" />
+<meta property="og:title" content="comparisons — Munder Difflin Blog" />
+<meta property="og:description" content="Munder Difflin blog posts on comparisons — agentic coding with Claude Code, the hive, GOD orchestrator, and long-term memory." />
+<meta property="og:url" content="https://munderdiffl.in/blog/topics/comparisons/" />
+<meta property="og:image" content="https://munderdiffl.in/media/og.png" />
+<meta property="og:locale" content="en_US" />
+
+
+<!-- Twitter -->
+<meta name="twitter:card" content="summary_large_image" />
+<meta name="twitter:title" content="comparisons — Munder Difflin Blog" />
+<meta name="twitter:description" content="Munder Difflin blog posts on comparisons — agentic coding with Claude Code, the hive, GOD orchestrator, and long-term memory." />
+<meta name="twitter:image" content="https://munderdiffl.in/media/og.png" />
+
+<link rel="alternate" type="application/atom+xml" title="Munder Difflin Blog" href="https://munderdiffl.in/blog/feed.xml" />
+<link rel="preconnect" href="https://fonts.googleapis.com" />
+<link rel="preconnect" href="https://fonts.gstatic.com" crossorigin />
+<link href="https://fonts.googleapis.com/css2?family=Geist:wght@400;500;600&family=JetBrains+Mono:wght@400;500;600;700&display=swap" rel="stylesheet" />
+<link rel="stylesheet" href="/blog/assets/blog.css" />
+
+</head>
+<body>
+<a class="skip-link" href="#main">Skip to content</a>
+<nav id="nav">
+ <a class="brand" href="/blog/" aria-label="Munder Difflin Blog home">
+ <span class="brand-mark">MD</span>
+ <span class="brand-word">MUNDER DIFFLIN<span class="sep">/</span><span class="blog">BLOG</span></span>
+ </a>
+ <span class="spacer"></span>
+ <div class="links">
+ <a href="/blog/">Latest</a>
+ <a href="/blog/topics/" aria-current="page">Topics</a>
+ <a href="/blog/about/">About</a>
+ <a href="https://munderdiffl.in">↗ Product</a>
+ </div>
+ <div class="nav-actions">
+ <a class="btn sm" href="https://munderdiffl.in/blog/feed.xml" aria-label="RSS feed">⤵ RSS</a>
+ <a class="btn sm primary" href="https://munderdiffl.in/#install">⤓ Download</a>
+ </div>
+</nav>
+
+<main id="main">
+
+<header class="page-head wrap">
+ <nav class="crumbs" aria-label="Breadcrumb" style="font-family:var(--font-mono);font-size:12px;color:var(--ink-faint);display:flex;gap:8px;">
+ <a href="/blog/" style="color:var(--ink-dim)">Blog</a><span>/</span>
+ <a href="/blog/topics/" style="color:var(--ink-dim)">Topics</a>
+ </nav>
+ <p class="eyebrow">Topic</p>
+ <h1>comparisons</h1>
+ <p class="lead">8 posts in this cluster.</p>
+
+ <div class="filters" role="navigation" aria-label="Topics">
+ <a class="chip" href="/blog/">All</a>
+
+ <a class="chip" href="/blog/topics/comparisons/" aria-current="page">comparisons<span class="ct">8</span></a>
+
+ <a class="chip" href="/blog/topics/guides/">guides<span class="ct">6</span></a>
+
+ <a class="chip" href="/blog/topics/internals/">internals<span class="ct">5</span></a>
+
+ <a class="chip" href="/blog/topics/concepts/">concepts<span class="ct">4</span></a>
+
+ <a class="chip" href="/blog/topics/orchestration/">orchestration<span class="ct">4</span></a>
+
+ <a class="chip" href="/blog/topics/use-cases/">use-cases<span class="ct">3</span></a>
+
+ <a class="chip" href="/blog/topics/memory/">memory<span class="ct">2</span></a>
+
+ <a class="chip" href="/blog/topics/story/">story<span class="ct">1</span></a>
+
+ </div>
+</header>
+
+<section class="wrap">
+ <div class="post-grid">
+ <article class="card">
+ <a class="thumb t-comparisons" href="/blog/best-claude-code-multi-agent-tools/" aria-hidden="true" tabindex="-1">
+ <span>COMPARISONS</span>
+ </a>
+ <div class="body">
+ <div class="meta">
+ <time datetime="2026-06-04">Jun 4, 2026</time>
+ <span class="dot" aria-hidden="true"></span>
+ <span>6 min</span>
+ </div>
+ <h3><a href="/blog/best-claude-code-multi-agent-tools/">The Best Tools to Run Multiple Claude Code Agents (2026)</a></h3>
+ <p class="dek">An honest 2026 roundup of tools to run multiple Claude Code agents — Claude Squad, Conductor, Crystal, vibe-kanban, and Munder Difflin — compared.</p>
+ <div class="foot">
+ <span class="tag kind">Comparisons</span>
+ <a class="more" href="/blog/best-claude-code-multi-agent-tools/" aria-label="Read: The Best Tools to Run Multiple Claude Code Agents (2026)">Read →</a>
+ </div>
+ </div>
+</article>
+<article class="card">
+ <a class="thumb t-comparisons" href="/blog/claude-code-orchestration-tools-compared/" aria-hidden="true" tabindex="-1">
+ <span>COMPARISONS</span>
+ </a>
+ <div class="body">
+ <div class="meta">
+ <time datetime="2026-06-04">Jun 4, 2026</time>
+ <span class="dot" aria-hidden="true"></span>
+ <span>3 min</span>
+ </div>
+ <h3><a href="/blog/claude-code-orchestration-tools-compared/">Claude Code Orchestration Tools, Compared</a></h3>
+ <p class="dek">Claude Code orchestration tools compared on memory, messaging, visibility, control, and local-first — across Claude Squad, Conductor, Crystal, and more.</p>
+ <div class="foot">
+ <span class="tag kind">Comparisons</span>
+ <a class="more" href="/blog/claude-code-orchestration-tools-compared/" aria-label="Read: Claude Code Orchestration Tools, Compared">Read →</a>
+ </div>
+ </div>
+</article>
+<article class="card">
+ <a class="thumb t-comparisons" href="/blog/claude-squad-vs-munder-difflin/" aria-hidden="true" tabindex="-1">
+ <span>COMPARISONS</span>
+ </a>
+ <div class="body">
+ <div class="meta">
+ <time datetime="2026-06-04">Jun 4, 2026</time>
+ <span class="dot" aria-hidden="true"></span>
+ <span>3 min</span>
+ </div>
+ <h3><a href="/blog/claude-squad-vs-munder-difflin/">Claude Squad vs Munder Difflin: Which Should You Use?</a></h3>
+ <p class="dek">Claude Squad vs Munder Difflin: a lean terminal session manager against a memory-backed, orchestrated, visual hive. Feature table and an honest verdict.</p>
+ <div class="foot">
+ <span class="tag kind">Comparisons</span>
+ <a class="more" href="/blog/claude-squad-vs-munder-difflin/" aria-label="Read: Claude Squad vs Munder Difflin: Which Should You Use?">Read →</a>
+ </div>
+ </div>
+</article>
+<article class="card">
+ <a class="thumb t-comparisons" href="/blog/claude-squad-alternative/" aria-hidden="true" tabindex="-1">
+ <span>COMPARISONS</span>
+ </a>
+ <div class="body">
+ <div class="meta">
+ <time datetime="2026-06-03">Jun 3, 2026</time>
+ <span class="dot" aria-hidden="true"></span>
+ <span>3 min</span>
+ </div>
+ <h3><a href="/blog/claude-squad-alternative/">Looking for a Claude Squad Alternative?</a></h3>
+ <p class="dek">What Claude Squad does well, where it stops, and why a memory-backed, orchestrated hive may be the Claude Squad alternative you&#39;re after.</p>
+ <div class="foot">
+ <span class="tag kind">Comparisons</span>
+ <a class="more" href="/blog/claude-squad-alternative/" aria-label="Read: Looking for a Claude Squad Alternative?">Read →</a>
+ </div>
+ </div>
+</article>
+<article class="card">
+ <a class="thumb t-comparisons" href="/blog/conductor-claude-code-alternative/" aria-hidden="true" tabindex="-1">
+ <span>COMPARISONS</span>
+ </a>
+ <div class="body">
+ <div class="meta">
+ <time datetime="2026-06-03">Jun 3, 2026</time>
+ <span class="dot" aria-hidden="true"></span>
+ <span>3 min</span>
+ </div>
+ <h3><a href="/blog/conductor-claude-code-alternative/">A Conductor Alternative for Orchestrating Claude Code</a></h3>
+ <p class="dek">Conductor is a polished macOS app for parallel Claude Code worktrees. When to pick a cross-platform, orchestrated hive as your Conductor alternative.</p>
+ <div class="foot">
+ <span class="tag kind">Comparisons</span>
+ <a class="more" href="/blog/conductor-claude-code-alternative/" aria-label="Read: A Conductor Alternative for Orchestrating Claude Code">Read →</a>
+ </div>
+ </div>
+</article>
+<article class="card">
+ <a class="thumb t-comparisons" href="/blog/crystal-claude-code-alternative/" aria-hidden="true" tabindex="-1">
+ <span>COMPARISONS</span>
+ </a>
+ <div class="body">
+ <div class="meta">
+ <time datetime="2026-06-03">Jun 3, 2026</time>
+ <span class="dot" aria-hidden="true"></span>
+ <span>3 min</span>
+ </div>
+ <h3><a href="/blog/crystal-claude-code-alternative/">A Crystal Alternative: Multi-Agent Claude Code with Memory</a></h3>
+ <p class="dek">Crystal runs parallel Claude Code worktrees well. Where a memory-backed, orchestrated hive changes the workflow — and when to stick with Crystal.</p>
+ <div class="foot">
+ <span class="tag kind">Comparisons</span>
+ <a class="more" href="/blog/crystal-claude-code-alternative/" aria-label="Read: A Crystal Alternative: Multi-Agent Claude Code with Memory">Read →</a>
+ </div>
+ </div>
+</article>
+<article class="card">
+ <a class="thumb t-comparisons" href="/blog/vibe-kanban-alternative/" aria-hidden="true" tabindex="-1">
+ <span>COMPARISONS</span>
+ </a>
+ <div class="body">
+ <div class="meta">
+ <time datetime="2026-06-03">Jun 3, 2026</time>
+ <span class="dot" aria-hidden="true"></span>
+ <span>3 min</span>
+ </div>
+ <h3><a href="/blog/vibe-kanban-alternative/">A vibe-kanban Alternative for Coordinating AI Agents</a></h3>
+ <p class="dek">vibe-kanban gives you a board to assign tasks to coding agents. When a self-routing hive is the better vibe-kanban alternative — and when a board wins.</p>
+ <div class="foot">
+ <span class="tag kind">Comparisons</span>
+ <a class="more" href="/blog/vibe-kanban-alternative/" aria-label="Read: A vibe-kanban Alternative for Coordinating AI Agents">Read →</a>
+ </div>
+ </div>
+</article>
+<article class="card">
+ <a class="thumb t-comparisons" href="/blog/how-to-choose-a-multi-agent-tool/" aria-hidden="true" tabindex="-1">
+ <span>COMPARISONS</span>
+ </a>
+ <div class="body">
+ <div class="meta">
+ <time datetime="2026-06-02">Jun 2, 2026</time>
+ <span class="dot" aria-hidden="true"></span>
+ <span>3 min</span>
+ </div>
+ <h3><a href="/blog/how-to-choose-a-multi-agent-tool/">How to Choose a Multi-Agent Coding Tool: A Buyer&#39;s Checklist</a></h3>
+ <p class="dek">A decision framework for choosing a multi-agent coding tool — memory, control, visibility, cost, local-first — with a simple scoring rubric you can run.</p>
+ <div class="foot">
+ <span class="tag kind">Comparisons</span>
+ <a class="more" href="/blog/how-to-choose-a-multi-agent-tool/" aria-label="Read: How to Choose a Multi-Agent Coding Tool: A Buyer&#39;s Checklist">Read →</a>
+ </div>
+ </div>
+</article>
+
+ </div>
+</section>
+
+
+</main>
+<footer>
+ <div class="wrap">
+ <div class="foot-top">
+ <a class="foot-brand brand" href="/blog/">
+ <span class="brand-mark">MD</span>
+ <span class="brand-word">MUNDER DIFFLIN<span class="sep">/</span><span class="blog">BLOG</span></span>
+ </a>
+ <div class="foot-links">
+ <a href="/blog/">Latest</a>
+ <a href="/blog/topics/">Topics</a>
+ <a href="/blog/about/">About</a>
+ <a href="https://munderdiffl.in/blog/feed.xml">RSS</a>
+ <a href="https://github.com/chaitanyagiri/munder-difflin">GitHub</a>
+ <a href="https://munderdiffl.in">munderdiffl.in ↗</a>
+ </div>
+ </div>
+ <div class="foot-meta">
+ © 2026 Munder Difflin · Local-first · MIT-licensed ·
+ Built on <a href="https://munderdiffl.in">Electron, React, Pixi.js, xterm.js &amp; node-pty</a>.
+ Run an office of agents while you sleep.
+ </div>
+ </div>
+</footer>
+
+<script>
+ // sticky-nav border on scroll
+ (function () {
+ var nav = document.getElementById('nav');
+ if (!nav) return;
+ var onScroll = function () { nav.classList.toggle('scrolled', window.scrollY > 8); };
+ onScroll(); window.addEventListener('scroll', onScroll, { passive: true });
+ })();
+</script>
+
+</body>
+</html>
diff --git a/docs/blog/topics/concepts/index.html b/docs/blog/topics/concepts/index.html
index 2d8fd5b2..0848797b 100644
--- a/docs/blog/topics/concepts/index.html
+++ b/docs/blog/topics/concepts/index.html
@@ -63,16 +63,26 @@
</nav>
<p class="eyebrow">Topic</p>
<h1>concepts</h1>
- <p class="lead">1 post in this cluster.</p>
+ <p class="lead">4 posts in this cluster.</p>
<div class="filters" role="navigation" aria-label="Topics">
<a class="chip" href="/blog/">All</a>
- <a class="chip" href="/blog/topics/concepts/" aria-current="page">concepts<span class="ct">1</span></a>
+ <a class="chip" href="/blog/topics/comparisons/">comparisons<span class="ct">8</span></a>
- <a class="chip" href="/blog/topics/memory/">memory<span class="ct">1</span></a>
+ <a class="chip" href="/blog/topics/guides/">guides<span class="ct">6</span></a>
- <a class="chip" href="/blog/topics/guides/">guides<span class="ct">1</span></a>
+ <a class="chip" href="/blog/topics/internals/">internals<span class="ct">5</span></a>
+
+ <a class="chip" href="/blog/topics/concepts/" aria-current="page">concepts<span class="ct">4</span></a>
+
+ <a class="chip" href="/blog/topics/orchestration/">orchestration<span class="ct">4</span></a>
+
+ <a class="chip" href="/blog/topics/use-cases/">use-cases<span class="ct">3</span></a>
+
+ <a class="chip" href="/blog/topics/memory/">memory<span class="ct">2</span></a>
+
+ <a class="chip" href="/blog/topics/story/">story<span class="ct">1</span></a>
</div>
</header>
@@ -80,6 +90,60 @@
<section class="wrap">
<div class="post-grid">
<article class="card">
+ <a class="thumb t-concepts" href="/blog/ai-agent-glossary/" aria-hidden="true" tabindex="-1">
+ <span>CONCEPTS</span>
+ </a>
+ <div class="body">
+ <div class="meta">
+ <time datetime="2026-06-02">Jun 2, 2026</time>
+ <span class="dot" aria-hidden="true"></span>
+ <span>3 min</span>
+ </div>
+ <h3><a href="/blog/ai-agent-glossary/">The AI Coding Agent Glossary: Harness, Orchestrator, Hive, Subagent</a></h3>
+ <p class="dek">Plain-English definitions of the AI coding agent terms everyone trips over — harness, orchestrator, hive, subagent, agent memory — each in one line.</p>
+ <div class="foot">
+ <span class="tag kind">Concepts</span>
+ <a class="more" href="/blog/ai-agent-glossary/" aria-label="Read: The AI Coding Agent Glossary: Harness, Orchestrator, Hive, Subagent">Read →</a>
+ </div>
+ </div>
+</article>
+<article class="card">
+ <a class="thumb t-concepts" href="/blog/munder-difflin-faq/" aria-hidden="true" tabindex="-1">
+ <span>CONCEPTS</span>
+ </a>
+ <div class="body">
+ <div class="meta">
+ <time datetime="2026-06-02">Jun 2, 2026</time>
+ <span class="dot" aria-hidden="true"></span>
+ <span>1 min</span>
+ </div>
+ <h3><a href="/blog/munder-difflin-faq/">Munder Difflin FAQ: Everything People Ask</a></h3>
+ <p class="dek">Answers to the top Munder Difflin questions — what it is, is it free, does it run locally, which platforms, and how it differs from many terminals.</p>
+ <div class="foot">
+ <span class="tag kind">Concepts</span>
+ <a class="more" href="/blog/munder-difflin-faq/" aria-label="Read: Munder Difflin FAQ: Everything People Ask">Read →</a>
+ </div>
+ </div>
+</article>
+<article class="card">
+ <a class="thumb t-concepts" href="/blog/what-are-claude-code-agents/" aria-hidden="true" tabindex="-1">
+ <span>CONCEPTS</span>
+ </a>
+ <div class="body">
+ <div class="meta">
+ <time datetime="2026-06-02">Jun 2, 2026</time>
+ <span class="dot" aria-hidden="true"></span>
+ <span>3 min</span>
+ </div>
+ <h3><a href="/blog/what-are-claude-code-agents/">What Are Claude Code Agents? And How to Use Many at Once</a></h3>
+ <p class="dek">Claude Code agents explained in plain English — what an agent actually is, how subagents differ, and the leap from one agent to a coordinated team.</p>
+ <div class="foot">
+ <span class="tag kind">Concepts</span>
+ <a class="more" href="/blog/what-are-claude-code-agents/" aria-label="Read: What Are Claude Code Agents? And How to Use Many at Once">Read →</a>
+ </div>
+ </div>
+</article>
+<article class="card">
<a class="thumb t-concepts" href="/blog/what-is-a-multi-agent-harness/" aria-hidden="true" tabindex="-1">
<span>CONCEPTS</span>
</a>
diff --git a/docs/blog/topics/guides/index.html b/docs/blog/topics/guides/index.html
index bb862f9c..9a220f94 100644
--- a/docs/blog/topics/guides/index.html
+++ b/docs/blog/topics/guides/index.html
@@ -63,16 +63,26 @@
</nav>
<p class="eyebrow">Topic</p>
<h1>guides</h1>
- <p class="lead">1 post in this cluster.</p>
+ <p class="lead">6 posts in this cluster.</p>
<div class="filters" role="navigation" aria-label="Topics">
<a class="chip" href="/blog/">All</a>
- <a class="chip" href="/blog/topics/concepts/">concepts<span class="ct">1</span></a>
+ <a class="chip" href="/blog/topics/comparisons/">comparisons<span class="ct">8</span></a>
- <a class="chip" href="/blog/topics/memory/">memory<span class="ct">1</span></a>
+ <a class="chip" href="/blog/topics/guides/" aria-current="page">guides<span class="ct">6</span></a>
- <a class="chip" href="/blog/topics/guides/" aria-current="page">guides<span class="ct">1</span></a>
+ <a class="chip" href="/blog/topics/internals/">internals<span class="ct">5</span></a>
+
+ <a class="chip" href="/blog/topics/concepts/">concepts<span class="ct">4</span></a>
+
+ <a class="chip" href="/blog/topics/orchestration/">orchestration<span class="ct">4</span></a>
+
+ <a class="chip" href="/blog/topics/use-cases/">use-cases<span class="ct">3</span></a>
+
+ <a class="chip" href="/blog/topics/memory/">memory<span class="ct">2</span></a>
+
+ <a class="chip" href="/blog/topics/story/">story<span class="ct">1</span></a>
</div>
</header>
@@ -80,6 +90,42 @@
<section class="wrap">
<div class="post-grid">
<article class="card">
+ <a class="thumb t-guides" href="/blog/claude-code-automation-while-you-sleep/" aria-hidden="true" tabindex="-1">
+ <span>GUIDES</span>
+ </a>
+ <div class="body">
+ <div class="meta">
+ <time datetime="2026-06-04">Jun 4, 2026</time>
+ <span class="dot" aria-hidden="true"></span>
+ <span>5 min</span>
+ </div>
+ <h3><a href="/blog/claude-code-automation-while-you-sleep/">Claude Code Automation: Let Agents Build While You Sleep</a></h3>
+ <p class="dek">Claude Code automation that runs overnight: an autonomous Stop-hook loop, safe permission bypass, and guardrails so you wake up to progress, not chaos.</p>
+ <div class="foot">
+ <span class="tag kind">Guides</span>
+ <a class="more" href="/blog/claude-code-automation-while-you-sleep/" aria-label="Read: Claude Code Automation: Let Agents Build While You Sleep">Read →</a>
+ </div>
+ </div>
+</article>
+<article class="card">
+ <a class="thumb t-guides" href="/blog/mcp-and-skills-in-a-hive/" aria-hidden="true" tabindex="-1">
+ <span>GUIDES</span>
+ </a>
+ <div class="body">
+ <div class="meta">
+ <time datetime="2026-06-03">Jun 3, 2026</time>
+ <span class="dot" aria-hidden="true"></span>
+ <span>6 min</span>
+ </div>
+ <h3><a href="/blog/mcp-and-skills-in-a-hive/">Bringing Your MCP Servers and Skills Into a Hive of Agents</a></h3>
+ <p class="dek">How agents in a hive inherit your existing Claude Code MCP servers, skills, and tools — and how to scope which agent gets which capability.</p>
+ <div class="foot">
+ <span class="tag kind">Guides</span>
+ <a class="more" href="/blog/mcp-and-skills-in-a-hive/" aria-label="Read: Bringing Your MCP Servers and Skills Into a Hive of Agents">Read →</a>
+ </div>
+ </div>
+</article>
+<article class="card">
<a class="thumb t-guides" href="/blog/how-to-run-multiple-claude-code-agents/" aria-hidden="true" tabindex="-1">
<span>GUIDES</span>
</a>
@@ -97,6 +143,60 @@
</div>
</div>
</article>
+<article class="card">
+ <a class="thumb t-guides" href="/blog/manage-multiple-claude-code-sessions/" aria-hidden="true" tabindex="-1">
+ <span>GUIDES</span>
+ </a>
+ <div class="body">
+ <div class="meta">
+ <time datetime="2026-05-25">May 25, 2026</time>
+ <span class="dot" aria-hidden="true"></span>
+ <span>4 min</span>
+ </div>
+ <h3><a href="/blog/manage-multiple-claude-code-sessions/">How to Manage Multiple Claude Code Sessions Like a Pro</a></h3>
+ <p class="dek">Tactics to manage multiple Claude Code sessions without losing track: naming, roles, context isolation, and when a harness beats juggling terminal tabs.</p>
+ <div class="foot">
+ <span class="tag kind">Guides</span>
+ <a class="more" href="/blog/manage-multiple-claude-code-sessions/" aria-label="Read: How to Manage Multiple Claude Code Sessions Like a Pro">Read →</a>
+ </div>
+ </div>
+</article>
+<article class="card">
+ <a class="thumb t-guides" href="/blog/claude-code-multi-agent-setup-tutorial/" aria-hidden="true" tabindex="-1">
+ <span>GUIDES</span>
+ </a>
+ <div class="body">
+ <div class="meta">
+ <time datetime="2026-05-24">May 24, 2026</time>
+ <span class="dot" aria-hidden="true"></span>
+ <span>5 min</span>
+ </div>
+ <h3><a href="/blog/claude-code-multi-agent-setup-tutorial/">Set Up a Claude Code Multi-Agent Workflow in 10 Minutes</a></h3>
+ <p class="dek">A from-zero Claude Code multi-agent setup: install Munder Difflin, onboard, spawn a few agents, and watch the GOD orchestrator route your first task.</p>
+ <div class="foot">
+ <span class="tag kind">Guides</span>
+ <a class="more" href="/blog/claude-code-multi-agent-setup-tutorial/" aria-label="Read: Set Up a Claude Code Multi-Agent Workflow in 10 Minutes">Read →</a>
+ </div>
+ </div>
+</article>
+<article class="card">
+ <a class="thumb t-guides" href="/blog/claude-code-subagents-vs-multi-agent-harness/" aria-hidden="true" tabindex="-1">
+ <span>GUIDES</span>
+ </a>
+ <div class="body">
+ <div class="meta">
+ <time datetime="2026-05-23">May 23, 2026</time>
+ <span class="dot" aria-hidden="true"></span>
+ <span>5 min</span>
+ </div>
+ <h3><a href="/blog/claude-code-subagents-vs-multi-agent-harness/">Claude Code Subagents vs a Multi-Agent Harness</a></h3>
+ <p class="dek">Claude Code subagents vs a multi-agent harness: where subagents stop and a harness with shared memory, messaging, and an orchestrator takes over.</p>
+ <div class="foot">
+ <span class="tag kind">Guides</span>
+ <a class="more" href="/blog/claude-code-subagents-vs-multi-agent-harness/" aria-label="Read: Claude Code Subagents vs a Multi-Agent Harness">Read →</a>
+ </div>
+ </div>
+</article>
</div>
</section>
diff --git a/docs/blog/topics/index.html b/docs/blog/topics/index.html
index b0583d2f..1e77552f 100644
--- a/docs/blog/topics/index.html
+++ b/docs/blog/topics/index.html
@@ -66,11 +66,56 @@
<section class="wrap">
<div class="post-grid">
+ <a class="card" href="/blog/topics/comparisons/" style="text-decoration:none">
+ <span class="thumb t-comparisons" aria-hidden="true">COMPARISONS</span>
+ <div class="body">
+ <h3 style="color:var(--ink)">comparisons</h3>
+ <p class="dek">8 posts.</p>
+ <div class="foot"><span class="more">View topic →</span></div>
+ </div>
+ </a>
+
+ <a class="card" href="/blog/topics/guides/" style="text-decoration:none">
+ <span class="thumb t-guides" aria-hidden="true">GUIDES</span>
+ <div class="body">
+ <h3 style="color:var(--ink)">guides</h3>
+ <p class="dek">6 posts.</p>
+ <div class="foot"><span class="more">View topic →</span></div>
+ </div>
+ </a>
+
+ <a class="card" href="/blog/topics/internals/" style="text-decoration:none">
+ <span class="thumb t-internals" aria-hidden="true">INTERNALS</span>
+ <div class="body">
+ <h3 style="color:var(--ink)">internals</h3>
+ <p class="dek">5 posts.</p>
+ <div class="foot"><span class="more">View topic →</span></div>
+ </div>
+ </a>
+
<a class="card" href="/blog/topics/concepts/" style="text-decoration:none">
<span class="thumb t-concepts" aria-hidden="true">CONCEPTS</span>
<div class="body">
<h3 style="color:var(--ink)">concepts</h3>
- <p class="dek">1 post.</p>
+ <p class="dek">4 posts.</p>
+ <div class="foot"><span class="more">View topic →</span></div>
+ </div>
+ </a>
+
+ <a class="card" href="/blog/topics/orchestration/" style="text-decoration:none">
+ <span class="thumb t-orchestration" aria-hidden="true">ORCHESTRATION</span>
+ <div class="body">
+ <h3 style="color:var(--ink)">orchestration</h3>
+ <p class="dek">4 posts.</p>
+ <div class="foot"><span class="more">View topic →</span></div>
+ </div>
+ </a>
+
+ <a class="card" href="/blog/topics/use-cases/" style="text-decoration:none">
+ <span class="thumb t-use-cases" aria-hidden="true">USE-CASES</span>
+ <div class="body">
+ <h3 style="color:var(--ink)">use-cases</h3>
+ <p class="dek">3 posts.</p>
<div class="foot"><span class="more">View topic →</span></div>
</div>
</a>
@@ -79,15 +124,15 @@
<span class="thumb t-memory" aria-hidden="true">MEMORY</span>
<div class="body">
<h3 style="color:var(--ink)">memory</h3>
- <p class="dek">1 post.</p>
+ <p class="dek">2 posts.</p>
<div class="foot"><span class="more">View topic →</span></div>
</div>
</a>
- <a class="card" href="/blog/topics/guides/" style="text-decoration:none">
- <span class="thumb t-guides" aria-hidden="true">GUIDES</span>
+ <a class="card" href="/blog/topics/story/" style="text-decoration:none">
+ <span class="thumb t-story" aria-hidden="true">STORY</span>
<div class="body">
- <h3 style="color:var(--ink)">guides</h3>
+ <h3 style="color:var(--ink)">story</h3>
<p class="dek">1 post.</p>
<div class="foot"><span class="more">View topic →</span></div>
</div>
@@ -99,19 +144,73 @@
<div class="filters" style="padding-top:36px">
<span class="eyebrow" style="align-self:center">Tags</span>
- <a class="chip" href="/blog/tags/claude-code/">Claude Code<span class="ct">3</span></a>
+ <a class="chip" href="/blog/tags/multi-agent/">Multi-Agent<span class="ct">24</span></a>
+
+ <a class="chip" href="/blog/tags/claude-code/">Claude Code<span class="ct">24</span></a>
+
+ <a class="chip" href="/blog/tags/comparisons/">Comparisons<span class="ct">8</span></a>
+
+ <a class="chip" href="/blog/tags/tools/">Tools<span class="ct">8</span></a>
+
+ <a class="chip" href="/blog/tags/orchestration/">Orchestration<span class="ct">7</span></a>
+
+ <a class="chip" href="/blog/tags/guides/">Guides<span class="ct">6</span></a>
+
+ <a class="chip" href="/blog/tags/internals/">Internals<span class="ct">6</span></a>
+
+ <a class="chip" href="/blog/tags/getting-started/">Getting Started<span class="ct">5</span></a>
+
+ <a class="chip" href="/blog/tags/concepts/">Concepts<span class="ct">4</span></a>
+
+ <a class="chip" href="/blog/tags/memory/">Memory<span class="ct">3</span></a>
+
+ <a class="chip" href="/blog/tags/use-cases/">Use Cases<span class="ct">3</span></a>
+
+ <a class="chip" href="/blog/tags/automation/">Automation<span class="ct">3</span></a>
+
+ <a class="chip" href="/blog/tags/workflow/">Workflow<span class="ct">2</span></a>
+
+ <a class="chip" href="/blog/tags/mempalace/">MemPalace<span class="ct">2</span></a>
+
+ <a class="chip" href="/blog/tags/god/">GOD<span class="ct">2</span></a>
+
+ <a class="chip" href="/blog/tags/story/">Story<span class="ct">2</span></a>
+
+ <a class="chip" href="/blog/tags/git/">Git<span class="ct">2</span></a>
+
+ <a class="chip" href="/blog/tags/terminals/">Terminals<span class="ct">2</span></a>
+
+ <a class="chip" href="/blog/tags/electron/">Electron<span class="ct">2</span></a>
+
+ <a class="chip" href="/blog/tags/subagents/">Subagents<span class="ct">1</span></a>
+
+ <a class="chip" href="/blog/tags/coordination/">Coordination<span class="ct">1</span></a>
+
+ <a class="chip" href="/blog/tags/messaging/">Messaging<span class="ct">1</span></a>
+
+ <a class="chip" href="/blog/tags/glossary/">Glossary<span class="ct">1</span></a>
+
+ <a class="chip" href="/blog/tags/faq/">FAQ<span class="ct">1</span></a>
+
+ <a class="chip" href="/blog/tags/concurrency/">Concurrency<span class="ct">1</span></a>
+
+ <a class="chip" href="/blog/tags/local-first/">Local-First<span class="ct">1</span></a>
+
+ <a class="chip" href="/blog/tags/privacy/">Privacy<span class="ct">1</span></a>
+
+ <a class="chip" href="/blog/tags/open-source/">Open Source<span class="ct">1</span></a>
- <a class="chip" href="/blog/tags/multi-agent/">Multi-Agent<span class="ct">2</span></a>
+ <a class="chip" href="/blog/tags/xtermjs/">xterm.js<span class="ct">1</span></a>
- <a class="chip" href="/blog/tags/concepts/">Concepts<span class="ct">1</span></a>
+ <a class="chip" href="/blog/tags/hooks/">Hooks<span class="ct">1</span></a>
- <a class="chip" href="/blog/tags/memory/">Memory<span class="ct">1</span></a>
+ <a class="chip" href="/blog/tags/mcp/">MCP<span class="ct">1</span></a>
- <a class="chip" href="/blog/tags/mempalace/">MemPalace<span class="ct">1</span></a>
+ <a class="chip" href="/blog/tags/skills/">Skills<span class="ct">1</span></a>
- <a class="chip" href="/blog/tags/guides/">Guides<span class="ct">1</span></a>
+ <a class="chip" href="/blog/tags/node-pty/">node-pty<span class="ct">1</span></a>
- <a class="chip" href="/blog/tags/getting-started/">Getting Started<span class="ct">1</span></a>
+ <a class="chip" href="/blog/tags/autonomous/">Autonomous<span class="ct">1</span></a>
</div>
diff --git a/docs/blog/topics/internals/index.html b/docs/blog/topics/internals/index.html
new file mode 100644
index 00000000..dd8e614f
--- /dev/null
+++ b/docs/blog/topics/internals/index.html
@@ -0,0 +1,223 @@
+<!doctype html>
+<html lang="en">
+<head>
+<meta charset="UTF-8" />
+<meta name="viewport" content="width=device-width, initial-scale=1.0" />
+<title>internals — Munder Difflin Blog</title>
+<meta name="description" content="Munder Difflin blog posts on internals — agentic coding with Claude Code, the hive, GOD orchestrator, and long-term memory." />
+<link rel="canonical" href="https://munderdiffl.in/blog/topics/internals/" />
+
+<link rel="icon" type="image/png" href="https://munderdiffl.in/logo.png" />
+<link rel="apple-touch-icon" href="https://munderdiffl.in/logo.png" />
+<meta name="theme-color" content="#F5F2E8" />
+
+<!-- Open Graph -->
+<meta property="og:site_name" content="Munder Difflin Blog" />
+<meta property="og:type" content="website" />
+<meta property="og:title" content="internals — Munder Difflin Blog" />
+<meta property="og:description" content="Munder Difflin blog posts on internals — agentic coding with Claude Code, the hive, GOD orchestrator, and long-term memory." />
+<meta property="og:url" content="https://munderdiffl.in/blog/topics/internals/" />
+<meta property="og:image" content="https://munderdiffl.in/media/og.png" />
+<meta property="og:locale" content="en_US" />
+
+
+<!-- Twitter -->
+<meta name="twitter:card" content="summary_large_image" />
+<meta name="twitter:title" content="internals — Munder Difflin Blog" />
+<meta name="twitter:description" content="Munder Difflin blog posts on internals — agentic coding with Claude Code, the hive, GOD orchestrator, and long-term memory." />
+<meta name="twitter:image" content="https://munderdiffl.in/media/og.png" />
+
+<link rel="alternate" type="application/atom+xml" title="Munder Difflin Blog" href="https://munderdiffl.in/blog/feed.xml" />
+<link rel="preconnect" href="https://fonts.googleapis.com" />
+<link rel="preconnect" href="https://fonts.gstatic.com" crossorigin />
+<link href="https://fonts.googleapis.com/css2?family=Geist:wght@400;500;600&family=JetBrains+Mono:wght@400;500;600;700&display=swap" rel="stylesheet" />
+<link rel="stylesheet" href="/blog/assets/blog.css" />
+
+</head>
+<body>
+<a class="skip-link" href="#main">Skip to content</a>
+<nav id="nav">
+ <a class="brand" href="/blog/" aria-label="Munder Difflin Blog home">
+ <span class="brand-mark">MD</span>
+ <span class="brand-word">MUNDER DIFFLIN<span class="sep">/</span><span class="blog">BLOG</span></span>
+ </a>
+ <span class="spacer"></span>
+ <div class="links">
+ <a href="/blog/">Latest</a>
+ <a href="/blog/topics/" aria-current="page">Topics</a>
+ <a href="/blog/about/">About</a>
+ <a href="https://munderdiffl.in">↗ Product</a>
+ </div>
+ <div class="nav-actions">
+ <a class="btn sm" href="https://munderdiffl.in/blog/feed.xml" aria-label="RSS feed">⤵ RSS</a>
+ <a class="btn sm primary" href="https://munderdiffl.in/#install">⤓ Download</a>
+ </div>
+</nav>
+
+<main id="main">
+
+<header class="page-head wrap">
+ <nav class="crumbs" aria-label="Breadcrumb" style="font-family:var(--font-mono);font-size:12px;color:var(--ink-faint);display:flex;gap:8px;">
+ <a href="/blog/" style="color:var(--ink-dim)">Blog</a><span>/</span>
+ <a href="/blog/topics/" style="color:var(--ink-dim)">Topics</a>
+ </nav>
+ <p class="eyebrow">Topic</p>
+ <h1>internals</h1>
+ <p class="lead">5 posts in this cluster.</p>
+
+ <div class="filters" role="navigation" aria-label="Topics">
+ <a class="chip" href="/blog/">All</a>
+
+ <a class="chip" href="/blog/topics/comparisons/">comparisons<span class="ct">8</span></a>
+
+ <a class="chip" href="/blog/topics/guides/">guides<span class="ct">6</span></a>
+
+ <a class="chip" href="/blog/topics/internals/" aria-current="page">internals<span class="ct">5</span></a>
+
+ <a class="chip" href="/blog/topics/concepts/">concepts<span class="ct">4</span></a>
+
+ <a class="chip" href="/blog/topics/orchestration/">orchestration<span class="ct">4</span></a>
+
+ <a class="chip" href="/blog/topics/use-cases/">use-cases<span class="ct">3</span></a>
+
+ <a class="chip" href="/blog/topics/memory/">memory<span class="ct">2</span></a>
+
+ <a class="chip" href="/blog/topics/story/">story<span class="ct">1</span></a>
+
+ </div>
+</header>
+
+<section class="wrap">
+ <div class="post-grid">
+ <article class="card">
+ <a class="thumb t-internals" href="/blog/building-a-terminal-ui-xterm-node-pty/" aria-hidden="true" tabindex="-1">
+ <span>INTERNALS</span>
+ </a>
+ <div class="body">
+ <div class="meta">
+ <time datetime="2026-06-03">Jun 3, 2026</time>
+ <span class="dot" aria-hidden="true"></span>
+ <span>8 min</span>
+ </div>
+ <h3><a href="/blog/building-a-terminal-ui-xterm-node-pty/">Building a Terminal UI with xterm.js and node-pty</a></h3>
+ <p class="dek">Wire xterm.js to a node-pty backend: stream output, write keystrokes back, handle resize, and keep many live terminals fast with a terminal pool.</p>
+ <div class="foot">
+ <span class="tag kind">Internals</span>
+ <a class="more" href="/blog/building-a-terminal-ui-xterm-node-pty/" aria-label="Read: Building a Terminal UI with xterm.js and node-pty">Read →</a>
+ </div>
+ </div>
+</article>
+<article class="card">
+ <a class="thumb t-internals" href="/blog/claude-code-hooks-explained/" aria-hidden="true" tabindex="-1">
+ <span>INTERNALS</span>
+ </a>
+ <div class="body">
+ <div class="meta">
+ <time datetime="2026-06-03">Jun 3, 2026</time>
+ <span class="dot" aria-hidden="true"></span>
+ <span>6 min</span>
+ </div>
+ <h3><a href="/blog/claude-code-hooks-explained/">Claude Code Hooks, Explained (PreToolUse, PostToolUse, Stop)</a></h3>
+ <p class="dek">A practical tour of Claude Code hooks — the PreToolUse, PostToolUse, and Stop lifecycle — and how a Unix-socket hook shim drives a live office floor.</p>
+ <div class="foot">
+ <span class="tag kind">Internals</span>
+ <a class="more" href="/blog/claude-code-hooks-explained/" aria-label="Read: Claude Code Hooks, Explained (PreToolUse, PostToolUse, Stop)">Read →</a>
+ </div>
+ </div>
+</article>
+<article class="card">
+ <a class="thumb t-internals" href="/blog/node-pty-electron-real-terminals/" aria-hidden="true" tabindex="-1">
+ <span>INTERNALS</span>
+ </a>
+ <div class="body">
+ <div class="meta">
+ <time datetime="2026-06-03">Jun 3, 2026</time>
+ <span class="dot" aria-hidden="true"></span>
+ <span>7 min</span>
+ </div>
+ <h3><a href="/blog/node-pty-electron-real-terminals/">Real Terminals in Electron with node-pty</a></h3>
+ <p class="dek">How to run byte-for-byte authentic shells inside Electron with node-pty: the native-rebuild gotcha, the macOS PATH trap, and streaming PTY output over IPC.</p>
+ <div class="foot">
+ <span class="tag kind">Internals</span>
+ <a class="more" href="/blog/node-pty-electron-real-terminals/" aria-label="Read: Real Terminals in Electron with node-pty">Read →</a>
+ </div>
+ </div>
+</article>
+<article class="card">
+ <a class="thumb t-internals" href="/blog/single-committer-git-pattern/" aria-hidden="true" tabindex="-1">
+ <span>INTERNALS</span>
+ </a>
+ <div class="body">
+ <div class="meta">
+ <time datetime="2026-06-02">Jun 2, 2026</time>
+ <span class="dot" aria-hidden="true"></span>
+ <span>5 min</span>
+ </div>
+ <h3><a href="/blog/single-committer-git-pattern/">The Single-Committer Pattern: Multi-Agent Git Without Corruption</a></h3>
+ <p class="dek">Parallel agents corrupt a repo with index.lock races. The single-committer pattern — agents write, one process commits — fixes concurrent git writes.</p>
+ <div class="foot">
+ <span class="tag kind">Internals</span>
+ <a class="more" href="/blog/single-committer-git-pattern/" aria-label="Read: The Single-Committer Pattern: Multi-Agent Git Without Corruption">Read →</a>
+ </div>
+ </div>
+</article>
+<article class="card">
+ <a class="thumb t-internals" href="/blog/atomic-file-mailboxes-for-agents/" aria-hidden="true" tabindex="-1">
+ <span>INTERNALS</span>
+ </a>
+ <div class="body">
+ <div class="meta">
+ <time datetime="2026-05-31">May 31, 2026</time>
+ <span class="dot" aria-hidden="true"></span>
+ <span>5 min</span>
+ </div>
+ <h3><a href="/blog/atomic-file-mailboxes-for-agents/">Atomic File Mailboxes: How Agents Message Each Other</a></h3>
+ <p class="dek">Can Claude Code agents talk to each other? Yes — the outbox-router-inbox design that lets agents message safely using plain files and atomic renames.</p>
+ <div class="foot">
+ <span class="tag kind">Internals</span>
+ <a class="more" href="/blog/atomic-file-mailboxes-for-agents/" aria-label="Read: Atomic File Mailboxes: How Agents Message Each Other">Read →</a>
+ </div>
+ </div>
+</article>
+
+ </div>
+</section>
+
+
+</main>
+<footer>
+ <div class="wrap">
+ <div class="foot-top">
+ <a class="foot-brand brand" href="/blog/">
+ <span class="brand-mark">MD</span>
+ <span class="brand-word">MUNDER DIFFLIN<span class="sep">/</span><span class="blog">BLOG</span></span>
+ </a>
+ <div class="foot-links">
+ <a href="/blog/">Latest</a>
+ <a href="/blog/topics/">Topics</a>
+ <a href="/blog/about/">About</a>
+ <a href="https://munderdiffl.in/blog/feed.xml">RSS</a>
+ <a href="https://github.com/chaitanyagiri/munder-difflin">GitHub</a>
+ <a href="https://munderdiffl.in">munderdiffl.in ↗</a>
+ </div>
+ </div>
+ <div class="foot-meta">
+ © 2026 Munder Difflin · Local-first · MIT-licensed ·
+ Built on <a href="https://munderdiffl.in">Electron, React, Pixi.js, xterm.js &amp; node-pty</a>.
+ Run an office of agents while you sleep.
+ </div>
+ </div>
+</footer>
+
+<script>
+ // sticky-nav border on scroll
+ (function () {
+ var nav = document.getElementById('nav');
+ if (!nav) return;
+ var onScroll = function () { nav.classList.toggle('scrolled', window.scrollY > 8); };
+ onScroll(); window.addEventListener('scroll', onScroll, { passive: true });
+ })();
+</script>
+
+</body>
+</html>
diff --git a/docs/blog/topics/memory/index.html b/docs/blog/topics/memory/index.html
index 0cf928d1..3eb014b5 100644
--- a/docs/blog/topics/memory/index.html
+++ b/docs/blog/topics/memory/index.html
@@ -63,16 +63,26 @@
</nav>
<p class="eyebrow">Topic</p>
<h1>memory</h1>
- <p class="lead">1 post in this cluster.</p>
+ <p class="lead">2 posts in this cluster.</p>
<div class="filters" role="navigation" aria-label="Topics">
<a class="chip" href="/blog/">All</a>
- <a class="chip" href="/blog/topics/concepts/">concepts<span class="ct">1</span></a>
+ <a class="chip" href="/blog/topics/comparisons/">comparisons<span class="ct">8</span></a>
- <a class="chip" href="/blog/topics/memory/" aria-current="page">memory<span class="ct">1</span></a>
+ <a class="chip" href="/blog/topics/guides/">guides<span class="ct">6</span></a>
- <a class="chip" href="/blog/topics/guides/">guides<span class="ct">1</span></a>
+ <a class="chip" href="/blog/topics/internals/">internals<span class="ct">5</span></a>
+
+ <a class="chip" href="/blog/topics/concepts/">concepts<span class="ct">4</span></a>
+
+ <a class="chip" href="/blog/topics/orchestration/">orchestration<span class="ct">4</span></a>
+
+ <a class="chip" href="/blog/topics/use-cases/">use-cases<span class="ct">3</span></a>
+
+ <a class="chip" href="/blog/topics/memory/" aria-current="page">memory<span class="ct">2</span></a>
+
+ <a class="chip" href="/blog/topics/story/">story<span class="ct">1</span></a>
</div>
</header>
@@ -97,6 +107,24 @@
</div>
</div>
</article>
+<article class="card">
+ <a class="thumb t-memory" href="/blog/semantic-memory-for-ai-agents/" aria-hidden="true" tabindex="-1">
+ <span>MEMORY</span>
+ </a>
+ <div class="body">
+ <div class="meta">
+ <time datetime="2026-05-26">May 26, 2026</time>
+ <span class="dot" aria-hidden="true"></span>
+ <span>6 min</span>
+ </div>
+ <h3><a href="/blog/semantic-memory-for-ai-agents/">Semantic Memory for AI Agents: Recall in Milliseconds</a></h3>
+ <p class="dek">What semantic memory for AI agents is, why a markdown-first store beats a heavy DB, and how a shared palace lets a hive recall a note by meaning, fast.</p>
+ <div class="foot">
+ <span class="tag kind">Memory</span>
+ <a class="more" href="/blog/semantic-memory-for-ai-agents/" aria-label="Read: Semantic Memory for AI Agents: Recall in Milliseconds">Read →</a>
+ </div>
+ </div>
+</article>
</div>
</section>
diff --git a/docs/blog/topics/orchestration/index.html b/docs/blog/topics/orchestration/index.html
new file mode 100644
index 00000000..46f43f69
--- /dev/null
+++ b/docs/blog/topics/orchestration/index.html
@@ -0,0 +1,205 @@
+<!doctype html>
+<html lang="en">
+<head>
+<meta charset="UTF-8" />
+<meta name="viewport" content="width=device-width, initial-scale=1.0" />
+<title>orchestration — Munder Difflin Blog</title>
+<meta name="description" content="Munder Difflin blog posts on orchestration — agentic coding with Claude Code, the hive, GOD orchestrator, and long-term memory." />
+<link rel="canonical" href="https://munderdiffl.in/blog/topics/orchestration/" />
+
+<link rel="icon" type="image/png" href="https://munderdiffl.in/logo.png" />
+<link rel="apple-touch-icon" href="https://munderdiffl.in/logo.png" />
+<meta name="theme-color" content="#F5F2E8" />
+
+<!-- Open Graph -->
+<meta property="og:site_name" content="Munder Difflin Blog" />
+<meta property="og:type" content="website" />
+<meta property="og:title" content="orchestration — Munder Difflin Blog" />
+<meta property="og:description" content="Munder Difflin blog posts on orchestration — agentic coding with Claude Code, the hive, GOD orchestrator, and long-term memory." />
+<meta property="og:url" content="https://munderdiffl.in/blog/topics/orchestration/" />
+<meta property="og:image" content="https://munderdiffl.in/media/og.png" />
+<meta property="og:locale" content="en_US" />
+
+
+<!-- Twitter -->
+<meta name="twitter:card" content="summary_large_image" />
+<meta name="twitter:title" content="orchestration — Munder Difflin Blog" />
+<meta name="twitter:description" content="Munder Difflin blog posts on orchestration — agentic coding with Claude Code, the hive, GOD orchestrator, and long-term memory." />
+<meta name="twitter:image" content="https://munderdiffl.in/media/og.png" />
+
+<link rel="alternate" type="application/atom+xml" title="Munder Difflin Blog" href="https://munderdiffl.in/blog/feed.xml" />
+<link rel="preconnect" href="https://fonts.googleapis.com" />
+<link rel="preconnect" href="https://fonts.gstatic.com" crossorigin />
+<link href="https://fonts.googleapis.com/css2?family=Geist:wght@400;500;600&family=JetBrains+Mono:wght@400;500;600;700&display=swap" rel="stylesheet" />
+<link rel="stylesheet" href="/blog/assets/blog.css" />
+
+</head>
+<body>
+<a class="skip-link" href="#main">Skip to content</a>
+<nav id="nav">
+ <a class="brand" href="/blog/" aria-label="Munder Difflin Blog home">
+ <span class="brand-mark">MD</span>
+ <span class="brand-word">MUNDER DIFFLIN<span class="sep">/</span><span class="blog">BLOG</span></span>
+ </a>
+ <span class="spacer"></span>
+ <div class="links">
+ <a href="/blog/">Latest</a>
+ <a href="/blog/topics/" aria-current="page">Topics</a>
+ <a href="/blog/about/">About</a>
+ <a href="https://munderdiffl.in">↗ Product</a>
+ </div>
+ <div class="nav-actions">
+ <a class="btn sm" href="https://munderdiffl.in/blog/feed.xml" aria-label="RSS feed">⤵ RSS</a>
+ <a class="btn sm primary" href="https://munderdiffl.in/#install">⤓ Download</a>
+ </div>
+</nav>
+
+<main id="main">
+
+<header class="page-head wrap">
+ <nav class="crumbs" aria-label="Breadcrumb" style="font-family:var(--font-mono);font-size:12px;color:var(--ink-faint);display:flex;gap:8px;">
+ <a href="/blog/" style="color:var(--ink-dim)">Blog</a><span>/</span>
+ <a href="/blog/topics/" style="color:var(--ink-dim)">Topics</a>
+ </nav>
+ <p class="eyebrow">Topic</p>
+ <h1>orchestration</h1>
+ <p class="lead">4 posts in this cluster.</p>
+
+ <div class="filters" role="navigation" aria-label="Topics">
+ <a class="chip" href="/blog/">All</a>
+
+ <a class="chip" href="/blog/topics/comparisons/">comparisons<span class="ct">8</span></a>
+
+ <a class="chip" href="/blog/topics/guides/">guides<span class="ct">6</span></a>
+
+ <a class="chip" href="/blog/topics/internals/">internals<span class="ct">5</span></a>
+
+ <a class="chip" href="/blog/topics/concepts/">concepts<span class="ct">4</span></a>
+
+ <a class="chip" href="/blog/topics/orchestration/" aria-current="page">orchestration<span class="ct">4</span></a>
+
+ <a class="chip" href="/blog/topics/use-cases/">use-cases<span class="ct">3</span></a>
+
+ <a class="chip" href="/blog/topics/memory/">memory<span class="ct">2</span></a>
+
+ <a class="chip" href="/blog/topics/story/">story<span class="ct">1</span></a>
+
+ </div>
+</header>
+
+<section class="wrap">
+ <div class="post-grid">
+ <article class="card">
+ <a class="thumb t-orchestration" href="/blog/claude-code-git-worktrees-vs-hive/" aria-hidden="true" tabindex="-1">
+ <span>ORCHESTRATION</span>
+ </a>
+ <div class="body">
+ <div class="meta">
+ <time datetime="2026-06-04">Jun 4, 2026</time>
+ <span class="dot" aria-hidden="true"></span>
+ <span>5 min</span>
+ </div>
+ <h3><a href="/blog/claude-code-git-worktrees-vs-hive/">Git Worktrees vs a Hive: Two Ways to Parallelize Claude Code</a></h3>
+ <p class="dek">Claude Code git worktrees vs a hive: when isolated worktrees suffice for parallel agents, and when you need memory, messaging, and an orchestrator on top.</p>
+ <div class="foot">
+ <span class="tag kind">Orchestration</span>
+ <a class="more" href="/blog/claude-code-git-worktrees-vs-hive/" aria-label="Read: Git Worktrees vs a Hive: Two Ways to Parallelize Claude Code">Read →</a>
+ </div>
+ </div>
+</article>
+<article class="card">
+ <a class="thumb t-orchestration" href="/blog/how-the-god-orchestrator-works/" aria-hidden="true" tabindex="-1">
+ <span>ORCHESTRATION</span>
+ </a>
+ <div class="body">
+ <div class="meta">
+ <time datetime="2026-05-30">May 30, 2026</time>
+ <span class="dot" aria-hidden="true"></span>
+ <span>6 min</span>
+ </div>
+ <h3><a href="/blog/how-the-god-orchestrator-works/">Inside the GOD Orchestrator: Routing, Adjudication, Escalation</a></h3>
+ <p class="dek">A deep dive into the Claude Code orchestrator: how a GOD agent reads requests, routes work, adjudicates routine traffic, and escalates the critical few.</p>
+ <div class="foot">
+ <span class="tag kind">Orchestration</span>
+ <a class="more" href="/blog/how-the-god-orchestrator-works/" aria-label="Read: Inside the GOD Orchestrator: Routing, Adjudication, Escalation">Read →</a>
+ </div>
+ </div>
+</article>
+<article class="card">
+ <a class="thumb t-orchestration" href="/blog/coordinating-ai-coding-agents/" aria-hidden="true" tabindex="-1">
+ <span>ORCHESTRATION</span>
+ </a>
+ <div class="body">
+ <div class="meta">
+ <time datetime="2026-05-29">May 29, 2026</time>
+ <span class="dot" aria-hidden="true"></span>
+ <span>5 min</span>
+ </div>
+ <h3><a href="/blog/coordinating-ai-coding-agents/">The Best Way to Coordinate AI Coding Agents</a></h3>
+ <p class="dek">The best way to coordinate AI coding agents: single-writer files, a message router, a one-scribe plan, and an orchestrator — cooperate, not clobber.</p>
+ <div class="foot">
+ <span class="tag kind">Orchestration</span>
+ <a class="more" href="/blog/coordinating-ai-coding-agents/" aria-label="Read: The Best Way to Coordinate AI Coding Agents">Read →</a>
+ </div>
+ </div>
+</article>
+<article class="card">
+ <a class="thumb t-orchestration" href="/blog/claude-code-orchestration-guide/" aria-hidden="true" tabindex="-1">
+ <span>ORCHESTRATION</span>
+ </a>
+ <div class="body">
+ <div class="meta">
+ <time datetime="2026-05-28">May 28, 2026</time>
+ <span class="dot" aria-hidden="true"></span>
+ <span>5 min</span>
+ </div>
+ <h3><a href="/blog/claude-code-orchestration-guide/">Orchestrating Claude Code Agents: A Practical Guide</a></h3>
+ <p class="dek">How to orchestrate Claude Code agents in practice: what orchestration means, how a GOD orchestrator routes and escalates work, and how to wire it up.</p>
+ <div class="foot">
+ <span class="tag kind">Orchestration</span>
+ <a class="more" href="/blog/claude-code-orchestration-guide/" aria-label="Read: Orchestrating Claude Code Agents: A Practical Guide">Read →</a>
+ </div>
+ </div>
+</article>
+
+ </div>
+</section>
+
+
+</main>
+<footer>
+ <div class="wrap">
+ <div class="foot-top">
+ <a class="foot-brand brand" href="/blog/">
+ <span class="brand-mark">MD</span>
+ <span class="brand-word">MUNDER DIFFLIN<span class="sep">/</span><span class="blog">BLOG</span></span>
+ </a>
+ <div class="foot-links">
+ <a href="/blog/">Latest</a>
+ <a href="/blog/topics/">Topics</a>
+ <a href="/blog/about/">About</a>
+ <a href="https://munderdiffl.in/blog/feed.xml">RSS</a>
+ <a href="https://github.com/chaitanyagiri/munder-difflin">GitHub</a>
+ <a href="https://munderdiffl.in">munderdiffl.in ↗</a>
+ </div>
+ </div>
+ <div class="foot-meta">
+ © 2026 Munder Difflin · Local-first · MIT-licensed ·
+ Built on <a href="https://munderdiffl.in">Electron, React, Pixi.js, xterm.js &amp; node-pty</a>.
+ Run an office of agents while you sleep.
+ </div>
+ </div>
+</footer>
+
+<script>
+ // sticky-nav border on scroll
+ (function () {
+ var nav = document.getElementById('nav');
+ if (!nav) return;
+ var onScroll = function () { nav.classList.toggle('scrolled', window.scrollY > 8); };
+ onScroll(); window.addEventListener('scroll', onScroll, { passive: true });
+ })();
+</script>
+
+</body>
+</html>
diff --git a/docs/blog/topics/story/index.html b/docs/blog/topics/story/index.html
new file mode 100644
index 00000000..0ba879a8
--- /dev/null
+++ b/docs/blog/topics/story/index.html
@@ -0,0 +1,151 @@
+<!doctype html>
+<html lang="en">
+<head>
+<meta charset="UTF-8" />
+<meta name="viewport" content="width=device-width, initial-scale=1.0" />
+<title>story — Munder Difflin Blog</title>
+<meta name="description" content="Munder Difflin blog posts on story — agentic coding with Claude Code, the hive, GOD orchestrator, and long-term memory." />
+<link rel="canonical" href="https://munderdiffl.in/blog/topics/story/" />
+
+<link rel="icon" type="image/png" href="https://munderdiffl.in/logo.png" />
+<link rel="apple-touch-icon" href="https://munderdiffl.in/logo.png" />
+<meta name="theme-color" content="#F5F2E8" />
+
+<!-- Open Graph -->
+<meta property="og:site_name" content="Munder Difflin Blog" />
+<meta property="og:type" content="website" />
+<meta property="og:title" content="story — Munder Difflin Blog" />
+<meta property="og:description" content="Munder Difflin blog posts on story — agentic coding with Claude Code, the hive, GOD orchestrator, and long-term memory." />
+<meta property="og:url" content="https://munderdiffl.in/blog/topics/story/" />
+<meta property="og:image" content="https://munderdiffl.in/media/og.png" />
+<meta property="og:locale" content="en_US" />
+
+
+<!-- Twitter -->
+<meta name="twitter:card" content="summary_large_image" />
+<meta name="twitter:title" content="story — Munder Difflin Blog" />
+<meta name="twitter:description" content="Munder Difflin blog posts on story — agentic coding with Claude Code, the hive, GOD orchestrator, and long-term memory." />
+<meta name="twitter:image" content="https://munderdiffl.in/media/og.png" />
+
+<link rel="alternate" type="application/atom+xml" title="Munder Difflin Blog" href="https://munderdiffl.in/blog/feed.xml" />
+<link rel="preconnect" href="https://fonts.googleapis.com" />
+<link rel="preconnect" href="https://fonts.gstatic.com" crossorigin />
+<link href="https://fonts.googleapis.com/css2?family=Geist:wght@400;500;600&family=JetBrains+Mono:wght@400;500;600;700&display=swap" rel="stylesheet" />
+<link rel="stylesheet" href="/blog/assets/blog.css" />
+
+</head>
+<body>
+<a class="skip-link" href="#main">Skip to content</a>
+<nav id="nav">
+ <a class="brand" href="/blog/" aria-label="Munder Difflin Blog home">
+ <span class="brand-mark">MD</span>
+ <span class="brand-word">MUNDER DIFFLIN<span class="sep">/</span><span class="blog">BLOG</span></span>
+ </a>
+ <span class="spacer"></span>
+ <div class="links">
+ <a href="/blog/">Latest</a>
+ <a href="/blog/topics/" aria-current="page">Topics</a>
+ <a href="/blog/about/">About</a>
+ <a href="https://munderdiffl.in">↗ Product</a>
+ </div>
+ <div class="nav-actions">
+ <a class="btn sm" href="https://munderdiffl.in/blog/feed.xml" aria-label="RSS feed">⤵ RSS</a>
+ <a class="btn sm primary" href="https://munderdiffl.in/#install">⤓ Download</a>
+ </div>
+</nav>
+
+<main id="main">
+
+<header class="page-head wrap">
+ <nav class="crumbs" aria-label="Breadcrumb" style="font-family:var(--font-mono);font-size:12px;color:var(--ink-faint);display:flex;gap:8px;">
+ <a href="/blog/" style="color:var(--ink-dim)">Blog</a><span>/</span>
+ <a href="/blog/topics/" style="color:var(--ink-dim)">Topics</a>
+ </nav>
+ <p class="eyebrow">Topic</p>
+ <h1>story</h1>
+ <p class="lead">1 post in this cluster.</p>
+
+ <div class="filters" role="navigation" aria-label="Topics">
+ <a class="chip" href="/blog/">All</a>
+
+ <a class="chip" href="/blog/topics/comparisons/">comparisons<span class="ct">8</span></a>
+
+ <a class="chip" href="/blog/topics/guides/">guides<span class="ct">6</span></a>
+
+ <a class="chip" href="/blog/topics/internals/">internals<span class="ct">5</span></a>
+
+ <a class="chip" href="/blog/topics/concepts/">concepts<span class="ct">4</span></a>
+
+ <a class="chip" href="/blog/topics/orchestration/">orchestration<span class="ct">4</span></a>
+
+ <a class="chip" href="/blog/topics/use-cases/">use-cases<span class="ct">3</span></a>
+
+ <a class="chip" href="/blog/topics/memory/">memory<span class="ct">2</span></a>
+
+ <a class="chip" href="/blog/topics/story/" aria-current="page">story<span class="ct">1</span></a>
+
+ </div>
+</header>
+
+<section class="wrap">
+ <div class="post-grid">
+ <article class="card">
+ <a class="thumb t-story" href="/blog/why-we-built-munder-difflin/" aria-hidden="true" tabindex="-1">
+ <span>STORY</span>
+ </a>
+ <div class="body">
+ <div class="meta">
+ <time datetime="2026-06-02">Jun 2, 2026</time>
+ <span class="dot" aria-hidden="true"></span>
+ <span>3 min</span>
+ </div>
+ <h3><a href="/blog/why-we-built-munder-difflin/">Why We Built Munder Difflin</a></h3>
+ <p class="dek">The origin story of Munder Difflin — how the pain of juggling Claude Code terminals led to a coordinated, memory-backed hive of agents you can watch.</p>
+ <div class="foot">
+ <span class="tag kind">Story</span>
+ <a class="more" href="/blog/why-we-built-munder-difflin/" aria-label="Read: Why We Built Munder Difflin">Read →</a>
+ </div>
+ </div>
+</article>
+
+ </div>
+</section>
+
+
+</main>
+<footer>
+ <div class="wrap">
+ <div class="foot-top">
+ <a class="foot-brand brand" href="/blog/">
+ <span class="brand-mark">MD</span>
+ <span class="brand-word">MUNDER DIFFLIN<span class="sep">/</span><span class="blog">BLOG</span></span>
+ </a>
+ <div class="foot-links">
+ <a href="/blog/">Latest</a>
+ <a href="/blog/topics/">Topics</a>
+ <a href="/blog/about/">About</a>
+ <a href="https://munderdiffl.in/blog/feed.xml">RSS</a>
+ <a href="https://github.com/chaitanyagiri/munder-difflin">GitHub</a>
+ <a href="https://munderdiffl.in">munderdiffl.in ↗</a>
+ </div>
+ </div>
+ <div class="foot-meta">
+ © 2026 Munder Difflin · Local-first · MIT-licensed ·
+ Built on <a href="https://munderdiffl.in">Electron, React, Pixi.js, xterm.js &amp; node-pty</a>.
+ Run an office of agents while you sleep.
+ </div>
+ </div>
+</footer>
+
+<script>
+ // sticky-nav border on scroll
+ (function () {
+ var nav = document.getElementById('nav');
+ if (!nav) return;
+ var onScroll = function () { nav.classList.toggle('scrolled', window.scrollY > 8); };
+ onScroll(); window.addEventListener('scroll', onScroll, { passive: true });
+ })();
+</script>
+
+</body>
+</html>
diff --git a/docs/blog/topics/use-cases/index.html b/docs/blog/topics/use-cases/index.html
new file mode 100644
index 00000000..c28133bc
--- /dev/null
+++ b/docs/blog/topics/use-cases/index.html
@@ -0,0 +1,187 @@
+<!doctype html>
+<html lang="en">
+<head>
+<meta charset="UTF-8" />
+<meta name="viewport" content="width=device-width, initial-scale=1.0" />
+<title>use-cases — Munder Difflin Blog</title>
+<meta name="description" content="Munder Difflin blog posts on use-cases — agentic coding with Claude Code, the hive, GOD orchestrator, and long-term memory." />
+<link rel="canonical" href="https://munderdiffl.in/blog/topics/use-cases/" />
+
+<link rel="icon" type="image/png" href="https://munderdiffl.in/logo.png" />
+<link rel="apple-touch-icon" href="https://munderdiffl.in/logo.png" />
+<meta name="theme-color" content="#F5F2E8" />
+
+<!-- Open Graph -->
+<meta property="og:site_name" content="Munder Difflin Blog" />
+<meta property="og:type" content="website" />
+<meta property="og:title" content="use-cases — Munder Difflin Blog" />
+<meta property="og:description" content="Munder Difflin blog posts on use-cases — agentic coding with Claude Code, the hive, GOD orchestrator, and long-term memory." />
+<meta property="og:url" content="https://munderdiffl.in/blog/topics/use-cases/" />
+<meta property="og:image" content="https://munderdiffl.in/media/og.png" />
+<meta property="og:locale" content="en_US" />
+
+
+<!-- Twitter -->
+<meta name="twitter:card" content="summary_large_image" />
+<meta name="twitter:title" content="use-cases — Munder Difflin Blog" />
+<meta name="twitter:description" content="Munder Difflin blog posts on use-cases — agentic coding with Claude Code, the hive, GOD orchestrator, and long-term memory." />
+<meta name="twitter:image" content="https://munderdiffl.in/media/og.png" />
+
+<link rel="alternate" type="application/atom+xml" title="Munder Difflin Blog" href="https://munderdiffl.in/blog/feed.xml" />
+<link rel="preconnect" href="https://fonts.googleapis.com" />
+<link rel="preconnect" href="https://fonts.gstatic.com" crossorigin />
+<link href="https://fonts.googleapis.com/css2?family=Geist:wght@400;500;600&family=JetBrains+Mono:wght@400;500;600;700&display=swap" rel="stylesheet" />
+<link rel="stylesheet" href="/blog/assets/blog.css" />
+
+</head>
+<body>
+<a class="skip-link" href="#main">Skip to content</a>
+<nav id="nav">
+ <a class="brand" href="/blog/" aria-label="Munder Difflin Blog home">
+ <span class="brand-mark">MD</span>
+ <span class="brand-word">MUNDER DIFFLIN<span class="sep">/</span><span class="blog">BLOG</span></span>
+ </a>
+ <span class="spacer"></span>
+ <div class="links">
+ <a href="/blog/">Latest</a>
+ <a href="/blog/topics/" aria-current="page">Topics</a>
+ <a href="/blog/about/">About</a>
+ <a href="https://munderdiffl.in">↗ Product</a>
+ </div>
+ <div class="nav-actions">
+ <a class="btn sm" href="https://munderdiffl.in/blog/feed.xml" aria-label="RSS feed">⤵ RSS</a>
+ <a class="btn sm primary" href="https://munderdiffl.in/#install">⤓ Download</a>
+ </div>
+</nav>
+
+<main id="main">
+
+<header class="page-head wrap">
+ <nav class="crumbs" aria-label="Breadcrumb" style="font-family:var(--font-mono);font-size:12px;color:var(--ink-faint);display:flex;gap:8px;">
+ <a href="/blog/" style="color:var(--ink-dim)">Blog</a><span>/</span>
+ <a href="/blog/topics/" style="color:var(--ink-dim)">Topics</a>
+ </nav>
+ <p class="eyebrow">Topic</p>
+ <h1>use-cases</h1>
+ <p class="lead">3 posts in this cluster.</p>
+
+ <div class="filters" role="navigation" aria-label="Topics">
+ <a class="chip" href="/blog/">All</a>
+
+ <a class="chip" href="/blog/topics/comparisons/">comparisons<span class="ct">8</span></a>
+
+ <a class="chip" href="/blog/topics/guides/">guides<span class="ct">6</span></a>
+
+ <a class="chip" href="/blog/topics/internals/">internals<span class="ct">5</span></a>
+
+ <a class="chip" href="/blog/topics/concepts/">concepts<span class="ct">4</span></a>
+
+ <a class="chip" href="/blog/topics/orchestration/">orchestration<span class="ct">4</span></a>
+
+ <a class="chip" href="/blog/topics/use-cases/" aria-current="page">use-cases<span class="ct">3</span></a>
+
+ <a class="chip" href="/blog/topics/memory/">memory<span class="ct">2</span></a>
+
+ <a class="chip" href="/blog/topics/story/">story<span class="ct">1</span></a>
+
+ </div>
+</header>
+
+<section class="wrap">
+ <div class="post-grid">
+ <article class="card">
+ <a class="thumb t-use-cases" href="/blog/from-one-terminal-to-a-team/" aria-hidden="true" tabindex="-1">
+ <span>USE CASES</span>
+ </a>
+ <div class="body">
+ <div class="meta">
+ <time datetime="2026-06-02">Jun 2, 2026</time>
+ <span class="dot" aria-hidden="true"></span>
+ <span>3 min</span>
+ </div>
+ <h3><a href="/blog/from-one-terminal-to-a-team/">From One Terminal to a Team: Scaling Your Claude Code Workflow</a></h3>
+ <p class="dek">The workflow shift from a single Claude Code session to a coordinated team of agents — what changes, where it breaks, and the concrete before-and-after.</p>
+ <div class="foot">
+ <span class="tag kind">Use Cases</span>
+ <a class="more" href="/blog/from-one-terminal-to-a-team/" aria-label="Read: From One Terminal to a Team: Scaling Your Claude Code Workflow">Read →</a>
+ </div>
+ </div>
+</article>
+<article class="card">
+ <a class="thumb t-use-cases" href="/blog/run-an-office-of-ai-agents/" aria-hidden="true" tabindex="-1">
+ <span>USE CASES</span>
+ </a>
+ <div class="body">
+ <div class="meta">
+ <time datetime="2026-06-02">Jun 2, 2026</time>
+ <span class="dot" aria-hidden="true"></span>
+ <span>3 min</span>
+ </div>
+ <h3><a href="/blog/run-an-office-of-ai-agents/">Run an Office of AI Agents While You Sleep</a></h3>
+ <p class="dek">What it takes to run a self-coordinating office of AI coding agents that keeps shipping after you log off — and the guardrails that keep it sane.</p>
+ <div class="foot">
+ <span class="tag kind">Use Cases</span>
+ <a class="more" href="/blog/run-an-office-of-ai-agents/" aria-label="Read: Run an Office of AI Agents While You Sleep">Read →</a>
+ </div>
+ </div>
+</article>
+<article class="card">
+ <a class="thumb t-use-cases" href="/blog/why-local-first-matters-for-ai-agents/" aria-hidden="true" tabindex="-1">
+ <span>USE CASES</span>
+ </a>
+ <div class="body">
+ <div class="meta">
+ <time datetime="2026-06-02">Jun 2, 2026</time>
+ <span class="dot" aria-hidden="true"></span>
+ <span>3 min</span>
+ </div>
+ <h3><a href="/blog/why-local-first-matters-for-ai-agents/">Why Local-First Matters for Your AI Agents</a></h3>
+ <p class="dek">The control, privacy, and cost case for keeping your AI agents and their memory on your own machine — and what cloud orchestration quietly costs.</p>
+ <div class="foot">
+ <span class="tag kind">Use Cases</span>
+ <a class="more" href="/blog/why-local-first-matters-for-ai-agents/" aria-label="Read: Why Local-First Matters for Your AI Agents">Read →</a>
+ </div>
+ </div>
+</article>
+
+ </div>
+</section>
+
+
+</main>
+<footer>
+ <div class="wrap">
+ <div class="foot-top">
+ <a class="foot-brand brand" href="/blog/">
+ <span class="brand-mark">MD</span>
+ <span class="brand-word">MUNDER DIFFLIN<span class="sep">/</span><span class="blog">BLOG</span></span>
+ </a>
+ <div class="foot-links">
+ <a href="/blog/">Latest</a>
+ <a href="/blog/topics/">Topics</a>
+ <a href="/blog/about/">About</a>
+ <a href="https://munderdiffl.in/blog/feed.xml">RSS</a>
+ <a href="https://github.com/chaitanyagiri/munder-difflin">GitHub</a>
+ <a href="https://munderdiffl.in">munderdiffl.in ↗</a>
+ </div>
+ </div>
+ <div class="foot-meta">
+ © 2026 Munder Difflin · Local-first · MIT-licensed ·
+ Built on <a href="https://munderdiffl.in">Electron, React, Pixi.js, xterm.js &amp; node-pty</a>.
+ Run an office of agents while you sleep.
+ </div>
+ </div>
+</footer>
+
+<script>
+ // sticky-nav border on scroll
+ (function () {
+ var nav = document.getElementById('nav');
+ if (!nav) return;
+ var onScroll = function () { nav.classList.toggle('scrolled', window.scrollY > 8); };
+ onScroll(); window.addEventListener('scroll', onScroll, { passive: true });
+ })();
+</script>
+
+</body>
+</html>
diff --git a/docs/blog/vibe-kanban-alternative/index.html b/docs/blog/vibe-kanban-alternative/index.html
new file mode 100644
index 00000000..6abd49b3
--- /dev/null
+++ b/docs/blog/vibe-kanban-alternative/index.html
@@ -0,0 +1,317 @@
+<!doctype html>
+<html lang="en">
+<head>
+<meta charset="UTF-8" />
+<meta name="viewport" content="width=device-width, initial-scale=1.0" />
+<title>A vibe-kanban Alternative for Coordinating AI Agents — Munder Difflin Blog</title>
+<meta name="description" content="vibe-kanban gives you a board to assign tasks to coding agents. When a self-routing hive is the better vibe-kanban alternative — and when a board wins." />
+<link rel="canonical" href="https://munderdiffl.in/blog/vibe-kanban-alternative/" />
+
+<link rel="icon" type="image/png" href="https://munderdiffl.in/logo.png" />
+<link rel="apple-touch-icon" href="https://munderdiffl.in/logo.png" />
+<meta name="theme-color" content="#F5F2E8" />
+
+<!-- Open Graph -->
+<meta property="og:site_name" content="Munder Difflin Blog" />
+<meta property="og:type" content="article" />
+<meta property="og:title" content="A vibe-kanban Alternative for Coordinating AI Agents — Munder Difflin Blog" />
+<meta property="og:description" content="vibe-kanban gives you a board to assign tasks to coding agents. When a self-routing hive is the better vibe-kanban alternative — and when a board wins." />
+<meta property="og:url" content="https://munderdiffl.in/blog/vibe-kanban-alternative/" />
+<meta property="og:image" content="https://munderdiffl.in/media/og.png" />
+<meta property="og:locale" content="en_US" />
+<meta property="article:published_time" content="2026-06-03T00:00:00.000Z" />
+<meta property="article:author" content="Chaitanya Giri" />
+<meta property="article:tag" content="Comparisons" />
+<meta property="article:tag" content="Orchestration" />
+<meta property="article:tag" content="Multi-Agent" />
+<meta property="article:tag" content="Tools" />
+
+
+<!-- Twitter -->
+<meta name="twitter:card" content="summary_large_image" />
+<meta name="twitter:title" content="A vibe-kanban Alternative for Coordinating AI Agents — Munder Difflin Blog" />
+<meta name="twitter:description" content="vibe-kanban gives you a board to assign tasks to coding agents. When a self-routing hive is the better vibe-kanban alternative — and when a board wins." />
+<meta name="twitter:image" content="https://munderdiffl.in/media/og.png" />
+
+<link rel="alternate" type="application/atom+xml" title="Munder Difflin Blog" href="https://munderdiffl.in/blog/feed.xml" />
+<link rel="preconnect" href="https://fonts.googleapis.com" />
+<link rel="preconnect" href="https://fonts.gstatic.com" crossorigin />
+<link href="https://fonts.googleapis.com/css2?family=Geist:wght@400;500;600&family=JetBrains+Mono:wght@400;500;600;700&display=swap" rel="stylesheet" />
+<link rel="stylesheet" href="/blog/assets/blog.css" />
+
+<script type="application/ld+json">
+{
+ "@context": "https://schema.org",
+ "@type": "BlogPosting",
+ "headline": "A vibe-kanban Alternative for Coordinating AI Agents",
+ "description": "vibe-kanban gives you a board to assign tasks to coding agents. When a self-routing hive is the better vibe-kanban alternative — and when a board wins.",
+ "image": ["https://munderdiffl.in/media/og.png"],
+ "datePublished": "2026-06-03T00:00:00.000Z",
+ "dateModified": "2026-06-03T00:00:00.000Z",
+ "author": { "@type": "Person", "name": "Chaitanya Giri" },
+ "publisher": {
+ "@type": "Organization",
+ "name": "Munder Difflin",
+ "logo": { "@type": "ImageObject", "url": "https://munderdiffl.in/logo.png" }
+ },
+ "mainEntityOfPage": { "@type": "WebPage", "@id": "https://munderdiffl.in/blog/vibe-kanban-alternative/" },
+ "keywords": "vibe kanban alternative, vibe kanban alternative, ai agent task board, agentic coding tools",
+ "articleSection": "Comparisons",
+ "inLanguage": "en-US",
+ "url": "https://munderdiffl.in/blog/vibe-kanban-alternative/"
+}
+</script>
+<script type="application/ld+json">
+{
+ "@context": "https://schema.org",
+ "@type": "BreadcrumbList",
+ "itemListElement": [
+ { "@type": "ListItem", "position": 1, "name": "Home", "item": "https://munderdiffl.in/" },
+ { "@type": "ListItem", "position": 2, "name": "Blog", "item": "https://munderdiffl.in/blog/" },
+ { "@type": "ListItem", "position": 3, "name": "A vibe-kanban Alternative for Coordinating AI Agents", "item": "https://munderdiffl.in/blog/vibe-kanban-alternative/" }
+ ]
+}
+</script>
+
+
+</head>
+<body>
+<a class="skip-link" href="#main">Skip to content</a>
+<nav id="nav">
+ <a class="brand" href="/blog/" aria-label="Munder Difflin Blog home">
+ <span class="brand-mark">MD</span>
+ <span class="brand-word">MUNDER DIFFLIN<span class="sep">/</span><span class="blog">BLOG</span></span>
+ </a>
+ <span class="spacer"></span>
+ <div class="links">
+ <a href="/blog/">Latest</a>
+ <a href="/blog/topics/">Topics</a>
+ <a href="/blog/about/">About</a>
+ <a href="https://munderdiffl.in">↗ Product</a>
+ </div>
+ <div class="nav-actions">
+ <a class="btn sm" href="https://munderdiffl.in/blog/feed.xml" aria-label="RSS feed">⤵ RSS</a>
+ <a class="btn sm primary" href="https://munderdiffl.in/#install">⤓ Download</a>
+ </div>
+</nav>
+
+<main id="main">
+
+<article>
+ <header class="post-head wrap">
+ <nav class="crumbs" aria-label="Breadcrumb">
+ <a href="/blog/">Blog</a>
+ <span>/</span>
+ <a href="/blog/topics/comparisons/">Comparisons</a>
+ </nav>
+ <h1>A vibe-kanban Alternative for Coordinating AI Agents</h1>
+ <p class="dek">vibe-kanban gives you a board to assign tasks to coding agents. When a self-routing hive is the better vibe-kanban alternative — and when a board wins.</p>
+ <div class="byline">
+ <span class="av" aria-hidden="true">CG</span>
+ <strong>Chaitanya Giri</strong>
+ <span class="dot" aria-hidden="true">·</span>
+ <time datetime="2026-06-03">Jun 3, 2026</time>
+ <span class="dot" aria-hidden="true">·</span>
+ <span>3 min read</span>
+ <span class="tag kind">Comparisons</span>
+ </div>
+ </header>
+
+ <div class="post-wrap wrap">
+ <div class="prose">
+ <div class="callout tldr"><span class="ic">TL;DR</span><p><strong>vibe-kanban</strong> is a kanban
+board for AI coding agents: you create tasks as cards, assign them to agents, and move work through
+columns. A <strong>vibe-kanban alternative</strong> makes sense when you'd rather <em>not</em> drive
+the board yourself — when you want an orchestrator that decomposes your intent and routes work, plus
+agents that share memory and message each other. Board vs. self-routing hive: pick by who you want
+doing the routing.</p></div>
+<p><a href="https://github.com/BloopAI/vibe-kanban">vibe-kanban</a> is a clever reframing of agentic coding: treat
+your agents like a team with a backlog. Before the alternative, here’s what it does well — because the
+board model is genuinely good for some workflows.</p>
+<h2 id="what-vibe-kanban-does-well" tabindex="-1">What vibe-kanban does well <a class="anchor" href="#what-vibe-kanban-does-well" aria-hidden="true">#</a></h2>
+<p>vibe-kanban is an open-source kanban board for orchestrating AI coding agents. It’s agent-agnostic
+(Claude Code, Gemini, Codex, and others), and you work the way you’d work any board: create tasks as
+cards, assign them to agents, and move them through columns from to-do to in-progress to review.</p>
+<ul>
+<li><strong>The board is a legible mental model.</strong> Everyone understands kanban. The state of all work is
+visible in one view.</li>
+<li><strong>It’s agent-agnostic.</strong> Mix and match the coding agents you already use.</li>
+<li><strong>Review is built into the flow.</strong> Cards move to a review column so you approve outputs before they
+land.</li>
+</ul>
+<p>If you think in tasks and want a project-management surface over your agents, vibe-kanban fits
+naturally. The reason to look elsewhere is about <em>who does the routing</em>.</p>
+<h2 id="where-a-board-leaves-the-work-to-you" tabindex="-1">Where a board leaves the work to you <a class="anchor" href="#where-a-board-leaves-the-work-to-you" aria-hidden="true">#</a></h2>
+<p>A kanban board is something a human drives. That’s its strength and its ceiling:</p>
+<h3 id="you-are-the-router" tabindex="-1">You are the router <a class="anchor" href="#you-are-the-router" aria-hidden="true">#</a></h3>
+<p>Cards don’t move themselves. <em>You</em> decompose the goal into tasks, decide which agent gets which card,
+and shuffle the board. For a tidy backlog that’s fine; for fluid, branching work it becomes the
+bottleneck — the <a href="/blog/from-one-terminal-to-a-team/">coordination overhead</a> you were trying to escape.</p>
+<h3 id="cards-dont-carry-shared-memory" tabindex="-1">Cards don’t carry shared memory <a class="anchor" href="#cards-dont-carry-shared-memory" aria-hidden="true">#</a></h3>
+<p>A card is a task, not a brain. Agents working different cards don’t pool what they learn; there’s no
+shared <a href="/blog/give-claude-code-long-term-memory/">long-term memory</a> across the board, so context
+doesn’t compound.</p>
+<h3 id="agents-dont-message-each-other" tabindex="-1">Agents don’t message each other <a class="anchor" href="#agents-dont-message-each-other" aria-hidden="true">#</a></h3>
+<p>Coordination between cards goes through you and the board, not agent-to-agent. There’s no mailbox for
+one agent to hand a finding directly to another.</p>
+<h2 id="what-a-self-routing-hive-does-instead" tabindex="-1">What a self-routing hive does instead <a class="anchor" href="#what-a-self-routing-hive-does-instead" aria-hidden="true">#</a></h2>
+<p>The alternative flips the model: instead of <em>you</em> working a board, you describe intent and the system
+routes the work.</p>
+<ul>
+<li><strong>An orchestrator decomposes and assigns.</strong> A <a href="/#how">GOD agent</a> you talk to in plain language
+breaks your goal into tasks and routes them to the right agents — the board management happens for
+you.</li>
+<li><strong>Shared memory.</strong> Every agent reads and writes a <a href="/#how">semantic memory layer</a> (MemPalace), so
+the team’s knowledge accrues instead of living in disconnected cards.</li>
+<li><strong>Direct messaging.</strong> Agents hand work and findings to each other through mailboxes.</li>
+<li><strong>Visibility without manual upkeep.</strong> You watch a live office floor rather than maintaining columns
+— the state is observed, not curated.</li>
+</ul>
+<p>That’s <a href="/#what">Munder Difflin</a>: a <a href="/#what">multi-agent harness</a> built around an orchestrator, shared
+memory, and messaging, visualized as a watchable floor. Open source (MIT), local-first, on macOS,
+Windows, and Linux.</p>
+<h2 id="board-or-hive-how-to-choose" tabindex="-1">Board or hive? How to choose <a class="anchor" href="#board-or-hive-how-to-choose" aria-hidden="true">#</a></h2>
+<ul>
+<li><strong>Keep vibe-kanban</strong> if you <em>want</em> a board — explicit tasks, manual assignment, a column-based
+review gate, and an agent-agnostic queue.</li>
+<li><strong>Choose a hive</strong> if you’d rather describe a goal and have it routed for you, with agents that
+remember and talk to each other.</li>
+</ul>
+<p>It’s not that one is better — they answer different questions. For the full field, see <a href="/blog/best-claude-code-multi-agent-tools/">the best
+tools to run multiple Claude Code agents</a> and the
+criteria-based <a href="/blog/claude-code-orchestration-tools-compared/">orchestration tools comparison</a>.</p>
+<hr>
+<blockquote>
+<p>The landscape changes quickly — check vibe-kanban’s repo for current features. We’ve described it
+on its own terms; Munder Difflin is our own project.</p>
+</blockquote>
+<p>If you’d rather orchestrate than administrate, <a href="/#install">download Munder Difflin</a> and let the
+routing happen for you — free and open source.</p>
+
+
+
+
+
+ <hr />
+ <div class="share">
+ <span class="lbl">Tags</span>
+ <a class="tag" href="/blog/tags/comparisons/">Comparisons</a><a class="tag" href="/blog/tags/orchestration/">Orchestration</a><a class="tag" href="/blog/tags/multi-agent/">Multi-Agent</a><a class="tag" href="/blog/tags/tools/">Tools</a>
+ </div>
+
+ </div>
+
+
+ <aside class="toc-rail" aria-label="Table of contents">
+ <div class="tt">On this page</div>
+ <ol>
+ <li class="lvl-2"><a href="#what-vibe-kanban-does-well">What vibe-kanban does well</a></li><li class="lvl-2"><a href="#where-a-board-leaves-the-work-to-you">Where a board leaves the work to you</a></li><li class="lvl-3"><a href="#you-are-the-router">You are the router</a></li><li class="lvl-3"><a href="#cards-dont-carry-shared-memory">Cards don’t carry shared memory</a></li><li class="lvl-3"><a href="#agents-dont-message-each-other">Agents don’t message each other</a></li><li class="lvl-2"><a href="#what-a-self-routing-hive-does-instead">What a self-routing hive does instead</a></li><li class="lvl-2"><a href="#board-or-hive-how-to-choose">Board or hive? How to choose</a></li>
+ </ol>
+ </aside>
+
+ </div>
+
+ <footer class="post-foot wrap"><div class="prevnext">
+ <a class="pn prev" href="/blog/ai-agent-glossary/"><span class="k">← Older</span><span class="t">The AI Coding Agent Glossary: Harness, Orchestrator, Hive, Subagent</span></a>
+ <a class="pn next" href="/blog/node-pty-electron-real-terminals/"><span class="k">Newer →</span><span class="t">Real Terminals in Electron with node-pty</span></a>
+ </div>
+ <section class="related">
+ <h2>Related in Comparisons</h2>
+ <div class="post-grid">
+ <article class="card">
+ <a class="thumb t-comparisons" href="/blog/best-claude-code-multi-agent-tools/" aria-hidden="true" tabindex="-1">
+ <span>COMPARISONS</span>
+ </a>
+ <div class="body">
+ <div class="meta">
+ <time datetime="2026-06-04">Jun 4, 2026</time>
+ <span class="dot" aria-hidden="true"></span>
+ <span>6 min</span>
+ </div>
+ <h3><a href="/blog/best-claude-code-multi-agent-tools/">The Best Tools to Run Multiple Claude Code Agents (2026)</a></h3>
+ <p class="dek">An honest 2026 roundup of tools to run multiple Claude Code agents — Claude Squad, Conductor, Crystal, vibe-kanban, and Munder Difflin — compared.</p>
+ <div class="foot">
+ <span class="tag kind">Comparisons</span>
+ <a class="more" href="/blog/best-claude-code-multi-agent-tools/" aria-label="Read: The Best Tools to Run Multiple Claude Code Agents (2026)">Read →</a>
+ </div>
+ </div>
+</article>
+<article class="card">
+ <a class="thumb t-comparisons" href="/blog/claude-code-orchestration-tools-compared/" aria-hidden="true" tabindex="-1">
+ <span>COMPARISONS</span>
+ </a>
+ <div class="body">
+ <div class="meta">
+ <time datetime="2026-06-04">Jun 4, 2026</time>
+ <span class="dot" aria-hidden="true"></span>
+ <span>3 min</span>
+ </div>
+ <h3><a href="/blog/claude-code-orchestration-tools-compared/">Claude Code Orchestration Tools, Compared</a></h3>
+ <p class="dek">Claude Code orchestration tools compared on memory, messaging, visibility, control, and local-first — across Claude Squad, Conductor, Crystal, and more.</p>
+ <div class="foot">
+ <span class="tag kind">Comparisons</span>
+ <a class="more" href="/blog/claude-code-orchestration-tools-compared/" aria-label="Read: Claude Code Orchestration Tools, Compared">Read →</a>
+ </div>
+ </div>
+</article>
+<article class="card">
+ <a class="thumb t-comparisons" href="/blog/claude-squad-vs-munder-difflin/" aria-hidden="true" tabindex="-1">
+ <span>COMPARISONS</span>
+ </a>
+ <div class="body">
+ <div class="meta">
+ <time datetime="2026-06-04">Jun 4, 2026</time>
+ <span class="dot" aria-hidden="true"></span>
+ <span>3 min</span>
+ </div>
+ <h3><a href="/blog/claude-squad-vs-munder-difflin/">Claude Squad vs Munder Difflin: Which Should You Use?</a></h3>
+ <p class="dek">Claude Squad vs Munder Difflin: a lean terminal session manager against a memory-backed, orchestrated, visual hive. Feature table and an honest verdict.</p>
+ <div class="foot">
+ <span class="tag kind">Comparisons</span>
+ <a class="more" href="/blog/claude-squad-vs-munder-difflin/" aria-label="Read: Claude Squad vs Munder Difflin: Which Should You Use?">Read →</a>
+ </div>
+ </div>
+</article>
+
+ </div>
+ </section>
+
+ </footer>
+</article>
+
+</main>
+<footer>
+ <div class="wrap">
+ <div class="foot-top">
+ <a class="foot-brand brand" href="/blog/">
+ <span class="brand-mark">MD</span>
+ <span class="brand-word">MUNDER DIFFLIN<span class="sep">/</span><span class="blog">BLOG</span></span>
+ </a>
+ <div class="foot-links">
+ <a href="/blog/">Latest</a>
+ <a href="/blog/topics/">Topics</a>
+ <a href="/blog/about/">About</a>
+ <a href="https://munderdiffl.in/blog/feed.xml">RSS</a>
+ <a href="https://github.com/chaitanyagiri/munder-difflin">GitHub</a>
+ <a href="https://munderdiffl.in">munderdiffl.in ↗</a>
+ </div>
+ </div>
+ <div class="foot-meta">
+ © 2026 Munder Difflin · Local-first · MIT-licensed ·
+ Built on <a href="https://munderdiffl.in">Electron, React, Pixi.js, xterm.js &amp; node-pty</a>.
+ Run an office of agents while you sleep.
+ </div>
+ </div>
+</footer>
+
+<script>
+ // sticky-nav border on scroll
+ (function () {
+ var nav = document.getElementById('nav');
+ if (!nav) return;
+ var onScroll = function () { nav.classList.toggle('scrolled', window.scrollY > 8); };
+ onScroll(); window.addEventListener('scroll', onScroll, { passive: true });
+ })();
+</script>
+
+</body>
+</html>
diff --git a/docs/blog/what-are-claude-code-agents/index.html b/docs/blog/what-are-claude-code-agents/index.html
new file mode 100644
index 00000000..62042997
--- /dev/null
+++ b/docs/blog/what-are-claude-code-agents/index.html
@@ -0,0 +1,346 @@
+<!doctype html>
+<html lang="en">
+<head>
+<meta charset="UTF-8" />
+<meta name="viewport" content="width=device-width, initial-scale=1.0" />
+<title>What Are Claude Code Agents? And How to Use Many at Once — Munder Difflin Blog</title>
+<meta name="description" content="Claude Code agents explained in plain English — what an agent actually is, how subagents differ, and the leap from one agent to a coordinated team." />
+<link rel="canonical" href="https://munderdiffl.in/blog/what-are-claude-code-agents/" />
+
+<link rel="icon" type="image/png" href="https://munderdiffl.in/logo.png" />
+<link rel="apple-touch-icon" href="https://munderdiffl.in/logo.png" />
+<meta name="theme-color" content="#F5F2E8" />
+
+<!-- Open Graph -->
+<meta property="og:site_name" content="Munder Difflin Blog" />
+<meta property="og:type" content="article" />
+<meta property="og:title" content="What Are Claude Code Agents? And How to Use Many at Once — Munder Difflin Blog" />
+<meta property="og:description" content="Claude Code agents explained in plain English — what an agent actually is, how subagents differ, and the leap from one agent to a coordinated team." />
+<meta property="og:url" content="https://munderdiffl.in/blog/what-are-claude-code-agents/" />
+<meta property="og:image" content="https://munderdiffl.in/media/og.png" />
+<meta property="og:locale" content="en_US" />
+<meta property="article:published_time" content="2026-06-02T00:00:00.000Z" />
+<meta property="article:author" content="Chaitanya Giri" />
+<meta property="article:tag" content="Concepts" />
+<meta property="article:tag" content="Multi-Agent" />
+<meta property="article:tag" content="Claude Code" />
+<meta property="article:tag" content="Getting Started" />
+
+
+<!-- Twitter -->
+<meta name="twitter:card" content="summary_large_image" />
+<meta name="twitter:title" content="What Are Claude Code Agents? And How to Use Many at Once — Munder Difflin Blog" />
+<meta name="twitter:description" content="Claude Code agents explained in plain English — what an agent actually is, how subagents differ, and the leap from one agent to a coordinated team." />
+<meta name="twitter:image" content="https://munderdiffl.in/media/og.png" />
+
+<link rel="alternate" type="application/atom+xml" title="Munder Difflin Blog" href="https://munderdiffl.in/blog/feed.xml" />
+<link rel="preconnect" href="https://fonts.googleapis.com" />
+<link rel="preconnect" href="https://fonts.gstatic.com" crossorigin />
+<link href="https://fonts.googleapis.com/css2?family=Geist:wght@400;500;600&family=JetBrains+Mono:wght@400;500;600;700&display=swap" rel="stylesheet" />
+<link rel="stylesheet" href="/blog/assets/blog.css" />
+
+<script type="application/ld+json">
+{
+ "@context": "https://schema.org",
+ "@type": "BlogPosting",
+ "headline": "What Are Claude Code Agents? And How to Use Many at Once",
+ "description": "Claude Code agents explained in plain English — what an agent actually is, how subagents differ, and the leap from one agent to a coordinated team.",
+ "image": ["https://munderdiffl.in/media/og.png"],
+ "datePublished": "2026-06-02T00:00:00.000Z",
+ "dateModified": "2026-06-02T00:00:00.000Z",
+ "author": { "@type": "Person", "name": "Chaitanya Giri" },
+ "publisher": {
+ "@type": "Organization",
+ "name": "Munder Difflin",
+ "logo": { "@type": "ImageObject", "url": "https://munderdiffl.in/logo.png" }
+ },
+ "mainEntityOfPage": { "@type": "WebPage", "@id": "https://munderdiffl.in/blog/what-are-claude-code-agents/" },
+ "keywords": "claude code agents, claude code agents, claude code subagents, ai coding agents",
+ "articleSection": "Concepts",
+ "inLanguage": "en-US",
+ "url": "https://munderdiffl.in/blog/what-are-claude-code-agents/"
+}
+</script>
+<script type="application/ld+json">
+{
+ "@context": "https://schema.org",
+ "@type": "BreadcrumbList",
+ "itemListElement": [
+ { "@type": "ListItem", "position": 1, "name": "Home", "item": "https://munderdiffl.in/" },
+ { "@type": "ListItem", "position": 2, "name": "Blog", "item": "https://munderdiffl.in/blog/" },
+ { "@type": "ListItem", "position": 3, "name": "What Are Claude Code Agents? And How to Use Many at Once", "item": "https://munderdiffl.in/blog/what-are-claude-code-agents/" }
+ ]
+}
+</script>
+
+<script type="application/ld+json">
+{
+ "@context": "https://schema.org",
+ "@type": "FAQPage",
+ "mainEntity": [
+ { "@type": "Question", "name": "What are Claude Code agents?", "acceptedAnswer": { "@type": "Answer", "text": "A Claude Code agent is a running Claude session with a goal and a set of tools — it can read and edit files, run commands, and work toward a task in a loop. Each terminal you start a Claude session in is an agent." } },
+ { "@type": "Question", "name": "What's the difference between an agent and a subagent in Claude Code?", "acceptedAnswer": { "@type": "Answer", "text": "An agent is a top-level session you drive. A subagent is a helper the main agent spawns inside its own run to fan out a piece of work — short-lived and scoped to that parent. Subagents are great for parallel sub-tasks but don't persist or share memory across your whole workflow." } },
+ { "@type": "Question", "name": "How do I use multiple Claude Code agents at once?", "acceptedAnswer": { "@type": "Answer", "text": "Open several sessions, give each a clear role, and coordinate them — ideally with shared memory and messaging so they don't collide or forget. A multi-agent harness like Munder Difflin automates that coordination so the sessions act as one team." } }
+
+ ]
+}
+</script>
+
+
+</head>
+<body>
+<a class="skip-link" href="#main">Skip to content</a>
+<nav id="nav">
+ <a class="brand" href="/blog/" aria-label="Munder Difflin Blog home">
+ <span class="brand-mark">MD</span>
+ <span class="brand-word">MUNDER DIFFLIN<span class="sep">/</span><span class="blog">BLOG</span></span>
+ </a>
+ <span class="spacer"></span>
+ <div class="links">
+ <a href="/blog/">Latest</a>
+ <a href="/blog/topics/">Topics</a>
+ <a href="/blog/about/">About</a>
+ <a href="https://munderdiffl.in">↗ Product</a>
+ </div>
+ <div class="nav-actions">
+ <a class="btn sm" href="https://munderdiffl.in/blog/feed.xml" aria-label="RSS feed">⤵ RSS</a>
+ <a class="btn sm primary" href="https://munderdiffl.in/#install">⤓ Download</a>
+ </div>
+</nav>
+
+<main id="main">
+
+<article>
+ <header class="post-head wrap">
+ <nav class="crumbs" aria-label="Breadcrumb">
+ <a href="/blog/">Blog</a>
+ <span>/</span>
+ <a href="/blog/topics/concepts/">Concepts</a>
+ </nav>
+ <h1>What Are Claude Code Agents? And How to Use Many at Once</h1>
+ <p class="dek">Claude Code agents explained in plain English — what an agent actually is, how subagents differ, and the leap from one agent to a coordinated team.</p>
+ <div class="byline">
+ <span class="av" aria-hidden="true">CG</span>
+ <strong>Chaitanya Giri</strong>
+ <span class="dot" aria-hidden="true">·</span>
+ <time datetime="2026-06-02">Jun 2, 2026</time>
+ <span class="dot" aria-hidden="true">·</span>
+ <span>3 min read</span>
+ <span class="tag kind">Concepts</span>
+ </div>
+ </header>
+
+ <div class="post-wrap wrap">
+ <div class="prose">
+ <div class="callout tldr"><span class="ic">TL;DR</span><p>A <strong>Claude Code agent</strong> is a
+running Claude session with a goal and tools — it reads files, edits code, and runs commands in a
+loop. <strong>Subagents</strong> are short-lived helpers an agent spawns for fan-out. The real leap
+isn't more agents; it's getting several to act as a <strong>coordinated team</strong> with roles,
+shared memory, and messaging.</p></div>
+<p>If you’re new to Claude Code, “agent” gets thrown around a lot. Here’s the plain-English version —
+what an agent actually is, how subagents fit, and what changes when you run several at once.</p>
+<h2 id="what-an-agent-actually-is" tabindex="-1">What an agent actually is <a class="anchor" href="#what-an-agent-actually-is" aria-hidden="true">#</a></h2>
+<p>An agent is just a loop with a goal. A Claude Code agent is a running Claude session that can:</p>
+<ul>
+<li><strong>read</strong> your files and project context,</li>
+<li><strong>act</strong> — edit code, run shell commands, call tools — toward a task, and</li>
+<li><strong>repeat</strong>, observing the results and deciding the next step.</li>
+</ul>
+<p>That’s it. Every terminal where you start a <code>claude</code> session is an agent: one goal, one context
+window, one loop. The magic isn’t the word “agent” — it’s that the loop can use tools and keep going
+until the job’s done.</p>
+<h2 id="agents-vs-subagents" tabindex="-1">Agents vs. subagents <a class="anchor" href="#agents-vs-subagents" aria-hidden="true">#</a></h2>
+<p>These two get conflated constantly, so let’s separate them:</p>
+<h3 id="agent" tabindex="-1">Agent <a class="anchor" href="#agent" aria-hidden="true">#</a></h3>
+<p>A top-level session <em>you</em> drive. It owns a task from start to finish and you interact with it
+directly.</p>
+<h3 id="subagent" tabindex="-1">Subagent <a class="anchor" href="#subagent" aria-hidden="true">#</a></h3>
+<p>A helper the main agent <strong>spawns inside its own run</strong> to fan out a chunk of work — “go research these
+five files in parallel,” for example. Subagents are powerful for parallelism, but they’re
+<strong>short-lived and scoped to that one parent</strong>: they don’t persist after the run, and they don’t share
+memory across your whole workflow. For the deeper trade-offs, the difference between <a href="/#what">subagents and a
+full harness</a> is worth understanding before you lean on either.</p>
+<p>The short version: subagents help <em>one</em> agent do more at once; they don’t make <em>many</em> agents into a
+team.</p>
+<h2 id="from-one-agent-to-many" tabindex="-1">From one agent to many <a class="anchor" href="#from-one-agent-to-many" aria-hidden="true">#</a></h2>
+<p>One agent handles most tasks fine. You start wanting <em>several</em> when work naturally splits — someone
+writes tests while someone refactors while someone updates docs. The naive way is to open more
+terminals, and that works… until it doesn’t:</p>
+<ul>
+<li>agents <strong>collide</strong> on the same files,</li>
+<li>each session <strong>forgets</strong> what the others learned, and</li>
+<li>you lose track of <strong>who’s doing what</strong> across a wall of tabs.</li>
+</ul>
+<p>That’s the wall every multi-agent setup hits. The fix isn’t more agents — it’s coordination. We wrote
+the practical playbook in <a href="/blog/how-to-run-multiple-claude-code-agents/">how to run multiple Claude Code
+agents</a>.</p>
+<h2 id="what-turns-agents-into-a-team" tabindex="-1">What turns agents into a team <a class="anchor" href="#what-turns-agents-into-a-team" aria-hidden="true">#</a></h2>
+<p>Three additions turn parallel sessions into something that behaves like a team:</p>
+<ul>
+<li><strong>Roles</strong> — each agent gets a job, so “who should do this?” is obvious.</li>
+<li><strong>Shared memory</strong> — a durable, <a href="/blog/give-claude-code-long-term-memory/">long-term memory</a> every
+agent reads, so knowledge compounds instead of resetting.</li>
+<li><strong>Coordination</strong> — agents message each other and an orchestrator routes work, so you’re not the bus.</li>
+</ul>
+<p>When you wrap your agents in that layer, you’ve got a <a href="/blog/what-is-a-multi-agent-harness/">multi-agent harness</a>
+— the concept that turns “five chat windows” into “one office.”</p>
+<h2 id="where-to-go-next" tabindex="-1">Where to go next <a class="anchor" href="#where-to-go-next" aria-hidden="true">#</a></h2>
+<ul>
+<li>Ready to run several? Start with <a href="/blog/how-to-run-multiple-claude-code-agents/">how to run multiple Claude Code
+agents</a>.</li>
+<li>Want the field of tools? See <a href="/blog/best-claude-code-multi-agent-tools/">the best tools to run multiple Claude Code
+agents</a>.</li>
+<li>Curious about the concept? <a href="/blog/what-is-a-multi-agent-harness/">What is a multi-agent harness?</a></li>
+</ul>
+<hr>
+<p>Munder Difflin is the team layer for the Claude Code agents you already run — roles, shared memory,
+messaging, and an orchestrator, all local. <a href="/#install">Download Munder Difflin</a> to turn your agents
+into an office; it’s free and open source.</p>
+
+
+
+ <section class="faq" aria-label="Frequently asked questions">
+ <h2 id="faq">FAQ</h2>
+
+ <div class="qa">
+ <p class="q">What are Claude Code agents?</p>
+ <p class="a">A Claude Code agent is a running Claude session with a goal and a set of tools — it can read and edit files, run commands, and work toward a task in a loop. Each terminal you start a Claude session in is an agent.</p>
+ </div>
+
+ <div class="qa">
+ <p class="q">What&#39;s the difference between an agent and a subagent in Claude Code?</p>
+ <p class="a">An agent is a top-level session you drive. A subagent is a helper the main agent spawns inside its own run to fan out a piece of work — short-lived and scoped to that parent. Subagents are great for parallel sub-tasks but don&#39;t persist or share memory across your whole workflow.</p>
+ </div>
+
+ <div class="qa">
+ <p class="q">How do I use multiple Claude Code agents at once?</p>
+ <p class="a">Open several sessions, give each a clear role, and coordinate them — ideally with shared memory and messaging so they don&#39;t collide or forget. A multi-agent harness like Munder Difflin automates that coordination so the sessions act as one team.</p>
+ </div>
+
+ </section>
+
+
+
+ <hr />
+ <div class="share">
+ <span class="lbl">Tags</span>
+ <a class="tag" href="/blog/tags/concepts/">Concepts</a><a class="tag" href="/blog/tags/multi-agent/">Multi-Agent</a><a class="tag" href="/blog/tags/claude-code/">Claude Code</a><a class="tag" href="/blog/tags/getting-started/">Getting Started</a>
+ </div>
+
+ </div>
+
+
+ <aside class="toc-rail" aria-label="Table of contents">
+ <div class="tt">On this page</div>
+ <ol>
+ <li class="lvl-2"><a href="#what-an-agent-actually-is">What an agent actually is</a></li><li class="lvl-2"><a href="#agents-vs-subagents">Agents vs. subagents</a></li><li class="lvl-3"><a href="#agent">Agent</a></li><li class="lvl-3"><a href="#subagent">Subagent</a></li><li class="lvl-2"><a href="#from-one-agent-to-many">From one agent to many</a></li><li class="lvl-2"><a href="#what-turns-agents-into-a-team">What turns agents into a team</a></li><li class="lvl-2"><a href="#where-to-go-next">Where to go next</a></li>
+ </ol>
+ </aside>
+
+ </div>
+
+ <footer class="post-foot wrap"><div class="prevnext">
+ <a class="pn prev" href="/blog/why-local-first-matters-for-ai-agents/"><span class="k">← Older</span><span class="t">Why Local-First Matters for Your AI Agents</span></a>
+ <a class="pn next" href="/blog/single-committer-git-pattern/"><span class="k">Newer →</span><span class="t">The Single-Committer Pattern: Multi-Agent Git Without Corruption</span></a>
+ </div>
+ <section class="related">
+ <h2>Related in Concepts</h2>
+ <div class="post-grid">
+ <article class="card">
+ <a class="thumb t-concepts" href="/blog/ai-agent-glossary/" aria-hidden="true" tabindex="-1">
+ <span>CONCEPTS</span>
+ </a>
+ <div class="body">
+ <div class="meta">
+ <time datetime="2026-06-02">Jun 2, 2026</time>
+ <span class="dot" aria-hidden="true"></span>
+ <span>3 min</span>
+ </div>
+ <h3><a href="/blog/ai-agent-glossary/">The AI Coding Agent Glossary: Harness, Orchestrator, Hive, Subagent</a></h3>
+ <p class="dek">Plain-English definitions of the AI coding agent terms everyone trips over — harness, orchestrator, hive, subagent, agent memory — each in one line.</p>
+ <div class="foot">
+ <span class="tag kind">Concepts</span>
+ <a class="more" href="/blog/ai-agent-glossary/" aria-label="Read: The AI Coding Agent Glossary: Harness, Orchestrator, Hive, Subagent">Read →</a>
+ </div>
+ </div>
+</article>
+<article class="card">
+ <a class="thumb t-concepts" href="/blog/munder-difflin-faq/" aria-hidden="true" tabindex="-1">
+ <span>CONCEPTS</span>
+ </a>
+ <div class="body">
+ <div class="meta">
+ <time datetime="2026-06-02">Jun 2, 2026</time>
+ <span class="dot" aria-hidden="true"></span>
+ <span>1 min</span>
+ </div>
+ <h3><a href="/blog/munder-difflin-faq/">Munder Difflin FAQ: Everything People Ask</a></h3>
+ <p class="dek">Answers to the top Munder Difflin questions — what it is, is it free, does it run locally, which platforms, and how it differs from many terminals.</p>
+ <div class="foot">
+ <span class="tag kind">Concepts</span>
+ <a class="more" href="/blog/munder-difflin-faq/" aria-label="Read: Munder Difflin FAQ: Everything People Ask">Read →</a>
+ </div>
+ </div>
+</article>
+<article class="card">
+ <a class="thumb t-concepts" href="/blog/what-is-a-multi-agent-harness/" aria-hidden="true" tabindex="-1">
+ <span>CONCEPTS</span>
+ </a>
+ <div class="body">
+ <div class="meta">
+ <time datetime="2026-05-22">May 22, 2026</time>
+ <span class="dot" aria-hidden="true"></span>
+ <span>2 min</span>
+ </div>
+ <h3><a href="/blog/what-is-a-multi-agent-harness/">What Is a Multi-Agent Harness? (Plain-English Guide)</a></h3>
+ <p class="dek">A multi-agent harness coordinates several AI coding agents into one team — here&#39;s what that means, and how it differs from a single agent or a framework.</p>
+ <div class="foot">
+ <span class="tag kind">Concepts</span>
+ <a class="more" href="/blog/what-is-a-multi-agent-harness/" aria-label="Read: What Is a Multi-Agent Harness? (Plain-English Guide)">Read →</a>
+ </div>
+ </div>
+</article>
+
+ </div>
+ </section>
+
+ </footer>
+</article>
+
+</main>
+<footer>
+ <div class="wrap">
+ <div class="foot-top">
+ <a class="foot-brand brand" href="/blog/">
+ <span class="brand-mark">MD</span>
+ <span class="brand-word">MUNDER DIFFLIN<span class="sep">/</span><span class="blog">BLOG</span></span>
+ </a>
+ <div class="foot-links">
+ <a href="/blog/">Latest</a>
+ <a href="/blog/topics/">Topics</a>
+ <a href="/blog/about/">About</a>
+ <a href="https://munderdiffl.in/blog/feed.xml">RSS</a>
+ <a href="https://github.com/chaitanyagiri/munder-difflin">GitHub</a>
+ <a href="https://munderdiffl.in">munderdiffl.in ↗</a>
+ </div>
+ </div>
+ <div class="foot-meta">
+ © 2026 Munder Difflin · Local-first · MIT-licensed ·
+ Built on <a href="https://munderdiffl.in">Electron, React, Pixi.js, xterm.js &amp; node-pty</a>.
+ Run an office of agents while you sleep.
+ </div>
+ </div>
+</footer>
+
+<script>
+ // sticky-nav border on scroll
+ (function () {
+ var nav = document.getElementById('nav');
+ if (!nav) return;
+ var onScroll = function () { nav.classList.toggle('scrolled', window.scrollY > 8); };
+ onScroll(); window.addEventListener('scroll', onScroll, { passive: true });
+ })();
+</script>
+
+</body>
+</html>
diff --git a/docs/blog/what-is-a-multi-agent-harness/index.html b/docs/blog/what-is-a-multi-agent-harness/index.html
index 7411cd5b..e9d89fb1 100644
--- a/docs/blog/what-is-a-multi-agent-harness/index.html
+++ b/docs/blog/what-is-a-multi-agent-harness/index.html
@@ -228,8 +228,69 @@ want to watch a coordinated team of agents work an office floor,
<footer class="post-foot wrap"><div class="prevnext">
<span></span>
- <a class="pn next" href="/blog/give-claude-code-long-term-memory/"><span class="k">Newer →</span><span class="t">How to Give Claude Code Long-Term Memory</span></a>
+ <a class="pn next" href="/blog/claude-code-subagents-vs-multi-agent-harness/"><span class="k">Newer →</span><span class="t">Claude Code Subagents vs a Multi-Agent Harness</span></a>
</div>
+ <section class="related">
+ <h2>Related in Concepts</h2>
+ <div class="post-grid">
+ <article class="card">
+ <a class="thumb t-concepts" href="/blog/ai-agent-glossary/" aria-hidden="true" tabindex="-1">
+ <span>CONCEPTS</span>
+ </a>
+ <div class="body">
+ <div class="meta">
+ <time datetime="2026-06-02">Jun 2, 2026</time>
+ <span class="dot" aria-hidden="true"></span>
+ <span>3 min</span>
+ </div>
+ <h3><a href="/blog/ai-agent-glossary/">The AI Coding Agent Glossary: Harness, Orchestrator, Hive, Subagent</a></h3>
+ <p class="dek">Plain-English definitions of the AI coding agent terms everyone trips over — harness, orchestrator, hive, subagent, agent memory — each in one line.</p>
+ <div class="foot">
+ <span class="tag kind">Concepts</span>
+ <a class="more" href="/blog/ai-agent-glossary/" aria-label="Read: The AI Coding Agent Glossary: Harness, Orchestrator, Hive, Subagent">Read →</a>
+ </div>
+ </div>
+</article>
+<article class="card">
+ <a class="thumb t-concepts" href="/blog/munder-difflin-faq/" aria-hidden="true" tabindex="-1">
+ <span>CONCEPTS</span>
+ </a>
+ <div class="body">
+ <div class="meta">
+ <time datetime="2026-06-02">Jun 2, 2026</time>
+ <span class="dot" aria-hidden="true"></span>
+ <span>1 min</span>
+ </div>
+ <h3><a href="/blog/munder-difflin-faq/">Munder Difflin FAQ: Everything People Ask</a></h3>
+ <p class="dek">Answers to the top Munder Difflin questions — what it is, is it free, does it run locally, which platforms, and how it differs from many terminals.</p>
+ <div class="foot">
+ <span class="tag kind">Concepts</span>
+ <a class="more" href="/blog/munder-difflin-faq/" aria-label="Read: Munder Difflin FAQ: Everything People Ask">Read →</a>
+ </div>
+ </div>
+</article>
+<article class="card">
+ <a class="thumb t-concepts" href="/blog/what-are-claude-code-agents/" aria-hidden="true" tabindex="-1">
+ <span>CONCEPTS</span>
+ </a>
+ <div class="body">
+ <div class="meta">
+ <time datetime="2026-06-02">Jun 2, 2026</time>
+ <span class="dot" aria-hidden="true"></span>
+ <span>3 min</span>
+ </div>
+ <h3><a href="/blog/what-are-claude-code-agents/">What Are Claude Code Agents? And How to Use Many at Once</a></h3>
+ <p class="dek">Claude Code agents explained in plain English — what an agent actually is, how subagents differ, and the leap from one agent to a coordinated team.</p>
+ <div class="foot">
+ <span class="tag kind">Concepts</span>
+ <a class="more" href="/blog/what-are-claude-code-agents/" aria-label="Read: What Are Claude Code Agents? And How to Use Many at Once">Read →</a>
+ </div>
+ </div>
+</article>
+
+ </div>
+ </section>
+
</footer>
</article>
diff --git a/docs/blog/why-local-first-matters-for-ai-agents/index.html b/docs/blog/why-local-first-matters-for-ai-agents/index.html
new file mode 100644
index 00000000..2303796f
--- /dev/null
+++ b/docs/blog/why-local-first-matters-for-ai-agents/index.html
@@ -0,0 +1,315 @@
+<!doctype html>
+<html lang="en">
+<head>
+<meta charset="UTF-8" />
+<meta name="viewport" content="width=device-width, initial-scale=1.0" />
+<title>Why Local-First Matters for Your AI Agents — Munder Difflin Blog</title>
+<meta name="description" content="The control, privacy, and cost case for keeping your AI agents and their memory on your own machine — and what cloud orchestration quietly costs." />
+<link rel="canonical" href="https://munderdiffl.in/blog/why-local-first-matters-for-ai-agents/" />
+
+<link rel="icon" type="image/png" href="https://munderdiffl.in/logo.png" />
+<link rel="apple-touch-icon" href="https://munderdiffl.in/logo.png" />
+<meta name="theme-color" content="#F5F2E8" />
+
+<!-- Open Graph -->
+<meta property="og:site_name" content="Munder Difflin Blog" />
+<meta property="og:type" content="article" />
+<meta property="og:title" content="Why Local-First Matters for Your AI Agents — Munder Difflin Blog" />
+<meta property="og:description" content="The control, privacy, and cost case for keeping your AI agents and their memory on your own machine — and what cloud orchestration quietly costs." />
+<meta property="og:url" content="https://munderdiffl.in/blog/why-local-first-matters-for-ai-agents/" />
+<meta property="og:image" content="https://munderdiffl.in/media/og.png" />
+<meta property="og:locale" content="en_US" />
+<meta property="article:published_time" content="2026-06-02T00:00:00.000Z" />
+<meta property="article:author" content="Chaitanya Giri" />
+<meta property="article:tag" content="Use Cases" />
+<meta property="article:tag" content="Local-First" />
+<meta property="article:tag" content="Privacy" />
+<meta property="article:tag" content="Multi-Agent" />
+
+
+<!-- Twitter -->
+<meta name="twitter:card" content="summary_large_image" />
+<meta name="twitter:title" content="Why Local-First Matters for Your AI Agents — Munder Difflin Blog" />
+<meta name="twitter:description" content="The control, privacy, and cost case for keeping your AI agents and their memory on your own machine — and what cloud orchestration quietly costs." />
+<meta name="twitter:image" content="https://munderdiffl.in/media/og.png" />
+
+<link rel="alternate" type="application/atom+xml" title="Munder Difflin Blog" href="https://munderdiffl.in/blog/feed.xml" />
+<link rel="preconnect" href="https://fonts.googleapis.com" />
+<link rel="preconnect" href="https://fonts.gstatic.com" crossorigin />
+<link href="https://fonts.googleapis.com/css2?family=Geist:wght@400;500;600&family=JetBrains+Mono:wght@400;500;600;700&display=swap" rel="stylesheet" />
+<link rel="stylesheet" href="/blog/assets/blog.css" />
+
+<script type="application/ld+json">
+{
+ "@context": "https://schema.org",
+ "@type": "BlogPosting",
+ "headline": "Why Local-First Matters for Your AI Agents",
+ "description": "The control, privacy, and cost case for keeping your AI agents and their memory on your own machine — and what cloud orchestration quietly costs.",
+ "image": ["https://munderdiffl.in/media/og.png"],
+ "datePublished": "2026-06-02T00:00:00.000Z",
+ "dateModified": "2026-06-02T00:00:00.000Z",
+ "author": { "@type": "Person", "name": "Chaitanya Giri" },
+ "publisher": {
+ "@type": "Organization",
+ "name": "Munder Difflin",
+ "logo": { "@type": "ImageObject", "url": "https://munderdiffl.in/logo.png" }
+ },
+ "mainEntityOfPage": { "@type": "WebPage", "@id": "https://munderdiffl.in/blog/why-local-first-matters-for-ai-agents/" },
+ "keywords": "local ai dev environment, local-first ai, privacy, ai data control",
+ "articleSection": "Use Cases",
+ "inLanguage": "en-US",
+ "url": "https://munderdiffl.in/blog/why-local-first-matters-for-ai-agents/"
+}
+</script>
+<script type="application/ld+json">
+{
+ "@context": "https://schema.org",
+ "@type": "BreadcrumbList",
+ "itemListElement": [
+ { "@type": "ListItem", "position": 1, "name": "Home", "item": "https://munderdiffl.in/" },
+ { "@type": "ListItem", "position": 2, "name": "Blog", "item": "https://munderdiffl.in/blog/" },
+ { "@type": "ListItem", "position": 3, "name": "Why Local-First Matters for Your AI Agents", "item": "https://munderdiffl.in/blog/why-local-first-matters-for-ai-agents/" }
+ ]
+}
+</script>
+
+<script type="application/ld+json">
+{
+ "@context": "https://schema.org",
+ "@type": "FAQPage",
+ "mainEntity": [
+ { "@type": "Question", "name": "What does local-first mean for AI agents?", "acceptedAnswer": { "@type": "Answer", "text": "Local-first means the orchestration layer, the agents, and their memory all run on your own machine — not in a vendor's cloud. Your agents still call the model API, but the coordination, files, and stored knowledge stay local." } },
+ { "@type": "Question", "name": "Is local-first more private than cloud agent platforms?", "acceptedAnswer": { "@type": "Answer", "text": "Generally yes for everything except the model call itself. Your code, memory, message history, and orchestration never leave your machine, so there's a far smaller surface where your project data could be stored or exposed." } }
+
+ ]
+}
+</script>
+
+
+</head>
+<body>
+<a class="skip-link" href="#main">Skip to content</a>
+<nav id="nav">
+ <a class="brand" href="/blog/" aria-label="Munder Difflin Blog home">
+ <span class="brand-mark">MD</span>
+ <span class="brand-word">MUNDER DIFFLIN<span class="sep">/</span><span class="blog">BLOG</span></span>
+ </a>
+ <span class="spacer"></span>
+ <div class="links">
+ <a href="/blog/">Latest</a>
+ <a href="/blog/topics/">Topics</a>
+ <a href="/blog/about/">About</a>
+ <a href="https://munderdiffl.in">↗ Product</a>
+ </div>
+ <div class="nav-actions">
+ <a class="btn sm" href="https://munderdiffl.in/blog/feed.xml" aria-label="RSS feed">⤵ RSS</a>
+ <a class="btn sm primary" href="https://munderdiffl.in/#install">⤓ Download</a>
+ </div>
+</nav>
+
+<main id="main">
+
+<article>
+ <header class="post-head wrap">
+ <nav class="crumbs" aria-label="Breadcrumb">
+ <a href="/blog/">Blog</a>
+ <span>/</span>
+ <a href="/blog/topics/use-cases/">Use Cases</a>
+ </nav>
+ <h1>Why Local-First Matters for Your AI Agents</h1>
+ <p class="dek">The control, privacy, and cost case for keeping your AI agents and their memory on your own machine — and what cloud orchestration quietly costs.</p>
+ <div class="byline">
+ <span class="av" aria-hidden="true">CG</span>
+ <strong>Chaitanya Giri</strong>
+ <span class="dot" aria-hidden="true">·</span>
+ <time datetime="2026-06-02">Jun 2, 2026</time>
+ <span class="dot" aria-hidden="true">·</span>
+ <span>3 min read</span>
+ <span class="tag kind">Use Cases</span>
+ </div>
+ </header>
+
+ <div class="post-wrap wrap">
+ <div class="prose">
+ <div class="callout tldr"><span class="ic">TL;DR</span><p><strong>Local-first</strong> means your
+agents, their orchestration, and their memory live on <em>your</em> machine — not in a vendor's cloud.
+You get more <strong>control</strong> (it's your files and your rules), more <strong>privacy</strong>
+(code and memory don't leave the box), and more predictable <strong>cost</strong> (no per-seat
+platform fees on top of model usage). For AI agents that touch your whole codebase, that's not a
+detail — it's the foundation.</p></div>
+<p>When people evaluate multi-agent tools, they fixate on features and skip the question that quietly
+shapes everything: <em>where does this actually run?</em> For agents that read and edit your entire
+codebase, the answer matters more than any single feature.</p>
+<h2 id="what-local-first-actually-means" tabindex="-1">What “local-first” actually means <a class="anchor" href="#what-local-first-actually-means" aria-hidden="true">#</a></h2>
+<p>Local-first doesn’t mean “no internet.” Your agents still call the model — that request goes to
+Anthropic the same way your editor’s does. Local-first is about <em>where the rest lives</em>:</p>
+<ul>
+<li>the <strong>orchestration</strong> that routes work between agents,</li>
+<li>the <strong>files</strong> the agents read and write,</li>
+<li>the <strong>memory</strong> the team accumulates, and</li>
+<li>the <strong>message history</strong> and event log of what happened.</li>
+</ul>
+<p>In a <a href="/#why">local-first setup</a>, all of that stays on your machine. In a cloud platform, much of it
+lives on someone else’s servers. Same agents, very different trust model.</p>
+<h2 id="three-reasons-it-matters" tabindex="-1">Three reasons it matters <a class="anchor" href="#three-reasons-it-matters" aria-hidden="true">#</a></h2>
+<h3 id="1-control-its-your-machine-your-rules" tabindex="-1">1. Control — it’s your machine, your rules <a class="anchor" href="#1-control-its-your-machine-your-rules" aria-hidden="true">#</a></h3>
+<p>Local agents work against your real working tree, your git, your environment, your tools. Nothing is
+mediated by a platform’s sandbox or subject to its outages, rate limits, or deprecations. When the
+team is local, <em>you</em> own the failure modes — and you can fix them.</p>
+<h3 id="2-privacy-your-code-and-memory-dont-leave-the-box" tabindex="-1">2. Privacy — your code and memory don’t leave the box <a class="anchor" href="#2-privacy-your-code-and-memory-dont-leave-the-box" aria-hidden="true">#</a></h3>
+<p>Agents that touch your whole repo accumulate a lot of context: source, secrets-adjacent config,
+internal docs, and a <a href="/blog/give-claude-code-long-term-memory/">memory store</a> full of your project’s
+hard-won knowledge. Keeping orchestration and memory local means there’s no third party storing your
+codebase’s working notes. For client work, regulated environments, or just good hygiene, that’s a real
+advantage.</p>
+<h3 id="3-cost-predictable-without-a-platform-tax" tabindex="-1">3. Cost — predictable, without a platform tax <a class="anchor" href="#3-cost-predictable-without-a-platform-tax" aria-hidden="true">#</a></h3>
+<p>Cloud agent platforms typically charge per seat or per run <em>on top of</em> your model usage. Local-first
+adds no platform tax — you pay for the model calls you’d make anyway. As you scale from a couple of
+agents to a team, that difference compounds.</p>
+<h2 id="what-you-give-up-in-the-cloud" tabindex="-1">What you give up in the cloud <a class="anchor" href="#what-you-give-up-in-the-cloud" aria-hidden="true">#</a></h2>
+<p>It’s only fair to name the trade. Cloud platforms can offer zero-setup onboarding, managed scaling,
+and team features out of the box. If you need a hosted, shared, always-on service for a distributed
+team, that convenience is real.</p>
+<p>But for an individual developer or a small team running agents against their own code, the
+convenience rarely outweighs handing over control, privacy, and predictable cost. You can have the
+coordination <em>and</em> keep it local.</p>
+<h2 id="local-first-doesnt-mean-uncoordinated" tabindex="-1">Local-first doesn’t mean uncoordinated <a class="anchor" href="#local-first-doesnt-mean-uncoordinated" aria-hidden="true">#</a></h2>
+<p>The old assumption was that local meant primitive — a few terminals, no shared brain. That’s no longer
+true. A <a href="/#what">local multi-agent harness</a> gives you the full coordination layer — shared memory,
+inter-agent messaging, an orchestrator, a visual floor — entirely on your machine. You don’t trade
+coordination for control; you get both.</p>
+<p>That’s the bet behind <a href="/blog/run-an-office-of-ai-agents/">running an office of AI agents</a> locally, and
+it’s why the <a href="/blog/from-one-terminal-to-a-team/">shift from one terminal to a team</a> doesn’t require
+moving to the cloud.</p>
+<h2 id="the-bottom-line" tabindex="-1">The bottom line <a class="anchor" href="#the-bottom-line" aria-hidden="true">#</a></h2>
+<p>For agents that live inside your codebase, <em>where it runs</em> is a first-class feature. Local-first buys
+control, privacy, and predictable cost — and modern tooling means you no longer sacrifice coordination
+to get them.</p>
+<hr>
+<p>Munder Difflin is local-first by design: the hive, the orchestrator, and MemPalace all run on your
+machine, on macOS, Windows, and Linux. <a href="/#install">Download Munder Difflin</a> — free and open source.</p>
+
+
+
+ <section class="faq" aria-label="Frequently asked questions">
+ <h2 id="faq">FAQ</h2>
+
+ <div class="qa">
+ <p class="q">What does local-first mean for AI agents?</p>
+ <p class="a">Local-first means the orchestration layer, the agents, and their memory all run on your own machine — not in a vendor&#39;s cloud. Your agents still call the model API, but the coordination, files, and stored knowledge stay local.</p>
+ </div>
+
+ <div class="qa">
+ <p class="q">Is local-first more private than cloud agent platforms?</p>
+ <p class="a">Generally yes for everything except the model call itself. Your code, memory, message history, and orchestration never leave your machine, so there&#39;s a far smaller surface where your project data could be stored or exposed.</p>
+ </div>
+
+ </section>
+
+
+
+ <hr />
+ <div class="share">
+ <span class="lbl">Tags</span>
+ <a class="tag" href="/blog/tags/use-cases/">Use Cases</a><a class="tag" href="/blog/tags/local-first/">Local-First</a><a class="tag" href="/blog/tags/privacy/">Privacy</a><a class="tag" href="/blog/tags/multi-agent/">Multi-Agent</a>
+ </div>
+
+ </div>
+
+
+ <aside class="toc-rail" aria-label="Table of contents">
+ <div class="tt">On this page</div>
+ <ol>
+ <li class="lvl-2"><a href="#what-local-first-actually-means">What “local-first” actually means</a></li><li class="lvl-2"><a href="#three-reasons-it-matters">Three reasons it matters</a></li><li class="lvl-3"><a href="#1-control-its-your-machine-your-rules">1. Control — it’s your machine, your rules</a></li><li class="lvl-3"><a href="#2-privacy-your-code-and-memory-dont-leave-the-box">2. Privacy — your code and memory don’t leave the box</a></li><li class="lvl-3"><a href="#3-cost-predictable-without-a-platform-tax">3. Cost — predictable, without a platform tax</a></li><li class="lvl-2"><a href="#what-you-give-up-in-the-cloud">What you give up in the cloud</a></li><li class="lvl-2"><a href="#local-first-doesnt-mean-uncoordinated">Local-first doesn’t mean uncoordinated</a></li><li class="lvl-2"><a href="#the-bottom-line">The bottom line</a></li>
+ </ol>
+ </aside>
+
+ </div>
+
+ <footer class="post-foot wrap"><div class="prevnext">
+ <a class="pn prev" href="/blog/why-we-built-munder-difflin/"><span class="k">← Older</span><span class="t">Why We Built Munder Difflin</span></a>
+ <a class="pn next" href="/blog/what-are-claude-code-agents/"><span class="k">Newer →</span><span class="t">What Are Claude Code Agents? And How to Use Many at Once</span></a>
+ </div>
+ <section class="related">
+ <h2>Related in Use Cases</h2>
+ <div class="post-grid">
+ <article class="card">
+ <a class="thumb t-use-cases" href="/blog/from-one-terminal-to-a-team/" aria-hidden="true" tabindex="-1">
+ <span>USE CASES</span>
+ </a>
+ <div class="body">
+ <div class="meta">
+ <time datetime="2026-06-02">Jun 2, 2026</time>
+ <span class="dot" aria-hidden="true"></span>
+ <span>3 min</span>
+ </div>
+ <h3><a href="/blog/from-one-terminal-to-a-team/">From One Terminal to a Team: Scaling Your Claude Code Workflow</a></h3>
+ <p class="dek">The workflow shift from a single Claude Code session to a coordinated team of agents — what changes, where it breaks, and the concrete before-and-after.</p>
+ <div class="foot">
+ <span class="tag kind">Use Cases</span>
+ <a class="more" href="/blog/from-one-terminal-to-a-team/" aria-label="Read: From One Terminal to a Team: Scaling Your Claude Code Workflow">Read →</a>
+ </div>
+ </div>
+</article>
+<article class="card">
+ <a class="thumb t-use-cases" href="/blog/run-an-office-of-ai-agents/" aria-hidden="true" tabindex="-1">
+ <span>USE CASES</span>
+ </a>
+ <div class="body">
+ <div class="meta">
+ <time datetime="2026-06-02">Jun 2, 2026</time>
+ <span class="dot" aria-hidden="true"></span>
+ <span>3 min</span>
+ </div>
+ <h3><a href="/blog/run-an-office-of-ai-agents/">Run an Office of AI Agents While You Sleep</a></h3>
+ <p class="dek">What it takes to run a self-coordinating office of AI coding agents that keeps shipping after you log off — and the guardrails that keep it sane.</p>
+ <div class="foot">
+ <span class="tag kind">Use Cases</span>
+ <a class="more" href="/blog/run-an-office-of-ai-agents/" aria-label="Read: Run an Office of AI Agents While You Sleep">Read →</a>
+ </div>
+ </div>
+</article>
+
+ </div>
+ </section>
+
+ </footer>
+</article>
+
+</main>
+<footer>
+ <div class="wrap">
+ <div class="foot-top">
+ <a class="foot-brand brand" href="/blog/">
+ <span class="brand-mark">MD</span>
+ <span class="brand-word">MUNDER DIFFLIN<span class="sep">/</span><span class="blog">BLOG</span></span>
+ </a>
+ <div class="foot-links">
+ <a href="/blog/">Latest</a>
+ <a href="/blog/topics/">Topics</a>
+ <a href="/blog/about/">About</a>
+ <a href="https://munderdiffl.in/blog/feed.xml">RSS</a>
+ <a href="https://github.com/chaitanyagiri/munder-difflin">GitHub</a>
+ <a href="https://munderdiffl.in">munderdiffl.in ↗</a>
+ </div>
+ </div>
+ <div class="foot-meta">
+ © 2026 Munder Difflin · Local-first · MIT-licensed ·
+ Built on <a href="https://munderdiffl.in">Electron, React, Pixi.js, xterm.js &amp; node-pty</a>.
+ Run an office of agents while you sleep.
+ </div>
+ </div>
+</footer>
+
+<script>
+ // sticky-nav border on scroll
+ (function () {
+ var nav = document.getElementById('nav');
+ if (!nav) return;
+ var onScroll = function () { nav.classList.toggle('scrolled', window.scrollY > 8); };
+ onScroll(); window.addEventListener('scroll', onScroll, { passive: true });
+ })();
+</script>
+
+</body>
+</html>
diff --git a/docs/blog/why-we-built-munder-difflin/index.html b/docs/blog/why-we-built-munder-difflin/index.html
new file mode 100644
index 00000000..b85d8f87
--- /dev/null
+++ b/docs/blog/why-we-built-munder-difflin/index.html
@@ -0,0 +1,249 @@
+<!doctype html>
+<html lang="en">
+<head>
+<meta charset="UTF-8" />
+<meta name="viewport" content="width=device-width, initial-scale=1.0" />
+<title>Why We Built Munder Difflin — Munder Difflin Blog</title>
+<meta name="description" content="The origin story of Munder Difflin — how the pain of juggling Claude Code terminals led to a coordinated, memory-backed hive of agents you can watch." />
+<link rel="canonical" href="https://munderdiffl.in/blog/why-we-built-munder-difflin/" />
+
+<link rel="icon" type="image/png" href="https://munderdiffl.in/logo.png" />
+<link rel="apple-touch-icon" href="https://munderdiffl.in/logo.png" />
+<meta name="theme-color" content="#F5F2E8" />
+
+<!-- Open Graph -->
+<meta property="og:site_name" content="Munder Difflin Blog" />
+<meta property="og:type" content="article" />
+<meta property="og:title" content="Why We Built Munder Difflin — Munder Difflin Blog" />
+<meta property="og:description" content="The origin story of Munder Difflin — how the pain of juggling Claude Code terminals led to a coordinated, memory-backed hive of agents you can watch." />
+<meta property="og:url" content="https://munderdiffl.in/blog/why-we-built-munder-difflin/" />
+<meta property="og:image" content="https://munderdiffl.in/media/og.png" />
+<meta property="og:locale" content="en_US" />
+<meta property="article:published_time" content="2026-06-02T00:00:00.000Z" />
+<meta property="article:author" content="Chaitanya Giri" />
+<meta property="article:tag" content="Story" />
+<meta property="article:tag" content="Multi-Agent" />
+<meta property="article:tag" content="Claude Code" />
+<meta property="article:tag" content="Open Source" />
+
+
+<!-- Twitter -->
+<meta name="twitter:card" content="summary_large_image" />
+<meta name="twitter:title" content="Why We Built Munder Difflin — Munder Difflin Blog" />
+<meta name="twitter:description" content="The origin story of Munder Difflin — how the pain of juggling Claude Code terminals led to a coordinated, memory-backed hive of agents you can watch." />
+<meta name="twitter:image" content="https://munderdiffl.in/media/og.png" />
+
+<link rel="alternate" type="application/atom+xml" title="Munder Difflin Blog" href="https://munderdiffl.in/blog/feed.xml" />
+<link rel="preconnect" href="https://fonts.googleapis.com" />
+<link rel="preconnect" href="https://fonts.gstatic.com" crossorigin />
+<link href="https://fonts.googleapis.com/css2?family=Geist:wght@400;500;600&family=JetBrains+Mono:wght@400;500;600;700&display=swap" rel="stylesheet" />
+<link rel="stylesheet" href="/blog/assets/blog.css" />
+
+<script type="application/ld+json">
+{
+ "@context": "https://schema.org",
+ "@type": "BlogPosting",
+ "headline": "Why We Built Munder Difflin",
+ "description": "The origin story of Munder Difflin — how the pain of juggling Claude Code terminals led to a coordinated, memory-backed hive of agents you can watch.",
+ "image": ["https://munderdiffl.in/media/og.png"],
+ "datePublished": "2026-06-02T00:00:00.000Z",
+ "dateModified": "2026-06-02T00:00:00.000Z",
+ "author": { "@type": "Person", "name": "Chaitanya Giri" },
+ "publisher": {
+ "@type": "Organization",
+ "name": "Munder Difflin",
+ "logo": { "@type": "ImageObject", "url": "https://munderdiffl.in/logo.png" }
+ },
+ "mainEntityOfPage": { "@type": "WebPage", "@id": "https://munderdiffl.in/blog/why-we-built-munder-difflin/" },
+ "keywords": "munder difflin, munder difflin github, multi-agent harness, why munder difflin",
+ "articleSection": "Story",
+ "inLanguage": "en-US",
+ "url": "https://munderdiffl.in/blog/why-we-built-munder-difflin/"
+}
+</script>
+<script type="application/ld+json">
+{
+ "@context": "https://schema.org",
+ "@type": "BreadcrumbList",
+ "itemListElement": [
+ { "@type": "ListItem", "position": 1, "name": "Home", "item": "https://munderdiffl.in/" },
+ { "@type": "ListItem", "position": 2, "name": "Blog", "item": "https://munderdiffl.in/blog/" },
+ { "@type": "ListItem", "position": 3, "name": "Why We Built Munder Difflin", "item": "https://munderdiffl.in/blog/why-we-built-munder-difflin/" }
+ ]
+}
+</script>
+
+
+</head>
+<body>
+<a class="skip-link" href="#main">Skip to content</a>
+<nav id="nav">
+ <a class="brand" href="/blog/" aria-label="Munder Difflin Blog home">
+ <span class="brand-mark">MD</span>
+ <span class="brand-word">MUNDER DIFFLIN<span class="sep">/</span><span class="blog">BLOG</span></span>
+ </a>
+ <span class="spacer"></span>
+ <div class="links">
+ <a href="/blog/">Latest</a>
+ <a href="/blog/topics/">Topics</a>
+ <a href="/blog/about/">About</a>
+ <a href="https://munderdiffl.in">↗ Product</a>
+ </div>
+ <div class="nav-actions">
+ <a class="btn sm" href="https://munderdiffl.in/blog/feed.xml" aria-label="RSS feed">⤵ RSS</a>
+ <a class="btn sm primary" href="https://munderdiffl.in/#install">⤓ Download</a>
+ </div>
+</nav>
+
+<main id="main">
+
+<article>
+ <header class="post-head wrap">
+ <nav class="crumbs" aria-label="Breadcrumb">
+ <a href="/blog/">Blog</a>
+ <span>/</span>
+ <a href="/blog/topics/story/">Story</a>
+ </nav>
+ <h1>Why We Built Munder Difflin</h1>
+ <p class="dek">The origin story of Munder Difflin — how the pain of juggling Claude Code terminals led to a coordinated, memory-backed hive of agents you can watch.</p>
+ <div class="byline">
+ <span class="av" aria-hidden="true">CG</span>
+ <strong>Chaitanya Giri</strong>
+ <span class="dot" aria-hidden="true">·</span>
+ <time datetime="2026-06-02">Jun 2, 2026</time>
+ <span class="dot" aria-hidden="true">·</span>
+ <span>3 min read</span>
+ <span class="tag kind">Story</span>
+ </div>
+ </header>
+
+ <div class="post-wrap wrap">
+ <div class="prose">
+ <div class="callout tldr"><span class="ic">TL;DR</span><p>We built <strong>Munder Difflin</strong>
+because running several Claude Code agents at once was powerful and miserable in equal measure — they
+collided, forgot, and turned us into a human message bus. The fix wasn't a better terminal; it was a
+<strong>coordination layer</strong>: roles, shared memory, messaging, and an orchestrator you talk to,
+visualized as an office floor. This is the story of that itch.</p></div>
+<p>Every tool starts with an annoyance specific enough to act on. Munder Difflin started with a wall of
+terminal tabs and the dawning realization that <em>I</em> had become the slowest part of my own setup.</p>
+<h2 id="the-itch" tabindex="-1">The itch <a class="anchor" href="#the-itch" aria-hidden="true">#</a></h2>
+<p>Claude Code is great. So great that one session was never enough for long. I’d open a second terminal
+to parallelize, then a third, then a fourth. Throughput went up — and so did the chaos.</p>
+<p>Three frustrations kept recurring, the same ones <a href="/blog/from-one-terminal-to-a-team/">everyone hits</a>:</p>
+<ul>
+<li><strong>They collided.</strong> Two agents would edit the same file and race each other; git would throw
+<code>index.lock</code> errors and leave half-applied changes.</li>
+<li><strong>They forgot.</strong> Each session started cold. What one agent figured out, the next couldn’t use — so I
+copy-pasted findings between windows like a courier.</li>
+<li><strong>I lost track.</strong> Six tabs in, “what is everyone doing right now?” had no answer. And lost track is
+where mistakes hide.</li>
+</ul>
+<p>The agents weren’t the bottleneck anymore. <em>I</em> was — the message bus, the conflict resolver, and the
+project’s only long-term memory.</p>
+<h2 id="the-realization" tabindex="-1">The realization <a class="anchor" href="#the-realization" aria-hidden="true">#</a></h2>
+<p>The instinct is to reach for a better terminal multiplexer. But the problem wasn’t <em>running</em> agents in
+parallel — plenty of tools do that well. The problem was that the agents had no way to <strong>coordinate</strong>:
+no shared memory, no way to message each other, no one routing the work but me.</p>
+<p>What I actually wanted was an <em>office</em>. A team where everyone has a role, shares what they learn, hands
+work off directly, and answers to a manager I could talk to in plain language. The missing thing wasn’t
+more parallelism — it was the <a href="/blog/what-is-a-multi-agent-harness/">coordination layer</a> on top of it.</p>
+<h2 id="what-we-built" tabindex="-1">What we built <a class="anchor" href="#what-we-built" aria-hidden="true">#</a></h2>
+<p>So that’s what Munder Difflin is: a layer that wraps the Claude Code agents you already run and makes
+them a team.</p>
+<ul>
+<li><strong>Roles</strong> so each agent stays in its lane.</li>
+<li><strong>Shared memory</strong> — a semantic store (MemPalace) the whole hive reads and writes, so knowledge
+compounds instead of resetting.</li>
+<li><strong>Messaging</strong> — every agent has a mailbox; a router delivers between them, so they hand off work
+without me in the middle.</li>
+<li><strong>A GOD orchestrator</strong> — a coordinator you talk to like a manager; it decomposes your intent and
+routes the work.</li>
+<li><strong>A floor you can watch</strong> — agents as avatars at their desks, so the black box becomes something you
+can supervise at a glance.</li>
+</ul>
+<p>And the joke that became the name: <em>the world’s best agents, the world’s worst paper company.</em> The
+office metaphor isn’t decoration — it turned out to be the clearest way to think about (and watch) a
+team of coordinating agents.</p>
+<h2 id="why-local-why-open-source" tabindex="-1">Why local, why open source <a class="anchor" href="#why-local-why-open-source" aria-hidden="true">#</a></h2>
+<p>Two decisions were never really in question. <strong>Local-first</strong>, because agents that touch your whole
+codebase shouldn’t ship your code and memory to someone else’s cloud — you keep the control, the
+privacy, and the predictable cost (<a href="/blog/why-local-first-matters-for-ai-agents/">the full case</a>).
+And <strong>open source (MIT)</strong>, because a tool you run against your own code is one you should be able to
+read, trust, and extend. The code lives on
+<a href="https://github.com/chaitanyagiri/munder-difflin">GitHub</a>.</p>
+<h2 id="what-its-for" tabindex="-1">What it’s for <a class="anchor" href="#what-its-for" aria-hidden="true">#</a></h2>
+<p>Munder Difflin is for the moment you’ve felt the wall — three or more agents, context evaporating, you
+alt-tabbing as the message bus. It’s the <a href="/blog/run-an-office-of-ai-agents/">office of agents</a> I wanted
+when I had eight tabs open and no idea what half of them were doing.</p>
+<p>If you’ve been there, you already understand the itch. The rest of the common questions are answered in
+the <a href="/blog/munder-difflin-faq/">Munder Difflin FAQ</a>.</p>
+<hr>
+<p>We built it to scratch our own itch, then made it free for everyone with the same one. <a href="/#install">Download
+Munder Difflin</a> — it’s open source and local-first, on macOS, Windows, and Linux.</p>
+
+
+
+
+
+ <hr />
+ <div class="share">
+ <span class="lbl">Tags</span>
+ <a class="tag" href="/blog/tags/story/">Story</a><a class="tag" href="/blog/tags/multi-agent/">Multi-Agent</a><a class="tag" href="/blog/tags/claude-code/">Claude Code</a><a class="tag" href="/blog/tags/open-source/">Open Source</a>
+ </div>
+
+ </div>
+
+
+ <aside class="toc-rail" aria-label="Table of contents">
+ <div class="tt">On this page</div>
+ <ol>
+ <li class="lvl-2"><a href="#the-itch">The itch</a></li><li class="lvl-2"><a href="#the-realization">The realization</a></li><li class="lvl-2"><a href="#what-we-built">What we built</a></li><li class="lvl-2"><a href="#why-local-why-open-source">Why local, why open source</a></li><li class="lvl-2"><a href="#what-its-for">What it’s for</a></li>
+ </ol>
+ </aside>
+
+ </div>
+
+ <footer class="post-foot wrap"><div class="prevnext">
+ <a class="pn prev" href="/blog/how-to-run-multiple-claude-code-agents/"><span class="k">← Older</span><span class="t">How to Run Multiple Claude Code Agents (Without Losing Track)</span></a>
+ <a class="pn next" href="/blog/why-local-first-matters-for-ai-agents/"><span class="k">Newer →</span><span class="t">Why Local-First Matters for Your AI Agents</span></a>
+ </div>
+ </footer>
+</article>
+
+</main>
+<footer>
+ <div class="wrap">
+ <div class="foot-top">
+ <a class="foot-brand brand" href="/blog/">
+ <span class="brand-mark">MD</span>
+ <span class="brand-word">MUNDER DIFFLIN<span class="sep">/</span><span class="blog">BLOG</span></span>
+ </a>
+ <div class="foot-links">
+ <a href="/blog/">Latest</a>
+ <a href="/blog/topics/">Topics</a>
+ <a href="/blog/about/">About</a>
+ <a href="https://munderdiffl.in/blog/feed.xml">RSS</a>
+ <a href="https://github.com/chaitanyagiri/munder-difflin">GitHub</a>
+ <a href="https://munderdiffl.in">munderdiffl.in ↗</a>
+ </div>
+ </div>
+ <div class="foot-meta">
+ © 2026 Munder Difflin · Local-first · MIT-licensed ·
+ Built on <a href="https://munderdiffl.in">Electron, React, Pixi.js, xterm.js &amp; node-pty</a>.
+ Run an office of agents while you sleep.
+ </div>
+ </div>
+</footer>
+
+<script>
+ // sticky-nav border on scroll
+ (function () {
+ var nav = document.getElementById('nav');
+ if (!nav) return;
+ var onScroll = function () { nav.classList.toggle('scrolled', window.scrollY > 8); };
+ onScroll(); window.addEventListener('scroll', onScroll, { passive: true });
+ })();
+</script>
+
+</body>
+</html>
diff --git a/docs/sitemap.xml b/docs/sitemap.xml
index c852474f..a46828fe 100644
--- a/docs/sitemap.xml
+++ b/docs/sitemap.xml
@@ -17,32 +17,244 @@
<url><loc>https://munderdiffl.in/blog/</loc><changefreq>daily</changefreq><priority>0.9</priority></url>
<url><loc>https://munderdiffl.in/blog/topics/</loc><changefreq>weekly</changefreq><priority>0.6</priority></url>
<url><loc>https://munderdiffl.in/blog/about/</loc><changefreq>monthly</changefreq><priority>0.4</priority></url>
+ <url>
+ <loc>https://munderdiffl.in/blog/best-claude-code-multi-agent-tools/</loc>
+ <lastmod>2026-06-04</lastmod>
+ <changefreq>monthly</changefreq>
+ <priority>0.8</priority>
+ </url>
+ <url>
+ <loc>https://munderdiffl.in/blog/claude-code-automation-while-you-sleep/</loc>
+ <lastmod>2026-06-04</lastmod>
+ <changefreq>monthly</changefreq>
+ <priority>0.8</priority>
+ </url>
+ <url>
+ <loc>https://munderdiffl.in/blog/claude-code-git-worktrees-vs-hive/</loc>
+ <lastmod>2026-06-04</lastmod>
+ <changefreq>monthly</changefreq>
+ <priority>0.8</priority>
+ </url>
+ <url>
+ <loc>https://munderdiffl.in/blog/claude-code-orchestration-tools-compared/</loc>
+ <lastmod>2026-06-04</lastmod>
+ <changefreq>monthly</changefreq>
+ <priority>0.8</priority>
+ </url>
+ <url>
+ <loc>https://munderdiffl.in/blog/claude-squad-vs-munder-difflin/</loc>
+ <lastmod>2026-06-04</lastmod>
+ <changefreq>monthly</changefreq>
+ <priority>0.8</priority>
+ </url>
+ <url>
+ <loc>https://munderdiffl.in/blog/building-a-terminal-ui-xterm-node-pty/</loc>
+ <lastmod>2026-06-03</lastmod>
+ <changefreq>monthly</changefreq>
+ <priority>0.8</priority>
+ </url>
+ <url>
+ <loc>https://munderdiffl.in/blog/claude-code-hooks-explained/</loc>
+ <lastmod>2026-06-03</lastmod>
+ <changefreq>monthly</changefreq>
+ <priority>0.8</priority>
+ </url>
+ <url>
+ <loc>https://munderdiffl.in/blog/claude-squad-alternative/</loc>
+ <lastmod>2026-06-03</lastmod>
+ <changefreq>monthly</changefreq>
+ <priority>0.8</priority>
+ </url>
+ <url>
+ <loc>https://munderdiffl.in/blog/conductor-claude-code-alternative/</loc>
+ <lastmod>2026-06-03</lastmod>
+ <changefreq>monthly</changefreq>
+ <priority>0.8</priority>
+ </url>
+ <url>
+ <loc>https://munderdiffl.in/blog/crystal-claude-code-alternative/</loc>
+ <lastmod>2026-06-03</lastmod>
+ <changefreq>monthly</changefreq>
+ <priority>0.8</priority>
+ </url>
+ <url>
+ <loc>https://munderdiffl.in/blog/mcp-and-skills-in-a-hive/</loc>
+ <lastmod>2026-06-03</lastmod>
+ <changefreq>monthly</changefreq>
+ <priority>0.8</priority>
+ </url>
+ <url>
+ <loc>https://munderdiffl.in/blog/node-pty-electron-real-terminals/</loc>
+ <lastmod>2026-06-03</lastmod>
+ <changefreq>monthly</changefreq>
+ <priority>0.8</priority>
+ </url>
+ <url>
+ <loc>https://munderdiffl.in/blog/vibe-kanban-alternative/</loc>
+ <lastmod>2026-06-03</lastmod>
+ <changefreq>monthly</changefreq>
+ <priority>0.8</priority>
+ </url>
+ <url>
+ <loc>https://munderdiffl.in/blog/ai-agent-glossary/</loc>
+ <lastmod>2026-06-02</lastmod>
+ <changefreq>monthly</changefreq>
+ <priority>0.8</priority>
+ </url>
+ <url>
+ <loc>https://munderdiffl.in/blog/from-one-terminal-to-a-team/</loc>
+ <lastmod>2026-06-02</lastmod>
+ <changefreq>monthly</changefreq>
+ <priority>0.8</priority>
+ </url>
+ <url>
+ <loc>https://munderdiffl.in/blog/how-to-choose-a-multi-agent-tool/</loc>
+ <lastmod>2026-06-02</lastmod>
+ <changefreq>monthly</changefreq>
+ <priority>0.8</priority>
+ </url>
+ <url>
+ <loc>https://munderdiffl.in/blog/munder-difflin-faq/</loc>
+ <lastmod>2026-06-02</lastmod>
+ <changefreq>monthly</changefreq>
+ <priority>0.8</priority>
+ </url>
+ <url>
+ <loc>https://munderdiffl.in/blog/run-an-office-of-ai-agents/</loc>
+ <lastmod>2026-06-02</lastmod>
+ <changefreq>monthly</changefreq>
+ <priority>0.8</priority>
+ </url>
+ <url>
+ <loc>https://munderdiffl.in/blog/single-committer-git-pattern/</loc>
+ <lastmod>2026-06-02</lastmod>
+ <changefreq>monthly</changefreq>
+ <priority>0.8</priority>
+ </url>
+ <url>
+ <loc>https://munderdiffl.in/blog/what-are-claude-code-agents/</loc>
+ <lastmod>2026-06-02</lastmod>
+ <changefreq>monthly</changefreq>
+ <priority>0.8</priority>
+ </url>
+ <url>
+ <loc>https://munderdiffl.in/blog/why-local-first-matters-for-ai-agents/</loc>
+ <lastmod>2026-06-02</lastmod>
+ <changefreq>monthly</changefreq>
+ <priority>0.8</priority>
+ </url>
+ <url>
+ <loc>https://munderdiffl.in/blog/why-we-built-munder-difflin/</loc>
+ <lastmod>2026-06-02</lastmod>
+ <changefreq>monthly</changefreq>
+ <priority>0.8</priority>
+ </url>
<url>
<loc>https://munderdiffl.in/blog/how-to-run-multiple-claude-code-agents/</loc>
<lastmod>2026-06-01</lastmod>
<changefreq>monthly</changefreq>
<priority>0.8</priority>
</url>
+ <url>
+ <loc>https://munderdiffl.in/blog/atomic-file-mailboxes-for-agents/</loc>
+ <lastmod>2026-05-31</lastmod>
+ <changefreq>monthly</changefreq>
+ <priority>0.8</priority>
+ </url>
+ <url>
+ <loc>https://munderdiffl.in/blog/how-the-god-orchestrator-works/</loc>
+ <lastmod>2026-05-30</lastmod>
+ <changefreq>monthly</changefreq>
+ <priority>0.8</priority>
+ </url>
+ <url>
+ <loc>https://munderdiffl.in/blog/coordinating-ai-coding-agents/</loc>
+ <lastmod>2026-05-29</lastmod>
+ <changefreq>monthly</changefreq>
+ <priority>0.8</priority>
+ </url>
+ <url>
+ <loc>https://munderdiffl.in/blog/claude-code-orchestration-guide/</loc>
+ <lastmod>2026-05-28</lastmod>
+ <changefreq>monthly</changefreq>
+ <priority>0.8</priority>
+ </url>
<url>
<loc>https://munderdiffl.in/blog/give-claude-code-long-term-memory/</loc>
<lastmod>2026-05-27</lastmod>
<changefreq>monthly</changefreq>
<priority>0.8</priority>
</url>
+ <url>
+ <loc>https://munderdiffl.in/blog/semantic-memory-for-ai-agents/</loc>
+ <lastmod>2026-05-26</lastmod>
+ <changefreq>monthly</changefreq>
+ <priority>0.8</priority>
+ </url>
+ <url>
+ <loc>https://munderdiffl.in/blog/manage-multiple-claude-code-sessions/</loc>
+ <lastmod>2026-05-25</lastmod>
+ <changefreq>monthly</changefreq>
+ <priority>0.8</priority>
+ </url>
+ <url>
+ <loc>https://munderdiffl.in/blog/claude-code-multi-agent-setup-tutorial/</loc>
+ <lastmod>2026-05-24</lastmod>
+ <changefreq>monthly</changefreq>
+ <priority>0.8</priority>
+ </url>
+ <url>
+ <loc>https://munderdiffl.in/blog/claude-code-subagents-vs-multi-agent-harness/</loc>
+ <lastmod>2026-05-23</lastmod>
+ <changefreq>monthly</changefreq>
+ <priority>0.8</priority>
+ </url>
<url>
<loc>https://munderdiffl.in/blog/what-is-a-multi-agent-harness/</loc>
<lastmod>2026-05-22</lastmod>
<changefreq>monthly</changefreq>
<priority>0.8</priority>
</url>
+ <url><loc>https://munderdiffl.in/blog/topics/comparisons/</loc><changefreq>weekly</changefreq><priority>0.5</priority></url>
+ <url><loc>https://munderdiffl.in/blog/topics/guides/</loc><changefreq>weekly</changefreq><priority>0.5</priority></url>
+ <url><loc>https://munderdiffl.in/blog/topics/internals/</loc><changefreq>weekly</changefreq><priority>0.5</priority></url>
<url><loc>https://munderdiffl.in/blog/topics/concepts/</loc><changefreq>weekly</changefreq><priority>0.5</priority></url>
+ <url><loc>https://munderdiffl.in/blog/topics/orchestration/</loc><changefreq>weekly</changefreq><priority>0.5</priority></url>
+ <url><loc>https://munderdiffl.in/blog/topics/use-cases/</loc><changefreq>weekly</changefreq><priority>0.5</priority></url>
<url><loc>https://munderdiffl.in/blog/topics/memory/</loc><changefreq>weekly</changefreq><priority>0.5</priority></url>
- <url><loc>https://munderdiffl.in/blog/topics/guides/</loc><changefreq>weekly</changefreq><priority>0.5</priority></url>
- <url><loc>https://munderdiffl.in/blog/tags/claude-code/</loc><changefreq>weekly</changefreq><priority>0.3</priority></url>
+ <url><loc>https://munderdiffl.in/blog/topics/story/</loc><changefreq>weekly</changefreq><priority>0.5</priority></url>
<url><loc>https://munderdiffl.in/blog/tags/multi-agent/</loc><changefreq>weekly</changefreq><priority>0.3</priority></url>
+ <url><loc>https://munderdiffl.in/blog/tags/claude-code/</loc><changefreq>weekly</changefreq><priority>0.3</priority></url>
+ <url><loc>https://munderdiffl.in/blog/tags/comparisons/</loc><changefreq>weekly</changefreq><priority>0.3</priority></url>
+ <url><loc>https://munderdiffl.in/blog/tags/tools/</loc><changefreq>weekly</changefreq><priority>0.3</priority></url>
+ <url><loc>https://munderdiffl.in/blog/tags/orchestration/</loc><changefreq>weekly</changefreq><priority>0.3</priority></url>
+ <url><loc>https://munderdiffl.in/blog/tags/guides/</loc><changefreq>weekly</changefreq><priority>0.3</priority></url>
+ <url><loc>https://munderdiffl.in/blog/tags/internals/</loc><changefreq>weekly</changefreq><priority>0.3</priority></url>
+ <url><loc>https://munderdiffl.in/blog/tags/getting-started/</loc><changefreq>weekly</changefreq><priority>0.3</priority></url>
<url><loc>https://munderdiffl.in/blog/tags/concepts/</loc><changefreq>weekly</changefreq><priority>0.3</priority></url>
<url><loc>https://munderdiffl.in/blog/tags/memory/</loc><changefreq>weekly</changefreq><priority>0.3</priority></url>
+ <url><loc>https://munderdiffl.in/blog/tags/use-cases/</loc><changefreq>weekly</changefreq><priority>0.3</priority></url>
+ <url><loc>https://munderdiffl.in/blog/tags/automation/</loc><changefreq>weekly</changefreq><priority>0.3</priority></url>
+ <url><loc>https://munderdiffl.in/blog/tags/workflow/</loc><changefreq>weekly</changefreq><priority>0.3</priority></url>
<url><loc>https://munderdiffl.in/blog/tags/mempalace/</loc><changefreq>weekly</changefreq><priority>0.3</priority></url>
- <url><loc>https://munderdiffl.in/blog/tags/guides/</loc><changefreq>weekly</changefreq><priority>0.3</priority></url>
- <url><loc>https://munderdiffl.in/blog/tags/getting-started/</loc><changefreq>weekly</changefreq><priority>0.3</priority></url>
+ <url><loc>https://munderdiffl.in/blog/tags/god/</loc><changefreq>weekly</changefreq><priority>0.3</priority></url>
+ <url><loc>https://munderdiffl.in/blog/tags/story/</loc><changefreq>weekly</changefreq><priority>0.3</priority></url>
+ <url><loc>https://munderdiffl.in/blog/tags/git/</loc><changefreq>weekly</changefreq><priority>0.3</priority></url>
+ <url><loc>https://munderdiffl.in/blog/tags/terminals/</loc><changefreq>weekly</changefreq><priority>0.3</priority></url>
+ <url><loc>https://munderdiffl.in/blog/tags/electron/</loc><changefreq>weekly</changefreq><priority>0.3</priority></url>
+ <url><loc>https://munderdiffl.in/blog/tags/subagents/</loc><changefreq>weekly</changefreq><priority>0.3</priority></url>
+ <url><loc>https://munderdiffl.in/blog/tags/coordination/</loc><changefreq>weekly</changefreq><priority>0.3</priority></url>
+ <url><loc>https://munderdiffl.in/blog/tags/messaging/</loc><changefreq>weekly</changefreq><priority>0.3</priority></url>
+ <url><loc>https://munderdiffl.in/blog/tags/glossary/</loc><changefreq>weekly</changefreq><priority>0.3</priority></url>
+ <url><loc>https://munderdiffl.in/blog/tags/faq/</loc><changefreq>weekly</changefreq><priority>0.3</priority></url>
+ <url><loc>https://munderdiffl.in/blog/tags/concurrency/</loc><changefreq>weekly</changefreq><priority>0.3</priority></url>
+ <url><loc>https://munderdiffl.in/blog/tags/local-first/</loc><changefreq>weekly</changefreq><priority>0.3</priority></url>
+ <url><loc>https://munderdiffl.in/blog/tags/privacy/</loc><changefreq>weekly</changefreq><priority>0.3</priority></url>
+ <url><loc>https://munderdiffl.in/blog/tags/open-source/</loc><changefreq>weekly</changefreq><priority>0.3</priority></url>
+ <url><loc>https://munderdiffl.in/blog/tags/xtermjs/</loc><changefreq>weekly</changefreq><priority>0.3</priority></url>
+ <url><loc>https://munderdiffl.in/blog/tags/hooks/</loc><changefreq>weekly</changefreq><priority>0.3</priority></url>
+ <url><loc>https://munderdiffl.in/blog/tags/mcp/</loc><changefreq>weekly</changefreq><priority>0.3</priority></url>
+ <url><loc>https://munderdiffl.in/blog/tags/skills/</loc><changefreq>weekly</changefreq><priority>0.3</priority></url>
+ <url><loc>https://munderdiffl.in/blog/tags/node-pty/</loc><changefreq>weekly</changefreq><priority>0.3</priority></url>
+ <url><loc>https://munderdiffl.in/blog/tags/autonomous/</loc><changefreq>weekly</changefreq><priority>0.3</priority></url>
</urlset>