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
HTML agent-harnessagent-orchestrationagentsai-agentsautonomous-agentsclaude-codecodexcoding-agentsdesktop-appdeveloper-toolselectrongemini-cliharnessharness-engineeringlocal-firstmemorymulti-agentopencodeorchestrationtypescript
chore(blog): final static build for the 38-post batch + screenshots
Chaitanya Giriac941e4018bc
diff --git a/blog/screenshots/index-desktop.png b/blog/screenshots/index-desktop.pngindex e7114929..9049f251 100644Binary files a/blog/screenshots/index-desktop.png and b/blog/screenshots/index-desktop.png differdiff --git a/blog/screenshots/index-mobile.png b/blog/screenshots/index-mobile.pngindex 9f1c3d8b..87cb5794 100644Binary files a/blog/screenshots/index-mobile.png and b/blog/screenshots/index-mobile.png differdiff --git a/blog/screenshots/post-desktop.png b/blog/screenshots/post-desktop.pngindex 339d78b2..abafac49 100644Binary files a/blog/screenshots/post-desktop.png and b/blog/screenshots/post-desktop.png differdiff --git a/blog/screenshots/post-mobile.png b/blog/screenshots/post-mobile.pngindex e85f27da..fc321004 100644Binary files a/blog/screenshots/post-mobile.png and b/blog/screenshots/post-mobile.png differdiff --git a/blog/screenshots/post2-desktop.png b/blog/screenshots/post2-desktop.pngindex d41fb8b2..4d74a3ad 100644Binary files a/blog/screenshots/post2-desktop.png and b/blog/screenshots/post2-desktop.png differdiff --git a/blog/screenshots/post2-mobile.png b/blog/screenshots/post2-mobile.pngindex 07b1e7ed..9d86c1c3 100644Binary files a/blog/screenshots/post2-mobile.png and b/blog/screenshots/post2-mobile.png differdiff --git a/docs/blog/append-only-event-log-agents/index.html b/docs/blog/append-only-event-log-agents/index.htmlindex 972743a3..02c65f59 100644--- a/docs/blog/append-only-event-log-agents/index.html+++ b/docs/blog/append-only-event-log-agents/index.html@@ -4,7 +4,7 @@<meta charset="UTF-8" /><meta name="viewport" content="width=device-width, initial-scale=1.0" /><title>An Append-Only Event Log for a Hive of Agents — Munder Difflin Blog</title>-<meta name="description" content="How an append-only event log makes a multi-agent system debuggable and replayable — what to record per event, and why one JSON line per event beats a database." />+<meta name="description" content="How an append-only event log makes a multi-agent system debuggable and replayable: what to record, and why one JSON line per event beats a database." /><link rel="canonical" href="https://munderdiffl.in/blog/append-only-event-log-agents/" /><link rel="icon" type="image/png" href="https://munderdiffl.in/logo.png" />@@ -15,7 +15,7 @@<meta property="og:site_name" content="Munder Difflin Blog" /><meta property="og:type" content="article" /><meta property="og:title" content="An Append-Only Event Log for a Hive of Agents — Munder Difflin Blog" />-<meta property="og:description" content="How an append-only event log makes a multi-agent system debuggable and replayable — what to record per event, and why one JSON line per event beats a database." />+<meta property="og:description" content="How an append-only event log makes a multi-agent system debuggable and replayable: what to record, and why one JSON line per event beats a database." /><meta property="og:url" content="https://munderdiffl.in/blog/append-only-event-log-agents/" /><meta property="og:image" content="https://munderdiffl.in/media/og.png" /><meta property="og:locale" content="en_US" />@@ -30,7 +30,7 @@<!-- Twitter --><meta name="twitter:card" content="summary_large_image" /><meta name="twitter:title" content="An Append-Only Event Log for a Hive of Agents — Munder Difflin Blog" />-<meta name="twitter:description" content="How an append-only event log makes a multi-agent system debuggable and replayable — what to record per event, and why one JSON line per event beats a database." />+<meta name="twitter:description" content="How an append-only event log makes a multi-agent system debuggable and replayable: what to record, and why one JSON line per event beats a database." /><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" />@@ -44,7 +44,7 @@"@context": "https://schema.org","@type": "BlogPosting","headline": "An Append-Only Event Log for a Hive of Agents",- "description": "How an append-only event log makes a multi-agent system debuggable and replayable — what to record per event, and why one JSON line per event beats a database.",+ "description": "How an append-only event log makes a multi-agent system debuggable and replayable: what to record, and why one JSON line per event beats a database.","image": ["https://munderdiffl.in/media/og.png"],"datePublished": "2026-06-01T00:00:00.000Z","dateModified": "2026-06-01T00:00:00.000Z",@@ -118,7 +118,7 @@<a href="/blog/topics/internals/">Internals</a></nav><h1>An Append-Only Event Log for a Hive of Agents</h1>- <p class="dek">How an append-only event log makes a multi-agent system debuggable and replayable — what to record per event, and why one JSON line per event beats a database.</p>+ <p class="dek">How an append-only event log makes a multi-agent system debuggable and replayable: what to record, and why one JSON line per event beats a database.</p><div class="byline"><span class="av" aria-hidden="true">CG</span><strong>Chaitanya Giri</strong>@@ -230,8 +230,9 @@ the debuggability benefit without committing to rebuild-everything-from-events.<append-only JSONL file is queryable, replayable, and durable — you can read it weeks later andreconstruct exactly what the hive did.</p><hr>-<p>Munder Difflin records every coordination step to an append-only event log that drives the live-activity feed and makes a hive replayable — committed alongside the rest of its state.+<p>Munder Difflin records every coordination step to an append-only event log that drives+<a href="https://munderdiffl.in/#how">the live activity feed</a> and makes a hive replayable — committed+alongside the rest of its state.<a href="https://munderdiffl.in/#install">Download Munder Difflin</a> to watch a hive you can actually audit;it’s free and open source.</p>@@ -285,56 +286,56 @@ it’s free and open source.</p><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">+ <a class="thumb t-internals" href="/blog/architecture-two-planes-one-renderer/" aria-hidden="true" tabindex="-1"><span>INTERNALS</span></a><div class="body"><div class="meta">- <time datetime="2026-06-03">Jun 3, 2026</time>+ <time datetime="2026-06-04">Jun 4, 2026</time><span class="dot" aria-hidden="true"></span>- <span>8 min</span>+ <span>5 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>+ <h3><a href="/blog/architecture-two-planes-one-renderer/">Munder Difflin's Architecture: Two Data Planes, One Renderer</a></h3>+ <p class="dek">A walkthrough of the multi-agent harness architecture: a node-pty terminal plane and a hooks/hive event plane feeding one React + Pixi.js renderer.</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>+ <a class="more" href="/blog/architecture-two-planes-one-renderer/" aria-label="Read: Munder Difflin's Architecture: Two Data Planes, One Renderer">Read →</a></div></div></article><article class="card">- <a class="thumb t-internals" href="/blog/claude-code-hooks-explained/" aria-hidden="true" tabindex="-1">+ <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>6 min</span>+ <span>8 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>+ <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/claude-code-hooks-explained/" aria-label="Read: Claude Code Hooks, Explained (PreToolUse, PostToolUse, Stop)">Read →</a>+ <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">+ <a class="thumb t-internals" href="/blog/building-an-ai-office-floor/" 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>+ <span>6 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>+ <h3><a href="/blog/building-an-ai-office-floor/">Building an AI "Office Floor": Avatars, Pathfinding, Envelopes</a></h3>+ <p class="dek">The game-dev techniques behind a dev tool's office floor: Tiled maps, BFS pathfinding, sprite recoloring, and flying message envelopes in Pixi.js.</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>+ <a class="more" href="/blog/building-an-ai-office-floor/" aria-label="Read: Building an AI "Office Floor": Avatars, Pathfinding, Envelopes">Read →</a></div></div></article>diff --git a/docs/blog/architecture-two-planes-one-renderer/index.html b/docs/blog/architecture-two-planes-one-renderer/index.htmlnew file mode 100644index 00000000..c498160e--- /dev/null+++ b/docs/blog/architecture-two-planes-one-renderer/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>Munder Difflin's Architecture: Two Data Planes, One Renderer — Munder Difflin Blog</title>+<meta name="description" content="A walkthrough of the multi-agent harness architecture: a node-pty terminal plane and a hooks/hive event plane feeding one React + Pixi.js renderer." />+<link rel="canonical" href="https://munderdiffl.in/blog/architecture-two-planes-one-renderer/" />++<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's Architecture: Two Data Planes, One Renderer — Munder Difflin Blog" />+<meta property="og:description" content="A walkthrough of the multi-agent harness architecture: a node-pty terminal plane and a hooks/hive event plane feeding one React + Pixi.js renderer." />+<meta property="og:url" content="https://munderdiffl.in/blog/architecture-two-planes-one-renderer/" />+<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="Internals" />+<meta property="article:tag" content="Architecture" />+<meta property="article:tag" content="Electron" />+<meta property="article:tag" content="Multi-Agent" />+++<!-- Twitter -->+<meta name="twitter:card" content="summary_large_image" />+<meta name="twitter:title" content="Munder Difflin's Architecture: Two Data Planes, One Renderer — Munder Difflin Blog" />+<meta name="twitter:description" content="A walkthrough of the multi-agent harness architecture: a node-pty terminal plane and a hooks/hive event plane feeding one React + Pixi.js renderer." />+<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's Architecture: Two Data Planes, One Renderer",+ "description": "A walkthrough of the multi-agent harness architecture: a node-pty terminal plane and a hooks/hive event plane feeding one React + Pixi.js renderer.",+ "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/architecture-two-planes-one-renderer/" },+ "keywords": "multi-agent harness architecture, electron architecture, ipc, agent harness design",+ "articleSection": "Internals",+ "inLanguage": "en-US",+ "url": "https://munderdiffl.in/blog/architecture-two-planes-one-renderer/"+}+</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's Architecture: Two Data Planes, One Renderer", "item": "https://munderdiffl.in/blog/architecture-two-planes-one-renderer/" }+ ]+}+</script>++<script type="application/ld+json">+{+ "@context": "https://schema.org",+ "@type": "FAQPage",+ "mainEntity": [+ { "@type": "Question", "name": "What are the two data planes in Munder Difflin?", "acceptedAnswer": { "@type": "Answer", "text": "The terminal plane carries raw pseudo-terminal bytes from each agent's shell (node-pty) to an xterm.js view. The event plane carries structured agent state — Claude Code hook events and routed hive messages — to the office-floor visualization. One is byte-for-byte authentic; the other is event-driven." } },+ { "@type": "Question", "name": "Why separate the terminal stream from the event stream?", "acceptedAnswer": { "@type": "Answer", "text": "Each answers a different question. The raw terminal stream shows exactly what the agent output; the event stream tells you which tool is running without parsing that output. Hooks alone miss the stream the user expects to see; the stream alone can't reliably say what's happening. Together they cover both." } },+ { "@type": "Question", "name": "How do the planes reach the UI?", "acceptedAnswer": { "@type": "Answer", "text": "Through Electron IPC. The main process owns the PTYs, a hook socket, and the hive; it forwards terminal bytes and structured events to the renderer, where React and Pixi.js draw the terminals and the office floor." } }++ ]+}+</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>Munder Difflin's Architecture: Two Data Planes, One Renderer</h1>+ <p class="dek">A walkthrough of the multi-agent harness architecture: a node-pty terminal plane and a hooks/hive event plane feeding one React + Pixi.js renderer.</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">Internals</span>+ </div>+ </header>++ <div class="post-wrap wrap">+ <div class="prose">+ <div class="callout tldr"><span class="ic">TL;DR</span><p>The+<strong>multi-agent harness architecture</strong> rests on one decision: <strong>two data+planes</strong>. A <strong>terminal plane</strong> streams raw node-pty bytes to xterm.js (authentic+shells), and an <strong>event plane</strong> carries structured Claude Code hook events plus routed+hive messages to a Pixi.js office floor (what's happening, at a glance). Both flow over Electron IPC+into <strong>one React + Pixi renderer</strong>. The terminal plane is the truth; the event plane is+the story.</p></div>+<p>Most of what Munder Difflin does follows from a single architectural choice, so it’s worth walking+through. The harness runs many real Claude Code agents and shows you two things about each: the exact+terminal output, and a live picture of what it’s doing. Those are different kinds of data, so they+travel on <strong>two separate planes</strong> that meet in one renderer. Here’s the whole shape.</p>+<h2 id="the-load-bearing-decision-two-planes" tabindex="-1">The load-bearing decision: two planes <a class="anchor" href="#the-load-bearing-decision-two-planes" aria-hidden="true">#</a></h2>+<pre><code>┌──────────────────── Electron Renderer (React + Pixi) ───────────────────┐+│ Office floor (Pixi.js) Terminal view (xterm.js) │+│ ▲ avatar state ▲ pty bytes │+└────────┼──────────────────────────────────┼────────────────────────────┘+ │ IPC │ IPC+ ┌─────┴───────────────┐ ┌──────┴──────────────┐+ │ Event Plane │ │ Terminal Plane │+ │ hooks + hive router │ │ node-pty │+ └─────▲───────────────┘ └──────▲──────────────┘+ │ JSON events │ raw bytes+ ┌─────┴───────────────────────────────────┴──────────────┐+ │ Claude Code processes (one per agent) │+ └────────────────────────────────────────────────────────┘+</code></pre>+<p>Each agent is one real <code>claude</code> process. From it we read two streams:</p>+<ul>+<li>a <strong>byte stream</strong> — exactly what the shell printed, and</li>+<li>an <strong>event stream</strong> — structured “I’m about to use this tool,” “a message routed,” “I stopped.”</li>+</ul>+<p>Keeping them separate is the whole trick. Let’s take each plane, then how they converge.</p>+<h2 id="the-terminal-plane-node-pty" tabindex="-1">The terminal plane (node-pty) <a class="anchor" href="#the-terminal-plane-node-pty" aria-hidden="true">#</a></h2>+<p>The terminal plane is about <em>fidelity</em>. Each agent runs in a real pseudo-terminal via+<a href="/blog/node-pty-electron-real-terminals/">node-pty</a>, so its shell behaves byte-for-byte like a normal+terminal — colors, prompts, full-screen TUIs, all authentic. The main process owns the PTY and+forwards its output to the renderer over IPC on a per-session channel; keystrokes from the UI travel+back the same way. The renderer paints it with a pooled xterm.js terminal per agent (the technique+behind <a href="/blog/rendering-many-live-terminals-performance/">rendering many live terminals</a>).</p>+<p>What the terminal plane gives you: the unfiltered truth of what each agent did. What it <em>can’t</em> easily+give you: a reliable “which tool is running right now?” without scraping and guessing at output. That’s+the other plane’s job.</p>+<h2 id="the-event-plane-hooks-hive" tabindex="-1">The event plane (hooks + hive) <a class="anchor" href="#the-event-plane-hooks-hive" aria-hidden="true">#</a></h2>+<p>The event plane is about <em>structure</em>. It has two sources, both feeding the main process:</p>+<p><strong>Claude Code hooks.</strong> Each agent is launched with lifecycle hooks wired through a tiny shim that+forwards every event — <code>PreToolUse</code>, <code>PostToolUse</code>, <code>Stop</code>, <code>Notification</code> — to a Unix domain socket+the main process listens on. These are clean, typed signals: “about to run Bash,” “finished editing,”+“idle and waiting.” No output parsing required. (See+<a href="/blog/claude-code-hooks-explained/">Claude Code hooks, explained</a>.)</p>+<p><strong>The hive.</strong> The coordination layer — per-agent mailboxes, a message router, single-committer git, and+shared memory — emits its own events as it works: a message routed from A to B, an item escalated to+the human. The <a href="/blog/how-the-god-orchestrator-works/">GOD orchestrator</a> lives here as the+intelligence; the main process is the mechanism that moves messages and commits state.</p>+<p>Both sources land in the main process, which forwards structured events to the renderer. There they+drive the office floor: avatars walk to stations on tool events, envelopes fly on message events.</p>+<h2 id="why-both-planes-the-rationale" tabindex="-1">Why both planes (the rationale) <a class="anchor" href="#why-both-planes-the-rationale" aria-hidden="true">#</a></h2>+<p>The temptation is to pick one. Each alone is insufficient:</p>+<ul>+<li><strong>Hooks alone</strong> don’t give you the raw stream the user expects to <em>see</em> — you’d know an agent ran a+command but not what it printed.</li>+<li><strong>The terminal stream alone</strong> can’t tell you which tool is running without fragile output parsing —+you’d see bytes but have to guess at meaning.</li>+</ul>+<p>Together they’re complementary: the office floor is <strong>event-driven</strong> (precise, structured, cheap to+render), and the terminal view is <strong>byte-for-byte authentic</strong> (the full detail when you want it). Two+planes, two questions, both answered well.</p>+<h2 id="one-renderer-convergence" tabindex="-1">One renderer convergence <a class="anchor" href="#one-renderer-convergence" aria-hidden="true">#</a></h2>+<p>Both planes terminate in a single Electron renderer running React and Pixi.js:</p>+<ul>+<li><strong>React</strong> owns the app shell, panels, and the xterm.js terminal views (the terminal plane).</li>+<li><strong>Pixi.js</strong> owns the office floor — avatars, the Tiled map, flying envelopes (the event plane), in+one camera-controlled world updated by a single ticker (the design in+<a href="/blog/visualizing-ai-agents-pixijs/">visualizing AI agents with Pixi.js</a>).</li>+</ul>+<p>The bridge between the main process and the renderer is a typed <strong>preload API</strong> exposed over Electron’s+context bridge — the renderer calls into it to spawn/write/resize PTYs and read hive state, and+subscribes to it for incoming terminal bytes and hive events. Crucially, the renderer never touches the+filesystem, git, or the agents directly; it only talks to the main process. That keeps a hard line+between <em>mechanism</em> (main process: PTYs, sockets, git, routing) and <em>presentation</em> (renderer: React ++Pixi).</p>+<h2 id="why-this-architecture-holds-up" tabindex="-1">Why this architecture holds up <a class="anchor" href="#why-this-architecture-holds-up" aria-hidden="true">#</a></h2>+<p>A few properties fall out of the two-plane design:</p>+<ul>+<li><strong>Separation of concerns.</strong> Fidelity and structure are independent problems solved independently. You+can improve terminal rendering without touching the event pipeline, and vice versa.</li>+<li><strong>The main process is the single source of authority.</strong> PTYs, the hook socket, the hive’s git repo,+and the memory layer all live in one place; the renderer is a consumer. That’s what makes the+<a href="/blog/single-committer-git-pattern/">single-committer git pattern</a> and safe IPC possible.</li>+<li><strong>Real, not simulated.</strong> Because the event plane carries actual hook and router events, the+visualization can’t drift from reality — it <em>is</em> reality, rendered.</li>+</ul>+<p>It’s the architecture that lets “a hive of Claude Code agents” be both something you can <em>read</em> (the+terminals) and something you can <em>watch</em> (the floor) — which is the heart of what a+<a href="https://munderdiffl.in/#what">multi-agent harness</a> is.</p>+<h2 id="faq" tabindex="-1">FAQ <a class="anchor" href="#faq" aria-hidden="true">#</a></h2>+<p><strong>Where does memory fit in the two planes?</strong> Alongside the event plane’s hive layer. The shared+semantic memory is driven by the main process (a CLI it points each agent at), and recall happens in+the agents themselves — it’s part of the coordination mechanism, not a third UI plane.</p>+<p><strong>Could you add a third plane?</strong> You could, but the discipline is to keep planes orthogonal. New+signals usually fit the event plane (more structured events) or the terminal plane (more byte+streams) rather than needing a new one.</p>+<hr>+<p>Munder Difflin’s two-plane architecture — authentic node-pty terminals plus an event-driven Pixi.js+floor, converging in one renderer — is what makes a hive both legible and real.+<a href="https://munderdiffl.in/#install">Download Munder Difflin</a> to see the architecture in action; 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 the two data planes in Munder Difflin?</p>+ <p class="a">The terminal plane carries raw pseudo-terminal bytes from each agent's shell (node-pty) to an xterm.js view. The event plane carries structured agent state — Claude Code hook events and routed hive messages — to the office-floor visualization. One is byte-for-byte authentic; the other is event-driven.</p>+ </div>++ <div class="qa">+ <p class="q">Why separate the terminal stream from the event stream?</p>+ <p class="a">Each answers a different question. The raw terminal stream shows exactly what the agent output; the event stream tells you which tool is running without parsing that output. Hooks alone miss the stream the user expects to see; the stream alone can't reliably say what's happening. Together they cover both.</p>+ </div>++ <div class="qa">+ <p class="q">How do the planes reach the UI?</p>+ <p class="a">Through Electron IPC. The main process owns the PTYs, a hook socket, and the hive; it forwards terminal bytes and structured events to the renderer, where React and Pixi.js draw the terminals and the office floor.</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/architecture/">Architecture</a><a class="tag" href="/blog/tags/electron/">Electron</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-load-bearing-decision-two-planes">The load-bearing decision: two planes</a></li><li class="lvl-2"><a href="#the-terminal-plane-node-pty">The terminal plane (node-pty)</a></li><li class="lvl-2"><a href="#the-event-plane-hooks-hive">The event plane (hooks + hive)</a></li><li class="lvl-2"><a href="#why-both-planes-the-rationale">Why both planes (the rationale)</a></li><li class="lvl-2"><a href="#one-renderer-convergence">One renderer convergence</a></li><li class="lvl-2"><a href="#why-this-architecture-holds-up">Why this architecture 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/best-claude-code-multi-agent-tools/"><span class="k">← Older</span><span class="t">The Best Tools to Run Multiple Claude Code Agents (2026)</span></a>+ <span></span>+ </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/building-an-ai-office-floor/" 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/building-an-ai-office-floor/">Building an AI "Office Floor": Avatars, Pathfinding, Envelopes</a></h3>+ <p class="dek">The game-dev techniques behind a dev tool's office floor: Tiled maps, BFS pathfinding, sprite recoloring, and flying message envelopes in Pixi.js.</p>+ <div class="foot">+ <span class="tag kind">Internals</span>+ <a class="more" href="/blog/building-an-ai-office-floor/" aria-label="Read: Building an AI "Office Floor": Avatars, Pathfinding, Envelopes">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>++ </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 & 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/atomic-file-mailboxes-for-agents/index.html b/docs/blog/atomic-file-mailboxes-for-agents/index.htmlindex dee21a4e..d16f80f8 100644--- a/docs/blog/atomic-file-mailboxes-for-agents/index.html+++ b/docs/blog/atomic-file-mailboxes-for-agents/index.html@@ -246,7 +246,7 @@ 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 isagent-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+<p>Munder Difflin runs exactly this mailbox system inside <a href="https://munderdiffl.in/#how">a hive the GOD orchestrator runs</a> — atomicdelivery, 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 onthe office floor; it’s free and open source.</p>@@ -301,56 +301,56 @@ the office floor; it’s free and open source.</p><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">+ <a class="thumb t-internals" href="/blog/architecture-two-planes-one-renderer/" aria-hidden="true" tabindex="-1"><span>INTERNALS</span></a><div class="body"><div class="meta">- <time datetime="2026-06-03">Jun 3, 2026</time>+ <time datetime="2026-06-04">Jun 4, 2026</time><span class="dot" aria-hidden="true"></span>- <span>8 min</span>+ <span>5 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>+ <h3><a href="/blog/architecture-two-planes-one-renderer/">Munder Difflin's Architecture: Two Data Planes, One Renderer</a></h3>+ <p class="dek">A walkthrough of the multi-agent harness architecture: a node-pty terminal plane and a hooks/hive event plane feeding one React + Pixi.js renderer.</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>+ <a class="more" href="/blog/architecture-two-planes-one-renderer/" aria-label="Read: Munder Difflin's Architecture: Two Data Planes, One Renderer">Read →</a></div></div></article><article class="card">- <a class="thumb t-internals" href="/blog/claude-code-hooks-explained/" aria-hidden="true" tabindex="-1">+ <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>6 min</span>+ <span>8 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>+ <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/claude-code-hooks-explained/" aria-label="Read: Claude Code Hooks, Explained (PreToolUse, PostToolUse, Stop)">Read →</a>+ <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">+ <a class="thumb t-internals" href="/blog/building-an-ai-office-floor/" 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>+ <span>6 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>+ <h3><a href="/blog/building-an-ai-office-floor/">Building an AI "Office Floor": Avatars, Pathfinding, Envelopes</a></h3>+ <p class="dek">The game-dev techniques behind a dev tool's office floor: Tiled maps, BFS pathfinding, sprite recoloring, and flying message envelopes in Pixi.js.</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>+ <a class="more" href="/blog/building-an-ai-office-floor/" aria-label="Read: Building an AI "Office Floor": Avatars, Pathfinding, Envelopes">Read →</a></div></div></article>diff --git a/docs/blog/best-claude-code-multi-agent-tools/index.html b/docs/blog/best-claude-code-multi-agent-tools/index.htmlindex 37600f2f..01d496c3 100644--- a/docs/blog/best-claude-code-multi-agent-tools/index.html+++ b/docs/blog/best-claude-code-multi-agent-tools/index.html@@ -349,7 +349,7 @@ real team of agents.</p><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>+ <a class="pn next" href="/blog/architecture-two-planes-one-renderer/"><span class="k">Newer →</span><span class="t">Munder Difflin's Architecture: Two Data Planes, One Renderer</span></a></div><section class="related"><h2>Related in Comparisons</h2>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.htmlindex 72766fab..25471e10 100644--- a/docs/blog/building-a-terminal-ui-xterm-node-pty/index.html+++ b/docs/blog/building-a-terminal-ui-xterm-node-pty/index.html@@ -272,7 +272,9 @@ unsubscribe from the stream, <code>term.dispose()</code>, and drop it from the psessions, 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>+streaming PTYs — gets its own deep dive in+<a href="/blog/rendering-many-live-terminals-performance/">rendering many live terminals without melting the CPU</a>,+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 watchthem stream simultaneously. Every detail above is load-bearing for that: real shells from@@ -335,63 +337,63 @@ to watch many real terminals at once; it’s free and open source.</p></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>+ <a class="pn prev" href="/blog/building-an-ai-office-floor/"><span class="k">← Older</span><span class="t">Building an AI "Office Floor": Avatars, Pathfinding, Envelopes</span></a>+ <a class="pn next" href="/blog/debugging-multi-agent-systems/"><span class="k">Newer →</span><span class="t">How to Debug a Multi-Agent System</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">+ <a class="thumb t-internals" href="/blog/architecture-two-planes-one-renderer/" aria-hidden="true" tabindex="-1"><span>INTERNALS</span></a><div class="body"><div class="meta">- <time datetime="2026-06-03">Jun 3, 2026</time>+ <time datetime="2026-06-04">Jun 4, 2026</time><span class="dot" aria-hidden="true"></span>- <span>6 min</span>+ <span>5 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>+ <h3><a href="/blog/architecture-two-planes-one-renderer/">Munder Difflin's Architecture: Two Data Planes, One Renderer</a></h3>+ <p class="dek">A walkthrough of the multi-agent harness architecture: a node-pty terminal plane and a hooks/hive event plane feeding one React + Pixi.js renderer.</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>+ <a class="more" href="/blog/architecture-two-planes-one-renderer/" aria-label="Read: Munder Difflin's Architecture: Two Data Planes, One Renderer">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">+ <a class="thumb t-internals" href="/blog/building-an-ai-office-floor/" 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>+ <span>6 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>+ <h3><a href="/blog/building-an-ai-office-floor/">Building an AI "Office Floor": Avatars, Pathfinding, Envelopes</a></h3>+ <p class="dek">The game-dev techniques behind a dev tool's office floor: Tiled maps, BFS pathfinding, sprite recoloring, and flying message envelopes in Pixi.js.</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>+ <a class="more" href="/blog/building-an-ai-office-floor/" aria-label="Read: Building an AI "Office Floor": Avatars, Pathfinding, Envelopes">Read →</a></div></div></article><article class="card">- <a class="thumb t-internals" href="/blog/single-committer-git-pattern/" aria-hidden="true" tabindex="-1">+ <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="2026-06-02">Jun 2, 2026</time>+ <time datetime="2026-06-03">Jun 3, 2026</time><span class="dot" aria-hidden="true"></span>- <span>5 min</span>+ <span>6 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>+ <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/single-committer-git-pattern/" aria-label="Read: The Single-Committer Pattern: Multi-Agent Git Without Corruption">Read →</a>+ <a class="more" href="/blog/claude-code-hooks-explained/" aria-label="Read: Claude Code Hooks, Explained (PreToolUse, PostToolUse, Stop)">Read →</a></div></div></article>diff --git a/docs/blog/building-an-ai-office-floor/index.html b/docs/blog/building-an-ai-office-floor/index.htmlnew file mode 100644index 00000000..c9621dc6--- /dev/null+++ b/docs/blog/building-an-ai-office-floor/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>Building an AI "Office Floor": Avatars, Pathfinding, Envelopes — Munder Difflin Blog</title>+<meta name="description" content="The game-dev techniques behind a dev tool's office floor: Tiled maps, BFS pathfinding, sprite recoloring, and flying message envelopes in Pixi.js." />+<link rel="canonical" href="https://munderdiffl.in/blog/building-an-ai-office-floor/" />++<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 an AI "Office Floor": Avatars, Pathfinding, Envelopes — Munder Difflin Blog" />+<meta property="og:description" content="The game-dev techniques behind a dev tool's office floor: Tiled maps, BFS pathfinding, sprite recoloring, and flying message envelopes in Pixi.js." />+<meta property="og:url" content="https://munderdiffl.in/blog/building-an-ai-office-floor/" />+<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="Pixi.js" />+<meta property="article:tag" content="Game Dev" />+<meta property="article:tag" content="Visualization" />+++<!-- Twitter -->+<meta name="twitter:card" content="summary_large_image" />+<meta name="twitter:title" content="Building an AI "Office Floor": Avatars, Pathfinding, Envelopes — Munder Difflin Blog" />+<meta name="twitter:description" content="The game-dev techniques behind a dev tool's office floor: Tiled maps, BFS pathfinding, sprite recoloring, and flying message envelopes in Pixi.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" />++<script type="application/ld+json">+{+ "@context": "https://schema.org",+ "@type": "BlogPosting",+ "headline": "Building an AI \"Office Floor\": Avatars, Pathfinding, Envelopes",+ "description": "The game-dev techniques behind a dev tool's office floor: Tiled maps, BFS pathfinding, sprite recoloring, and flying message envelopes in Pixi.js.",+ "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-an-ai-office-floor/" },+ "keywords": "ai agent visualization, tiled maps, pathfinding, game-ui for tools",+ "articleSection": "Internals",+ "inLanguage": "en-US",+ "url": "https://munderdiffl.in/blog/building-an-ai-office-floor/"+}+</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 an AI \"Office Floor\": Avatars, Pathfinding, Envelopes", "item": "https://munderdiffl.in/blog/building-an-ai-office-floor/" }+ ]+}+</script>++<script type="application/ld+json">+{+ "@context": "https://schema.org",+ "@type": "FAQPage",+ "mainEntity": [+ { "@type": "Question", "name": "What game-dev techniques does an AI office floor use?", "acceptedAnswer": { "@type": "Answer", "text": "Tiled tile maps for the level, a grid pathfinder for movement, sprite-sheet slicing and recoloring for distinct avatars, a seat-reservation pool for desk assignment, and tween-based animation for flying message envelopes — all rendered with a 2D engine like Pixi.js." } },+ { "@type": "Question", "name": "Do you need a game engine to build an office floor?", "acceptedAnswer": { "@type": "Answer", "text": "No — a 2D renderer like Pixi.js plus a few classic techniques is enough. The map comes from the Tiled editor, pathfinding is a small BFS, and avatars are sprite sheets. It's game tech, but lightweight enough to live inside a developer tool." } },+ { "@type": "Question", "name": "How are the avatars made distinct?", "acceptedAnswer": { "@type": "Answer", "text": "They start from a shared character walk sheet and are recolored per character with palette recipes (skin, hair, shirt), so each agent reads as a different person on the floor without drawing every sprite by hand." } }++ ]+}+</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 an AI "Office Floor": Avatars, Pathfinding, Envelopes</h1>+ <p class="dek">The game-dev techniques behind a dev tool's office floor: Tiled maps, BFS pathfinding, sprite recoloring, and flying message envelopes in Pixi.js.</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>An <strong>AI agent visualization</strong>+that looks like a tiny office game uses ordinary game-dev tech: a <strong>Tiled</strong> tile map for+the floor, a small <strong>BFS pathfinder</strong> for movement, <strong>sprite-sheet</strong> slicing++ recoloring for distinct avatars, a <strong>seat pool</strong> for desk assignment, and tweened+<strong>envelopes</strong> for messages — all in Pixi.js. None of it is heavy; it's game craft applied+to a developer tool.</p></div>+<p>The office floor in Munder Difflin looks like a little workplace sim, and that’s on purpose — a+spatial, game-like view makes a hive of agents legible. Under the hood it’s a handful of classic+game-development techniques, kept deliberately lightweight so they fit inside a dev tool. This post is+the techniques tour. (For <em>why</em> a visualization matters and the Pixi.js plumbing, start with+<a href="/blog/visualizing-ai-agents-pixijs/">visualizing AI agents with Pixi.js</a>.)</p>+<p>A note up front: several of these pieces are ported from an open-source 2D office game+(shahar061/the-office), with character art from LimeZu’s sprite packs. Standing on game-dev shoulders+is exactly the point — these are solved problems.</p>+<h2 id="the-floor-is-a-tiled-map" tabindex="-1">The floor is a Tiled map <a class="anchor" href="#the-floor-is-a-tiled-map" aria-hidden="true">#</a></h2>+<p>The office isn’t drawn in code; it’s authored in <strong>Tiled</strong>, the standard 2D map editor, and exported as+a <code>.tmj</code> (JSON) file. The renderer reads its layers:</p>+<ul>+<li><strong>Tile layers</strong> — floor, walls, furniture — drawn from tileset textures. Each tile references a+global id, resolved back to the right tileset by its <code>firstgid</code> offset.</li>+<li>A <strong>collision layer</strong> — which tiles are solid (walls, desks) versus walkable floor.</li>+<li>A <strong>spawn-points</strong> object layer — named anchors for desks and seats.</li>+</ul>+<p>Because the level is data, changing the office is a <em>design</em> task: open the map in Tiled, move a desk,+re-export. No code changes to rearrange the furniture. One subtlety worth stealing: desk/seat tiles are+marked solid for collision but force-flagged <em>walkable</em> for pathing, so an avatar can walk <em>onto</em> its+chair instead of treating it as a wall.</p>+<h2 id="movement-is-grid-pathfinding" tabindex="-1">Movement is grid pathfinding <a class="anchor" href="#movement-is-grid-pathfinding" aria-hidden="true">#</a></h2>+<p>Avatars walk from their desk to a station and back. The pathfinder is a <strong>breadth-first search</strong> on the+map’s walkability grid — four-directional, no diagonals:</p>+<pre class="language-ts"><code class="language-ts"><span class="token comment">// BFS over walkable tiles → shortest tile path from start to goal</span>+<span class="token keyword">function</span> <span class="token function">findPath</span><span class="token punctuation">(</span>map<span class="token punctuation">,</span> start<span class="token punctuation">,</span> goal<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>map<span class="token punctuation">.</span><span class="token function">isWalkable</span><span class="token punctuation">(</span>goal<span class="token punctuation">.</span>x<span class="token punctuation">,</span> goal<span class="token punctuation">.</span>y<span class="token punctuation">)</span><span class="token punctuation">)</span> <span class="token keyword">return</span> <span class="token keyword">null</span><span class="token punctuation">;</span>+ <span class="token keyword">const</span> queue <span class="token operator">=</span> <span class="token punctuation">[</span>start<span class="token punctuation">]</span><span class="token punctuation">,</span> visited <span class="token operator">=</span> <span class="token keyword">new</span> <span class="token class-name">Set</span><span class="token punctuation">(</span><span class="token punctuation">[</span><span class="token function">key</span><span class="token punctuation">(</span>start<span class="token punctuation">)</span><span class="token punctuation">]</span><span class="token punctuation">)</span><span class="token punctuation">,</span> parent <span class="token operator">=</span> <span class="token keyword">new</span> <span class="token class-name">Map</span><span class="token punctuation">(</span><span class="token punctuation">)</span><span class="token punctuation">;</span>+ <span class="token keyword">while</span> <span class="token punctuation">(</span>queue<span class="token punctuation">.</span>length<span class="token punctuation">)</span> <span class="token punctuation">{</span>+ <span class="token keyword">const</span> cur <span class="token operator">=</span> queue<span class="token punctuation">.</span><span class="token function">shift</span><span class="token punctuation">(</span><span class="token punctuation">)</span><span class="token punctuation">;</span>+ <span class="token keyword">for</span> <span class="token punctuation">(</span><span class="token keyword">const</span> d <span class="token keyword">of</span> <span class="token punctuation">[</span><span class="token punctuation">{</span>x<span class="token operator">:</span><span class="token number">0</span><span class="token punctuation">,</span>y<span class="token operator">:</span><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>x<span class="token operator">:</span><span class="token number">0</span><span class="token punctuation">,</span>y<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>x<span class="token operator">:</span><span class="token operator">-</span><span class="token number">1</span><span class="token punctuation">,</span>y<span class="token operator">:</span><span class="token number">0</span><span class="token punctuation">}</span><span class="token punctuation">,</span><span class="token punctuation">{</span>x<span class="token operator">:</span><span class="token number">1</span><span class="token punctuation">,</span>y<span class="token operator">:</span><span class="token number">0</span><span class="token punctuation">}</span><span class="token punctuation">]</span><span class="token punctuation">)</span> <span class="token punctuation">{</span>+ <span class="token keyword">const</span> next <span class="token operator">=</span> <span class="token punctuation">{</span> x<span class="token operator">:</span> cur<span class="token punctuation">.</span>x <span class="token operator">+</span> d<span class="token punctuation">.</span>x<span class="token punctuation">,</span> y<span class="token operator">:</span> cur<span class="token punctuation">.</span>y <span class="token operator">+</span> d<span class="token punctuation">.</span>y <span class="token punctuation">}</span><span class="token punctuation">;</span>+ <span class="token keyword">if</span> <span class="token punctuation">(</span>visited<span class="token punctuation">.</span><span class="token function">has</span><span class="token punctuation">(</span><span class="token function">key</span><span class="token punctuation">(</span>next<span class="token punctuation">)</span><span class="token punctuation">)</span> <span class="token operator">||</span> <span class="token operator">!</span>map<span class="token punctuation">.</span><span class="token function">isWalkable</span><span class="token punctuation">(</span>next<span class="token punctuation">.</span>x<span class="token punctuation">,</span> next<span class="token punctuation">.</span>y<span class="token punctuation">)</span><span class="token punctuation">)</span> <span class="token keyword">continue</span><span class="token punctuation">;</span>+ visited<span class="token punctuation">.</span><span class="token function">add</span><span class="token punctuation">(</span><span class="token function">key</span><span class="token punctuation">(</span>next<span class="token punctuation">)</span><span class="token punctuation">)</span><span class="token punctuation">;</span> parent<span class="token punctuation">.</span><span class="token function">set</span><span class="token punctuation">(</span><span class="token function">key</span><span class="token punctuation">(</span>next<span class="token punctuation">)</span><span class="token punctuation">,</span> cur<span class="token punctuation">)</span><span class="token punctuation">;</span>+ <span class="token keyword">if</span> <span class="token punctuation">(</span>next<span class="token punctuation">.</span>x <span class="token operator">===</span> goal<span class="token punctuation">.</span>x <span class="token operator">&&</span> next<span class="token punctuation">.</span>y <span class="token operator">===</span> goal<span class="token punctuation">.</span>y<span class="token punctuation">)</span> <span class="token keyword">return</span> <span class="token function">reconstruct</span><span class="token punctuation">(</span>parent<span class="token punctuation">,</span> start<span class="token punctuation">,</span> goal<span class="token punctuation">)</span><span class="token punctuation">;</span>+ queue<span class="token punctuation">.</span><span class="token function">push</span><span class="token punctuation">(</span>next<span class="token punctuation">)</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 keyword">null</span><span class="token punctuation">;</span>+<span class="token punctuation">}</span></code></pre>+<p>On an unweighted grid, BFS returns the shortest path for free — no heuristic, no priority queue, no A*+needed at office scale. It’s a dozen lines and it’s correct, which is the right trade for a map this+size.</p>+<h2 id="avatars-one-sheet-many-people" tabindex="-1">Avatars: one sheet, many people <a class="anchor" href="#avatars-one-sheet-many-people" aria-hidden="true">#</a></h2>+<p>Drawing fifteen unique characters by hand would be a slog. Instead, avatars start from a shared+<strong>character walk sheet</strong> and are made distinct by <em>recoloring</em>:</p>+<ul>+<li>A <strong>sprite adapter</strong> slices the sheet into frames — walk cycles for each facing direction. The sheet+packs directions in a known order (right, up, left, down); the adapter maps them into the+three-row grid the renderer wants, and <em>left</em> is just <em>right</em> drawn flipped, so you store fewer+frames.</li>+<li>The <strong>character sprite</strong> plays walk / type / read / idle animations and applies a small <strong>leg-crop+mask</strong> when an agent sits, so it tucks under the desk instead of standing on it.</li>+<li>Each character gets a <strong>palette recipe</strong> — skin, hair, shirt — so the cast is visually distinct from+one base sheet. (If the cast looks suspiciously like a certain paper company’s staff, that’s not an+accident.)</li>+</ul>+<p>The payoff: a recognizable, individuated team without an artist hand-drawing every avatar.</p>+<h2 id="seats-a-reservation-pool" tabindex="-1">Seats: a reservation pool <a class="anchor" href="#seats-a-reservation-pool" aria-hidden="true">#</a></h2>+<p>When an agent joins, it needs a desk. A tiny <strong>seat pool</strong> holds the ordered list of spawn points from+the map and hands out the first free one, releasing it when the agent leaves:</p>+<pre class="language-ts"><code class="language-ts"><span class="token function">reserveNext</span><span class="token punctuation">(</span><span class="token punctuation">)</span> <span class="token punctuation">{</span> <span class="token comment">// first unclaimed seat, in map order</span>+ <span class="token keyword">for</span> <span class="token punctuation">(</span><span class="token keyword">const</span> seat <span class="token keyword">of</span> <span class="token keyword">this</span><span class="token punctuation">.</span>seats<span class="token punctuation">)</span>+ <span class="token keyword">if</span> <span class="token punctuation">(</span><span class="token operator">!</span><span class="token keyword">this</span><span class="token punctuation">.</span>claimed<span class="token punctuation">.</span><span class="token function">has</span><span class="token punctuation">(</span>seat<span class="token punctuation">)</span><span class="token punctuation">)</span> <span class="token punctuation">{</span> <span class="token keyword">this</span><span class="token punctuation">.</span>claimed<span class="token punctuation">.</span><span class="token function">add</span><span class="token punctuation">(</span>seat<span class="token punctuation">)</span><span class="token punctuation">;</span> <span class="token keyword">return</span> seat<span class="token punctuation">;</span> <span class="token punctuation">}</span>+ <span class="token keyword">return</span> <span class="token keyword">null</span><span class="token punctuation">;</span> <span class="token comment">// office is full</span>+<span class="token punctuation">}</span></code></pre>+<p>First-come, first-served, one desk each — so a growing team fills the office in order rather than+stacking onto one chair. Thirty-three lines of bookkeeping that make dynamic agents Just Work.</p>+<h2 id="envelopes-messages-you-can-see-fly" tabindex="-1">Envelopes: messages you can see fly <a class="anchor" href="#envelopes-messages-you-can-see-fly" aria-hidden="true">#</a></h2>+<p>When the hive routes a message between agents, the floor spawns a little pixel <strong>envelope</strong> that arcs+from the sender’s desk to the recipient’s. The animation is a quadratic arc — lerp the endpoints, lift+the midpoint with a sine — eased in and out, with a small burst ring on arrival. The envelope is+<strong>tinted by the message’s speech act</strong>: asks are cool-colored, agreements and confirmations warm,+refusals red, and an escalation to the human a distinct color. So you don’t just see <em>that</em> a message+moved — you see <em>who asked whom, and what kind of ask it was</em>, at a glance.</p>+<p>That envelope is pure presentation riding on real data: it only flies because the+<a href="/blog/atomic-file-mailboxes-for-agents/">message router</a> actually delivered something.</p>+<h2 id="keeping-it-lightweight" tabindex="-1">Keeping it lightweight <a class="anchor" href="#keeping-it-lightweight" aria-hidden="true">#</a></h2>+<p>The whole point is that this is <em>game tech in a dev tool</em>, not a game. So the implementation stays+lean: pixel-art settings (no antialias, nearest-neighbor scaling, integer positions), a single shared+animation ticker, and a camera that transforms one world container rather than every sprite. That+discipline is what lets the floor run alongside a fleet of live terminals without contention — the same+performance mindset as <a href="/blog/rendering-many-live-terminals-performance/">rendering many live terminals</a>.</p>+<h2 id="why-borrow-from-games-at-all" tabindex="-1">Why borrow from games at all <a class="anchor" href="#why-borrow-from-games-at-all" aria-hidden="true">#</a></h2>+<p>Developer tools usually present work as text. A spatial, animated floor borrows what games are great at+— making <em>state</em> immediately readable through position and motion — and applies it to “what is my team+of agents doing?” The techniques are old and solved; the novelty is pointing them at observability+instead of entertainment. An avatar at the terminal, an envelope in flight, a teammate waving for your+input: that’s a status dashboard you read with your eyes instead of your patience.</p>+<h2 id="faq" tabindex="-1">FAQ <a class="anchor" href="#faq" aria-hidden="true">#</a></h2>+<p><strong>Is the office floor just eye candy?</strong> No — it’s observability. Every position and motion maps to a+real event (a tool call, a routed message), so the floor is a live, glanceable read of the hive’s+state, not decoration.</p>+<p><strong>Do I need to know game dev to build something like this?</strong> Not deeply. A 2D renderer, the Tiled+editor, a BFS, and sprite sheets get you most of the way. These are approachable, well-documented+techniques — the hard part is wiring them to <em>real</em> agent events, not the rendering.</p>+<hr>+<p>Munder Difflin’s <a href="https://munderdiffl.in/#how">office floor</a> turns a hive of Claude Code agents into a little workplace you can watch+— Tiled maps, pathing avatars, and flying envelopes, all driven by real activity.+<a href="https://munderdiffl.in/#install">Download Munder Difflin</a> to see it run; 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 game-dev techniques does an AI office floor use?</p>+ <p class="a">Tiled tile maps for the level, a grid pathfinder for movement, sprite-sheet slicing and recoloring for distinct avatars, a seat-reservation pool for desk assignment, and tween-based animation for flying message envelopes — all rendered with a 2D engine like Pixi.js.</p>+ </div>++ <div class="qa">+ <p class="q">Do you need a game engine to build an office floor?</p>+ <p class="a">No — a 2D renderer like Pixi.js plus a few classic techniques is enough. The map comes from the Tiled editor, pathfinding is a small BFS, and avatars are sprite sheets. It's game tech, but lightweight enough to live inside a developer tool.</p>+ </div>++ <div class="qa">+ <p class="q">How are the avatars made distinct?</p>+ <p class="a">They start from a shared character walk sheet and are recolored per character with palette recipes (skin, hair, shirt), so each agent reads as a different person on the floor without drawing every sprite by hand.</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/pixijs/">Pixi.js</a><a class="tag" href="/blog/tags/game-dev/">Game Dev</a><a class="tag" href="/blog/tags/visualization/">Visualization</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-floor-is-a-tiled-map">The floor is a Tiled map</a></li><li class="lvl-2"><a href="#movement-is-grid-pathfinding">Movement is grid pathfinding</a></li><li class="lvl-2"><a href="#avatars-one-sheet-many-people">Avatars: one sheet, many people</a></li><li class="lvl-2"><a href="#seats-a-reservation-pool">Seats: a reservation pool</a></li><li class="lvl-2"><a href="#envelopes-messages-you-can-see-fly">Envelopes: messages you can see fly</a></li><li class="lvl-2"><a href="#keeping-it-lightweight">Keeping it lightweight</a></li><li class="lvl-2"><a href="#why-borrow-from-games-at-all">Why borrow from games at all</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/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/architecture-two-planes-one-renderer/" aria-hidden="true" tabindex="-1">+ <span>INTERNALS</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/architecture-two-planes-one-renderer/">Munder Difflin's Architecture: Two Data Planes, One Renderer</a></h3>+ <p class="dek">A walkthrough of the multi-agent harness architecture: a node-pty terminal plane and a hooks/hive event plane feeding one React + Pixi.js renderer.</p>+ <div class="foot">+ <span class="tag kind">Internals</span>+ <a class="more" href="/blog/architecture-two-planes-one-renderer/" aria-label="Read: Munder Difflin's Architecture: Two Data Planes, One Renderer">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>++ </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 & 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.htmlindex 48614b34..172d7c94 100644--- a/docs/blog/claude-code-automation-while-you-sleep/index.html+++ b/docs/blog/claude-code-automation-while-you-sleep/index.html@@ -191,8 +191,10 @@ escalate to a human queue instead of executing. A good default critical list:</p<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>+it makes itself, critical ones it routes to an approvals queue — the+<a href="/blog/human-in-the-loop-ai-agents/">human-in-the-loop approvals</a> that keep an overnight run safe. 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: “addvalidation to these three forms, with tests.” Bounded scope means the queue drains to empty — which,@@ -229,7 +231,7 @@ shouldn’t be handed open-ended mandates with money or production access. The rdiligent overnight shift with a clear ticket list and a manager who escalates — not a genie. Keep thegoals 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+<p>Munder Difflin gives you <a href="https://munderdiffl.in/#why">everything an overnight hive needs</a>: an autonomous Stop-hook loop, an auto mode that skips routineapprovals, 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 buildwhile you sleep; it’s free and open source.</p>@@ -284,56 +286,56 @@ while you sleep; it’s free and open source.</p><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">+ <a class="thumb t-guides" href="/blog/debugging-multi-agent-systems/" aria-hidden="true" tabindex="-1"><span>GUIDES</span></a><div class="body"><div class="meta">- <time datetime="2026-06-03">Jun 3, 2026</time>+ <time datetime="2026-06-04">Jun 4, 2026</time><span class="dot" aria-hidden="true"></span>- <span>6 min</span>+ <span>5 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>+ <h3><a href="/blog/debugging-multi-agent-systems/">How to Debug a Multi-Agent System</a></h3>+ <p class="dek">How to debug a multi-agent system: use the event log, per-agent terminals, message trails, and git history to find why a hive of AI agents went sideways.</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>+ <a class="more" href="/blog/debugging-multi-agent-systems/" aria-label="Read: How to Debug a Multi-Agent System">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">+ <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="2026-06-01">Jun 1, 2026</time>+ <time datetime="2026-06-03">Jun 3, 2026</time><span class="dot" aria-hidden="true"></span>- <span>3 min</span>+ <span>6 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>+ <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/how-to-run-multiple-claude-code-agents/" aria-label="Read: How to Run Multiple Claude Code Agents (Without Losing Track)">Read →</a>+ <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">+ <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="2026-05-25">May 25, 2026</time>+ <time datetime="2026-06-01">Jun 1, 2026</time><span class="dot" aria-hidden="true"></span>- <span>4 min</span>+ <span>3 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>+ <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/manage-multiple-claude-code-sessions/" aria-label="Read: How to Manage Multiple Claude Code Sessions Like a Pro">Read →</a>+ <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>diff --git a/docs/blog/claude-code-git-worktrees-vs-hive/index.html b/docs/blog/claude-code-git-worktrees-vs-hive/index.htmlindex acd4e5b7..71af1e13 100644--- a/docs/blog/claude-code-git-worktrees-vs-hive/index.html+++ b/docs/blog/claude-code-git-worktrees-vs-hive/index.html@@ -224,7 +224,8 @@ steering wheel.</p><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>+scale. For a concrete tool-vs-tool take on that coordination layer, see+<a href="/blog/claude-squad-vs-munder-difflin/">Claude Squad vs Munder Difflin</a>.</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, whichare the common ones. Shared refs and the object store are still common, so concurrent operations that@@ -234,7 +235,7 @@ repo even when agents work in separate worktrees.</p>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+<p>Munder Difflin is <a href="https://munderdiffl.in/#how">the coordination layer</a>: shared memory, messaging, and a GOD orchestrator for a hiveof 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 ateam; it’s free and open source.</p>@@ -299,7 +300,7 @@ team; it’s free and open source.</p><span>5 min</span></div><h3><a href="/blog/human-in-the-loop-ai-agents/">Human-in-the-Loop AI Agents: Approvals That Don't Slow You Down</a></h3>- <p class="dek">Design human-in-the-loop AI agents that stay autonomous: an approvals queue that escalates only spend, destructive ops, and scope — and relays your answer back.</p>+ <p class="dek">Design human-in-the-loop AI agents that stay autonomous: an approvals queue that escalates only spend, destructive ops, and scope changes.</p><div class="foot"><span class="tag kind">Orchestration</span><a class="more" href="/blog/human-in-the-loop-ai-agents/" aria-label="Read: Human-in-the-Loop AI Agents: Approvals That Don't Slow You Down">Read →</a>diff --git a/docs/blog/claude-code-hooks-explained/index.html b/docs/blog/claude-code-hooks-explained/index.htmlindex 202fc04f..71cad87e 100644--- a/docs/blog/claude-code-hooks-explained/index.html+++ b/docs/blog/claude-code-hooks-explained/index.html@@ -212,7 +212,8 @@ flags and environment variables.</p><p>Every tool event the harness receives is forwarded to the UI. That’s what drives the office floor: whenan agent calls a file tool, its avatar walks to the right station; when it runs a command, it moves toa 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>+<em>real</em> activity rather than a scripted animation or fragile log-scraping — and it pairs with each+agent’s actual live terminal, <a href="/blog/rendering-many-live-terminals-performance/">streamed without melting the CPU</a>.</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’sinbox for unread messages. If there are any, it returns <code>{"decision":"block","reason": <the messages>}</code> — so instead of stopping, the agent reads its new messages and keeps working. If the inbox@@ -247,7 +248,7 @@ queue for that judgment, but the hook-level gate is available.</p>payload over a local socket adds negligible overhead, which is exactly why the heavy logic liveselsewhere.</p><hr>-<p>Munder Difflin turns Claude Code’s hook lifecycle into a live, autonomous office: real-time avatars+<p>Munder Difflin turns Claude Code’s hook lifecycle into <a href="https://munderdiffl.in/#how">a live, autonomous office</a>: real-time avatarsfrom 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’sfree and open source.</p>@@ -296,62 +297,62 @@ free and open source.</p><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>+ <a class="pn next" href="/blog/building-an-ai-office-floor/"><span class="k">Newer →</span><span class="t">Building an AI "Office Floor": Avatars, Pathfinding, Envelopes</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">+ <a class="thumb t-internals" href="/blog/architecture-two-planes-one-renderer/" aria-hidden="true" tabindex="-1"><span>INTERNALS</span></a><div class="body"><div class="meta">- <time datetime="2026-06-03">Jun 3, 2026</time>+ <time datetime="2026-06-04">Jun 4, 2026</time><span class="dot" aria-hidden="true"></span>- <span>8 min</span>+ <span>5 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>+ <h3><a href="/blog/architecture-two-planes-one-renderer/">Munder Difflin's Architecture: Two Data Planes, One Renderer</a></h3>+ <p class="dek">A walkthrough of the multi-agent harness architecture: a node-pty terminal plane and a hooks/hive event plane feeding one React + Pixi.js renderer.</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>+ <a class="more" href="/blog/architecture-two-planes-one-renderer/" aria-label="Read: Munder Difflin's Architecture: Two Data Planes, One Renderer">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">+ <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>7 min</span>+ <span>8 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>+ <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/node-pty-electron-real-terminals/" aria-label="Read: Real Terminals in Electron with node-pty">Read →</a>+ <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/single-committer-git-pattern/" aria-hidden="true" tabindex="-1">+ <a class="thumb t-internals" href="/blog/building-an-ai-office-floor/" aria-hidden="true" tabindex="-1"><span>INTERNALS</span></a><div class="body"><div class="meta">- <time datetime="2026-06-02">Jun 2, 2026</time>+ <time datetime="2026-06-03">Jun 3, 2026</time><span class="dot" aria-hidden="true"></span>- <span>5 min</span>+ <span>6 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>+ <h3><a href="/blog/building-an-ai-office-floor/">Building an AI "Office Floor": Avatars, Pathfinding, Envelopes</a></h3>+ <p class="dek">The game-dev techniques behind a dev tool's office floor: Tiled maps, BFS pathfinding, sprite recoloring, and flying message envelopes in Pixi.js.</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>+ <a class="more" href="/blog/building-an-ai-office-floor/" aria-label="Read: Building an AI "Office Floor": Avatars, Pathfinding, Envelopes">Read →</a></div></div></article>diff --git a/docs/blog/claude-code-multi-agent-setup-tutorial/index.html b/docs/blog/claude-code-multi-agent-setup-tutorial/index.htmlindex d1bf33fc..215ac202 100644--- a/docs/blog/claude-code-multi-agent-setup-tutorial/index.html+++ b/docs/blog/claude-code-multi-agent-setup-tutorial/index.html@@ -298,38 +298,38 @@ coordinated team of Claude Code agents — it’s free, local, and open source.<</div></article><article class="card">- <a class="thumb t-guides" href="/blog/mcp-and-skills-in-a-hive/" aria-hidden="true" tabindex="-1">+ <a class="thumb t-guides" href="/blog/debugging-multi-agent-systems/" aria-hidden="true" tabindex="-1"><span>GUIDES</span></a><div class="body"><div class="meta">- <time datetime="2026-06-03">Jun 3, 2026</time>+ <time datetime="2026-06-04">Jun 4, 2026</time><span class="dot" aria-hidden="true"></span>- <span>6 min</span>+ <span>5 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>+ <h3><a href="/blog/debugging-multi-agent-systems/">How to Debug a Multi-Agent System</a></h3>+ <p class="dek">How to debug a multi-agent system: use the event log, per-agent terminals, message trails, and git history to find why a hive of AI agents went sideways.</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>+ <a class="more" href="/blog/debugging-multi-agent-systems/" aria-label="Read: How to Debug a Multi-Agent System">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">+ <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="2026-06-01">Jun 1, 2026</time>+ <time datetime="2026-06-03">Jun 3, 2026</time><span class="dot" aria-hidden="true"></span>- <span>3 min</span>+ <span>6 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>+ <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/how-to-run-multiple-claude-code-agents/" aria-label="Read: How to Run Multiple Claude Code Agents (Without Losing Track)">Read →</a>+ <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>diff --git a/docs/blog/claude-code-orchestration-guide/index.html b/docs/blog/claude-code-orchestration-guide/index.htmlindex e2facce0..c39857bc 100644--- a/docs/blog/claude-code-orchestration-guide/index.html+++ b/docs/blog/claude-code-orchestration-guide/index.html@@ -234,7 +234,7 @@ 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 exchangeyou 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+<p>Munder Difflin ships this <a href="https://munderdiffl.in/#how">orchestration model</a> out of the box: a GOD agent you talk to, a reliablemessage 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 Codeagents; it’s free and open source.</p>@@ -317,7 +317,7 @@ agents; it’s free and open source.</p><span>5 min</span></div><h3><a href="/blog/human-in-the-loop-ai-agents/">Human-in-the-Loop AI Agents: Approvals That Don't Slow You Down</a></h3>- <p class="dek">Design human-in-the-loop AI agents that stay autonomous: an approvals queue that escalates only spend, destructive ops, and scope — and relays your answer back.</p>+ <p class="dek">Design human-in-the-loop AI agents that stay autonomous: an approvals queue that escalates only spend, destructive ops, and scope changes.</p><div class="foot"><span class="tag kind">Orchestration</span><a class="more" href="/blog/human-in-the-loop-ai-agents/" aria-label="Read: Human-in-the-Loop AI Agents: Approvals That Don't Slow You Down">Read →</a>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.htmlindex 674cfaa0..b1e44f70 100644--- a/docs/blog/claude-code-subagents-vs-multi-agent-harness/index.html+++ b/docs/blog/claude-code-subagents-vs-multi-agent-harness/index.html@@ -255,7 +255,8 @@ gives you a coordinated team.</p></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>+and for a concrete head-to-head of two ways to get a team, see+<a href="/blog/claude-squad-vs-munder-difflin/">Claude Squad vs Munder Difflin</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 thebigger additions are <em>shared memory</em> and <em>direct inter-agent messaging</em> — a subagent that merely lived@@ -337,38 +338,38 @@ open source.</p></div></article><article class="card">- <a class="thumb t-guides" href="/blog/mcp-and-skills-in-a-hive/" aria-hidden="true" tabindex="-1">+ <a class="thumb t-guides" href="/blog/debugging-multi-agent-systems/" aria-hidden="true" tabindex="-1"><span>GUIDES</span></a><div class="body"><div class="meta">- <time datetime="2026-06-03">Jun 3, 2026</time>+ <time datetime="2026-06-04">Jun 4, 2026</time><span class="dot" aria-hidden="true"></span>- <span>6 min</span>+ <span>5 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>+ <h3><a href="/blog/debugging-multi-agent-systems/">How to Debug a Multi-Agent System</a></h3>+ <p class="dek">How to debug a multi-agent system: use the event log, per-agent terminals, message trails, and git history to find why a hive of AI agents went sideways.</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>+ <a class="more" href="/blog/debugging-multi-agent-systems/" aria-label="Read: How to Debug a Multi-Agent System">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">+ <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="2026-06-01">Jun 1, 2026</time>+ <time datetime="2026-06-03">Jun 3, 2026</time><span class="dot" aria-hidden="true"></span>- <span>3 min</span>+ <span>6 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>+ <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/how-to-run-multiple-claude-code-agents/" aria-label="Read: How to Run Multiple Claude Code Agents (Without Losing Track)">Read →</a>+ <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>diff --git a/docs/blog/claude-squad-vs-munder-difflin/index.html b/docs/blog/claude-squad-vs-munder-difflin/index.htmlindex a3780339..24733a41 100644--- a/docs/blog/claude-squad-vs-munder-difflin/index.html+++ b/docs/blog/claude-squad-vs-munder-difflin/index.html@@ -295,7 +295,7 @@ local-first.</p></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 prev" href="/blog/debugging-multi-agent-systems/"><span class="k">← Older</span><span class="t">How to Debug a Multi-Agent System</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">diff --git a/docs/blog/coordinating-ai-coding-agents/index.html b/docs/blog/coordinating-ai-coding-agents/index.htmlindex d04c8e15..24e283ff 100644--- a/docs/blog/coordinating-ai-coding-agents/index.html+++ b/docs/blog/coordinating-ai-coding-agents/index.html@@ -222,8 +222,8 @@ other’s files.</li>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+message router, a single-committer git layer, a single-scribe shared board, and a+<a href="https://munderdiffl.in/#how">GOD orchestrator</a> — all local and open source. <a href="https://munderdiffl.in/#install">Download Munder Difflin</a> to coordinateyour own team of Claude Code agents.</p>@@ -304,7 +304,7 @@ your own team of Claude Code agents.</p><span>5 min</span></div><h3><a href="/blog/human-in-the-loop-ai-agents/">Human-in-the-Loop AI Agents: Approvals That Don't Slow You Down</a></h3>- <p class="dek">Design human-in-the-loop AI agents that stay autonomous: an approvals queue that escalates only spend, destructive ops, and scope — and relays your answer back.</p>+ <p class="dek">Design human-in-the-loop AI agents that stay autonomous: an approvals queue that escalates only spend, destructive ops, and scope changes.</p><div class="foot"><span class="tag kind">Orchestration</span><a class="more" href="/blog/human-in-the-loop-ai-agents/" aria-label="Read: Human-in-the-Loop AI Agents: Approvals That Don't Slow You Down">Read →</a>diff --git a/docs/blog/debugging-multi-agent-systems/index.html b/docs/blog/debugging-multi-agent-systems/index.htmlnew file mode 100644index 00000000..c0d3ea39--- /dev/null+++ b/docs/blog/debugging-multi-agent-systems/index.html@@ -0,0 +1,370 @@+<!doctype html>+<html lang="en">+<head>+<meta charset="UTF-8" />+<meta name="viewport" content="width=device-width, initial-scale=1.0" />+<title>How to Debug a Multi-Agent System — Munder Difflin Blog</title>+<meta name="description" content="How to debug a multi-agent system: use the event log, per-agent terminals, message trails, and git history to find why a hive of AI agents went sideways." />+<link rel="canonical" href="https://munderdiffl.in/blog/debugging-multi-agent-systems/" />++<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 Debug a Multi-Agent System — Munder Difflin Blog" />+<meta property="og:description" content="How to debug a multi-agent system: use the event log, per-agent terminals, message trails, and git history to find why a hive of AI agents went sideways." />+<meta property="og:url" content="https://munderdiffl.in/blog/debugging-multi-agent-systems/" />+<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="Debugging" />+<meta property="article:tag" content="Observability" />+<meta property="article:tag" content="Multi-Agent" />+++<!-- Twitter -->+<meta name="twitter:card" content="summary_large_image" />+<meta name="twitter:title" content="How to Debug a Multi-Agent System — Munder Difflin Blog" />+<meta name="twitter:description" content="How to debug a multi-agent system: use the event log, per-agent terminals, message trails, and git history to find why a hive of AI agents went sideways." />+<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 Debug a Multi-Agent System",+ "description": "How to debug a multi-agent system: use the event log, per-agent terminals, message trails, and git history to find why a hive of AI agents went sideways.",+ "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/debugging-multi-agent-systems/" },+ "keywords": "debug multi-agent system, multi-agent debugging, agent observability, event log",+ "articleSection": "Guides",+ "inLanguage": "en-US",+ "url": "https://munderdiffl.in/blog/debugging-multi-agent-systems/"+}+</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 Debug a Multi-Agent System", "item": "https://munderdiffl.in/blog/debugging-multi-agent-systems/" }+ ]+}+</script>++<script type="application/ld+json">+{+ "@context": "https://schema.org",+ "@type": "FAQPage",+ "mainEntity": [+ { "@type": "Question", "name": "How do you debug a multi-agent system?", "acceptedAnswer": { "@type": "Answer", "text": "Start from the timeline, not a single agent. Read the append-only event log to find when things diverged, follow the message trail between the agents involved, then drop into the specific agent's terminal for the byte-level detail. The order — log, messages, terminal — keeps you from guessing." } },+ { "@type": "Question", "name": "Why is debugging multiple agents harder than one?", "acceptedAnswer": { "@type": "Answer", "text": "Concurrency and interaction. A bug may not live in any one agent but in how two of them coordinated — a misrouted message, a missed handoff, a shared assumption that was wrong. You need the cross-agent view, not just per-agent logs." } },+ { "@type": "Question", "name": "What's the single most useful artifact for multi-agent debugging?", "acceptedAnswer": { "@type": "Answer", "text": "The append-only event log. It's the ordered, immutable timeline of everything that happened — who spawned, who messaged whom, what escalated — so you can replay the run and find the exact event where it went wrong." } }++ ]+}+</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 Debug a Multi-Agent System</h1>+ <p class="dek">How to debug a multi-agent system: use the event log, per-agent terminals, message trails, and git history to find why a hive of AI agents went sideways.</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>To+<strong>debug a multi-agent system</strong>, work from the outside in: read the+<strong>event log</strong> to find when the run diverged, follow the <strong>message trail</strong>+between the agents involved, then open the offending agent's <strong>terminal</strong> for byte-level+detail — and use <strong>git history</strong> to replay the coordination state. The bug often lives in+the interaction between agents, not inside any one of them, so start with the timeline.</p></div>+<p>Debugging one agent is familiar: read its output, find the bad step. Debugging a <em>hive</em> is different,+because the failure is often relational — two agents coordinated wrong, a message went to the wrong+place, a handoff never happened. Staring at a single agent’s terminal won’t show you that. This is a+practical method for finding out why a multi-agent system went sideways, using the observability a+well-built hive already gives you.</p>+<h2 id="start-with-the-timeline-not-an-agent" tabindex="-1">Start with the timeline, not an agent <a class="anchor" href="#start-with-the-timeline-not-an-agent" aria-hidden="true">#</a></h2>+<p>The first instinct — “open the agent that misbehaved” — is usually the slow path. The fast path is the+<a href="/blog/append-only-event-log-agents/">append-only event log</a>: the ordered, immutable record of+everything the hive did. Every spawn, every routed message, every escalation and approval is one+timestamped line. Read it and you get the <em>sequence</em>, which is exactly what a per-agent view hides.</p>+<p>Scan the log for the moment things diverged from what you expected:</p>+<ul>+<li>a message routed to the wrong agent (or never routed),</li>+<li>an escalation that should have fired and didn’t (or fired when it shouldn’t),</li>+<li>an agent that went idle while it still had work,</li>+<li>a burst of activity where there should have been calm.</li>+</ul>+<p>The event where reality and expectation part is your starting point. Now you know <em>which agents</em> and+<em>which moment</em> to investigate — instead of reading six terminals hoping to spot it.</p>+<h2 id="follow-the-message-trail" tabindex="-1">Follow the message trail <a class="anchor" href="#follow-the-message-trail" aria-hidden="true">#</a></h2>+<p>Multi-agent bugs frequently live in the messaging. Once the log points you at the agents involved,+follow the trail their mailboxes leave. Because messaging is file-based+(<a href="/blog/atomic-file-mailboxes-for-agents/">atomic file mailboxes</a>), the evidence is sitting on disk:</p>+<ul>+<li>An agent’s <strong>outbox archive</strong> (sent messages) shows exactly what it asked for, and how it phrased the+request.</li>+<li>An agent’s <strong>inbox</strong> and its <strong>handled folder</strong> show what it received and what it acted on.</li>+<li>The <strong>speech act</strong> on each message (<code>request</code>, <code>inform</code>, <code>done</code>…) tells you whether a reply was even+expected — a common bug is one agent replying to a terminal <code>inform</code> and starting a loop, or <em>not</em>+replying to a <code>request</code> and leaving a peer stuck.</li>+</ul>+<p>Reading the trail answers the relational question: did A actually ask B what you think it did, and did+B get it? Half of “the hive stalled” bugs resolve right here — a message that was malformed, misrouted,+or never sent.</p>+<h2 id="drop-into-the-agents-terminal" tabindex="-1">Drop into the agent’s terminal <a class="anchor" href="#drop-into-the-agents-terminal" aria-hidden="true">#</a></h2>+<p>Now — and only now — open the specific agent’s terminal. Because every agent runs in a real+pseudo-terminal, you have its byte-for-byte output, not a summary. With the log and the message trail+having narrowed <em>which</em> agent and <em>which</em> moment, the terminal gives you the detail: the exact command+that failed, the error it hit, the reasoning it printed. This is where a multi-agent bug finally+becomes a single-agent bug you can fix.</p>+<p>The office floor helps here too: the <a href="/blog/visualizing-ai-agents-pixijs/">live visualization</a> shows+you, at a glance, which agent is blocked (waving at the mailbox), which is spinning, and which went+idle — often pointing you at the right terminal before you’ve even opened the log.</p>+<h2 id="replay-with-git" tabindex="-1">Replay with git <a class="anchor" href="#replay-with-git" aria-hidden="true">#</a></h2>+<p>The hive’s coordination state lives in a git repo that the main process commits to as it works (the+<a href="/blog/single-committer-git-pattern/">single-committer pattern</a>). That makes the whole run+<strong>replayable</strong>: each coordination step is a commit, so you can walk the history and reconstruct exactly+what the hive knew at any point — the roster, the pending messages, the board. When “what state was the+system in when it broke?” matters, the git log answers it precisely instead of from memory.</p>+<h2 id="check-the-usual-suspects" tabindex="-1">Check the usual suspects <a class="anchor" href="#check-the-usual-suspects" aria-hidden="true">#</a></h2>+<p>Some failure modes recur in multi-agent systems. When you’re stuck, check these directly:</p>+<ul>+<li><strong>Livelock.</strong> Two agents ping-ponging. The log shows a tight back-and-forth; the fix is usually a+message type that shouldn’t have obligated a reply, or a hop cap that should have escalated.</li>+<li><strong>A stuck agent.</strong> One agent waiting on a reply that never came. The message trail shows the unanswered+<code>request</code>; the peer either didn’t receive it or didn’t treat it as needing a reply.</li>+<li><strong>Reprocessing.</strong> An agent acting on the same message twice. Check its cursor and whether handled+messages were moved aside — idempotent handling should make re-seeing a message a no-op.</li>+<li><strong>A silent escalation.</strong> Something critical that should have reached the human but didn’t (or vice+versa). The approvals queue and the log’s escalation events tell you what the policy actually did.</li>+</ul>+<h2 id="build-for-debuggability-up-front" tabindex="-1">Build for debuggability up front <a class="anchor" href="#build-for-debuggability-up-front" aria-hidden="true">#</a></h2>+<p>The reason this method works is that the observability was designed in, not bolted on. If you’re+building a multi-agent system, the lesson is to make it debuggable <em>before</em> you need to debug it:</p>+<ul>+<li>record an <strong>append-only event log</strong> so you always have a timeline,</li>+<li>keep messaging <strong>file-based and archived</strong> so trails persist,</li>+<li>give each agent a <strong>real terminal</strong> so detail is never lost, and</li>+<li>commit coordination state to <strong>git</strong> so any moment is replayable.</li>+</ul>+<p>Get those four right and “why did the hive do that?” stops being a mystery and becomes a query.</p>+<h2 id="faq" tabindex="-1">FAQ <a class="anchor" href="#faq" aria-hidden="true">#</a></h2>+<p><strong>Can I debug without stopping the agents?</strong> Yes — the log, message files, and git history are all+read-only artifacts you can inspect while the hive runs. The visualization is live. You rarely need to+halt the team to understand it.</p>+<p><strong>What if the bug is in my orchestrator’s judgment?</strong> That’s a prompt problem, not a code problem. The+log shows you the routing decision that went wrong; you correct the orchestrator’s instructions (its+escalation and routing policy) rather than patching the mechanism.</p>+<hr>+<p>Munder Difflin makes a hive debuggable by design: an event log, file-based message trails, real+per-agent terminals, a git-committed history, and <a href="https://munderdiffl.in/#how">a live floor</a>. <a href="https://munderdiffl.in/#install">Download Munder Difflin</a>+to run agents you can actually trace; 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 you debug a multi-agent system?</p>+ <p class="a">Start from the timeline, not a single agent. Read the append-only event log to find when things diverged, follow the message trail between the agents involved, then drop into the specific agent's terminal for the byte-level detail. The order — log, messages, terminal — keeps you from guessing.</p>+ </div>++ <div class="qa">+ <p class="q">Why is debugging multiple agents harder than one?</p>+ <p class="a">Concurrency and interaction. A bug may not live in any one agent but in how two of them coordinated — a misrouted message, a missed handoff, a shared assumption that was wrong. You need the cross-agent view, not just per-agent logs.</p>+ </div>++ <div class="qa">+ <p class="q">What's the single most useful artifact for multi-agent debugging?</p>+ <p class="a">The append-only event log. It's the ordered, immutable timeline of everything that happened — who spawned, who messaged whom, what escalated — so you can replay the run and find the exact event where it went wrong.</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/debugging/">Debugging</a><a class="tag" href="/blog/tags/observability/">Observability</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="#start-with-the-timeline-not-an-agent">Start with the timeline, not an agent</a></li><li class="lvl-2"><a href="#follow-the-message-trail">Follow the message trail</a></li><li class="lvl-2"><a href="#drop-into-the-agents-terminal">Drop into the agent’s terminal</a></li><li class="lvl-2"><a href="#replay-with-git">Replay with git</a></li><li class="lvl-2"><a href="#check-the-usual-suspects">Check the usual suspects</a></li><li class="lvl-2"><a href="#build-for-debuggability-up-front">Build for debuggability up front</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/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-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 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 & 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.xmlindex 92597f33..11441661 100644--- a/docs/blog/feed.xml+++ b/docs/blog/feed.xml@@ -7,6 +7,14 @@<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>Munder Difflin's Architecture: Two Data Planes, One Renderer</title>+ <link href="https://munderdiffl.in/blog/architecture-two-planes-one-renderer/" />+ <id>https://munderdiffl.in/blog/architecture-two-planes-one-renderer/</id>+ <published>2026-06-04T00:00:00.000Z</published>+ <updated>2026-06-04T00:00:00.000Z</updated><category term="Internals" />+ <summary>A walkthrough of the multi-agent harness architecture: a node-pty terminal plane and a hooks/hive event plane feeding one React + Pixi.js renderer.</summary>+ </entry><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/" />@@ -47,6 +55,14 @@<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>How to Debug a Multi-Agent System</title>+ <link href="https://munderdiffl.in/blog/debugging-multi-agent-systems/" />+ <id>https://munderdiffl.in/blog/debugging-multi-agent-systems/</id>+ <published>2026-06-04T00:00:00.000Z</published>+ <updated>2026-06-04T00:00:00.000Z</updated><category term="Guides" />+ <summary>How to debug a multi-agent system: use the event log, per-agent terminals, message trails, and git history to find why a hive of AI agents went sideways.</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/" />@@ -55,6 +71,14 @@<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>Building an AI "Office Floor": Avatars, Pathfinding, Envelopes</title>+ <link href="https://munderdiffl.in/blog/building-an-ai-office-floor/" />+ <id>https://munderdiffl.in/blog/building-an-ai-office-floor/</id>+ <published>2026-06-03T00:00:00.000Z</published>+ <updated>2026-06-03T00:00:00.000Z</updated><category term="Internals" />+ <summary>The game-dev techniques behind a dev tool's office floor: Tiled maps, BFS pathfinding, sprite recoloring, and flying message envelopes in Pixi.js.</summary>+ </entry><entry><title>Claude Code Hooks, Explained (PreToolUse, PostToolUse, Stop)</title><link href="https://munderdiffl.in/blog/claude-code-hooks-explained/" />@@ -103,6 +127,14 @@<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>Rendering Many Live Terminals Without Melting the CPU</title>+ <link href="https://munderdiffl.in/blog/rendering-many-live-terminals-performance/" />+ <id>https://munderdiffl.in/blog/rendering-many-live-terminals-performance/</id>+ <published>2026-06-03T00:00:00.000Z</published>+ <updated>2026-06-03T00:00:00.000Z</updated><category term="Internals" />+ <summary>xterm.js performance for many live PTYs: a terminal pool, render-only-visible, smart scrollback, and accelerated rendering to stream dozens at once.</summary>+ </entry><entry><title>A vibe-kanban Alternative for Coordinating AI Agents</title><link href="https://munderdiffl.in/blog/vibe-kanban-alternative/" />@@ -141,7 +173,7 @@<id>https://munderdiffl.in/blog/human-in-the-loop-ai-agents/</id><published>2026-06-02T00:00:00.000Z</published><updated>2026-06-02T00:00:00.000Z</updated><category term="Orchestration" />- <summary>Design human-in-the-loop AI agents that stay autonomous: an approvals queue that escalates only spend, destructive ops, and scope — and relays your answer back.</summary>+ <summary>Design human-in-the-loop AI agents that stay autonomous: an approvals queue that escalates only spend, destructive ops, and scope changes.</summary></entry><entry><title>Munder Difflin FAQ: Everything People Ask</title>@@ -167,6 +199,14 @@<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>Visualizing AI Agents with Pixi.js: An Office You Can Watch</title>+ <link href="https://munderdiffl.in/blog/visualizing-ai-agents-pixijs/" />+ <id>https://munderdiffl.in/blog/visualizing-ai-agents-pixijs/</id>+ <published>2026-06-02T00:00:00.000Z</published>+ <updated>2026-06-02T00:00:00.000Z</updated><category term="Internals" />+ <summary>How we render AI agents as avatars on a Pixi.js office floor — driven by real hook and message events, with seat assignment, pathing, and flying envelopes.</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/" />@@ -197,7 +237,7 @@<id>https://munderdiffl.in/blog/append-only-event-log-agents/</id><published>2026-06-01T00:00:00.000Z</published><updated>2026-06-01T00:00:00.000Z</updated><category term="Internals" />- <summary>How an append-only event log makes a multi-agent system debuggable and replayable — what to record per event, and why one JSON line per event beats a database.</summary>+ <summary>How an append-only event log makes a multi-agent system debuggable and replayable: what to record, and why one JSON line per event beats a database.</summary></entry><entry><title>How to Run Multiple Claude Code Agents (Without Losing Track)</title>@@ -247,6 +287,14 @@<updated>2026-05-27T00:00:00.000Z</updated><category term="Memory" /><summary>Claude Code forgets between sessions. Here's how a markdown-first memory layer with semantic recall lets your agents remember across runs.</summary></entry>+ <entry>+ <title>Why We Built Agent Memory Markdown-First</title>+ <link href="https://munderdiffl.in/blog/markdown-first-agent-memory/" />+ <id>https://munderdiffl.in/blog/markdown-first-agent-memory/</id>+ <published>2026-05-27T00:00:00.000Z</published>+ <updated>2026-05-27T00:00:00.000Z</updated><category term="Memory" />+ <summary>Markdown-first AI agent long-term memory: plain notes a human can read and git can diff, with a semantic index on top that degrades gracefully.</summary>+ </entry><entry><title>Semantic Memory for AI Agents: Recall in Milliseconds</title><link href="https://munderdiffl.in/blog/semantic-memory-for-ai-agents/" />diff --git a/docs/blog/give-claude-code-long-term-memory/index.html b/docs/blog/give-claude-code-long-term-memory/index.htmlindex a3e1b77a..98324099 100644--- a/docs/blog/give-claude-code-long-term-memory/index.html+++ b/docs/blog/give-claude-code-long-term-memory/index.html@@ -201,13 +201,31 @@ 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/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 prev" href="/blog/markdown-first-agent-memory/"><span class="k">← Older</span><span class="t">Why We Built Agent Memory Markdown-First</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/markdown-first-agent-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>5 min</span>+ </div>+ <h3><a href="/blog/markdown-first-agent-memory/">Why We Built Agent Memory Markdown-First</a></h3>+ <p class="dek">Markdown-first AI agent long-term memory: plain notes a human can read and git can diff, with a semantic index on top that degrades gracefully.</p>+ <div class="foot">+ <span class="tag kind">Memory</span>+ <a class="more" href="/blog/markdown-first-agent-memory/" aria-label="Read: Why We Built Agent Memory Markdown-First">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>diff --git a/docs/blog/how-the-god-orchestrator-works/index.html b/docs/blog/how-the-god-orchestrator-works/index.htmlindex e74d5b2a..bd2cd8e3 100644--- a/docs/blog/how-the-god-orchestrator-works/index.html+++ b/docs/blog/how-the-god-orchestrator-works/index.html@@ -216,9 +216,10 @@ addressed to the human (or flags it as needing human attention), and the harness<strong>approvals queue</strong> surfaced in the UI. You approve or reject — optionally with a note, like “yes, butcap 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+<p>Everything not on the critical list stays autonomous. This selective escalation —+<a href="/blog/human-in-the-loop-ai-agents/">human-in-the-loop done right</a> — 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 youtighten 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>@@ -256,7 +257,7 @@ off your plate.</p>room, naturally), with a reserved desk. It boots with the hive and runs alongside the workers as justanother <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+<p>Munder Difflin’s <a href="https://munderdiffl.in/#how">GOD orchestrator</a> routes, adjudicates, and escalates for a whole hive of Claude Codeagents — 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>@@ -338,7 +339,7 @@ to put one in charge of your floor; it’s free and open source.</p><span>5 min</span></div><h3><a href="/blog/human-in-the-loop-ai-agents/">Human-in-the-Loop AI Agents: Approvals That Don't Slow You Down</a></h3>- <p class="dek">Design human-in-the-loop AI agents that stay autonomous: an approvals queue that escalates only spend, destructive ops, and scope — and relays your answer back.</p>+ <p class="dek">Design human-in-the-loop AI agents that stay autonomous: an approvals queue that escalates only spend, destructive ops, and scope changes.</p><div class="foot"><span class="tag kind">Orchestration</span><a class="more" href="/blog/human-in-the-loop-ai-agents/" aria-label="Read: Human-in-the-Loop AI Agents: Approvals That Don't Slow You Down">Read →</a>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.htmlindex 5d6ba34e..c313d956 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@@ -233,38 +233,38 @@ free and open source.</p></div></article><article class="card">- <a class="thumb t-guides" href="/blog/mcp-and-skills-in-a-hive/" aria-hidden="true" tabindex="-1">+ <a class="thumb t-guides" href="/blog/debugging-multi-agent-systems/" aria-hidden="true" tabindex="-1"><span>GUIDES</span></a><div class="body"><div class="meta">- <time datetime="2026-06-03">Jun 3, 2026</time>+ <time datetime="2026-06-04">Jun 4, 2026</time><span class="dot" aria-hidden="true"></span>- <span>6 min</span>+ <span>5 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>+ <h3><a href="/blog/debugging-multi-agent-systems/">How to Debug a Multi-Agent System</a></h3>+ <p class="dek">How to debug a multi-agent system: use the event log, per-agent terminals, message trails, and git history to find why a hive of AI agents went sideways.</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>+ <a class="more" href="/blog/debugging-multi-agent-systems/" aria-label="Read: How to Debug a Multi-Agent System">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">+ <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="2026-05-25">May 25, 2026</time>+ <time datetime="2026-06-03">Jun 3, 2026</time><span class="dot" aria-hidden="true"></span>- <span>4 min</span>+ <span>6 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>+ <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/manage-multiple-claude-code-sessions/" aria-label="Read: How to Manage Multiple Claude Code Sessions Like a Pro">Read →</a>+ <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>diff --git a/docs/blog/human-in-the-loop-ai-agents/index.html b/docs/blog/human-in-the-loop-ai-agents/index.htmlindex 66d532ea..3a100a1b 100644--- a/docs/blog/human-in-the-loop-ai-agents/index.html+++ b/docs/blog/human-in-the-loop-ai-agents/index.html@@ -4,7 +4,7 @@<meta charset="UTF-8" /><meta name="viewport" content="width=device-width, initial-scale=1.0" /><title>Human-in-the-Loop AI Agents: Approvals That Don't Slow You Down — Munder Difflin Blog</title>-<meta name="description" content="Design human-in-the-loop AI agents that stay autonomous: an approvals queue that escalates only spend, destructive ops, and scope — and relays your answer back." />+<meta name="description" content="Design human-in-the-loop AI agents that stay autonomous: an approvals queue that escalates only spend, destructive ops, and scope changes." /><link rel="canonical" href="https://munderdiffl.in/blog/human-in-the-loop-ai-agents/" /><link rel="icon" type="image/png" href="https://munderdiffl.in/logo.png" />@@ -15,7 +15,7 @@<meta property="og:site_name" content="Munder Difflin Blog" /><meta property="og:type" content="article" /><meta property="og:title" content="Human-in-the-Loop AI Agents: Approvals That Don't Slow You Down — Munder Difflin Blog" />-<meta property="og:description" content="Design human-in-the-loop AI agents that stay autonomous: an approvals queue that escalates only spend, destructive ops, and scope — and relays your answer back." />+<meta property="og:description" content="Design human-in-the-loop AI agents that stay autonomous: an approvals queue that escalates only spend, destructive ops, and scope changes." /><meta property="og:url" content="https://munderdiffl.in/blog/human-in-the-loop-ai-agents/" /><meta property="og:image" content="https://munderdiffl.in/media/og.png" /><meta property="og:locale" content="en_US" />@@ -30,7 +30,7 @@<!-- Twitter --><meta name="twitter:card" content="summary_large_image" /><meta name="twitter:title" content="Human-in-the-Loop AI Agents: Approvals That Don't Slow You Down — Munder Difflin Blog" />-<meta name="twitter:description" content="Design human-in-the-loop AI agents that stay autonomous: an approvals queue that escalates only spend, destructive ops, and scope — and relays your answer back." />+<meta name="twitter:description" content="Design human-in-the-loop AI agents that stay autonomous: an approvals queue that escalates only spend, destructive ops, and scope changes." /><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" />@@ -44,7 +44,7 @@"@context": "https://schema.org","@type": "BlogPosting","headline": "Human-in-the-Loop AI Agents: Approvals That Don't Slow You Down",- "description": "Design human-in-the-loop AI agents that stay autonomous: an approvals queue that escalates only spend, destructive ops, and scope — and relays your answer back.",+ "description": "Design human-in-the-loop AI agents that stay autonomous: an approvals queue that escalates only spend, destructive ops, and scope changes.","image": ["https://munderdiffl.in/media/og.png"],"datePublished": "2026-06-02T00:00:00.000Z","dateModified": "2026-06-02T00:00:00.000Z",@@ -118,7 +118,7 @@<a href="/blog/topics/orchestration/">Orchestration</a></nav><h1>Human-in-the-Loop AI Agents: Approvals That Don't Slow You Down</h1>- <p class="dek">Design human-in-the-loop AI agents that stay autonomous: an approvals queue that escalates only spend, destructive ops, and scope — and relays your answer back.</p>+ <p class="dek">Design human-in-the-loop AI agents that stay autonomous: an approvals queue that escalates only spend, destructive ops, and scope changes.</p><div class="byline"><span class="av" aria-hidden="true">CG</span><strong>Chaitanya Giri</strong>@@ -224,7 +224,7 @@ working. Nothing critical happens without you.</p><p><strong>Can the agents escalate too much?</strong> They can, early on — which is exactly why the critical list istunable. If the queue is noisy, tighten the policy so more decisions are handled autonomously.</p><hr>-<p>Munder Difflin ships human-in-the-loop the right way: a GOD orchestrator that resolves routine traffic+<p>Munder Difflin ships human-in-the-loop the right way: a <a href="https://munderdiffl.in/#how">GOD orchestrator</a> that resolves routine trafficitself and an approvals queue that escalates only the critical few — with your notes relayed straightback. <a href="https://munderdiffl.in/#install">Download Munder Difflin</a> to run agents that stay autonomousand ask only when they should; it’s free and open source.</p>diff --git a/docs/blog/index.html b/docs/blog/index.htmlindex d89eaf3e..93247737 100644--- a/docs/blog/index.html+++ b/docs/blog/index.html@@ -85,21 +85,21 @@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">35</span></a>+ <a class="chip" aria-current="page">All<span class="ct">41</span></a>- <a class="chip" href="/blog/topics/comparisons/">comparisons<span class="ct">8</span></a>+ <a class="chip" href="/blog/topics/internals/">internals<span class="ct">10</span></a>- <a class="chip" href="/blog/topics/guides/">guides<span class="ct">6</span></a>+ <a class="chip" href="/blog/topics/comparisons/">comparisons<span class="ct">8</span></a>- <a class="chip" href="/blog/topics/internals/">internals<span class="ct">6</span></a>+ <a class="chip" href="/blog/topics/guides/">guides<span class="ct">7</span></a><a class="chip" href="/blog/topics/orchestration/">orchestration<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/use-cases/">use-cases<span class="ct">3</span></a>+ <a class="chip" href="/blog/topics/memory/">memory<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/use-cases/">use-cases<span class="ct">3</span></a><a class="chip" href="/blog/topics/story/">story<span class="ct">1</span></a>@@ -108,20 +108,20 @@<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 class="thumb t-internals" href="/blog/architecture-two-planes-one-renderer/" aria-hidden="true" tabindex="-1">+ <span>INTERNALS</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>+ <span>5 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>+ <h3><a href="/blog/architecture-two-planes-one-renderer/">Munder Difflin's Architecture: Two Data Planes, One Renderer</a></h3>+ <p class="dek">A walkthrough of the multi-agent harness architecture: a node-pty terminal plane and a hooks/hive event plane feeding one React + Pixi.js renderer.</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>+ <span class="tag kind">Internals</span>+ <a class="more" href="/blog/architecture-two-planes-one-renderer/" aria-label="Read: Munder Difflin's Architecture: Two Data Planes, One Renderer">Read →</a></div></div></article>@@ -132,6 +132,24 @@<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>@@ -203,6 +221,24 @@</div></div></article>+<article class="card">+ <a class="thumb t-guides" href="/blog/debugging-multi-agent-systems/" 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/debugging-multi-agent-systems/">How to Debug a Multi-Agent System</a></h3>+ <p class="dek">How to debug a multi-agent system: use the event log, per-agent terminals, message trails, and git history to find why a hive of AI agents went sideways.</p>+ <div class="foot">+ <span class="tag kind">Guides</span>+ <a class="more" href="/blog/debugging-multi-agent-systems/" aria-label="Read: How to Debug a Multi-Agent System">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>@@ -221,6 +257,24 @@</div></div></article>+<article class="card">+ <a class="thumb t-internals" href="/blog/building-an-ai-office-floor/" 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/building-an-ai-office-floor/">Building an AI "Office Floor": Avatars, Pathfinding, Envelopes</a></h3>+ <p class="dek">The game-dev techniques behind a dev tool's office floor: Tiled maps, BFS pathfinding, sprite recoloring, and flying message envelopes in Pixi.js.</p>+ <div class="foot">+ <span class="tag kind">Internals</span>+ <a class="more" href="/blog/building-an-ai-office-floor/" aria-label="Read: Building an AI "Office Floor": Avatars, Pathfinding, Envelopes">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>@@ -329,6 +383,24 @@</div></div></article>+<article class="card">+ <a class="thumb t-internals" href="/blog/rendering-many-live-terminals-performance/" 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>5 min</span>+ </div>+ <h3><a href="/blog/rendering-many-live-terminals-performance/">Rendering Many Live Terminals Without Melting the CPU</a></h3>+ <p class="dek">xterm.js performance for many live PTYs: a terminal pool, render-only-visible, smart scrollback, and accelerated rendering to stream dozens at once.</p>+ <div class="foot">+ <span class="tag kind">Internals</span>+ <a class="more" href="/blog/rendering-many-live-terminals-performance/" aria-label="Read: Rendering Many Live Terminals Without Melting the CPU">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>@@ -412,7 +484,7 @@<span>5 min</span></div><h3><a href="/blog/human-in-the-loop-ai-agents/">Human-in-the-Loop AI Agents: Approvals That Don't Slow You Down</a></h3>- <p class="dek">Design human-in-the-loop AI agents that stay autonomous: an approvals queue that escalates only spend, destructive ops, and scope — and relays your answer back.</p>+ <p class="dek">Design human-in-the-loop AI agents that stay autonomous: an approvals queue that escalates only spend, destructive ops, and scope changes.</p><div class="foot"><span class="tag kind">Orchestration</span><a class="more" href="/blog/human-in-the-loop-ai-agents/" aria-label="Read: Human-in-the-Loop AI Agents: Approvals That Don't Slow You Down">Read →</a>@@ -473,6 +545,24 @@</div></div></article>+<article class="card">+ <a class="thumb t-internals" href="/blog/visualizing-ai-agents-pixijs/" 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/visualizing-ai-agents-pixijs/">Visualizing AI Agents with Pixi.js: An Office You Can Watch</a></h3>+ <p class="dek">How we render AI agents as avatars on a Pixi.js office floor — driven by real hook and message events, with seat assignment, pathing, and flying envelopes.</p>+ <div class="foot">+ <span class="tag kind">Internals</span>+ <a class="more" href="/blog/visualizing-ai-agents-pixijs/" aria-label="Read: Visualizing AI Agents with Pixi.js: An Office You Can Watch">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>@@ -538,7 +628,7 @@<span>5 min</span></div><h3><a href="/blog/append-only-event-log-agents/">An Append-Only Event Log for a Hive of Agents</a></h3>- <p class="dek">How an append-only event log makes a multi-agent system debuggable and replayable — what to record per event, and why one JSON line per event beats a database.</p>+ <p class="dek">How an append-only event log makes a multi-agent system debuggable and replayable: what to record, and why one JSON line per event beats a database.</p><div class="foot"><span class="tag kind">Internals</span><a class="more" href="/blog/append-only-event-log-agents/" aria-label="Read: An Append-Only Event Log for a Hive of Agents">Read →</a>@@ -653,6 +743,24 @@</div></div></article>+<article class="card">+ <a class="thumb t-memory" href="/blog/markdown-first-agent-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>5 min</span>+ </div>+ <h3><a href="/blog/markdown-first-agent-memory/">Why We Built Agent Memory Markdown-First</a></h3>+ <p class="dek">Markdown-first AI agent long-term memory: plain notes a human can read and git can diff, with a semantic index on top that degrades gracefully.</p>+ <div class="foot">+ <span class="tag kind">Memory</span>+ <a class="more" href="/blog/markdown-first-agent-memory/" aria-label="Read: Why We Built Agent Memory Markdown-First">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>diff --git a/docs/blog/manage-multiple-claude-code-sessions/index.html b/docs/blog/manage-multiple-claude-code-sessions/index.htmlindex c0c2d66a..722eb9da 100644--- a/docs/blog/manage-multiple-claude-code-sessions/index.html+++ b/docs/blog/manage-multiple-claude-code-sessions/index.html@@ -214,7 +214,7 @@ the same progression with the orchestration layer in view.</p><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,+<p>When the checklist starts feeling like a second job, that’s what a <a href="https://munderdiffl.in/#what">multi-agent harness</a> like 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>@@ -286,38 +286,38 @@ isolated agents, shared memory, and a single committer, all on your own machine.</div></article><article class="card">- <a class="thumb t-guides" href="/blog/mcp-and-skills-in-a-hive/" aria-hidden="true" tabindex="-1">+ <a class="thumb t-guides" href="/blog/debugging-multi-agent-systems/" aria-hidden="true" tabindex="-1"><span>GUIDES</span></a><div class="body"><div class="meta">- <time datetime="2026-06-03">Jun 3, 2026</time>+ <time datetime="2026-06-04">Jun 4, 2026</time><span class="dot" aria-hidden="true"></span>- <span>6 min</span>+ <span>5 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>+ <h3><a href="/blog/debugging-multi-agent-systems/">How to Debug a Multi-Agent System</a></h3>+ <p class="dek">How to debug a multi-agent system: use the event log, per-agent terminals, message trails, and git history to find why a hive of AI agents went sideways.</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>+ <a class="more" href="/blog/debugging-multi-agent-systems/" aria-label="Read: How to Debug a Multi-Agent System">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">+ <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="2026-06-01">Jun 1, 2026</time>+ <time datetime="2026-06-03">Jun 3, 2026</time><span class="dot" aria-hidden="true"></span>- <span>3 min</span>+ <span>6 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>+ <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/how-to-run-multiple-claude-code-agents/" aria-label="Read: How to Run Multiple Claude Code Agents (Without Losing Track)">Read →</a>+ <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>diff --git a/docs/blog/markdown-first-agent-memory/index.html b/docs/blog/markdown-first-agent-memory/index.htmlnew file mode 100644index 00000000..286982f3--- /dev/null+++ b/docs/blog/markdown-first-agent-memory/index.html@@ -0,0 +1,354 @@+<!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 Agent Memory Markdown-First — Munder Difflin Blog</title>+<meta name="description" content="Markdown-first AI agent long-term memory: plain notes a human can read and git can diff, with a semantic index on top that degrades gracefully." />+<link rel="canonical" href="https://munderdiffl.in/blog/markdown-first-agent-memory/" />++<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 Agent Memory Markdown-First — Munder Difflin Blog" />+<meta property="og:description" content="Markdown-first AI agent long-term memory: plain notes a human can read and git can diff, with a semantic index on top that degrades gracefully." />+<meta property="og:url" content="https://munderdiffl.in/blog/markdown-first-agent-memory/" />+<meta property="og:image" content="https://munderdiffl.in/media/og.png" />+<meta property="og:locale" content="en_US" />+<meta property="article:published_time" content="2026-05-27T00:00:00.000Z" />+<meta property="article:author" content="Chaitanya Giri" />+<meta property="article:tag" content="Memory" />+<meta property="article:tag" content="MemPalace" />+<meta property="article:tag" content="Markdown" />+<meta property="article:tag" content="Multi-Agent" />+++<!-- Twitter -->+<meta name="twitter:card" content="summary_large_image" />+<meta name="twitter:title" content="Why We Built Agent Memory Markdown-First — Munder Difflin Blog" />+<meta name="twitter:description" content="Markdown-first AI agent long-term memory: plain notes a human can read and git can diff, with a semantic index on top that degrades gracefully." />+<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 Agent Memory Markdown-First",+ "description": "Markdown-first AI agent long-term memory: plain notes a human can read and git can diff, with a semantic index on top that degrades gracefully.",+ "image": ["https://munderdiffl.in/media/og.png"],+ "datePublished": "2026-05-27T00:00:00.000Z",+ "dateModified": "2026-05-27T00:00:00.000Z",+ "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/markdown-first-agent-memory/" },+ "keywords": "ai agent long-term memory, markdown memory, agent knowledge base, long-term memory",+ "articleSection": "Memory",+ "inLanguage": "en-US",+ "url": "https://munderdiffl.in/blog/markdown-first-agent-memory/"+}+</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 Agent Memory Markdown-First", "item": "https://munderdiffl.in/blog/markdown-first-agent-memory/" }+ ]+}+</script>++<script type="application/ld+json">+{+ "@context": "https://schema.org",+ "@type": "FAQPage",+ "mainEntity": [+ { "@type": "Question", "name": "What is markdown-first agent memory?", "acceptedAnswer": { "@type": "Answer", "text": "It's an approach where each agent's durable knowledge lives in plain markdown files it reads on startup and appends to as it learns. A semantic index is built on top of those files for fast recall — but the markdown, not the index, is the source of truth." } },+ { "@type": "Question", "name": "Why not just use a vector database for agent memory?", "acceptedAnswer": { "@type": "Answer", "text": "A vector DB stores opaque embeddings you can't read or diff, and many memory frameworks want to own the agent's runtime. Markdown-first keeps memory human-readable and git-diffable, treats the index as a removable accelerator, and fits agents whose runtime is already Claude Code." } },+ { "@type": "Question", "name": "What happens if the semantic index breaks?", "acceptedAnswer": { "@type": "Answer", "text": "Nothing catastrophic — the agent falls back to reading its markdown directly. Because the files are the source of truth and the index sits on top, a broken or missing index degrades to plain markdown memory instead of losing everything." } }++ ]+}+</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>Why We Built Agent Memory Markdown-First</h1>+ <p class="dek">Markdown-first AI agent long-term memory: plain notes a human can read and git can diff, with a semantic index on top that degrades gracefully.</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="2026-05-27">May 27, 2026</time>+ <span class="dot" aria-hidden="true">·</span>+ <span>5 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>We built+<strong>AI agent long-term memory</strong> markdown-first: each agent writes durable facts to plain+markdown files, and a semantic index sits <em>on top</em> for fast recall. The reason is durability —+markdown is <strong>human-readable</strong>, <strong>git-diffable</strong>, and <strong>degrades+gracefully</strong> (if the index breaks, the files still work). A vector database can't say the same,+and it's the wrong fit when the agent's runtime is already Claude Code.</p></div>+<p>When you add long-term memory to an agent, the tempting first move is to reach for a vector database or+a full memory framework. We went the other way: plain markdown files first, with a semantic index+layered on top. This post is the argument for that ordering — why the <em>source of truth</em> should be+files you can read, and the index should be a removable accelerator.</p>+<h2 id="what-markdown-first-means" tabindex="-1">What “markdown-first” means <a class="anchor" href="#what-markdown-first-means" aria-hidden="true">#</a></h2>+<p>The design is simple. Each agent has a <code>memory.md</code>. The rule it follows:</p>+<ul>+<li><strong>Read it at the start of a task</strong> — recall what you already know before starting.</li>+<li><strong>Append durable facts as you learn them</strong> — a decision, a convention, a gotcha — in small, atomic+entries.</li>+</ul>+<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).+<span class="token list punctuation">-</span> Never hand-edit docs/index.html during a release — it's the REL fallback source.</code></pre>+<p>A semantic index is built <em>from</em> these files so the agent can recall by meaning instead of re-reading+everything (<a href="/blog/semantic-memory-for-ai-agents/">semantic memory for AI agents</a> covers that layer).+But the markdown is primary. The index is derived, and disposable.</p>+<h2 id="three-reasons-the-ordering-matters" tabindex="-1">Three reasons the ordering matters <a class="anchor" href="#three-reasons-the-ordering-matters" aria-hidden="true">#</a></h2>+<h3 id="1-memory-you-can-read-is-memory-you-can-trust" tabindex="-1">1. Memory you can read is memory you can trust <a class="anchor" href="#1-memory-you-can-read-is-memory-you-can-trust" aria-hidden="true">#</a></h3>+<p>Open an agent’s <code>memory.md</code> and you see exactly what it “knows” — in your language, not as a blob of+floating-point vectors. That’s not a nicety; it’s how you debug an agent that’s acting on a stale or+wrong belief. With markdown, you find the bad note and fix it. With opaque embeddings, you’re guessing+at what the agent remembers and re-indexing to change it. The most important property of a memory+system is that a human can audit it, and plain text wins that outright.</p>+<h3 id="2-memory-that-diffs-is-memory-you-can-review" tabindex="-1">2. Memory that diffs is memory you can review <a class="anchor" href="#2-memory-that-diffs-is-memory-you-can-review" aria-hidden="true">#</a></h3>+<p>Because the notes are files, they live in git. Every change to what an agent knows is a diff you can+read in a commit — memory becomes reviewable like any other artifact. You can watch an agent’s+understanding evolve, catch the moment it learned something wrong, and roll it back. A database of+embeddings has no meaningful diff; “the vectors changed” tells you nothing. Text under version control+turns memory from a black box into a reviewable record, which pairs naturally with the+<a href="/blog/append-only-event-log-agents/">append-only event log</a> for full auditability.</p>+<h3 id="3-memory-that-degrades-gracefully-never-strands-you" tabindex="-1">3. Memory that degrades gracefully never strands you <a class="anchor" href="#3-memory-that-degrades-gracefully-never-strands-you" aria-hidden="true">#</a></h3>+<p>This is the durability clincher. If the semantic index breaks, isn’t installed, or you move to a+machine without it, the markdown files <strong>still work</strong> — the agent reads them directly. The fancy recall+is an upgrade, not a dependency. Contrast a database that won’t open: it takes the memory with it. With+markdown-first, the floor never falls out from under the agent; the worst case is slower recall, not+lost knowledge.</p>+<h2 id="why-not-a-vector-database-or-a-memory-framework" tabindex="-1">Why not a vector database or a memory framework? <a class="anchor" href="#why-not-a-vector-database-or-a-memory-framework" aria-hidden="true">#</a></h2>+<p>Vector DBs and dedicated memory frameworks are real tools with real uses. They’re the wrong default+<em>here</em> for two reasons.</p>+<p><strong>They store what you can’t read.</strong> Their native unit is the embedding — great for similarity search,+useless for human inspection or git review. You end up bolting a “show me the source text” layer back+on, which is just markdown wearing a costume.</p>+<p><strong>They want to own the runtime.</strong> Many agent-memory frameworks assume <em>they</em> are the thing running the+agent loop — they expect to be in charge. But when your agents are real <code>claude</code> sessions, the runtime+is already Claude Code. The memory layer should be a lightweight companion beside it, not a framework+that wants to replace it. Markdown files plus a CLI-driven index fit that shape exactly: the agent+writes notes as a normal part of its work, and a separate process mines those notes into a searchable+store without intruding on the loop.</p>+<p>That mining is the bridge: the index reads each agent’s markdown and makes it recall-able by the whole+team, on a schedule, only re-processing files that changed. You get vector-quality recall <em>and</em>+human-quality source text — because the vectors are derived from the text, not instead of it.</p>+<h2 id="the-single-writer-detail" tabindex="-1">The single-writer detail <a class="anchor" href="#the-single-writer-detail" aria-hidden="true">#</a></h2>+<p>One subtlety that markdown-first gets right almost for free: <strong>one writer per memory file.</strong> Each agent+owns its own <code>memory.md</code> and only it appends there. A shared index aggregates everyone’s notes+read-only, so the whole team can recall across agents without any file being written by two processes.+It’s the same single-writer discipline that keeps+<a href="/blog/single-committer-git-pattern/">multi-agent git safe</a> — applied to memory. Co-edited memory files+would tear; per-agent files plus a read-only shared index don’t.</p>+<h2 id="when-markdown-first-is-the-right-call" tabindex="-1">When markdown-first is the right call <a class="anchor" href="#when-markdown-first-is-the-right-call" aria-hidden="true">#</a></h2>+<p>This approach shines when:</p>+<ul>+<li>you want to <strong>audit and trust</strong> what your agents remember,</li>+<li>you want memory <strong>under version control</strong> so you can review and revert it,</li>+<li>your agents’ runtime is something you don’t control (a CLI like Claude Code), and</li>+<li>you value <strong>graceful degradation</strong> over maximal indexing sophistication.</li>+</ul>+<p>It’s less compelling if you’re building a system at a scale where you genuinely need a dedicated vector+store’s throughput and you’re willing to give up readability for it. For a hive of a handful to a few+dozen agents, markdown-first is the durable, debuggable default. For the plain-English version of why+agents forget and what shared memory changes, see+<a href="/blog/give-claude-code-long-term-memory/">how to give Claude Code long-term memory</a>.</p>+<h2 id="faq" tabindex="-1">FAQ <a class="anchor" href="#faq" aria-hidden="true">#</a></h2>+<p><strong>Doesn’t markdown get unwieldy at thousands of notes?</strong> The <em>files</em> stay fine; the challenge is recall,+which is exactly what the semantic index on top solves — you recall the few relevant notes by meaning+rather than reading them all. The markdown scales as storage; the index scales as retrieval.</p>+<p><strong>Can I edit an agent’s memory by hand?</strong> Yes — it’s a text file. Fix a wrong note, remove a stale one,+and the next mining pass picks up the change. Try that with a vector store.</p>+<hr>+<p>Munder Difflin gives every agent a plain <code>memory.md</code> plus+<a href="https://munderdiffl.in/#how">a shared semantic palace mined from it</a> — readable, diffable, and+graceful when the index is gone. <a href="https://munderdiffl.in/#install">Download Munder Difflin</a>+to give your agents memory you can actually read; 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 markdown-first agent memory?</p>+ <p class="a">It's an approach where each agent's durable knowledge lives in plain markdown files it reads on startup and appends to as it learns. A semantic index is built on top of those files for fast recall — but the markdown, not the index, is the source of truth.</p>+ </div>++ <div class="qa">+ <p class="q">Why not just use a vector database for agent memory?</p>+ <p class="a">A vector DB stores opaque embeddings you can't read or diff, and many memory frameworks want to own the agent's runtime. Markdown-first keeps memory human-readable and git-diffable, treats the index as a removable accelerator, and fits agents whose runtime is already Claude Code.</p>+ </div>++ <div class="qa">+ <p class="q">What happens if the semantic index breaks?</p>+ <p class="a">Nothing catastrophic — the agent falls back to reading its markdown directly. Because the files are the source of truth and the index sits on top, a broken or missing index degrades to plain markdown memory instead of losing everything.</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/markdown/">Markdown</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-markdown-first-means">What “markdown-first” means</a></li><li class="lvl-2"><a href="#three-reasons-the-ordering-matters">Three reasons the ordering matters</a></li><li class="lvl-3"><a href="#1-memory-you-can-read-is-memory-you-can-trust">1. Memory you can read is memory you can trust</a></li><li class="lvl-3"><a href="#2-memory-that-diffs-is-memory-you-can-review">2. Memory that diffs is memory you can review</a></li><li class="lvl-3"><a href="#3-memory-that-degrades-gracefully-never-strands-you">3. Memory that degrades gracefully never strands you</a></li><li class="lvl-2"><a href="#why-not-a-vector-database-or-a-memory-framework">Why not a vector database or a memory framework?</a></li><li class="lvl-2"><a href="#the-single-writer-detail">The single-writer detail</a></li><li class="lvl-2"><a href="#when-markdown-first-is-the-right-call">When markdown-first is the right call</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/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/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'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>+<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>++</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 & 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.htmlindex 413c16b6..374c2e5e 100644--- a/docs/blog/mcp-and-skills-in-a-hive/index.html+++ b/docs/blog/mcp-and-skills-in-a-hive/index.html@@ -302,38 +302,38 @@ existing setup into a coordinated team of agents; it’s free and open source.</</div></article><article class="card">- <a class="thumb t-guides" href="/blog/how-to-run-multiple-claude-code-agents/" aria-hidden="true" tabindex="-1">+ <a class="thumb t-guides" href="/blog/debugging-multi-agent-systems/" aria-hidden="true" tabindex="-1"><span>GUIDES</span></a><div class="body"><div class="meta">- <time datetime="2026-06-01">Jun 1, 2026</time>+ <time datetime="2026-06-04">Jun 4, 2026</time><span class="dot" aria-hidden="true"></span>- <span>3 min</span>+ <span>5 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>+ <h3><a href="/blog/debugging-multi-agent-systems/">How to Debug a Multi-Agent System</a></h3>+ <p class="dek">How to debug a multi-agent system: use the event log, per-agent terminals, message trails, and git history to find why a hive of AI agents went sideways.</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>+ <a class="more" href="/blog/debugging-multi-agent-systems/" aria-label="Read: How to Debug a Multi-Agent System">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">+ <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="2026-05-25">May 25, 2026</time>+ <time datetime="2026-06-01">Jun 1, 2026</time><span class="dot" aria-hidden="true"></span>- <span>4 min</span>+ <span>3 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>+ <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/manage-multiple-claude-code-sessions/" aria-label="Read: How to Manage Multiple Claude Code Sessions Like a Pro">Read →</a>+ <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>diff --git a/docs/blog/node-pty-electron-real-terminals/index.html b/docs/blog/node-pty-electron-real-terminals/index.htmlindex 4625fbde..d9b7652f 100644--- a/docs/blog/node-pty-electron-real-terminals/index.html+++ b/docs/blog/node-pty-electron-real-terminals/index.html@@ -317,63 +317,63 @@ real terminals driving real agents; it’s free and open source.</p></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 prev" href="/blog/rendering-many-live-terminals-performance/"><span class="k">← Older</span><span class="t">Rendering Many Live Terminals Without Melting the CPU</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">+ <a class="thumb t-internals" href="/blog/architecture-two-planes-one-renderer/" aria-hidden="true" tabindex="-1"><span>INTERNALS</span></a><div class="body"><div class="meta">- <time datetime="2026-06-03">Jun 3, 2026</time>+ <time datetime="2026-06-04">Jun 4, 2026</time><span class="dot" aria-hidden="true"></span>- <span>8 min</span>+ <span>5 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>+ <h3><a href="/blog/architecture-two-planes-one-renderer/">Munder Difflin's Architecture: Two Data Planes, One Renderer</a></h3>+ <p class="dek">A walkthrough of the multi-agent harness architecture: a node-pty terminal plane and a hooks/hive event plane feeding one React + Pixi.js renderer.</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>+ <a class="more" href="/blog/architecture-two-planes-one-renderer/" aria-label="Read: Munder Difflin's Architecture: Two Data Planes, One Renderer">Read →</a></div></div></article><article class="card">- <a class="thumb t-internals" href="/blog/claude-code-hooks-explained/" aria-hidden="true" tabindex="-1">+ <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>6 min</span>+ <span>8 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>+ <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/claude-code-hooks-explained/" aria-label="Read: Claude Code Hooks, Explained (PreToolUse, PostToolUse, Stop)">Read →</a>+ <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/single-committer-git-pattern/" aria-hidden="true" tabindex="-1">+ <a class="thumb t-internals" href="/blog/building-an-ai-office-floor/" aria-hidden="true" tabindex="-1"><span>INTERNALS</span></a><div class="body"><div class="meta">- <time datetime="2026-06-02">Jun 2, 2026</time>+ <time datetime="2026-06-03">Jun 3, 2026</time><span class="dot" aria-hidden="true"></span>- <span>5 min</span>+ <span>6 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>+ <h3><a href="/blog/building-an-ai-office-floor/">Building an AI "Office Floor": Avatars, Pathfinding, Envelopes</a></h3>+ <p class="dek">The game-dev techniques behind a dev tool's office floor: Tiled maps, BFS pathfinding, sprite recoloring, and flying message envelopes in Pixi.js.</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>+ <a class="more" href="/blog/building-an-ai-office-floor/" aria-label="Read: Building an AI "Office Floor": Avatars, Pathfinding, Envelopes">Read →</a></div></div></article>diff --git a/docs/blog/rendering-many-live-terminals-performance/index.html b/docs/blog/rendering-many-live-terminals-performance/index.htmlnew file mode 100644index 00000000..4fc21239--- /dev/null+++ b/docs/blog/rendering-many-live-terminals-performance/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>Rendering Many Live Terminals Without Melting the CPU — Munder Difflin Blog</title>+<meta name="description" content="xterm.js performance for many live PTYs: a terminal pool, render-only-visible, smart scrollback, and accelerated rendering to stream dozens at once." />+<link rel="canonical" href="https://munderdiffl.in/blog/rendering-many-live-terminals-performance/" />++<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="Rendering Many Live Terminals Without Melting the CPU — Munder Difflin Blog" />+<meta property="og:description" content="xterm.js performance for many live PTYs: a terminal pool, render-only-visible, smart scrollback, and accelerated rendering to stream dozens at once." />+<meta property="og:url" content="https://munderdiffl.in/blog/rendering-many-live-terminals-performance/" />+<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="Performance" />+<meta property="article:tag" content="xterm.js" />+<meta property="article:tag" content="Terminals" />+++<!-- Twitter -->+<meta name="twitter:card" content="summary_large_image" />+<meta name="twitter:title" content="Rendering Many Live Terminals Without Melting the CPU — Munder Difflin Blog" />+<meta name="twitter:description" content="xterm.js performance for many live PTYs: a terminal pool, render-only-visible, smart scrollback, and accelerated rendering to stream dozens at once." />+<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": "Rendering Many Live Terminals Without Melting the CPU",+ "description": "xterm.js performance for many live PTYs: a terminal pool, render-only-visible, smart scrollback, and accelerated rendering to stream dozens at once.",+ "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/rendering-many-live-terminals-performance/" },+ "keywords": "xterm.js performance, terminal rendering, xterm.js performance, electron performance",+ "articleSection": "Internals",+ "inLanguage": "en-US",+ "url": "https://munderdiffl.in/blog/rendering-many-live-terminals-performance/"+}+</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": "Rendering Many Live Terminals Without Melting the CPU", "item": "https://munderdiffl.in/blog/rendering-many-live-terminals-performance/" }+ ]+}+</script>++<script type="application/ld+json">+{+ "@context": "https://schema.org",+ "@type": "FAQPage",+ "mainEntity": [+ { "@type": "Question", "name": "How do you render many xterm.js terminals without high CPU?", "acceptedAnswer": { "@type": "Answer", "text": "Keep one persistent terminal per session and only render the visible one(s); re-parent the terminal's element instead of recreating it, tune scrollback, and use an accelerated renderer when throughput is high. The buffers keep filling in the background while you paint just what's on screen." } },+ { "@type": "Question", "name": "Why is recreating an xterm terminal on tab switch slow and buggy?", "acceptedAnswer": { "@type": "Answer", "text": "node-pty keeps no scrollback, so a freshly created terminal is blank until the program repaints — and recreating instances thrashes the CPU. A persistent pool avoids both: the terminal lives for the session and its DOM element is moved in and out of views." } },+ { "@type": "Question", "name": "Does scrollback size affect performance?", "acceptedAnswer": { "@type": "Answer", "text": "Yes. xterm holds scrollback in memory per terminal, so a large scrollback multiplied by many terminals adds up. Pick a generous-but-bounded value and tune it to your workload." } }++ ]+}+</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>Rendering Many Live Terminals Without Melting the CPU</h1>+ <p class="dek">xterm.js performance for many live PTYs: a terminal pool, render-only-visible, smart scrollback, and accelerated rendering to stream dozens at once.</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>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>Streaming dozens of live PTYs to xterm.js+stays cheap if you do four things: keep <strong>one persistent terminal per session</strong> (don't+recreate on tab switch), <strong>render only what's visible</strong> while buffers fill in the+background, <strong>bound your scrollback</strong>, and reach for an <strong>accelerated renderer</strong>+only when throughput demands it. The big win is the persistent pool — it fixes both the blank-terminal+bug and the CPU thrash at once.</p></div>+<p>A single xterm.js terminal is cheap. Thirty of them, all streaming output from live agents while the+user switches between them, is where naive implementations melt the CPU — or show blank panes. This+post is the performance playbook for rendering many live terminals at once, built on the same techniques+that keep an agent harness’s floor of terminals smooth.</p>+<h2 id="the-naive-approach-and-why-it-hurts" tabindex="-1">The naive approach and why it hurts <a class="anchor" href="#the-naive-approach-and-why-it-hurts" aria-hidden="true">#</a></h2>+<p>The obvious design: when a terminal view mounts, create an xterm <code>Terminal</code>; when it unmounts, dispose+it. For one terminal it’s fine. For many, it fails twice:</p>+<ol>+<li><strong>CPU thrash.</strong> Creating and destroying terminal instances as the user switches tabs is expensive —+you’re rebuilding the emulator, re-opening it, re-measuring the grid, over and over.</li>+<li><strong>Blank terminals.</strong> node-pty keeps <strong>no scrollback</strong> — the buffer lives in xterm, not the PTY. So a+freshly created terminal starts empty and stays blank until the running program happens to repaint.+For an idle shell, that might be never.</li>+</ol>+<p>Both problems have the same root: tying the terminal’s <em>lifetime</em> to a <em>view’s</em> lifetime. The fix is to+decouple them.</p>+<h2 id="technique-1-a-persistent-terminal-pool" tabindex="-1">Technique 1 — A persistent terminal pool <a class="anchor" href="#technique-1-a-persistent-terminal-pool" aria-hidden="true">#</a></h2>+<p>Create <strong>one</strong> xterm terminal per PTY session and keep it alive for the whole app lifetime, independent+of any view:</p>+<ul>+<li>The terminal is opened into a <strong>detached host element</strong> and subscribes to its PTY’s output stream+<strong>once</strong>. Its buffer keeps filling whether or not it’s currently on screen.</li>+<li>A view doesn’t create a terminal — it <strong>borrows</strong> one. On mount it re-parents the existing host+element into itself; on unmount it lets go. The rendered content moves with the element, so the+terminal is populated and visible <em>immediately</em>, with no repaint.</li>+</ul>+<pre class="language-ts"><code class="language-ts"><span class="token comment">// borrow, don't build: move the live terminal's element into the view</span>+<span class="token keyword">function</span> <span class="token function">attachTerminal</span><span class="token punctuation">(</span>entry<span class="token punctuation">,</span> container<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> 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> 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 comment">// open once, lazily</span>+<span class="token punctuation">}</span></code></pre>+<p>This single change fixes both naive problems: no per-switch teardown (no thrash) and no empty buffer+(no blank pane). It’s the structural decision everything else builds on — the same pool pattern at the+center of <a href="/blog/building-a-terminal-ui-xterm-node-pty/">building a terminal UI with xterm.js and node-pty</a>.</p>+<h2 id="technique-2-render-only-whats-visible" tabindex="-1">Technique 2 — Render only what’s visible <a class="anchor" href="#technique-2-render-only-whats-visible" aria-hidden="true">#</a></h2>+<p>A pool keeps every session’s <em>buffer</em> current, but you don’t need to <em>paint</em> every terminal every+frame. Only the terminal(s) actually on screen need to be laid out and rendered; the rest keep+accumulating output in memory at near-zero cost. When the user switches to one, it’s already+up to date — you just attach its element.</p>+<p>The principle: <strong>decouple “receiving output” from “drawing pixels.”</strong> Receiving is cheap and always-on;+drawing is the expensive part, so do it only for what’s visible. A floor of thirty agents costs you the+rendering of the one or few panes you’re looking at, not all thirty.</p>+<h2 id="technique-3-bound-your-scrollback" tabindex="-1">Technique 3 — Bound your scrollback <a class="anchor" href="#technique-3-bound-your-scrollback" aria-hidden="true">#</a></h2>+<p>xterm holds scrollback in memory, per terminal. A 10,000-line scrollback is comfortable for one+terminal and adds up fast across many. So:</p>+<ul>+<li>Pick a <strong>generous but bounded</strong> scrollback (enough to scroll back usefully, not infinite).</li>+<li>Remember it’s <strong>per terminal</strong> — multiply by your terminal count for the real memory cost.</li>+<li>Tune to your workload: high-volume log streams want less retained history than an interactive shell.</li>+</ul>+<p>It’s a small knob with a real effect when you have dozens of buffers alive at once.</p>+<h2 id="technique-4-stream-efficiently-from-the-pty" tabindex="-1">Technique 4 — Stream efficiently from the PTY <a class="anchor" href="#technique-4-stream-efficiently-from-the-pty" aria-hidden="true">#</a></h2>+<p>The bytes have to cross from the main process (where node-pty lives) to the renderer (where xterm+lives) over IPC. A few habits keep that path cheap:</p>+<ul>+<li><strong>Per-session channels.</strong> Each PTY forwards its output on its own channel so the renderer routes+chunks to the right terminal without inspecting them.</li>+<li><strong>Guard sends during teardown.</strong> Killing a PTY fires its exit asynchronously; if the window is gone+by then, sending throws. Check the target is alive before each send so quit stays clean (and you+don’t pay for sends into the void).</li>+<li><strong>Let xterm batch.</strong> xterm coalesces writes internally; feed it raw chunks and let it manage its own+render scheduling rather than forcing a refresh per byte.</li>+</ul>+<p>These come straight from how the <a href="/blog/node-pty-electron-real-terminals/">node-pty terminal plane</a>+streams to the UI.</p>+<h2 id="technique-5-reach-for-an-accelerated-renderer-when-needed" tabindex="-1">Technique 5 — Reach for an accelerated renderer when needed <a class="anchor" href="#technique-5-reach-for-an-accelerated-renderer-when-needed" aria-hidden="true">#</a></h2>+<p>xterm’s default DOM renderer is fine for a handful of terminals. When you’re rendering many+high-throughput streams, an accelerated rendering addon (canvas/WebGL) moves the drawing off the DOM+and reduces CPU. The discipline: <strong>measure first.</strong> Add it when your real workload shows the DOM+renderer is the bottleneck — not preemptively, since for modest terminal counts it’s unnecessary+complexity.</p>+<h2 id="the-shape-of-a-fast-many-terminal-ui" tabindex="-1">The shape of a fast many-terminal UI <a class="anchor" href="#the-shape-of-a-fast-many-terminal-ui" aria-hidden="true">#</a></h2>+<p>Put it together and the system looks like this:</p>+<ol>+<li><strong>One persistent terminal per PTY</strong>, in a pool, subscribed once.</li>+<li><strong>Only the visible terminals render</strong>; the rest keep filling buffers cheaply.</li>+<li><strong>Bounded scrollback</strong>, tuned per workload.</li>+<li><strong>Per-session IPC streaming</strong> with teardown-safe sends.</li>+<li><strong>An accelerated renderer</strong> added only when measurement says so.</li>+</ol>+<p>That’s how a single window can show a whole floor of live agents — each in its own real terminal,+switchable instantly — without the fans spinning up. The visual companion to all those terminals, the+office floor, follows the same keep-the-hot-loop-tight philosophy in+<a href="/blog/visualizing-ai-agents-pixijs/">visualizing AI agents with Pixi.js</a>.</p>+<h2 id="faq" tabindex="-1">FAQ <a class="anchor" href="#faq" aria-hidden="true">#</a></h2>+<p><strong>How many terminals can this handle?</strong> Enough that your bottleneck becomes the agents and your RAM,+not the rendering. Because only visible terminals paint and buffers are cheap, the count you can keep+<em>alive</em> is far higher than the count you’d ever look at simultaneously.</p>+<p><strong>Do I lose output for terminals I’m not looking at?</strong> No — that’s the point of the pool. Off-screen+terminals still receive and buffer their PTY’s output; you just aren’t paying to draw them until you+switch over.</p>+<hr>+<p>Munder Difflin streams <a href="https://munderdiffl.in/#what">a whole floor of live Claude Code terminals</a> with this exact approach — a+persistent pool, visible-only rendering, and teardown-safe IPC. <a href="https://munderdiffl.in/#install">Download Munder Difflin</a>+to run many real terminals without melting your CPU; 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 you render many xterm.js terminals without high CPU?</p>+ <p class="a">Keep one persistent terminal per session and only render the visible one(s); re-parent the terminal's element instead of recreating it, tune scrollback, and use an accelerated renderer when throughput is high. The buffers keep filling in the background while you paint just what's on screen.</p>+ </div>++ <div class="qa">+ <p class="q">Why is recreating an xterm terminal on tab switch slow and buggy?</p>+ <p class="a">node-pty keeps no scrollback, so a freshly created terminal is blank until the program repaints — and recreating instances thrashes the CPU. A persistent pool avoids both: the terminal lives for the session and its DOM element is moved in and out of views.</p>+ </div>++ <div class="qa">+ <p class="q">Does scrollback size affect performance?</p>+ <p class="a">Yes. xterm holds scrollback in memory per terminal, so a large scrollback multiplied by many terminals adds up. Pick a generous-but-bounded value and tune it to your workload.</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/performance/">Performance</a><a class="tag" href="/blog/tags/xtermjs/">xterm.js</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="#the-naive-approach-and-why-it-hurts">The naive approach and why it hurts</a></li><li class="lvl-2"><a href="#technique-1-a-persistent-terminal-pool">Technique 1 — A persistent terminal pool</a></li><li class="lvl-2"><a href="#technique-2-render-only-whats-visible">Technique 2 — Render only what’s visible</a></li><li class="lvl-2"><a href="#technique-3-bound-your-scrollback">Technique 3 — Bound your scrollback</a></li><li class="lvl-2"><a href="#technique-4-stream-efficiently-from-the-pty">Technique 4 — Stream efficiently from the PTY</a></li><li class="lvl-2"><a href="#technique-5-reach-for-an-accelerated-renderer-when-needed">Technique 5 — Reach for an accelerated renderer when needed</a></li><li class="lvl-2"><a href="#the-shape-of-a-fast-many-terminal-ui">The shape of a fast many-terminal UI</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/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 Internals</h2>+ <div class="post-grid">+ <article class="card">+ <a class="thumb t-internals" href="/blog/architecture-two-planes-one-renderer/" aria-hidden="true" tabindex="-1">+ <span>INTERNALS</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/architecture-two-planes-one-renderer/">Munder Difflin's Architecture: Two Data Planes, One Renderer</a></h3>+ <p class="dek">A walkthrough of the multi-agent harness architecture: a node-pty terminal plane and a hooks/hive event plane feeding one React + Pixi.js renderer.</p>+ <div class="foot">+ <span class="tag kind">Internals</span>+ <a class="more" href="/blog/architecture-two-planes-one-renderer/" aria-label="Read: Munder Difflin's Architecture: Two Data Planes, One Renderer">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/building-an-ai-office-floor/" 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/building-an-ai-office-floor/">Building an AI "Office Floor": Avatars, Pathfinding, Envelopes</a></h3>+ <p class="dek">The game-dev techniques behind a dev tool's office floor: Tiled maps, BFS pathfinding, sprite recoloring, and flying message envelopes in Pixi.js.</p>+ <div class="foot">+ <span class="tag kind">Internals</span>+ <a class="more" href="/blog/building-an-ai-office-floor/" aria-label="Read: Building an AI "Office Floor": Avatars, Pathfinding, Envelopes">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 & 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.htmlindex 5cd52579..c6b65263 100644--- a/docs/blog/semantic-memory-for-ai-agents/index.html+++ b/docs/blog/semantic-memory-for-ai-agents/index.html@@ -184,8 +184,9 @@ of markdown never does.</li>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 tothat, 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>+wants to be in charge doesn’t. (For the full argument, see+<a href="/blog/markdown-first-agent-memory/">why we built agent memory markdown-first</a>; for the plain-English+version, <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>@@ -246,8 +247,9 @@ source of truth; the index is a recall accelerator built from it. That orderingthey work. Good memory hygiene — small, atomic, factual notes — makes recall sharp; rambling notes makeit 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.+<p>Munder Difflin gives every Claude Code agent markdown memory plus+<a href="https://munderdiffl.in/#how">a shared semantic palace the whole hive can recall from</a> — local, fast,+and graceful when offline.<a href="https://munderdiffl.in/#install">Download Munder Difflin</a> to give your agents memory that actuallysticks; it’s free and open source.</p>@@ -295,7 +297,7 @@ sticks; it’s free and open source.</p><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>+ <a class="pn next" href="/blog/markdown-first-agent-memory/"><span class="k">Newer →</span><span class="t">Why We Built Agent Memory Markdown-First</span></a></div><section class="related"><h2>Related in Memory</h2>@@ -318,6 +320,24 @@ sticks; it’s free and open source.</p></div></div></article>+<article class="card">+ <a class="thumb t-memory" href="/blog/markdown-first-agent-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>5 min</span>+ </div>+ <h3><a href="/blog/markdown-first-agent-memory/">Why We Built Agent Memory Markdown-First</a></h3>+ <p class="dek">Markdown-first AI agent long-term memory: plain notes a human can read and git can diff, with a semantic index on top that degrades gracefully.</p>+ <div class="foot">+ <span class="tag kind">Memory</span>+ <a class="more" href="/blog/markdown-first-agent-memory/" aria-label="Read: Why We Built Agent Memory Markdown-First">Read →</a>+ </div>+ </div>+</article></div></section>diff --git a/docs/blog/single-committer-git-pattern/index.html b/docs/blog/single-committer-git-pattern/index.htmlindex 147cc75f..1405c3f6 100644--- a/docs/blog/single-committer-git-pattern/index.html+++ b/docs/blog/single-committer-git-pattern/index.html@@ -205,8 +205,9 @@ 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 repostops 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>+message, each task assignment, each memory update lands as its own commit, in order — a natural+companion to the <a href="/blog/append-only-event-log-agents/">append-only event log</a> the hive also keeps. When+a multi-agent run goes sideways, you don’t guess — you read the history.</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 commitsthose file changes as they happen. The same single-writer discipline runs through both — it’s the@@ -235,7 +236,7 @@ refs can still contend. Worktrees and single-committer solve different halves ofit does nothing for a <em>stale</em> lock from a dead process — that one never clears on its own. You need theage-based cleanup, not just retries.</p><hr>-<p>Munder Difflin uses the single-committer pattern for its entire coordination layer: agents write+<p>Munder Difflin uses the single-committer pattern across the <a href="https://munderdiffl.in/#what">multi-agent harness</a>: agents writefiles, 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 thatnever corrupt their own state; it’s free and open source.</p>@@ -283,63 +284,63 @@ never corrupt their own state; it’s free and open source.</p></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 prev" href="/blog/visualizing-ai-agents-pixijs/"><span class="k">← Older</span><span class="t">Visualizing AI Agents with Pixi.js: An Office You Can Watch</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">+ <a class="thumb t-internals" href="/blog/architecture-two-planes-one-renderer/" aria-hidden="true" tabindex="-1"><span>INTERNALS</span></a><div class="body"><div class="meta">- <time datetime="2026-06-03">Jun 3, 2026</time>+ <time datetime="2026-06-04">Jun 4, 2026</time><span class="dot" aria-hidden="true"></span>- <span>8 min</span>+ <span>5 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>+ <h3><a href="/blog/architecture-two-planes-one-renderer/">Munder Difflin's Architecture: Two Data Planes, One Renderer</a></h3>+ <p class="dek">A walkthrough of the multi-agent harness architecture: a node-pty terminal plane and a hooks/hive event plane feeding one React + Pixi.js renderer.</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>+ <a class="more" href="/blog/architecture-two-planes-one-renderer/" aria-label="Read: Munder Difflin's Architecture: Two Data Planes, One Renderer">Read →</a></div></div></article><article class="card">- <a class="thumb t-internals" href="/blog/claude-code-hooks-explained/" aria-hidden="true" tabindex="-1">+ <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>6 min</span>+ <span>8 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>+ <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/claude-code-hooks-explained/" aria-label="Read: Claude Code Hooks, Explained (PreToolUse, PostToolUse, Stop)">Read →</a>+ <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">+ <a class="thumb t-internals" href="/blog/building-an-ai-office-floor/" 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>+ <span>6 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>+ <h3><a href="/blog/building-an-ai-office-floor/">Building an AI "Office Floor": Avatars, Pathfinding, Envelopes</a></h3>+ <p class="dek">The game-dev techniques behind a dev tool's office floor: Tiled maps, BFS pathfinding, sprite recoloring, and flying message envelopes in Pixi.js.</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>+ <a class="more" href="/blog/building-an-ai-office-floor/" aria-label="Read: Building an AI "Office Floor": Avatars, Pathfinding, Envelopes">Read →</a></div></div></article>diff --git a/docs/blog/tags/architecture/index.html b/docs/blog/tags/architecture/index.htmlnew file mode 100644index 00000000..b32b9df4--- /dev/null+++ b/docs/blog/tags/architecture/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>Architecture — Munder Difflin Blog</title>+<meta name="description" content="Munder Difflin blog posts tagged Architecture." />+<link rel="canonical" href="https://munderdiffl.in/blog/tags/architecture/" />++<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="Architecture — Munder Difflin Blog" />+<meta property="og:description" content="Munder Difflin blog posts tagged Architecture." />+<meta property="og:url" content="https://munderdiffl.in/blog/tags/architecture/" />+<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="Architecture — Munder Difflin Blog" />+<meta name="twitter:description" content="Munder Difflin blog posts tagged Architecture." />+<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>#Architecture</h1>+ <p class="lead">1 post tagged <strong>Architecture</strong>.</p>+</header>+<section class="wrap">+ <div class="post-grid">+ <article class="card">+ <a class="thumb t-internals" href="/blog/architecture-two-planes-one-renderer/" aria-hidden="true" tabindex="-1">+ <span>INTERNALS</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/architecture-two-planes-one-renderer/">Munder Difflin's Architecture: Two Data Planes, One Renderer</a></h3>+ <p class="dek">A walkthrough of the multi-agent harness architecture: a node-pty terminal plane and a hooks/hive event plane feeding one React + Pixi.js renderer.</p>+ <div class="foot">+ <span class="tag kind">Internals</span>+ <a class="more" href="/blog/architecture-two-planes-one-renderer/" aria-label="Read: Munder Difflin's Architecture: Two Data Planes, One Renderer">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 & 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/debugging/index.html b/docs/blog/tags/debugging/index.htmlnew file mode 100644index 00000000..fa3cfb87--- /dev/null+++ b/docs/blog/tags/debugging/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>Debugging — Munder Difflin Blog</title>+<meta name="description" content="Munder Difflin blog posts tagged Debugging." />+<link rel="canonical" href="https://munderdiffl.in/blog/tags/debugging/" />++<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="Debugging — Munder Difflin Blog" />+<meta property="og:description" content="Munder Difflin blog posts tagged Debugging." />+<meta property="og:url" content="https://munderdiffl.in/blog/tags/debugging/" />+<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="Debugging — Munder Difflin Blog" />+<meta name="twitter:description" content="Munder Difflin blog posts tagged Debugging." />+<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>#Debugging</h1>+ <p class="lead">1 post tagged <strong>Debugging</strong>.</p>+</header>+<section class="wrap">+ <div class="post-grid">+ <article class="card">+ <a class="thumb t-guides" href="/blog/debugging-multi-agent-systems/" 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/debugging-multi-agent-systems/">How to Debug a Multi-Agent System</a></h3>+ <p class="dek">How to debug a multi-agent system: use the event log, per-agent terminals, message trails, and git history to find why a hive of AI agents went sideways.</p>+ <div class="foot">+ <span class="tag kind">Guides</span>+ <a class="more" href="/blog/debugging-multi-agent-systems/" aria-label="Read: How to Debug a Multi-Agent System">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 & 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.htmlindex 38d61e30..efa5417d 100644--- a/docs/blog/tags/electron/index.html+++ b/docs/blog/tags/electron/index.html@@ -58,11 +58,29 @@<header class="page-head wrap"><p class="eyebrow">Tag</p><h1>#Electron</h1>- <p class="lead">2 posts tagged <strong>Electron</strong>.</p>+ <p class="lead">3 posts tagged <strong>Electron</strong>.</p></header><section class="wrap"><div class="post-grid"><article class="card">+ <a class="thumb t-internals" href="/blog/architecture-two-planes-one-renderer/" aria-hidden="true" tabindex="-1">+ <span>INTERNALS</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/architecture-two-planes-one-renderer/">Munder Difflin's Architecture: Two Data Planes, One Renderer</a></h3>+ <p class="dek">A walkthrough of the multi-agent harness architecture: a node-pty terminal plane and a hooks/hive event plane feeding one React + Pixi.js renderer.</p>+ <div class="foot">+ <span class="tag kind">Internals</span>+ <a class="more" href="/blog/architecture-two-planes-one-renderer/" aria-label="Read: Munder Difflin's Architecture: Two Data Planes, One Renderer">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>diff --git a/docs/blog/tags/event-log/index.html b/docs/blog/tags/event-log/index.htmlindex 8aba0440..d8e2898c 100644--- a/docs/blog/tags/event-log/index.html+++ b/docs/blog/tags/event-log/index.html@@ -73,7 +73,7 @@<span>5 min</span></div><h3><a href="/blog/append-only-event-log-agents/">An Append-Only Event Log for a Hive of Agents</a></h3>- <p class="dek">How an append-only event log makes a multi-agent system debuggable and replayable — what to record per event, and why one JSON line per event beats a database.</p>+ <p class="dek">How an append-only event log makes a multi-agent system debuggable and replayable: what to record, and why one JSON line per event beats a database.</p><div class="foot"><span class="tag kind">Internals</span><a class="more" href="/blog/append-only-event-log-agents/" aria-label="Read: An Append-Only Event Log for a Hive of Agents">Read →</a>diff --git a/docs/blog/tags/game-dev/index.html b/docs/blog/tags/game-dev/index.htmlnew file mode 100644index 00000000..5d3e4031--- /dev/null+++ b/docs/blog/tags/game-dev/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>Game Dev — Munder Difflin Blog</title>+<meta name="description" content="Munder Difflin blog posts tagged Game Dev." />+<link rel="canonical" href="https://munderdiffl.in/blog/tags/game-dev/" />++<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="Game Dev — Munder Difflin Blog" />+<meta property="og:description" content="Munder Difflin blog posts tagged Game Dev." />+<meta property="og:url" content="https://munderdiffl.in/blog/tags/game-dev/" />+<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="Game Dev — Munder Difflin Blog" />+<meta name="twitter:description" content="Munder Difflin blog posts tagged Game Dev." />+<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>#Game Dev</h1>+ <p class="lead">1 post tagged <strong>Game Dev</strong>.</p>+</header>+<section class="wrap">+ <div class="post-grid">+ <article class="card">+ <a class="thumb t-internals" href="/blog/building-an-ai-office-floor/" 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/building-an-ai-office-floor/">Building an AI "Office Floor": Avatars, Pathfinding, Envelopes</a></h3>+ <p class="dek">The game-dev techniques behind a dev tool's office floor: Tiled maps, BFS pathfinding, sprite recoloring, and flying message envelopes in Pixi.js.</p>+ <div class="foot">+ <span class="tag kind">Internals</span>+ <a class="more" href="/blog/building-an-ai-office-floor/" aria-label="Read: Building an AI "Office Floor": Avatars, Pathfinding, Envelopes">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 & 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/guardrails/index.html b/docs/blog/tags/guardrails/index.htmlindex 165b39a5..d2ff48fa 100644--- a/docs/blog/tags/guardrails/index.html+++ b/docs/blog/tags/guardrails/index.html@@ -73,7 +73,7 @@<span>5 min</span></div><h3><a href="/blog/human-in-the-loop-ai-agents/">Human-in-the-Loop AI Agents: Approvals That Don't Slow You Down</a></h3>- <p class="dek">Design human-in-the-loop AI agents that stay autonomous: an approvals queue that escalates only spend, destructive ops, and scope — and relays your answer back.</p>+ <p class="dek">Design human-in-the-loop AI agents that stay autonomous: an approvals queue that escalates only spend, destructive ops, and scope changes.</p><div class="foot"><span class="tag kind">Orchestration</span><a class="more" href="/blog/human-in-the-loop-ai-agents/" aria-label="Read: Human-in-the-Loop AI Agents: Approvals That Don't Slow You Down">Read →</a>diff --git a/docs/blog/tags/guides/index.html b/docs/blog/tags/guides/index.htmlindex 788786ec..d7fd4e49 100644--- a/docs/blog/tags/guides/index.html+++ b/docs/blog/tags/guides/index.html@@ -58,7 +58,7 @@<header class="page-head wrap"><p class="eyebrow">Tag</p><h1>#Guides</h1>- <p class="lead">6 posts tagged <strong>Guides</strong>.</p>+ <p class="lead">7 posts tagged <strong>Guides</strong>.</p></header><section class="wrap"><div class="post-grid">@@ -80,6 +80,24 @@</div></div></article>+<article class="card">+ <a class="thumb t-guides" href="/blog/debugging-multi-agent-systems/" 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/debugging-multi-agent-systems/">How to Debug a Multi-Agent System</a></h3>+ <p class="dek">How to debug a multi-agent system: use the event log, per-agent terminals, message trails, and git history to find why a hive of AI agents went sideways.</p>+ <div class="foot">+ <span class="tag kind">Guides</span>+ <a class="more" href="/blog/debugging-multi-agent-systems/" aria-label="Read: How to Debug a Multi-Agent System">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>diff --git a/docs/blog/tags/human-in-the-loop/index.html b/docs/blog/tags/human-in-the-loop/index.htmlindex 007b573a..b9bfcd3b 100644--- a/docs/blog/tags/human-in-the-loop/index.html+++ b/docs/blog/tags/human-in-the-loop/index.html@@ -73,7 +73,7 @@<span>5 min</span></div><h3><a href="/blog/human-in-the-loop-ai-agents/">Human-in-the-Loop AI Agents: Approvals That Don't Slow You Down</a></h3>- <p class="dek">Design human-in-the-loop AI agents that stay autonomous: an approvals queue that escalates only spend, destructive ops, and scope — and relays your answer back.</p>+ <p class="dek">Design human-in-the-loop AI agents that stay autonomous: an approvals queue that escalates only spend, destructive ops, and scope changes.</p><div class="foot"><span class="tag kind">Orchestration</span><a class="more" href="/blog/human-in-the-loop-ai-agents/" aria-label="Read: Human-in-the-Loop AI Agents: Approvals That Don't Slow You Down">Read →</a>diff --git a/docs/blog/tags/internals/index.html b/docs/blog/tags/internals/index.htmlindex df89e6b7..feaf1f36 100644--- a/docs/blog/tags/internals/index.html+++ b/docs/blog/tags/internals/index.html@@ -58,11 +58,29 @@<header class="page-head wrap"><p class="eyebrow">Tag</p><h1>#Internals</h1>- <p class="lead">7 posts tagged <strong>Internals</strong>.</p>+ <p class="lead">11 posts tagged <strong>Internals</strong>.</p></header><section class="wrap"><div class="post-grid"><article class="card">+ <a class="thumb t-internals" href="/blog/architecture-two-planes-one-renderer/" aria-hidden="true" tabindex="-1">+ <span>INTERNALS</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/architecture-two-planes-one-renderer/">Munder Difflin's Architecture: Two Data Planes, One Renderer</a></h3>+ <p class="dek">A walkthrough of the multi-agent harness architecture: a node-pty terminal plane and a hooks/hive event plane feeding one React + Pixi.js renderer.</p>+ <div class="foot">+ <span class="tag kind">Internals</span>+ <a class="more" href="/blog/architecture-two-planes-one-renderer/" aria-label="Read: Munder Difflin's Architecture: Two Data Planes, One Renderer">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>@@ -80,6 +98,24 @@</div></div></article>+<article class="card">+ <a class="thumb t-internals" href="/blog/building-an-ai-office-floor/" 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/building-an-ai-office-floor/">Building an AI "Office Floor": Avatars, Pathfinding, Envelopes</a></h3>+ <p class="dek">The game-dev techniques behind a dev tool's office floor: Tiled maps, BFS pathfinding, sprite recoloring, and flying message envelopes in Pixi.js.</p>+ <div class="foot">+ <span class="tag kind">Internals</span>+ <a class="more" href="/blog/building-an-ai-office-floor/" aria-label="Read: Building an AI "Office Floor": Avatars, Pathfinding, Envelopes">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>@@ -116,6 +152,24 @@</div></div></article>+<article class="card">+ <a class="thumb t-internals" href="/blog/rendering-many-live-terminals-performance/" 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>5 min</span>+ </div>+ <h3><a href="/blog/rendering-many-live-terminals-performance/">Rendering Many Live Terminals Without Melting the CPU</a></h3>+ <p class="dek">xterm.js performance for many live PTYs: a terminal pool, render-only-visible, smart scrollback, and accelerated rendering to stream dozens at once.</p>+ <div class="foot">+ <span class="tag kind">Internals</span>+ <a class="more" href="/blog/rendering-many-live-terminals-performance/" aria-label="Read: Rendering Many Live Terminals Without Melting the CPU">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>@@ -134,6 +188,24 @@</div></div></article>+<article class="card">+ <a class="thumb t-internals" href="/blog/visualizing-ai-agents-pixijs/" 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/visualizing-ai-agents-pixijs/">Visualizing AI Agents with Pixi.js: An Office You Can Watch</a></h3>+ <p class="dek">How we render AI agents as avatars on a Pixi.js office floor — driven by real hook and message events, with seat assignment, pathing, and flying envelopes.</p>+ <div class="foot">+ <span class="tag kind">Internals</span>+ <a class="more" href="/blog/visualizing-ai-agents-pixijs/" aria-label="Read: Visualizing AI Agents with Pixi.js: An Office You Can Watch">Read →</a>+ </div>+ </div>+</article><article class="card"><a class="thumb t-internals" href="/blog/append-only-event-log-agents/" aria-hidden="true" tabindex="-1"><span>INTERNALS</span>@@ -145,7 +217,7 @@<span>5 min</span></div><h3><a href="/blog/append-only-event-log-agents/">An Append-Only Event Log for a Hive of Agents</a></h3>- <p class="dek">How an append-only event log makes a multi-agent system debuggable and replayable — what to record per event, and why one JSON line per event beats a database.</p>+ <p class="dek">How an append-only event log makes a multi-agent system debuggable and replayable: what to record, and why one JSON line per event beats a database.</p><div class="foot"><span class="tag kind">Internals</span><a class="more" href="/blog/append-only-event-log-agents/" aria-label="Read: An Append-Only Event Log for a Hive of Agents">Read →</a>diff --git a/docs/blog/tags/markdown/index.html b/docs/blog/tags/markdown/index.htmlnew file mode 100644index 00000000..1a0f5b26--- /dev/null+++ b/docs/blog/tags/markdown/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>Markdown — Munder Difflin Blog</title>+<meta name="description" content="Munder Difflin blog posts tagged Markdown." />+<link rel="canonical" href="https://munderdiffl.in/blog/tags/markdown/" />++<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="Markdown — Munder Difflin Blog" />+<meta property="og:description" content="Munder Difflin blog posts tagged Markdown." />+<meta property="og:url" content="https://munderdiffl.in/blog/tags/markdown/" />+<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="Markdown — Munder Difflin Blog" />+<meta name="twitter:description" content="Munder Difflin blog posts tagged Markdown." />+<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>#Markdown</h1>+ <p class="lead">1 post tagged <strong>Markdown</strong>.</p>+</header>+<section class="wrap">+ <div class="post-grid">+ <article class="card">+ <a class="thumb t-memory" href="/blog/markdown-first-agent-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>5 min</span>+ </div>+ <h3><a href="/blog/markdown-first-agent-memory/">Why We Built Agent Memory Markdown-First</a></h3>+ <p class="dek">Markdown-first AI agent long-term memory: plain notes a human can read and git can diff, with a semantic index on top that degrades gracefully.</p>+ <div class="foot">+ <span class="tag kind">Memory</span>+ <a class="more" href="/blog/markdown-first-agent-memory/" aria-label="Read: Why We Built Agent Memory Markdown-First">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 & 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.htmlindex f30a5565..126cd91c 100644--- a/docs/blog/tags/memory/index.html+++ b/docs/blog/tags/memory/index.html@@ -58,7 +58,7 @@<header class="page-head wrap"><p class="eyebrow">Tag</p><h1>#Memory</h1>- <p class="lead">3 posts tagged <strong>Memory</strong>.</p>+ <p class="lead">4 posts tagged <strong>Memory</strong>.</p></header><section class="wrap"><div class="post-grid">@@ -98,6 +98,24 @@</div></div></article>+<article class="card">+ <a class="thumb t-memory" href="/blog/markdown-first-agent-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>5 min</span>+ </div>+ <h3><a href="/blog/markdown-first-agent-memory/">Why We Built Agent Memory Markdown-First</a></h3>+ <p class="dek">Markdown-first AI agent long-term memory: plain notes a human can read and git can diff, with a semantic index on top that degrades gracefully.</p>+ <div class="foot">+ <span class="tag kind">Memory</span>+ <a class="more" href="/blog/markdown-first-agent-memory/" aria-label="Read: Why We Built Agent Memory Markdown-First">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>diff --git a/docs/blog/tags/mempalace/index.html b/docs/blog/tags/mempalace/index.htmlindex 339754df..dfbdd617 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">2 posts tagged <strong>MemPalace</strong>.</p>+ <p class="lead">3 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/markdown-first-agent-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>5 min</span>+ </div>+ <h3><a href="/blog/markdown-first-agent-memory/">Why We Built Agent Memory Markdown-First</a></h3>+ <p class="dek">Markdown-first AI agent long-term memory: plain notes a human can read and git can diff, with a semantic index on top that degrades gracefully.</p>+ <div class="foot">+ <span class="tag kind">Memory</span>+ <a class="more" href="/blog/markdown-first-agent-memory/" aria-label="Read: Why We Built Agent Memory Markdown-First">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>diff --git a/docs/blog/tags/multi-agent/index.html b/docs/blog/tags/multi-agent/index.htmlindex fcf98def..71f0c6ba 100644--- a/docs/blog/tags/multi-agent/index.html+++ b/docs/blog/tags/multi-agent/index.html@@ -58,11 +58,29 @@<header class="page-head wrap"><p class="eyebrow">Tag</p><h1>#Multi-Agent</h1>- <p class="lead">26 posts tagged <strong>Multi-Agent</strong>.</p>+ <p class="lead">29 posts tagged <strong>Multi-Agent</strong>.</p></header><section class="wrap"><div class="post-grid"><article class="card">+ <a class="thumb t-internals" href="/blog/architecture-two-planes-one-renderer/" aria-hidden="true" tabindex="-1">+ <span>INTERNALS</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/architecture-two-planes-one-renderer/">Munder Difflin's Architecture: Two Data Planes, One Renderer</a></h3>+ <p class="dek">A walkthrough of the multi-agent harness architecture: a node-pty terminal plane and a hooks/hive event plane feeding one React + Pixi.js renderer.</p>+ <div class="foot">+ <span class="tag kind">Internals</span>+ <a class="more" href="/blog/architecture-two-planes-one-renderer/" aria-label="Read: Munder Difflin's Architecture: Two Data Planes, One Renderer">Read →</a>+ </div>+ </div>+</article>+<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>@@ -116,6 +134,24 @@</div></div></article>+<article class="card">+ <a class="thumb t-guides" href="/blog/debugging-multi-agent-systems/" 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/debugging-multi-agent-systems/">How to Debug a Multi-Agent System</a></h3>+ <p class="dek">How to debug a multi-agent system: use the event log, per-agent terminals, message trails, and git history to find why a hive of AI agents went sideways.</p>+ <div class="foot">+ <span class="tag kind">Guides</span>+ <a class="more" href="/blog/debugging-multi-agent-systems/" aria-label="Read: How to Debug a Multi-Agent System">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>@@ -217,7 +253,7 @@<span>5 min</span></div><h3><a href="/blog/human-in-the-loop-ai-agents/">Human-in-the-Loop AI Agents: Approvals That Don't Slow You Down</a></h3>- <p class="dek">Design human-in-the-loop AI agents that stay autonomous: an approvals queue that escalates only spend, destructive ops, and scope — and relays your answer back.</p>+ <p class="dek">Design human-in-the-loop AI agents that stay autonomous: an approvals queue that escalates only spend, destructive ops, and scope changes.</p><div class="foot"><span class="tag kind">Orchestration</span><a class="more" href="/blog/human-in-the-loop-ai-agents/" aria-label="Read: Human-in-the-Loop AI Agents: Approvals That Don't Slow You Down">Read →</a>@@ -343,7 +379,7 @@<span>5 min</span></div><h3><a href="/blog/append-only-event-log-agents/">An Append-Only Event Log for a Hive of Agents</a></h3>- <p class="dek">How an append-only event log makes a multi-agent system debuggable and replayable — what to record per event, and why one JSON line per event beats a database.</p>+ <p class="dek">How an append-only event log makes a multi-agent system debuggable and replayable: what to record, and why one JSON line per event beats a database.</p><div class="foot"><span class="tag kind">Internals</span><a class="more" href="/blog/append-only-event-log-agents/" aria-label="Read: An Append-Only Event Log for a Hive of Agents">Read →</a>@@ -440,6 +476,24 @@</div></div></article>+<article class="card">+ <a class="thumb t-memory" href="/blog/markdown-first-agent-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>5 min</span>+ </div>+ <h3><a href="/blog/markdown-first-agent-memory/">Why We Built Agent Memory Markdown-First</a></h3>+ <p class="dek">Markdown-first AI agent long-term memory: plain notes a human can read and git can diff, with a semantic index on top that degrades gracefully.</p>+ <div class="foot">+ <span class="tag kind">Memory</span>+ <a class="more" href="/blog/markdown-first-agent-memory/" aria-label="Read: Why We Built Agent Memory Markdown-First">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>diff --git a/docs/blog/tags/observability/index.html b/docs/blog/tags/observability/index.htmlindex dc9e0dce..07f4a0ab 100644--- a/docs/blog/tags/observability/index.html+++ b/docs/blog/tags/observability/index.html@@ -58,11 +58,47 @@<header class="page-head wrap"><p class="eyebrow">Tag</p><h1>#Observability</h1>- <p class="lead">1 post tagged <strong>Observability</strong>.</p>+ <p class="lead">3 posts tagged <strong>Observability</strong>.</p></header><section class="wrap"><div class="post-grid"><article class="card">+ <a class="thumb t-guides" href="/blog/debugging-multi-agent-systems/" 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/debugging-multi-agent-systems/">How to Debug a Multi-Agent System</a></h3>+ <p class="dek">How to debug a multi-agent system: use the event log, per-agent terminals, message trails, and git history to find why a hive of AI agents went sideways.</p>+ <div class="foot">+ <span class="tag kind">Guides</span>+ <a class="more" href="/blog/debugging-multi-agent-systems/" aria-label="Read: How to Debug a Multi-Agent System">Read →</a>+ </div>+ </div>+</article>+<article class="card">+ <a class="thumb t-internals" href="/blog/visualizing-ai-agents-pixijs/" 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/visualizing-ai-agents-pixijs/">Visualizing AI Agents with Pixi.js: An Office You Can Watch</a></h3>+ <p class="dek">How we render AI agents as avatars on a Pixi.js office floor — driven by real hook and message events, with seat assignment, pathing, and flying envelopes.</p>+ <div class="foot">+ <span class="tag kind">Internals</span>+ <a class="more" href="/blog/visualizing-ai-agents-pixijs/" aria-label="Read: Visualizing AI Agents with Pixi.js: An Office You Can Watch">Read →</a>+ </div>+ </div>+</article>+<article class="card"><a class="thumb t-internals" href="/blog/append-only-event-log-agents/" aria-hidden="true" tabindex="-1"><span>INTERNALS</span></a>@@ -73,7 +109,7 @@<span>5 min</span></div><h3><a href="/blog/append-only-event-log-agents/">An Append-Only Event Log for a Hive of Agents</a></h3>- <p class="dek">How an append-only event log makes a multi-agent system debuggable and replayable — what to record per event, and why one JSON line per event beats a database.</p>+ <p class="dek">How an append-only event log makes a multi-agent system debuggable and replayable: what to record, and why one JSON line per event beats a database.</p><div class="foot"><span class="tag kind">Internals</span><a class="more" href="/blog/append-only-event-log-agents/" aria-label="Read: An Append-Only Event Log for a Hive of Agents">Read →</a>diff --git a/docs/blog/tags/orchestration/index.html b/docs/blog/tags/orchestration/index.htmlindex d133e98f..50b7581e 100644--- a/docs/blog/tags/orchestration/index.html+++ b/docs/blog/tags/orchestration/index.html@@ -145,7 +145,7 @@<span>5 min</span></div><h3><a href="/blog/human-in-the-loop-ai-agents/">Human-in-the-Loop AI Agents: Approvals That Don't Slow You Down</a></h3>- <p class="dek">Design human-in-the-loop AI agents that stay autonomous: an approvals queue that escalates only spend, destructive ops, and scope — and relays your answer back.</p>+ <p class="dek">Design human-in-the-loop AI agents that stay autonomous: an approvals queue that escalates only spend, destructive ops, and scope changes.</p><div class="foot"><span class="tag kind">Orchestration</span><a class="more" href="/blog/human-in-the-loop-ai-agents/" aria-label="Read: Human-in-the-Loop AI Agents: Approvals That Don't Slow You Down">Read →</a>diff --git a/docs/blog/tags/performance/index.html b/docs/blog/tags/performance/index.htmlnew file mode 100644index 00000000..5696f1c3--- /dev/null+++ b/docs/blog/tags/performance/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>Performance — Munder Difflin Blog</title>+<meta name="description" content="Munder Difflin blog posts tagged Performance." />+<link rel="canonical" href="https://munderdiffl.in/blog/tags/performance/" />++<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="Performance — Munder Difflin Blog" />+<meta property="og:description" content="Munder Difflin blog posts tagged Performance." />+<meta property="og:url" content="https://munderdiffl.in/blog/tags/performance/" />+<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="Performance — Munder Difflin Blog" />+<meta name="twitter:description" content="Munder Difflin blog posts tagged Performance." />+<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>#Performance</h1>+ <p class="lead">1 post tagged <strong>Performance</strong>.</p>+</header>+<section class="wrap">+ <div class="post-grid">+ <article class="card">+ <a class="thumb t-internals" href="/blog/rendering-many-live-terminals-performance/" 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>5 min</span>+ </div>+ <h3><a href="/blog/rendering-many-live-terminals-performance/">Rendering Many Live Terminals Without Melting the CPU</a></h3>+ <p class="dek">xterm.js performance for many live PTYs: a terminal pool, render-only-visible, smart scrollback, and accelerated rendering to stream dozens at once.</p>+ <div class="foot">+ <span class="tag kind">Internals</span>+ <a class="more" href="/blog/rendering-many-live-terminals-performance/" aria-label="Read: Rendering Many Live Terminals Without Melting the CPU">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 & 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/pixijs/index.html b/docs/blog/tags/pixijs/index.htmlnew file mode 100644index 00000000..4fe3194d--- /dev/null+++ b/docs/blog/tags/pixijs/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>Pixi.js — Munder Difflin Blog</title>+<meta name="description" content="Munder Difflin blog posts tagged Pixi.js." />+<link rel="canonical" href="https://munderdiffl.in/blog/tags/pixijs/" />++<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="Pixi.js — Munder Difflin Blog" />+<meta property="og:description" content="Munder Difflin blog posts tagged Pixi.js." />+<meta property="og:url" content="https://munderdiffl.in/blog/tags/pixijs/" />+<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="Pixi.js — Munder Difflin Blog" />+<meta name="twitter:description" content="Munder Difflin blog posts tagged Pixi.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>#Pixi.js</h1>+ <p class="lead">2 posts tagged <strong>Pixi.js</strong>.</p>+</header>+<section class="wrap">+ <div class="post-grid">+ <article class="card">+ <a class="thumb t-internals" href="/blog/building-an-ai-office-floor/" 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/building-an-ai-office-floor/">Building an AI "Office Floor": Avatars, Pathfinding, Envelopes</a></h3>+ <p class="dek">The game-dev techniques behind a dev tool's office floor: Tiled maps, BFS pathfinding, sprite recoloring, and flying message envelopes in Pixi.js.</p>+ <div class="foot">+ <span class="tag kind">Internals</span>+ <a class="more" href="/blog/building-an-ai-office-floor/" aria-label="Read: Building an AI "Office Floor": Avatars, Pathfinding, Envelopes">Read →</a>+ </div>+ </div>+</article>+<article class="card">+ <a class="thumb t-internals" href="/blog/visualizing-ai-agents-pixijs/" 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/visualizing-ai-agents-pixijs/">Visualizing AI Agents with Pixi.js: An Office You Can Watch</a></h3>+ <p class="dek">How we render AI agents as avatars on a Pixi.js office floor — driven by real hook and message events, with seat assignment, pathing, and flying envelopes.</p>+ <div class="foot">+ <span class="tag kind">Internals</span>+ <a class="more" href="/blog/visualizing-ai-agents-pixijs/" aria-label="Read: Visualizing AI Agents with Pixi.js: An Office You Can Watch">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 & 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.htmlindex cc808e7b..00a1ca31 100644--- a/docs/blog/tags/terminals/index.html+++ b/docs/blog/tags/terminals/index.html@@ -58,7 +58,7 @@<header class="page-head wrap"><p class="eyebrow">Tag</p><h1>#Terminals</h1>- <p class="lead">2 posts tagged <strong>Terminals</strong>.</p>+ <p class="lead">3 posts tagged <strong>Terminals</strong>.</p></header><section class="wrap"><div class="post-grid">@@ -98,6 +98,24 @@</div></div></article>+<article class="card">+ <a class="thumb t-internals" href="/blog/rendering-many-live-terminals-performance/" 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>5 min</span>+ </div>+ <h3><a href="/blog/rendering-many-live-terminals-performance/">Rendering Many Live Terminals Without Melting the CPU</a></h3>+ <p class="dek">xterm.js performance for many live PTYs: a terminal pool, render-only-visible, smart scrollback, and accelerated rendering to stream dozens at once.</p>+ <div class="foot">+ <span class="tag kind">Internals</span>+ <a class="more" href="/blog/rendering-many-live-terminals-performance/" aria-label="Read: Rendering Many Live Terminals Without Melting the CPU">Read →</a>+ </div>+ </div>+</article></div></section>diff --git a/docs/blog/tags/visualization/index.html b/docs/blog/tags/visualization/index.htmlnew file mode 100644index 00000000..082c2d9b--- /dev/null+++ b/docs/blog/tags/visualization/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>Visualization — Munder Difflin Blog</title>+<meta name="description" content="Munder Difflin blog posts tagged Visualization." />+<link rel="canonical" href="https://munderdiffl.in/blog/tags/visualization/" />++<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="Visualization — Munder Difflin Blog" />+<meta property="og:description" content="Munder Difflin blog posts tagged Visualization." />+<meta property="og:url" content="https://munderdiffl.in/blog/tags/visualization/" />+<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="Visualization — Munder Difflin Blog" />+<meta name="twitter:description" content="Munder Difflin blog posts tagged Visualization." />+<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>#Visualization</h1>+ <p class="lead">2 posts tagged <strong>Visualization</strong>.</p>+</header>+<section class="wrap">+ <div class="post-grid">+ <article class="card">+ <a class="thumb t-internals" href="/blog/building-an-ai-office-floor/" 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/building-an-ai-office-floor/">Building an AI "Office Floor": Avatars, Pathfinding, Envelopes</a></h3>+ <p class="dek">The game-dev techniques behind a dev tool's office floor: Tiled maps, BFS pathfinding, sprite recoloring, and flying message envelopes in Pixi.js.</p>+ <div class="foot">+ <span class="tag kind">Internals</span>+ <a class="more" href="/blog/building-an-ai-office-floor/" aria-label="Read: Building an AI "Office Floor": Avatars, Pathfinding, Envelopes">Read →</a>+ </div>+ </div>+</article>+<article class="card">+ <a class="thumb t-internals" href="/blog/visualizing-ai-agents-pixijs/" 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/visualizing-ai-agents-pixijs/">Visualizing AI Agents with Pixi.js: An Office You Can Watch</a></h3>+ <p class="dek">How we render AI agents as avatars on a Pixi.js office floor — driven by real hook and message events, with seat assignment, pathing, and flying envelopes.</p>+ <div class="foot">+ <span class="tag kind">Internals</span>+ <a class="more" href="/blog/visualizing-ai-agents-pixijs/" aria-label="Read: Visualizing AI Agents with Pixi.js: An Office You Can Watch">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 & 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.htmlindex b3663a71..5e464e4a 100644--- a/docs/blog/tags/xtermjs/index.html+++ b/docs/blog/tags/xtermjs/index.html@@ -58,7 +58,7 @@<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>+ <p class="lead">2 posts tagged <strong>xterm.js</strong>.</p></header><section class="wrap"><div class="post-grid">@@ -80,6 +80,24 @@</div></div></article>+<article class="card">+ <a class="thumb t-internals" href="/blog/rendering-many-live-terminals-performance/" 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>5 min</span>+ </div>+ <h3><a href="/blog/rendering-many-live-terminals-performance/">Rendering Many Live Terminals Without Melting the CPU</a></h3>+ <p class="dek">xterm.js performance for many live PTYs: a terminal pool, render-only-visible, smart scrollback, and accelerated rendering to stream dozens at once.</p>+ <div class="foot">+ <span class="tag kind">Internals</span>+ <a class="more" href="/blog/rendering-many-live-terminals-performance/" aria-label="Read: Rendering Many Live Terminals Without Melting the CPU">Read →</a>+ </div>+ </div>+</article></div></section>diff --git a/docs/blog/topics/comparisons/index.html b/docs/blog/topics/comparisons/index.htmlindex ae9b4f10..fd0d1e76 100644--- a/docs/blog/topics/comparisons/index.html+++ b/docs/blog/topics/comparisons/index.html@@ -68,19 +68,19 @@<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/internals/">internals<span class="ct">10</span></a>- <a class="chip" href="/blog/topics/guides/">guides<span class="ct">6</span></a>+ <a class="chip" href="/blog/topics/comparisons/" aria-current="page">comparisons<span class="ct">8</span></a>- <a class="chip" href="/blog/topics/internals/">internals<span class="ct">6</span></a>+ <a class="chip" href="/blog/topics/guides/">guides<span class="ct">7</span></a><a class="chip" href="/blog/topics/orchestration/">orchestration<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/use-cases/">use-cases<span class="ct">3</span></a>+ <a class="chip" href="/blog/topics/memory/">memory<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/use-cases/">use-cases<span class="ct">3</span></a><a class="chip" href="/blog/topics/story/">story<span class="ct">1</span></a>diff --git a/docs/blog/topics/concepts/index.html b/docs/blog/topics/concepts/index.htmlindex c5731d09..abb19581 100644--- a/docs/blog/topics/concepts/index.html+++ b/docs/blog/topics/concepts/index.html@@ -68,19 +68,19 @@<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/internals/">internals<span class="ct">10</span></a>- <a class="chip" href="/blog/topics/guides/">guides<span class="ct">6</span></a>+ <a class="chip" href="/blog/topics/comparisons/">comparisons<span class="ct">8</span></a>- <a class="chip" href="/blog/topics/internals/">internals<span class="ct">6</span></a>+ <a class="chip" href="/blog/topics/guides/">guides<span class="ct">7</span></a><a class="chip" href="/blog/topics/orchestration/">orchestration<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/use-cases/">use-cases<span class="ct">3</span></a>+ <a class="chip" href="/blog/topics/memory/">memory<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/use-cases/">use-cases<span class="ct">3</span></a><a class="chip" href="/blog/topics/story/">story<span class="ct">1</span></a>diff --git a/docs/blog/topics/guides/index.html b/docs/blog/topics/guides/index.htmlindex 645a42ab..d9f859f8 100644--- a/docs/blog/topics/guides/index.html+++ b/docs/blog/topics/guides/index.html@@ -63,24 +63,24 @@</nav><p class="eyebrow">Topic</p><h1>guides</h1>- <p class="lead">6 posts in this cluster.</p>+ <p class="lead">7 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/internals/">internals<span class="ct">10</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/comparisons/">comparisons<span class="ct">8</span></a>- <a class="chip" href="/blog/topics/internals/">internals<span class="ct">6</span></a>+ <a class="chip" href="/blog/topics/guides/" aria-current="page">guides<span class="ct">7</span></a><a class="chip" href="/blog/topics/orchestration/">orchestration<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/use-cases/">use-cases<span class="ct">3</span></a>+ <a class="chip" href="/blog/topics/memory/">memory<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/use-cases/">use-cases<span class="ct">3</span></a><a class="chip" href="/blog/topics/story/">story<span class="ct">1</span></a>@@ -107,6 +107,24 @@</div></div></article>+<article class="card">+ <a class="thumb t-guides" href="/blog/debugging-multi-agent-systems/" 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/debugging-multi-agent-systems/">How to Debug a Multi-Agent System</a></h3>+ <p class="dek">How to debug a multi-agent system: use the event log, per-agent terminals, message trails, and git history to find why a hive of AI agents went sideways.</p>+ <div class="foot">+ <span class="tag kind">Guides</span>+ <a class="more" href="/blog/debugging-multi-agent-systems/" aria-label="Read: How to Debug a Multi-Agent System">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>diff --git a/docs/blog/topics/index.html b/docs/blog/topics/index.htmlindex a1530227..cb9bc9c9 100644--- a/docs/blog/topics/index.html+++ b/docs/blog/topics/index.html@@ -66,6 +66,15 @@<section class="wrap"><div class="post-grid">+ <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">10 posts.</p>+ <div class="foot"><span class="more">View topic →</span></div>+ </div>+ </a>+<a class="card" href="/blog/topics/comparisons/" style="text-decoration:none"><span class="thumb t-comparisons" aria-hidden="true">COMPARISONS</span><div class="body">@@ -79,16 +88,7 @@<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">6 posts.</p>+ <p class="dek">7 posts.</p><div class="foot"><span class="more">View topic →</span></div></div></a>@@ -111,20 +111,20 @@</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>+ <a class="card" href="/blog/topics/memory/" style="text-decoration:none">+ <span class="thumb t-memory" aria-hidden="true">MEMORY</span><div class="body">- <h3 style="color:var(--ink)">use-cases</h3>+ <h3 style="color:var(--ink)">memory</h3><p class="dek">3 posts.</p><div class="foot"><span class="more">View topic →</span></div></div></a>- <a class="card" href="/blog/topics/memory/" style="text-decoration:none">- <span class="thumb t-memory" aria-hidden="true">MEMORY</span>+ <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)">memory</h3>- <p class="dek">2 posts.</p>+ <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>@@ -144,33 +144,39 @@<div class="filters" style="padding-top:36px"><span class="eyebrow" style="align-self:center">Tags</span>- <a class="chip" href="/blog/tags/multi-agent/">Multi-Agent<span class="ct">26</span></a>+ <a class="chip" href="/blog/tags/multi-agent/">Multi-Agent<span class="ct">29</span></a><a class="chip" href="/blog/tags/claude-code/">Claude Code<span class="ct">24</span></a>+ <a class="chip" href="/blog/tags/internals/">Internals<span class="ct">11</span></a>+<a class="chip" href="/blog/tags/orchestration/">Orchestration<span class="ct">8</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/internals/">Internals<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/guides/">Guides<span class="ct">7</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/memory/">Memory<span class="ct">4</span></a>++ <a class="chip" href="/blog/tags/mempalace/">MemPalace<span class="ct">3</span></a>++ <a class="chip" href="/blog/tags/observability/">Observability<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/terminals/">Terminals<span class="ct">3</span></a>- <a class="chip" href="/blog/tags/mempalace/">MemPalace<span class="ct">2</span></a>+ <a class="chip" href="/blog/tags/electron/">Electron<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/god/">GOD<span class="ct">2</span></a>@@ -178,18 +184,20 @@<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/pixijs/">Pixi.js<span class="ct">2</span></a>++ <a class="chip" href="/blog/tags/visualization/">Visualization<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/xtermjs/">xterm.js<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/markdown/">Markdown<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/observability/">Observability<span class="ct">1</span></a>-<a class="chip" href="/blog/tags/event-log/">Event Log<span class="ct">1</span></a><a class="chip" href="/blog/tags/glossary/">Glossary<span class="ct">1</span></a>@@ -208,7 +216,7 @@<a class="chip" href="/blog/tags/open-source/">Open Source<span class="ct">1</span></a>- <a class="chip" href="/blog/tags/xtermjs/">xterm.js<span class="ct">1</span></a>+ <a class="chip" href="/blog/tags/game-dev/">Game Dev<span class="ct">1</span></a><a class="chip" href="/blog/tags/hooks/">Hooks<span class="ct">1</span></a>@@ -218,8 +226,14 @@<a class="chip" href="/blog/tags/node-pty/">node-pty<span class="ct">1</span></a>+ <a class="chip" href="/blog/tags/performance/">Performance<span class="ct">1</span></a>++ <a class="chip" href="/blog/tags/architecture/">Architecture<span class="ct">1</span></a>+<a class="chip" href="/blog/tags/autonomous/">Autonomous<span class="ct">1</span></a>+ <a class="chip" href="/blog/tags/debugging/">Debugging<span class="ct">1</span></a>+</div></section>diff --git a/docs/blog/topics/internals/index.html b/docs/blog/topics/internals/index.htmlindex b39469b8..bcc8fb4d 100644--- a/docs/blog/topics/internals/index.html+++ b/docs/blog/topics/internals/index.html@@ -63,24 +63,24 @@</nav><p class="eyebrow">Topic</p><h1>internals</h1>- <p class="lead">6 posts in this cluster.</p>+ <p class="lead">10 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/internals/" aria-current="page">internals<span class="ct">10</span></a>- <a class="chip" href="/blog/topics/guides/">guides<span class="ct">6</span></a>+ <a class="chip" href="/blog/topics/comparisons/">comparisons<span class="ct">8</span></a>- <a class="chip" href="/blog/topics/internals/" aria-current="page">internals<span class="ct">6</span></a>+ <a class="chip" href="/blog/topics/guides/">guides<span class="ct">7</span></a><a class="chip" href="/blog/topics/orchestration/">orchestration<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/use-cases/">use-cases<span class="ct">3</span></a>+ <a class="chip" href="/blog/topics/memory/">memory<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/use-cases/">use-cases<span class="ct">3</span></a><a class="chip" href="/blog/topics/story/">story<span class="ct">1</span></a>@@ -90,6 +90,24 @@<section class="wrap"><div class="post-grid"><article class="card">+ <a class="thumb t-internals" href="/blog/architecture-two-planes-one-renderer/" aria-hidden="true" tabindex="-1">+ <span>INTERNALS</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/architecture-two-planes-one-renderer/">Munder Difflin's Architecture: Two Data Planes, One Renderer</a></h3>+ <p class="dek">A walkthrough of the multi-agent harness architecture: a node-pty terminal plane and a hooks/hive event plane feeding one React + Pixi.js renderer.</p>+ <div class="foot">+ <span class="tag kind">Internals</span>+ <a class="more" href="/blog/architecture-two-planes-one-renderer/" aria-label="Read: Munder Difflin's Architecture: Two Data Planes, One Renderer">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>@@ -107,6 +125,24 @@</div></div></article>+<article class="card">+ <a class="thumb t-internals" href="/blog/building-an-ai-office-floor/" 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/building-an-ai-office-floor/">Building an AI "Office Floor": Avatars, Pathfinding, Envelopes</a></h3>+ <p class="dek">The game-dev techniques behind a dev tool's office floor: Tiled maps, BFS pathfinding, sprite recoloring, and flying message envelopes in Pixi.js.</p>+ <div class="foot">+ <span class="tag kind">Internals</span>+ <a class="more" href="/blog/building-an-ai-office-floor/" aria-label="Read: Building an AI "Office Floor": Avatars, Pathfinding, Envelopes">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>@@ -143,6 +179,24 @@</div></div></article>+<article class="card">+ <a class="thumb t-internals" href="/blog/rendering-many-live-terminals-performance/" 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>5 min</span>+ </div>+ <h3><a href="/blog/rendering-many-live-terminals-performance/">Rendering Many Live Terminals Without Melting the CPU</a></h3>+ <p class="dek">xterm.js performance for many live PTYs: a terminal pool, render-only-visible, smart scrollback, and accelerated rendering to stream dozens at once.</p>+ <div class="foot">+ <span class="tag kind">Internals</span>+ <a class="more" href="/blog/rendering-many-live-terminals-performance/" aria-label="Read: Rendering Many Live Terminals Without Melting the CPU">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>@@ -161,6 +215,24 @@</div></div></article>+<article class="card">+ <a class="thumb t-internals" href="/blog/visualizing-ai-agents-pixijs/" 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/visualizing-ai-agents-pixijs/">Visualizing AI Agents with Pixi.js: An Office You Can Watch</a></h3>+ <p class="dek">How we render AI agents as avatars on a Pixi.js office floor — driven by real hook and message events, with seat assignment, pathing, and flying envelopes.</p>+ <div class="foot">+ <span class="tag kind">Internals</span>+ <a class="more" href="/blog/visualizing-ai-agents-pixijs/" aria-label="Read: Visualizing AI Agents with Pixi.js: An Office You Can Watch">Read →</a>+ </div>+ </div>+</article><article class="card"><a class="thumb t-internals" href="/blog/append-only-event-log-agents/" aria-hidden="true" tabindex="-1"><span>INTERNALS</span>@@ -172,7 +244,7 @@<span>5 min</span></div><h3><a href="/blog/append-only-event-log-agents/">An Append-Only Event Log for a Hive of Agents</a></h3>- <p class="dek">How an append-only event log makes a multi-agent system debuggable and replayable — what to record per event, and why one JSON line per event beats a database.</p>+ <p class="dek">How an append-only event log makes a multi-agent system debuggable and replayable: what to record, and why one JSON line per event beats a database.</p><div class="foot"><span class="tag kind">Internals</span><a class="more" href="/blog/append-only-event-log-agents/" aria-label="Read: An Append-Only Event Log for a Hive of Agents">Read →</a>diff --git a/docs/blog/topics/memory/index.html b/docs/blog/topics/memory/index.htmlindex dfaf34e2..dfaa7bc5 100644--- a/docs/blog/topics/memory/index.html+++ b/docs/blog/topics/memory/index.html@@ -63,24 +63,24 @@</nav><p class="eyebrow">Topic</p><h1>memory</h1>- <p class="lead">2 posts in this cluster.</p>+ <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/internals/">internals<span class="ct">10</span></a>- <a class="chip" href="/blog/topics/guides/">guides<span class="ct">6</span></a>+ <a class="chip" href="/blog/topics/comparisons/">comparisons<span class="ct">8</span></a>- <a class="chip" href="/blog/topics/internals/">internals<span class="ct">6</span></a>+ <a class="chip" href="/blog/topics/guides/">guides<span class="ct">7</span></a><a class="chip" href="/blog/topics/orchestration/">orchestration<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/use-cases/">use-cases<span class="ct">3</span></a>+ <a class="chip" href="/blog/topics/memory/" aria-current="page">memory<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/use-cases/">use-cases<span class="ct">3</span></a><a class="chip" href="/blog/topics/story/">story<span class="ct">1</span></a>@@ -107,6 +107,24 @@</div></div></article>+<article class="card">+ <a class="thumb t-memory" href="/blog/markdown-first-agent-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>5 min</span>+ </div>+ <h3><a href="/blog/markdown-first-agent-memory/">Why We Built Agent Memory Markdown-First</a></h3>+ <p class="dek">Markdown-first AI agent long-term memory: plain notes a human can read and git can diff, with a semantic index on top that degrades gracefully.</p>+ <div class="foot">+ <span class="tag kind">Memory</span>+ <a class="more" href="/blog/markdown-first-agent-memory/" aria-label="Read: Why We Built Agent Memory Markdown-First">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>diff --git a/docs/blog/topics/orchestration/index.html b/docs/blog/topics/orchestration/index.htmlindex c99e5a27..6c7029b4 100644--- a/docs/blog/topics/orchestration/index.html+++ b/docs/blog/topics/orchestration/index.html@@ -68,19 +68,19 @@<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/internals/">internals<span class="ct">10</span></a>- <a class="chip" href="/blog/topics/guides/">guides<span class="ct">6</span></a>+ <a class="chip" href="/blog/topics/comparisons/">comparisons<span class="ct">8</span></a>- <a class="chip" href="/blog/topics/internals/">internals<span class="ct">6</span></a>+ <a class="chip" href="/blog/topics/guides/">guides<span class="ct">7</span></a><a class="chip" href="/blog/topics/orchestration/" aria-current="page">orchestration<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/use-cases/">use-cases<span class="ct">3</span></a>+ <a class="chip" href="/blog/topics/memory/">memory<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/use-cases/">use-cases<span class="ct">3</span></a><a class="chip" href="/blog/topics/story/">story<span class="ct">1</span></a>@@ -118,7 +118,7 @@<span>5 min</span></div><h3><a href="/blog/human-in-the-loop-ai-agents/">Human-in-the-Loop AI Agents: Approvals That Don't Slow You Down</a></h3>- <p class="dek">Design human-in-the-loop AI agents that stay autonomous: an approvals queue that escalates only spend, destructive ops, and scope — and relays your answer back.</p>+ <p class="dek">Design human-in-the-loop AI agents that stay autonomous: an approvals queue that escalates only spend, destructive ops, and scope changes.</p><div class="foot"><span class="tag kind">Orchestration</span><a class="more" href="/blog/human-in-the-loop-ai-agents/" aria-label="Read: Human-in-the-Loop AI Agents: Approvals That Don't Slow You Down">Read →</a>diff --git a/docs/blog/topics/story/index.html b/docs/blog/topics/story/index.htmlindex 53278e4e..d6b302be 100644--- a/docs/blog/topics/story/index.html+++ b/docs/blog/topics/story/index.html@@ -68,19 +68,19 @@<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/internals/">internals<span class="ct">10</span></a>- <a class="chip" href="/blog/topics/guides/">guides<span class="ct">6</span></a>+ <a class="chip" href="/blog/topics/comparisons/">comparisons<span class="ct">8</span></a>- <a class="chip" href="/blog/topics/internals/">internals<span class="ct">6</span></a>+ <a class="chip" href="/blog/topics/guides/">guides<span class="ct">7</span></a><a class="chip" href="/blog/topics/orchestration/">orchestration<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/use-cases/">use-cases<span class="ct">3</span></a>+ <a class="chip" href="/blog/topics/memory/">memory<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/use-cases/">use-cases<span class="ct">3</span></a><a class="chip" href="/blog/topics/story/" aria-current="page">story<span class="ct">1</span></a>diff --git a/docs/blog/topics/use-cases/index.html b/docs/blog/topics/use-cases/index.htmlindex d255dbb3..30fba373 100644--- a/docs/blog/topics/use-cases/index.html+++ b/docs/blog/topics/use-cases/index.html@@ -68,19 +68,19 @@<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/internals/">internals<span class="ct">10</span></a>- <a class="chip" href="/blog/topics/guides/">guides<span class="ct">6</span></a>+ <a class="chip" href="/blog/topics/comparisons/">comparisons<span class="ct">8</span></a>- <a class="chip" href="/blog/topics/internals/">internals<span class="ct">6</span></a>+ <a class="chip" href="/blog/topics/guides/">guides<span class="ct">7</span></a><a class="chip" href="/blog/topics/orchestration/">orchestration<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/use-cases/" aria-current="page">use-cases<span class="ct">3</span></a>+ <a class="chip" href="/blog/topics/memory/">memory<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/use-cases/" aria-current="page">use-cases<span class="ct">3</span></a><a class="chip" href="/blog/topics/story/">story<span class="ct">1</span></a>diff --git a/docs/blog/vibe-kanban-alternative/index.html b/docs/blog/vibe-kanban-alternative/index.htmlindex 6abd49b3..d980f28b 100644--- a/docs/blog/vibe-kanban-alternative/index.html+++ b/docs/blog/vibe-kanban-alternative/index.html@@ -212,7 +212,7 @@ routing happen for you — free and open source.</p><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>+ <a class="pn next" href="/blog/rendering-many-live-terminals-performance/"><span class="k">Newer →</span><span class="t">Rendering Many Live Terminals Without Melting the CPU</span></a></div><section class="related"><h2>Related in Comparisons</h2>diff --git a/docs/blog/visualizing-ai-agents-pixijs/index.html b/docs/blog/visualizing-ai-agents-pixijs/index.htmlnew file mode 100644index 00000000..cf53c4b6--- /dev/null+++ b/docs/blog/visualizing-ai-agents-pixijs/index.html@@ -0,0 +1,380 @@+<!doctype html>+<html lang="en">+<head>+<meta charset="UTF-8" />+<meta name="viewport" content="width=device-width, initial-scale=1.0" />+<title>Visualizing AI Agents with Pixi.js: An Office You Can Watch — Munder Difflin Blog</title>+<meta name="description" content="How we render AI agents as avatars on a Pixi.js office floor — driven by real hook and message events, with seat assignment, pathing, and flying envelopes." />+<link rel="canonical" href="https://munderdiffl.in/blog/visualizing-ai-agents-pixijs/" />++<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="Visualizing AI Agents with Pixi.js: An Office You Can Watch — Munder Difflin Blog" />+<meta property="og:description" content="How we render AI agents as avatars on a Pixi.js office floor — driven by real hook and message events, with seat assignment, pathing, and flying envelopes." />+<meta property="og:url" content="https://munderdiffl.in/blog/visualizing-ai-agents-pixijs/" />+<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="Pixi.js" />+<meta property="article:tag" content="Visualization" />+<meta property="article:tag" content="Observability" />+++<!-- Twitter -->+<meta name="twitter:card" content="summary_large_image" />+<meta name="twitter:title" content="Visualizing AI Agents with Pixi.js: An Office You Can Watch — Munder Difflin Blog" />+<meta name="twitter:description" content="How we render AI agents as avatars on a Pixi.js office floor — driven by real hook and message events, with seat assignment, pathing, and flying envelopes." />+<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": "Visualizing AI Agents with Pixi.js: An Office You Can Watch",+ "description": "How we render AI agents as avatars on a Pixi.js office floor — driven by real hook and message events, with seat assignment, pathing, and flying envelopes.",+ "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/visualizing-ai-agents-pixijs/" },+ "keywords": "ai agent visualization, pixijs, agent observability, ai agent visualization",+ "articleSection": "Internals",+ "inLanguage": "en-US",+ "url": "https://munderdiffl.in/blog/visualizing-ai-agents-pixijs/"+}+</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": "Visualizing AI Agents with Pixi.js: An Office You Can Watch", "item": "https://munderdiffl.in/blog/visualizing-ai-agents-pixijs/" }+ ]+}+</script>++<script type="application/ld+json">+{+ "@context": "https://schema.org",+ "@type": "FAQPage",+ "mainEntity": [+ { "@type": "Question", "name": "Why visualize AI agents instead of just reading logs?", "acceptedAnswer": { "@type": "Answer", "text": "A spatial view answers 'what is everyone doing right now?' at a glance — who's working, who's idle, who's blocked, and who's messaging whom. Logs answer that too, but slowly; a floor you can watch turns a multi-agent system from a wall of text into something you can supervise." } },+ { "@type": "Question", "name": "Is the office floor a simulation or real activity?", "acceptedAnswer": { "@type": "Answer", "text": "Real. Avatars move in response to actual Claude Code hook events (PreToolUse, PostToolUse, Stop) and real routed messages — not a scripted animation. When an avatar walks to the terminal station, an agent really did run a command." } },+ { "@type": "Question", "name": "Why Pixi.js for an agent visualization?", "acceptedAnswer": { "@type": "Answer", "text": "Pixi.js is a fast 2D WebGL renderer that handles many sprites smoothly, which suits a floor of avatars, tile maps, and animated envelopes. It gives game-quality rendering inside an Electron app without a heavy engine." } }++ ]+}+</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>Visualizing AI Agents with Pixi.js: An Office You Can Watch</h1>+ <p class="dek">How we render AI agents as avatars on a Pixi.js office floor — driven by real hook and message events, with seat assignment, pathing, and flying envelopes.</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>An <strong>AI agent visualization</strong>+turns "what is the team doing?" into something you can see. Munder Difflin renders agents as avatars+on a <strong>Pixi.js</strong> office floor, driven by <strong>real events</strong>: Claude Code hooks+move an avatar to the station matching its current tool, and routed hive messages fly as envelopes+desk-to-desk. It's not a simulation — every motion reflects something an agent actually did.</p></div>+<p>A multi-agent system is, by default, a wall of text: many terminals, many logs, no spatial sense of+who’s doing what. The office floor exists to fix that — to make a hive <em>legible at a glance</em>. This post+is how it’s built with Pixi.js, and the one principle that keeps it honest: it’s driven by real+activity, not animation.</p>+<h2 id="why-a-floor-at-all" tabindex="-1">Why a floor at all <a class="anchor" href="#why-a-floor-at-all" aria-hidden="true">#</a></h2>+<p>The value of a visualization is answering “what is everyone doing right now?” instantly. On the floor:</p>+<ul>+<li>an avatar at the terminal station = an agent running a command,</li>+<li>an avatar at the file shelf = an agent reading or writing,</li>+<li>an avatar waving at the mailbox = an agent blocked, needing you,</li>+<li>an avatar at its desk = idle, awaiting work,</li>+<li>an envelope flying between desks = a message being routed.</li>+</ul>+<p>You get the team’s state in one look. That’s not a gimmick — it’s+<a href="https://munderdiffl.in/#how">an office you can actually see</a>, the visible counterpart to reading the+<a href="/blog/append-only-event-log-agents/">event log</a>.</p>+<h2 id="the-pixijs-setup" tabindex="-1">The Pixi.js setup <a class="anchor" href="#the-pixijs-setup" aria-hidden="true">#</a></h2>+<p>The renderer is a Pixi <code>Application</code>, tuned for crisp pixel art rather than smooth gradients:</p>+<pre class="language-ts"><code class="language-ts"><span class="token keyword">const</span> app <span class="token operator">=</span> <span class="token keyword">new</span> <span class="token class-name">Application</span><span class="token punctuation">(</span><span class="token punctuation">)</span><span class="token punctuation">;</span>+<span class="token keyword">await</span> app<span class="token punctuation">.</span><span class="token function">init</span><span class="token punctuation">(</span><span class="token punctuation">{</span>+ antialias<span class="token operator">:</span> <span class="token boolean">false</span><span class="token punctuation">,</span> <span class="token comment">// hard pixel edges, no blur</span>+ roundPixels<span class="token operator">:</span> <span class="token boolean">true</span><span class="token punctuation">,</span> <span class="token comment">// snap sprites to integer positions</span>+ resolution<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">// nearest-neighbour scaling keeps the pixel art sharp when zoomed</span>+texture<span class="token punctuation">.</span>source<span class="token punctuation">.</span>scaleMode <span class="token operator">=</span> <span class="token string">'nearest'</span><span class="token punctuation">;</span></code></pre>+<p>On top of the stage sits a single <code>world</code> container that everything else lives in — the tile map, the+character layer, the envelopes. Putting it all under one container means the <strong>camera</strong> can pan and+zoom the entire scene by transforming just that one node, with map-edge clamping and a smooth lerp so+following a selected agent feels natural rather than jumpy.</p>+<p>One more structural choice: a <strong>single shared ticker</strong> drives all animation. Every frame, the ticker+hands out a delta-time and each live thing (avatars, envelopes, camera) advances by <code>dt</code>. One loop,+not dozens of timers — which keeps motion synchronized and the frame budget predictable.</p>+<h2 id="the-floor-is-a-tiled-map" tabindex="-1">The floor is a Tiled map <a class="anchor" href="#the-floor-is-a-tiled-map" aria-hidden="true">#</a></h2>+<p>The office isn’t hand-coded geometry; it’s a <strong>Tiled</strong> map (<code>.tmj</code>) — the same format 2D game+designers use. The renderer parses its layers:</p>+<ul>+<li><strong>Tile layers</strong> (floor, walls, furniture) are drawn from tileset textures, resolved by each tile’s+global id.</li>+<li>A <strong>collision layer</strong> marks which tiles are walls vs. walkable floor.</li>+<li>A <strong>spawn-points</strong> object layer names the desks and seats.</li>+</ul>+<p>Editing the office is therefore a design task, not a code change — open the map in Tiled, move a desk,+re-export. The renderer just reads it.</p>+<h2 id="seats-giving-each-agent-a-desk" tabindex="-1">Seats: giving each agent a desk <a class="anchor" href="#seats-giving-each-agent-a-desk" aria-hidden="true">#</a></h2>+<p>When an agent joins the hive, it needs a home. A small <strong>seat pool</strong> reserves the next free desk from+the map’s spawn points and hands it to that agent; release it when the agent is gone. First-come,+first-served, one desk each — so a dynamically growing team fills the office in order instead of+piling onto one desk.</p>+<h2 id="avatars-sprites-driven-by-state" tabindex="-1">Avatars: sprites driven by state <a class="anchor" href="#avatars-sprites-driven-by-state" aria-hidden="true">#</a></h2>+<p>Each avatar is a sprite sliced from a character walk sheet. The frames are mapped into walk / type /+read / idle animations for three facing directions (left is just the right-facing row flipped), and a+small <strong>leg-crop mask</strong> tucks a seated agent under its desk so it reads as <em>sitting</em> rather than+standing on the furniture. The cast is recolored per character, so the team is visually+distinguishable at a glance.</p>+<p>But the sprites are just the <em>body</em>. What makes them meaningful is what drives them.</p>+<h2 id="the-honest-part-real-events-not-a-script" tabindex="-1">The honest part: real events, not a script <a class="anchor" href="#the-honest-part-real-events-not-a-script" aria-hidden="true">#</a></h2>+<p>This is the design principle that matters most. The avatars are <strong>not</strong> playing a canned animation —+they move in response to real signals from two sources:</p>+<p><strong>Claude Code hooks.</strong> Each agent runs lifecycle hooks that report its activity. A <code>PreToolUse</code> event+(“about to run a tool”) sends the avatar walking toward the station that matches the tool — the+terminal station for a shell command, the file shelf for an edit. <code>PostToolUse</code> walks it back.+<code>Stop</code> drops it to idle at its desk; a notification sends it to the mailbox to wave for you. Because+these come straight from Claude, the floor reflects <em>real</em> tool use, with no fragile log-scraping. (The+hook lifecycle is covered in <a href="/blog/claude-code-hooks-explained/">Claude Code hooks, explained</a>.)</p>+<p><strong>Hive messages.</strong> When the router delivers a message between agents, it emits an event the floor turns+into a flying <strong>envelope</strong> — a little pixel letter that arcs from the sender’s desk to the recipient’s,+tinted by the message’s speech act (asks are cool-colored, agreements warm, refusals red, escalations+to a human a distinct color), with a small burst on arrival. You don’t just know a message was sent;+you see <em>who asked whom, and what kind of ask it was</em>.</p>+<p>Getting from a station to a desk uses a tiny <strong>breadth-first pathfinder</strong> on the map’s walkability+grid — short, predictable shortest paths around the furniture. Nothing fancier is needed at office+scale, and BFS on an unweighted grid gives the shortest route for free.</p>+<h2 id="why-this-scales" tabindex="-1">Why this scales <a class="anchor" href="#why-this-scales" aria-hidden="true">#</a></h2>+<p>A floor of avatars, a tile map, and animated envelopes is a lot of sprites — which is exactly what+Pixi.js is good at. The single-ticker design keeps the per-frame work bounded, the camera transforms+one container instead of every node, and the pixel-art settings (no antialias, nearest scaling) are+cheap to render. The same performance discipline shows up next door in+<a href="/blog/rendering-many-live-terminals-performance/">rendering many live terminals</a> — keep the hot loop+tight and let the renderer do what it’s fast at.</p>+<p>For the deeper game-dev mechanics — Tiled maps, pathfinding, sprite recoloring — see+<a href="/blog/building-an-ai-office-floor/">building an AI office floor</a>.</p>+<h2 id="faq" tabindex="-1">FAQ <a class="anchor" href="#faq" aria-hidden="true">#</a></h2>+<p><strong>Does the visualization slow the agents down?</strong> No — the agents run as normal Claude Code processes;+the floor is a read-only consumer of events they already emit. Rendering happens in the UI, separate+from the agents’ work.</p>+<p><strong>Can I still see the raw terminals?</strong> Yes. The floor is one view; the actual xterm.js terminals are+another. The avatars tell you <em>what</em> at a glance; the terminals show you the byte-for-byte detail when+you want it.</p>+<hr>+<p>Munder Difflin renders your hive of Claude Code agents as a live Pixi.js office floor — real avatars,+driven by real events, that you can actually watch. <a href="https://munderdiffl.in/#install">Download Munder Difflin</a>+to see your agents at work; 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 visualize AI agents instead of just reading logs?</p>+ <p class="a">A spatial view answers 'what is everyone doing right now?' at a glance — who's working, who's idle, who's blocked, and who's messaging whom. Logs answer that too, but slowly; a floor you can watch turns a multi-agent system from a wall of text into something you can supervise.</p>+ </div>++ <div class="qa">+ <p class="q">Is the office floor a simulation or real activity?</p>+ <p class="a">Real. Avatars move in response to actual Claude Code hook events (PreToolUse, PostToolUse, Stop) and real routed messages — not a scripted animation. When an avatar walks to the terminal station, an agent really did run a command.</p>+ </div>++ <div class="qa">+ <p class="q">Why Pixi.js for an agent visualization?</p>+ <p class="a">Pixi.js is a fast 2D WebGL renderer that handles many sprites smoothly, which suits a floor of avatars, tile maps, and animated envelopes. It gives game-quality rendering inside an Electron app without a heavy engine.</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/pixijs/">Pixi.js</a><a class="tag" href="/blog/tags/visualization/">Visualization</a><a class="tag" href="/blog/tags/observability/">Observability</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-floor-at-all">Why a floor at all</a></li><li class="lvl-2"><a href="#the-pixijs-setup">The Pixi.js setup</a></li><li class="lvl-2"><a href="#the-floor-is-a-tiled-map">The floor is a Tiled map</a></li><li class="lvl-2"><a href="#seats-giving-each-agent-a-desk">Seats: giving each agent a desk</a></li><li class="lvl-2"><a href="#avatars-sprites-driven-by-state">Avatars: sprites driven by state</a></li><li class="lvl-2"><a href="#the-honest-part-real-events-not-a-script">The honest part: real events, not a script</a></li><li class="lvl-2"><a href="#why-this-scales">Why this scales</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/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 Internals</h2>+ <div class="post-grid">+ <article class="card">+ <a class="thumb t-internals" href="/blog/architecture-two-planes-one-renderer/" aria-hidden="true" tabindex="-1">+ <span>INTERNALS</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/architecture-two-planes-one-renderer/">Munder Difflin's Architecture: Two Data Planes, One Renderer</a></h3>+ <p class="dek">A walkthrough of the multi-agent harness architecture: a node-pty terminal plane and a hooks/hive event plane feeding one React + Pixi.js renderer.</p>+ <div class="foot">+ <span class="tag kind">Internals</span>+ <a class="more" href="/blog/architecture-two-planes-one-renderer/" aria-label="Read: Munder Difflin's Architecture: Two Data Planes, One Renderer">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/building-an-ai-office-floor/" 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/building-an-ai-office-floor/">Building an AI "Office Floor": Avatars, Pathfinding, Envelopes</a></h3>+ <p class="dek">The game-dev techniques behind a dev tool's office floor: Tiled maps, BFS pathfinding, sprite recoloring, and flying message envelopes in Pixi.js.</p>+ <div class="foot">+ <span class="tag kind">Internals</span>+ <a class="more" href="/blog/building-an-ai-office-floor/" aria-label="Read: Building an AI "Office Floor": Avatars, Pathfinding, Envelopes">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 & 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.htmlindex 62042997..2ab6afe4 100644--- a/docs/blog/what-are-claude-code-agents/index.html+++ b/docs/blog/what-are-claude-code-agents/index.html@@ -241,7 +241,7 @@ into an office; it’s free and open source.</p><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>+ <a class="pn next" href="/blog/visualizing-ai-agents-pixijs/"><span class="k">Newer →</span><span class="t">Visualizing AI Agents with Pixi.js: An Office You Can Watch</span></a></div><section class="related"><h2>Related in Concepts</h2>diff --git a/docs/sitemap.xml b/docs/sitemap.xmlindex 322d3ce9..0b8464ca 100644--- a/docs/sitemap.xml+++ b/docs/sitemap.xml@@ -17,6 +17,12 @@<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/architecture-two-planes-one-renderer/</loc>+ <lastmod>2026-06-04</lastmod>+ <changefreq>monthly</changefreq>+ <priority>0.8</priority>+ </url><url><loc>https://munderdiffl.in/blog/best-claude-code-multi-agent-tools/</loc><lastmod>2026-06-04</lastmod>@@ -47,12 +53,24 @@<changefreq>monthly</changefreq><priority>0.8</priority></url>+ <url>+ <loc>https://munderdiffl.in/blog/debugging-multi-agent-systems/</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/building-an-ai-office-floor/</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>@@ -89,6 +107,12 @@<changefreq>monthly</changefreq><priority>0.8</priority></url>+ <url>+ <loc>https://munderdiffl.in/blog/rendering-many-live-terminals-performance/</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>@@ -137,6 +161,12 @@<changefreq>monthly</changefreq><priority>0.8</priority></url>+ <url>+ <loc>https://munderdiffl.in/blog/visualizing-ai-agents-pixijs/</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>@@ -197,6 +227,12 @@<changefreq>monthly</changefreq><priority>0.8</priority></url>+ <url>+ <loc>https://munderdiffl.in/blog/markdown-first-agent-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>@@ -227,37 +263,41 @@<changefreq>monthly</changefreq><priority>0.8</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/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/orchestration/</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/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/use-cases/</loc><changefreq>weekly</changefreq><priority>0.5</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/internals/</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/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/internals/</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/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/mempalace/</loc><changefreq>weekly</changefreq><priority>0.3</priority></url>+ <url><loc>https://munderdiffl.in/blog/tags/observability/</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/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/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/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/pixijs/</loc><changefreq>weekly</changefreq><priority>0.3</priority></url>+ <url><loc>https://munderdiffl.in/blog/tags/visualization/</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/subagents/</loc><changefreq>weekly</changefreq><priority>0.3</priority></url>+ <url><loc>https://munderdiffl.in/blog/tags/markdown/</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/observability/</loc><changefreq>weekly</changefreq><priority>0.3</priority></url><url><loc>https://munderdiffl.in/blog/tags/event-log/</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/human-in-the-loop/</loc><changefreq>weekly</changefreq><priority>0.3</priority></url>@@ -267,10 +307,13 @@<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/game-dev/</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/performance/</loc><changefreq>weekly</changefreq><priority>0.3</priority></url>+ <url><loc>https://munderdiffl.in/blog/tags/architecture/</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>+ <url><loc>https://munderdiffl.in/blog/tags/debugging/</loc><changefreq>weekly</changefreq><priority>0.3</priority></url></urlset>