Skip to content

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

26.8 KB
Raw Blame
<!doctype html>
<html lang="en">
<head>
<!-- Google tag (gtag.js), Google Ads AW-18388216863. Loaded only when Do Not Track is
     off, so it follows the same rule as the PostHog block on this site. -->
<script>
  window.dataLayer = window.dataLayer || [];
  function gtag(){ dataLayer.push(arguments); }
  if (navigator.doNotTrack !== '1') {
    var gtagScript = document.createElement('script');
    gtagScript.async = true;
    gtagScript.src = 'https://www.googletagmanager.com/gtag/js?id=AW-18388216863';
    document.head.appendChild(gtagScript);
    gtag('js', new Date());
    gtag('config', 'AW-18388216863');
  }
</script>

<meta charset="UTF-8" />
<meta name="viewport" content="width=device-width, initial-scale=1.0" />
<title>The Best Way to Coordinate AI Coding Agents — Munder Difflin Blog</title>
<meta name="description" content="The best way to coordinate AI coding agents: single-writer files, a message router, a one-scribe plan, and an orchestrator — cooperate, not clobber." />
<link rel="canonical" href="https://munderdiffl.in/blog/coordinating-ai-coding-agents/" />

<link rel="icon" type="image/png" href="https://munderdiffl.in/logo.png" />
<link rel="apple-touch-icon" href="https://munderdiffl.in/logo.png" />
<meta name="theme-color" content="#F5F2E8" />

<!-- Open Graph -->
<meta property="og:site_name" content="Munder Difflin Blog" />
<meta property="og:type" content="article" />
<meta property="og:title" content="The Best Way to Coordinate AI Coding Agents — Munder Difflin Blog" />
<meta property="og:description" content="The best way to coordinate AI coding agents: single-writer files, a message router, a one-scribe plan, and an orchestrator — cooperate, not clobber." />
<meta property="og:url" content="https://munderdiffl.in/blog/coordinating-ai-coding-agents/" />
<meta property="og:image" content="https://munderdiffl.in/blog/assets/media/coordinating-ai-coding-agents/hero.png" />
<meta property="og:image:width" content="1600" />
<meta property="og:image:height" content="900" />
<meta property="og:image:alt" content="Illustration: The Best Way to Coordinate AI Coding Agents" />
<meta property="og:locale" content="en_US" />
<meta property="article:published_time" content="2026-05-29T00:00:00.000Z" />
<meta property="article:author" content="Chaitanya Giri" />
<meta property="article:tag" content="Orchestration" />
<meta property="article:tag" content="Multi-Agent" />
<meta property="article:tag" content="Coordination" />
<meta property="article:tag" content="Claude Code" />


<!-- Twitter -->
<meta name="twitter:card" content="summary_large_image" />
<meta name="twitter:title" content="The Best Way to Coordinate AI Coding Agents — Munder Difflin Blog" />
<meta name="twitter:description" content="The best way to coordinate AI coding agents: single-writer files, a message router, a one-scribe plan, and an orchestrator — cooperate, not clobber." />
<meta name="twitter:image" content="https://munderdiffl.in/blog/assets/media/coordinating-ai-coding-agents/hero.png" />
<meta name="twitter:image:alt" content="Illustration: The Best Way to Coordinate AI Coding Agents" />

<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=Fraunces:opsz,[email protected],500;9..144,600;9..144,700;9..144,900&amp;family=Source+Serif+4:opsz,[email protected],400;8..60,600;8..60,700&amp;family=Space+Grotesk:wght@500;600;700&amp;family=JetBrains+Mono:wght@400;600&amp;display=swap" rel="stylesheet" />
<link rel="stylesheet" href="/blog/assets/blog-press.css" />

<script type="application/ld+json">
{
  "@context": "https://schema.org",
  "@type": "BlogPosting",
  "headline": "The Best Way to Coordinate AI Coding Agents",
  "description": "The best way to coordinate AI coding agents: single-writer files, a message router, a one-scribe plan, and an orchestrator — cooperate, not clobber.",
  "image": ["https://munderdiffl.in/blog/assets/media/coordinating-ai-coding-agents/hero.png"],
  "datePublished": "2026-05-29T00:00:00.000Z",
  "dateModified": "2026-05-29T00:00:00.000Z",
  "author": { "@type": "Person", "name": "Chaitanya Giri" },
  "publisher": {
    "@type": "Organization",
    "name": "Munder Difflin",
    "logo": { "@type": "ImageObject", "url": "https://munderdiffl.in/logo.png" }
  },
  "mainEntityOfPage": { "@type": "WebPage", "@id": "https://munderdiffl.in/blog/coordinating-ai-coding-agents/" },
  "keywords": "best way to coordinate ai coding agents, coordinate ai agents, ai coding agent teams, agent collaboration",
  "articleSection": "Orchestration",
  "inLanguage": "en-US",
  "url": "https://munderdiffl.in/blog/coordinating-ai-coding-agents/"
}
</script>
<script type="application/ld+json">
{
  "@context": "https://schema.org",
  "@type": "BreadcrumbList",
  "itemListElement": [
    { "@type": "ListItem", "position": 1, "name": "Home", "item": "https://munderdiffl.in/" },
    { "@type": "ListItem", "position": 2, "name": "Blog", "item": "https://munderdiffl.in/blog/" },
    { "@type": "ListItem", "position": 3, "name": "The Best Way to Coordinate AI Coding Agents", "item": "https://munderdiffl.in/blog/coordinating-ai-coding-agents/" }
  ]
}
</script>

<script type="application/ld+json">
{
  "@context": "https://schema.org",
  "@type": "FAQPage",
  "mainEntity": [
    { "@type": "Question", "name": "What's the most common way multi-agent coding setups fail?", "acceptedAnswer": { "@type": "Answer", "text": "Two agents writing the same thing at the same time — the same file, or the same git index — which produces half-applied changes and lock errors. Almost every coordination design is really an answer to 'who is allowed to write what.'" } },
    { "@type": "Question", "name": "Do AI coding agents need a message bus to coordinate?", "acceptedAnswer": { "@type": "Answer", "text": "They need a way to pass information without going through you, and a rule that stops them from looping forever. That can be as simple as files plus a router: each agent writes to its own outbox, and one process delivers messages to recipients' inboxes." } },
    { "@type": "Question", "name": "Should every agent be able to edit the shared plan?", "acceptedAnswer": { "@type": "Answer", "text": "No. A plan that everyone edits is the one file guaranteed to conflict. Route changes through a single scribe — usually the orchestrator — so the shared plan has exactly one writer." } }
    
  ]
}
</script>


<script>
  // Anonymous blog analytics (PostHog) — same posture as the main site and the
  // app's TELEMETRY.md: public write-only token ('' = inert), anonymous-only
  // (person_profiles 'never'), no autocapture/recording, DNT respected.
  (function () {
    var PH_KEY = 'phc_qJzsokwcbtTGHemnvywR3nSqivNNgMjHeNVEWkZNydFB';
    if (!PH_KEY || navigator.doNotTrack === '1') return;
    var s = document.createElement('script');
    s.async = true;
    s.src = 'https://us-assets.i.posthog.com/static/array.js';
    s.onload = function () {
      if (!window.posthog) return;
      window.posthog.init(PH_KEY, {
        api_host: 'https://us.i.posthog.com',
        person_profiles: 'never',
        autocapture: false,
        before_send: function (event) {
          // PostHog fills $ip from the connection unless the event carries one.
          // Null it here and disable the GeoIP lookup so no IP, city, postal
          // code or lat/long is ever derived or stored for this page view.
          if (event && event.properties) {
            event.properties.$ip = null;
            event.properties.$geoip_disable = true;
          }
          return event;
        },
        disable_session_recording: true,
        respect_dnt: true
      });
    };
    document.head.appendChild(s);
  })();
</script>
</head>
<body class="theme-press">
<a class="skip-link" href="#main">Skip to content</a>
<nav id="nav">
  <a class="brand" href="https://munderdiffl.in" aria-label="Munder Difflin home">
    <img class="brand-logo" src="https://munderdiffl.in/logo.png" width="1318" height="840" alt="Munder Difflin, Inc. — Multi-Agent Harness" />
  </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 class="t-orchestration">
  <header class="post-head wrap">
    <nav class="crumbs" aria-label="Breadcrumb">
      <a href="/blog/">Blog</a>
      <span>/</span>
      <a href="/blog/topics/orchestration/">Orchestration</a>
    </nav>
    <h1>The Best Way to Coordinate AI Coding Agents</h1>
    <p class="dek">The best way to coordinate AI coding agents: single-writer files, a message router, a one-scribe plan, and an orchestrator — cooperate, not clobber.</p>
    <div class="byline">
      <span class="av" aria-hidden="true">CG</span>
      <strong>Chaitanya Giri</strong>
      <span class="dot" aria-hidden="true">·</span>
      <time datetime="2026-05-29">May 29, 2026</time>
      <span class="dot" aria-hidden="true">·</span>
      <span>5 min read</span>
      <span class="tag kind">Orchestration</span>
    </div>
  </header>

  <div class="hero-wrap wrap"><figure class="fig fig-hero"><img src="/blog/assets/media/coordinating-ai-coding-agents/hero.png" alt="Illustration: The Best Way to Coordinate AI Coding Agents" loading="lazy" decoding="async" /></figure></div>

  <div class="post-wrap wrap">
    <div class="prose">
      <div class="callout tldr"><span class="ic">TL;DR</span><p>The best way to
<strong>coordinate AI coding agents</strong> is to make collisions structurally impossible:
<strong>one writer per file</strong>, message-passing through a router instead of shared edits, a
<strong>single committer</strong> for git, a shared plan with <strong>one scribe</strong>, and an
orchestrator that routes work and breaks ties. Get those five right and agents cooperate instead of
clobbering each other.</p></div>
<p>Coordinating AI coding agents sounds like a prompting problem — “just tell them to be careful.” It
isn’t. The moment two agents share a filesystem and a git repo, “be careful” is a race condition
waiting to happen. The reliable approach is to design the coordination so the bad outcomes <em>can’t</em>
occur, not to hope the agents avoid them. Here are the five rules that do that.</p>
<h2 id="rule-1-one-writer-per-file" tabindex="-1">Rule 1 — One writer per file <a class="anchor" href="#rule-1-one-writer-per-file" aria-hidden="true">#</a></h2>
<p>The root cause of almost every multi-agent coding mess is two processes writing the same thing at
once. So the first rule is the strictest: <strong>every file has exactly one writer.</strong></p>
<p>In practice that means each agent gets its own private workspace — its own memory file, its own inbox,
its own outbox — and never reaches into another agent’s directory. If agent A needs agent B to do
something, A does not edit B’s files; A sends a message. No file is ever touched by two processes, so
there’s nothing to race over.</p>
<p>This sounds restrictive until you realize it’s what makes everything else safe. Single-writer is the
foundation the other four rules sit on.</p>
<h2 id="rule-2-pass-messages-through-a-router-not-through-shared-edits" tabindex="-1">Rule 2 — Pass messages through a router, not through shared edits <a class="anchor" href="#rule-2-pass-messages-through-a-router-not-through-shared-edits" aria-hidden="true">#</a></h2>
<p>If agents can’t write into each other’s space, they need another channel. The clean one is a
<strong>mailbox</strong> with a router in the middle:</p>
<ul>
<li>Each agent has an <code>outbox/</code> it writes to and an <code>inbox/</code> it reads from.</li>
<li>A router (a single coordinating process) drains every outbox and delivers each message into the
recipient’s inbox.</li>
<li>Messages are written as individual files via an atomic rename — write to a temp name, then rename
into place — so a reader never sees a half-written message.</li>
</ul>
<p>One file per message, delivered atomically, is dramatically more robust than a shared “chat log” file
that every agent appends to (that file is just a multi-writer conflict by another name). The full
design — speech acts, hop caps to prevent ping-pong, idempotent delivery — is in
<a href="/blog/atomic-file-mailboxes-for-agents/">atomic file mailboxes for agents</a>.</p>
<figure class="fig fig-inline"><img src="/blog/assets/media/coordinating-ai-coding-agents/note-1.png" alt="Hand-drawn sketch from “The Best Way to Coordinate AI Coding Agents”" loading="lazy" decoding="async" /></figure>
<h2 id="rule-3-one-committer-for-git" tabindex="-1">Rule 3 — One committer for git <a class="anchor" href="#rule-3-one-committer-for-git" aria-hidden="true">#</a></h2>
<p>Here’s the rule people learn the hard way. Git is not safe to drive from many processes at once. The
moment two agents run <code>git add</code>/<code>git commit</code> concurrently, they race on <code>.git/index.lock</code> and you get
errors and half-staged commits.</p>
<p>The fix is the same shape as Rule 1: <strong>one committer.</strong> Agents never call git at all — they only write
plain files. A single process owns every commit, serializes them, and recovers from a stale lock if a
previous run died mid-write. That turns git from a liability into the team’s audit log: every
coordination step is a commit you can read back. The mechanics, including the retry-and-backoff that
makes it bulletproof, are in
<a href="/blog/single-committer-git-pattern/">the single-committer pattern</a>.</p>
<h2 id="rule-4-a-shared-plan-with-a-single-scribe" tabindex="-1">Rule 4 — A shared plan with a single scribe <a class="anchor" href="#rule-4-a-shared-plan-with-a-single-scribe" aria-hidden="true">#</a></h2>
<p>Teams need a shared picture of the plan — what’s being built, in what order, by whom. But a shared
plan document is the <em>one</em> file you most want everyone to edit and the one that will conflict the most
if they do.</p>
<p>Resolve the tension by separating reading from writing: everyone can <strong>read</strong> the plan; only one agent
<strong>writes</strong> it. Other agents <em>propose</em> changes; the scribe — typically the orchestrator — incorporates
them. The plan stays coherent because it has one author, and it stays current because everyone can
suggest edits. Same single-writer principle, applied to the one genuinely co-owned artifact.</p>
<figure class="fig fig-inline"><img src="/blog/assets/media/coordinating-ai-coding-agents/note-2.png" alt="Hand-drawn sketch from “The Best Way to Coordinate AI Coding Agents”" loading="lazy" decoding="async" /></figure>
<h2 id="rule-5-an-orchestrator-to-route-and-break-ties" tabindex="-1">Rule 5 — An orchestrator to route and break ties <a class="anchor" href="#rule-5-an-orchestrator-to-route-and-break-ties" aria-hidden="true">#</a></h2>
<p>The first four rules make collisions impossible. The fifth makes the team <em>productive</em>: someone has to
decide who does what and settle disputes.</p>
<p>That’s the orchestrator. It reads your goal, decomposes it, routes each piece to the right agent, and
adjudicates the routine questions agents raise for each other — escalating only the genuinely critical
calls to you. Without it, you’re back to hand-assigning work and relaying messages, which is the chore
coordination was supposed to remove. For the full picture of routing and escalation, see
<a href="/blog/claude-code-orchestration-guide/">orchestrating Claude Code agents</a> and
<a href="/blog/how-the-god-orchestrator-works/">inside the GOD orchestrator</a>.</p>
<h2 id="why-just-prompt-them-to-cooperate-fails" tabindex="-1">Why “just prompt them to cooperate” fails <a class="anchor" href="#why-just-prompt-them-to-cooperate-fails" aria-hidden="true">#</a></h2>
<p>It’s worth being concrete about why the prompt-only approach breaks, because it’s tempting:</p>
<ul>
<li><strong>Prompts are advisory; races are physical.</strong> You can ask two agents not to commit simultaneously,
but if both finish a task at the same second, both will try. Only serialization in the mechanism
prevents it.</li>
<li><strong>Context windows forget.</strong> An agent that “agreed” to own a file in one turn doesn’t remember that
agreement in the next session. Ownership has to live in structure, not in a conversation.</li>
<li><strong>Politeness loops.</strong> Two agents instructed to “coordinate” will message back and forth — “thanks!”
“no, thank you!” — until something caps it. You need hop limits and a rule that only certain message
types obligate a reply.</li>
</ul>
<p>The pattern across all three: put the guarantee in the mechanism, and let the agents be smart on top
of a floor that’s already safe.</p>
<h2 id="putting-it-together" tabindex="-1">Putting it together <a class="anchor" href="#putting-it-together" aria-hidden="true">#</a></h2>
<p>A well-coordinated team of coding agents looks like this in motion:</p>
<ol>
<li>You state a goal to the orchestrator.</li>
<li>It decomposes and routes work to agents in their private workspaces.</li>
<li>Agents do the work, messaging each other through the router when they need to — never editing each
other’s files.</li>
<li>One process commits the coordination state to git, serialized and auditable.</li>
<li>The shared plan stays coherent because the orchestrator is its only scribe.</li>
<li>You’re consulted only for the critical few decisions.</li>
</ol>
<p>No collisions, no lock errors, no human message bus. That’s the difference between
<a href="/blog/how-to-run-multiple-claude-code-agents/">running multiple Claude Code agents</a> and merely
running multiple agents.</p>
<hr>
<p>Munder Difflin implements all five rules so you don’t have to: single-writer workspaces, an atomic
message router, a single-committer git layer, a single-scribe shared board, and a
<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 coordinate
your own team of Claude Code agents.</p>


      
      <section class="faq" aria-label="Frequently asked questions">
        <h2 id="faq">FAQ</h2>
        
        <div class="qa">
          <p class="q">What&#39;s the most common way multi-agent coding setups fail?</p>
          <p class="a">Two agents writing the same thing at the same time — the same file, or the same git index — which produces half-applied changes and lock errors. Almost every coordination design is really an answer to &#39;who is allowed to write what.&#39;</p>
        </div>
        
        <div class="qa">
          <p class="q">Do AI coding agents need a message bus to coordinate?</p>
          <p class="a">They need a way to pass information without going through you, and a rule that stops them from looping forever. That can be as simple as files plus a router: each agent writes to its own outbox, and one process delivers messages to recipients&#39; inboxes.</p>
        </div>
        
        <div class="qa">
          <p class="q">Should every agent be able to edit the shared plan?</p>
          <p class="a">No. A plan that everyone edits is the one file guaranteed to conflict. Route changes through a single scribe — usually the orchestrator — so the shared plan has exactly one writer.</p>
        </div>
        
      </section>
      

      
      <hr />
      <div class="share">
        <span class="lbl">Tags</span>
        <a class="tag" href="/blog/tags/orchestration/">Orchestration</a><a class="tag" href="/blog/tags/multi-agent/">Multi-Agent</a><a class="tag" href="/blog/tags/coordination/">Coordination</a><a class="tag" href="/blog/tags/claude-code/">Claude Code</a>
      </div>
      
    </div>

    
    <aside class="toc-rail" aria-label="Table of contents">
      <div class="tt">On this page</div>
      <ol>
        <li class="lvl-2"><a href="#rule-1-one-writer-per-file">Rule 1 — One writer per file</a></li><li class="lvl-2"><a href="#rule-2-pass-messages-through-a-router-not-through-shared-edits">Rule 2 — Pass messages through a router, not through shared edits</a></li><li class="lvl-2"><a href="#rule-3-one-committer-for-git">Rule 3 — One committer for git</a></li><li class="lvl-2"><a href="#rule-4-a-shared-plan-with-a-single-scribe">Rule 4 — A shared plan with a single scribe</a></li><li class="lvl-2"><a href="#rule-5-an-orchestrator-to-route-and-break-ties">Rule 5 — An orchestrator to route and break ties</a></li><li class="lvl-2"><a href="#why-just-prompt-them-to-cooperate-fails">Why “just prompt them to cooperate” fails</a></li><li class="lvl-2"><a href="#putting-it-together">Putting it together</a></li>
      </ol>
    </aside>
    
  </div>

  <footer class="post-foot wrap"><div class="prevnext">
      <a class="pn prev" href="/blog/claude-code-orchestration-guide/"><span class="k">← Older</span><span class="t">Orchestrating Claude Code Agents: A Practical Guide</span></a>
      <a class="pn next" href="/blog/how-the-god-orchestrator-works/"><span class="k">Newer →</span><span class="t">Inside the GOD Orchestrator: Routing, Adjudication, Escalation</span></a>
    </div>
    <section class="related">
      <h2>Related in Orchestration</h2>
      <div class="post-grid">
        <article class="card t-orchestration">
  <a class="thumb t-orchestration" href="/blog/deploy-automated-pr-reviewer-agent/" aria-hidden="true" tabindex="-1"><img src="/blog/assets/media/deploy-automated-pr-reviewer-agent/hero.png" alt="" loading="lazy" decoding="async" /></a>
  <div class="body">
    <div class="meta">
      <time datetime="2026-06-10">Jun 10, 2026</time>
      <span class="dot" aria-hidden="true"></span>
      <span>7 min</span>
    </div>
    <h3><a href="/blog/deploy-automated-pr-reviewer-agent/">Deploy a PR Reviewer That Never Sleeps — In About One Prompt</a></h3>
    <p class="dek">A how-to for standing up a fully automated PR-reviewing agent in Munder Difflin — one that reads your real source (not just the PR description), de-dupes noise, and only escalates what matters. With a real triage run that turned 22 duplicate firings into a clean v0.2.5 patch queue.</p>
    <div class="foot">
      <span class="tag kind">Orchestration</span>
      <a class="more" href="/blog/deploy-automated-pr-reviewer-agent/" aria-label="Read: Deploy a PR Reviewer That Never Sleeps — In About One Prompt">Read →</a>
    </div>
  </div>
</article>
<article class="card t-orchestration">
  <a class="thumb t-orchestration" href="/blog/multi-agent-orchestration-patterns/" aria-hidden="true" tabindex="-1"><img src="/blog/assets/media/multi-agent-orchestration-patterns/hero.png" alt="" loading="lazy" decoding="async" /></a>
  <div class="body">
    <div class="meta">
      <time datetime="2026-06-05">Jun 5, 2026</time>
      <span class="dot" aria-hidden="true"></span>
      <span>5 min</span>
    </div>
    <h3><a href="/blog/multi-agent-orchestration-patterns/">Multi-Agent Orchestration Patterns: Which Topology, and When</a></h3>
    <p class="dek">The multi-agent orchestration patterns — orchestrator-worker, pipeline, fan-out, debate, swarm, blackboard — when to use each, and when one agent wins.</p>
    <div class="foot">
      <span class="tag kind">Orchestration</span>
      <a class="more" href="/blog/multi-agent-orchestration-patterns/" aria-label="Read: Multi-Agent Orchestration Patterns: Which Topology, and When">Read →</a>
    </div>
  </div>
</article>
<article class="card t-orchestration">
  <a class="thumb t-orchestration" href="/blog/claude-code-git-worktrees-vs-hive/" aria-hidden="true" tabindex="-1"><img src="/blog/assets/media/claude-code-git-worktrees-vs-hive/hero.png" alt="" loading="lazy" decoding="async" /></a>
  <div class="body">
    <div class="meta">
      <time datetime="2026-06-04">Jun 4, 2026</time>
      <span class="dot" aria-hidden="true"></span>
      <span>5 min</span>
    </div>
    <h3><a href="/blog/claude-code-git-worktrees-vs-hive/">Git Worktrees vs a Hive: Two Ways to Parallelize Claude Code</a></h3>
    <p class="dek">Claude Code git worktrees vs a hive: when isolated worktrees suffice for parallel agents, and when you need memory, messaging, and an orchestrator on top.</p>
    <div class="foot">
      <span class="tag kind">Orchestration</span>
      <a class="more" href="/blog/claude-code-git-worktrees-vs-hive/" aria-label="Read: Git Worktrees vs a Hive: Two Ways to Parallelize Claude Code">Read →</a>
    </div>
  </div>
</article>

      </div>
    </section>
    
  </footer>
</article>

</main>
<footer class="site-foot">
  <div class="wrap">
    <div class="foot-top">
      <a class="foot-brand brand" href="https://munderdiffl.in" aria-label="Munder Difflin home">
        <img class="brand-logo" src="https://munderdiffl.in/logo.png" width="1318" height="840" alt="Munder Difflin, Inc. — Multi-Agent Harness" />
      </a>
      <div class="foot-links">
        <a href="/blog/">Latest</a>
        <a href="/blog/topics/">Topics</a>
        <a href="/blog/about/">About</a>
        <a href="https://munderdiffl.in/blog/feed.xml">RSS</a>
        <a href="https://github.com/chaitanyagiri/munder-difflin">GitHub</a>
        <a href="https://munderdiffl.in">munderdiffl.in ↗</a>
      </div>
    </div>
    <div class="foot-meta">
      © 2026 Munder Difflin · Local-first · MIT-licensed ·
      Built on <a href="https://munderdiffl.in">Electron, React, Pixi.js, xterm.js &amp; node-pty</a>.
      Run an office of agents while you sleep.
    </div>
  </div>
</footer>

<script>
  // sticky-nav border on scroll
  (function () {
    var nav = document.getElementById('nav');
    if (!nav) return;
    var onScroll = function () { nav.classList.toggle('scrolled', window.scrollY > 8); };
    onScroll(); window.addEventListener('scroll', onScroll, { passive: true });
  })();
  // YouTube click-to-load: thumbnail button → youtube-nocookie iframe
  (function () {
    document.addEventListener('click', function (e) {
      var btn = e.target.closest('.yt-load');
      if (!btn) return;
      var box = btn.closest('.yt');
      var id = box && box.getAttribute('data-yt');
      // Only an 11 character YouTube video id may reach the iframe URL.
      if (!id || !/^[A-Za-z0-9_-]{11}$/.test(id)) return;
      var frame = document.createElement('iframe');
      frame.src = 'https://www.youtube-nocookie.com/embed/' + encodeURIComponent(id) + '?autoplay=1';
      frame.title = box.getAttribute('data-title') || 'YouTube video';
      frame.allow = 'accelerometer; autoplay; clipboard-write; encrypted-media; gyroscope; picture-in-picture; web-share';
      frame.setAttribute('allowfullscreen', '');
      box.replaceChildren(frame);
    });
  })();
</script>

</body>
</html>