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
<!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>Orchestrating Claude Code Agents: A Practical Guide — Munder Difflin Blog</title>
<meta name="description" content="How to orchestrate Claude Code agents in practice: what orchestration means, how a GOD orchestrator routes and escalates work, and how to wire it up." />
<link rel="canonical" href="https://munderdiffl.in/blog/claude-code-orchestration-guide/" />
<link rel="icon" type="image/png" href="https://munderdiffl.in/logo.png" />
<link rel="apple-touch-icon" href="https://munderdiffl.in/logo.png" />
<meta name="theme-color" content="#F5F2E8" />
<!-- Open Graph -->
<meta property="og:site_name" content="Munder Difflin Blog" />
<meta property="og:type" content="article" />
<meta property="og:title" content="Orchestrating Claude Code Agents: A Practical Guide — Munder Difflin Blog" />
<meta property="og:description" content="How to orchestrate Claude Code agents in practice: what orchestration means, how a GOD orchestrator routes and escalates work, and how to wire it up." />
<meta property="og:url" content="https://munderdiffl.in/blog/claude-code-orchestration-guide/" />
<meta property="og:image" content="https://munderdiffl.in/blog/assets/media/claude-code-orchestration-guide/hero.png" />
<meta property="og:image:width" content="1600" />
<meta property="og:image:height" content="900" />
<meta property="og:image:alt" content="Illustration: Orchestrating Claude Code Agents: A Practical Guide" />
<meta property="og:locale" content="en_US" />
<meta property="article:published_time" content="2026-05-28T00:00:00.000Z" />
<meta property="article:author" content="Chaitanya Giri" />
<meta property="article:tag" content="Orchestration" />
<meta property="article:tag" content="Multi-Agent" />
<meta property="article:tag" content="Claude Code" />
<meta property="article:tag" content="GOD" />
<!-- Twitter -->
<meta name="twitter:card" content="summary_large_image" />
<meta name="twitter:title" content="Orchestrating Claude Code Agents: A Practical Guide — Munder Difflin Blog" />
<meta name="twitter:description" content="How to orchestrate Claude Code agents in practice: what orchestration means, how a GOD orchestrator routes and escalates work, and how to wire it up." />
<meta name="twitter:image" content="https://munderdiffl.in/blog/assets/media/claude-code-orchestration-guide/hero.png" />
<meta name="twitter:image:alt" content="Illustration: Orchestrating Claude Code Agents: A Practical Guide" />
<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&family=Source+Serif+4:opsz,[email protected],400;8..60,600;8..60,700&family=Space+Grotesk:wght@500;600;700&family=JetBrains+Mono:wght@400;600&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": "Orchestrating Claude Code Agents: A Practical Guide",
"description": "How to orchestrate Claude Code agents in practice: what orchestration means, how a GOD orchestrator routes and escalates work, and how to wire it up.",
"image": ["https://munderdiffl.in/blog/assets/media/claude-code-orchestration-guide/hero.png"],
"datePublished": "2026-05-28T00:00:00.000Z",
"dateModified": "2026-05-28T00:00:00.000Z",
"author": { "@type": "Person", "name": "Chaitanya Giri" },
"publisher": {
"@type": "Organization",
"name": "Munder Difflin",
"logo": { "@type": "ImageObject", "url": "https://munderdiffl.in/logo.png" }
},
"mainEntityOfPage": { "@type": "WebPage", "@id": "https://munderdiffl.in/blog/claude-code-orchestration-guide/" },
"keywords": "how to orchestrate claude code agents, claude code orchestration, claude code orchestrator, ai agent orchestration",
"articleSection": "Orchestration",
"inLanguage": "en-US",
"url": "https://munderdiffl.in/blog/claude-code-orchestration-guide/"
}
</script>
<script type="application/ld+json">
{
"@context": "https://schema.org",
"@type": "BreadcrumbList",
"itemListElement": [
{ "@type": "ListItem", "position": 1, "name": "Home", "item": "https://munderdiffl.in/" },
{ "@type": "ListItem", "position": 2, "name": "Blog", "item": "https://munderdiffl.in/blog/" },
{ "@type": "ListItem", "position": 3, "name": "Orchestrating Claude Code Agents: A Practical Guide", "item": "https://munderdiffl.in/blog/claude-code-orchestration-guide/" }
]
}
</script>
<script type="application/ld+json">
{
"@context": "https://schema.org",
"@type": "FAQPage",
"mainEntity": [
{ "@type": "Question", "name": "What does it mean to orchestrate Claude Code agents?", "acceptedAnswer": { "@type": "Answer", "text": "Orchestration is the layer that decides which agent does what: it reads your intent, decomposes it into tasks, routes each to the right agent, resolves routine questions between agents, and escalates only the decisions that genuinely need a human." } },
{ "@type": "Question", "name": "Do I write the orchestration logic myself?", "acceptedAnswer": { "@type": "Answer", "text": "You can, but you don't have to. In Munder Difflin the orchestrator is itself a Claude agent — the GOD agent — so the routing intelligence is a prompt you tune, not code you maintain. The harness provides the mechanism (messaging, git, escalation queue); the agent provides the judgment." } },
{ "@type": "Question", "name": "How is an orchestrator different from a task queue?", "acceptedAnswer": { "@type": "Answer", "text": "A queue hands out work in order; it doesn't reason about it. An orchestrator reads each request, decides who's best suited, writes a self-contained task spec, and adapts when an agent gets blocked or two agents conflict." } }
]
}
</script>
<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>Orchestrating Claude Code Agents: A Practical Guide</h1>
<p class="dek">How to orchestrate Claude Code agents in practice: what orchestration means, how a GOD orchestrator routes and escalates work, and how to wire it up.</p>
<div class="byline">
<span class="av" aria-hidden="true">CG</span>
<strong>Chaitanya Giri</strong>
<span class="dot" aria-hidden="true">·</span>
<time datetime="2026-05-28">May 28, 2026</time>
<span class="dot" aria-hidden="true">·</span>
<span>5 min read</span>
<span class="tag kind">Orchestration</span>
</div>
</header>
<div class="hero-wrap wrap"><figure class="fig fig-hero"><img src="/blog/assets/media/claude-code-orchestration-guide/hero.png" alt="Illustration: Orchestrating Claude Code Agents: A Practical Guide" 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><strong>Orchestration</strong> is the layer
that turns "a few Claude Code agents" into "a team that finishes a goal." It reads your intent,
<strong>decomposes</strong> it, <strong>routes</strong> each piece to the right agent, <strong>adjudicates</strong>
the routine back-and-forth between agents, and <strong>escalates</strong> only the critical calls to
you. In Munder Difflin that role is played by a GOD orchestrator — a Claude agent whose only job is to
run the floor.</p></div>
<p>Most “multi-agent” setups are really just multiple agents — several sessions running side by side
with you in the middle, deciding who does what. The thing that makes them a <em>team</em> is orchestration.
This guide explains what orchestration actually does for coding agents, and how to wire it so it runs
without you in the loop for every decision.</p>
<h2 id="what-orchestration-means-for-coding-agents" tabindex="-1">What “orchestration” means for coding agents <a class="anchor" href="#what-orchestration-means-for-coding-agents" aria-hidden="true">#</a></h2>
<p>Strip away the buzzword and orchestration is five concrete jobs:</p>
<ol>
<li><strong>Read intent.</strong> Take a plain-language goal (“ship input validation with tests and docs”) instead
of pre-chopped tasks.</li>
<li><strong>Decompose.</strong> Break the goal into units small enough for one agent to own.</li>
<li><strong>Route.</strong> Assign each unit to the agent best suited for it, with a self-contained task spec so the
agent doesn’t have to ask what you meant.</li>
<li><strong>Adjudicate.</strong> Handle the questions agents raise <em>for each other</em> — clarifications, data asks,
small plan changes — so the team keeps moving without bouncing everything back to you.</li>
<li><strong>Escalate.</strong> Recognize the few decisions that genuinely need a human (spending money, destructive
operations, scope changes, conflicts nobody can resolve) and stop there.</li>
</ol>
<p>A task queue does #3 and nothing else. Orchestration is the other four — the <em>judgment</em> — which is
why, in a well-designed harness, the orchestrator is itself an intelligent agent rather than a switch
statement.</p>
<h2 id="the-mechanism-vs-the-intelligence" tabindex="-1">The mechanism vs. the intelligence <a class="anchor" href="#the-mechanism-vs-the-intelligence" aria-hidden="true">#</a></h2>
<p>The cleanest way to build this is to split it in two:</p>
<ul>
<li><strong>The mechanism</strong> is plumbing: deliver messages, commit state, hold a queue of items waiting on a
human. It has no opinions. It must be reliable, not smart.</li>
<li><strong>The intelligence</strong> is an agent — the orchestrator — that reads requests and decides. It must be
smart, and it’s allowed to be imperfect, because the mechanism keeps the system safe.</li>
</ul>
<p>In Munder Difflin the mechanism is the harness’s main process (it runs git, the message router, and
the approvals queue) and the intelligence is the <strong>GOD agent</strong> — an ordinary <code>claude</code> process flagged
as the orchestrator, seated in the corner office. Because the orchestrator is a prompt, not a
codebase, you tune <em>how</em> it routes and <em>what</em> it considers critical by editing its instructions, not
by redeploying. That’s the practical heart of
<a href="/blog/how-the-god-orchestrator-works/">how the GOD orchestrator works</a>.</p>
<figure class="fig fig-inline"><img src="/blog/assets/media/claude-code-orchestration-guide/note-1.png" alt="Hand-drawn sketch from “Orchestrating Claude Code Agents: A Practical Guide”" loading="lazy" decoding="async" /></figure>
<h2 id="how-a-request-flows-through-the-orchestrator" tabindex="-1">How a request flows through the orchestrator <a class="anchor" href="#how-a-request-flows-through-the-orchestrator" aria-hidden="true">#</a></h2>
<p>Here’s the path a single instruction takes, end to end:</p>
<h3 id="1-you-describe-a-goal-to-the-orchestrator" tabindex="-1">1. You describe a goal to the orchestrator <a class="anchor" href="#1-you-describe-a-goal-to-the-orchestrator" aria-hidden="true">#</a></h3>
<p>You talk to one agent — the orchestrator — in plain language. You don’t address the workers directly
and you don’t pre-assign tasks. This is the whole ergonomic win: one conversation instead of N.</p>
<h3 id="2-it-decomposes-and-routes" tabindex="-1">2. It decomposes and routes <a class="anchor" href="#2-it-decomposes-and-routes" aria-hidden="true">#</a></h3>
<p>The orchestrator reads its roster (who exists, their roles and capabilities) and assigns each piece of
work, writing a task spec that’s self-contained enough for the receiving agent to act without a
follow-up. Routing to the <em>right</em> agent is where roles earn their keep — a <code>test-writer</code> gets the
tests, not the migration.</p>
<h3 id="3-agents-work-and-message-each-other" tabindex="-1">3. Agents work, and message each other <a class="anchor" href="#3-agents-work-and-message-each-other" aria-hidden="true">#</a></h3>
<p>Each worker is its own session with isolated context. When one needs something from another, it sends
a message rather than going through you. Crucially, agents never write into each other’s files — they
drop a message in their own outbox and the harness delivers it. That single-writer discipline is what
keeps the whole thing from corrupting itself; the mechanics are in
<a href="/blog/atomic-file-mailboxes-for-agents/">atomic file mailboxes</a>.</p>
<h3 id="4-the-orchestrator-adjudicates-the-routine-stuff" tabindex="-1">4. The orchestrator adjudicates the routine stuff <a class="anchor" href="#4-the-orchestrator-adjudicates-the-routine-stuff" aria-hidden="true">#</a></h3>
<p>Most inter-agent traffic is mundane: “which schema do I validate against?” “is the staging URL still
X?” The orchestrator answers these itself and keeps the floor autonomous. Anti-loop rules matter
here — only requests, queries, and proposals obligate a reply, and a hop counter caps how long any
exchange can ping-pong before the orchestrator steps in. Without those rules, two polite agents will
thank each other forever.</p>
<h3 id="5-it-escalates-only-the-critical-few" tabindex="-1">5. It escalates only the critical few <a class="anchor" href="#5-it-escalates-only-the-critical-few" aria-hidden="true">#</a></h3>
<p>When something crosses a line — real spend, a destructive operation, a scope change, a conflict it
can’t resolve — the orchestrator escalates to <em>you</em> instead of deciding. That item lands in a
human-approval queue; your answer (with an optional note like “yes, but cap it at $5”) is relayed back
to the agent that asked. Everything else stays autonomous. This selective escalation is the difference
between an agent team that needs constant supervision and one that only taps you on the shoulder when
it should.</p>
<h2 id="designing-good-orchestration" tabindex="-1">Designing good orchestration <a class="anchor" href="#designing-good-orchestration" aria-hidden="true">#</a></h2>
<p>If you’re building or tuning an orchestrator, a few principles separate the ones that work from the
ones that thrash:</p>
<ul>
<li><strong>Make the escalation policy explicit.</strong> “Critical” should be a written list (spend, destructive
ops, scope, unresolvable conflict), not a vibe. It’s the single most important control surface —
too loose and the team does scary things; too tight and you become the bottleneck again.</li>
<li><strong>Give the orchestrator a real roster.</strong> It can only route well if it knows who exists and what
they’re good at. Roles and capabilities aren’t decoration; they’re the routing table.</li>
<li><strong>Keep the orchestrator out of the work.</strong> Its job is to route and adjudicate, not to write the
code itself. An orchestrator that starts doing the tasks is a bottleneck wearing a manager’s hat.</li>
<li><strong>Make coordination auditable.</strong> Every routed message and every escalation should be logged, so
when the team goes sideways you can replay what happened. For the broader patterns here, see
<a href="/blog/coordinating-ai-coding-agents/">the best way to coordinate AI coding agents</a>.</li>
</ul>
<figure class="fig fig-inline"><img src="/blog/assets/media/claude-code-orchestration-guide/note-2.png" alt="Hand-drawn sketch from “Orchestrating Claude Code Agents: A Practical Guide”" loading="lazy" decoding="async" /></figure>
<h2 id="when-you-actually-need-an-orchestrator" tabindex="-1">When you actually need an orchestrator <a class="anchor" href="#when-you-actually-need-an-orchestrator" aria-hidden="true">#</a></h2>
<p>You don’t need orchestration for one agent, or even for two or three independent tasks you’re happy to
assign by hand. You need it when:</p>
<ul>
<li>you’re describing the <em>same</em> context to multiple agents over and over,</li>
<li>you find yourself relaying messages between agents, or</li>
<li>you want to state a goal once and have the team figure out the division of labor.</li>
</ul>
<p>That’s the threshold where <a href="/blog/how-to-run-multiple-claude-code-agents/">running multiple Claude Code agents</a>
turns from a chore into something that genuinely compounds.</p>
<h2 id="faq" tabindex="-1">FAQ <a class="anchor" href="#faq" aria-hidden="true">#</a></h2>
<p><strong>Can the orchestrator route to the wrong agent?</strong> Yes — it’s a model, so it can misjudge. The
mechanism contains the damage: misrouted work still goes through messaging and the single-committer
git layer, so a bad routing decision is recoverable, not corrupting. And because the policy is a
prompt, you correct the pattern by editing instructions.</p>
<p><strong>Does orchestration add latency?</strong> A little — there’s a routing hop before work starts. In exchange
you stop being the router yourself, which is almost always the bigger time sink.</p>
<hr>
<p>Munder Difflin ships this <a href="https://munderdiffl.in/#how">orchestration model</a> out of the box: a GOD agent you talk to, a reliable
message router, and a human-approval queue for the critical few — all running locally.
<a href="https://munderdiffl.in/#install">Download Munder Difflin</a> to orchestrate your own team of Claude Code
agents; it’s free and open source.</p>
<section class="faq" aria-label="Frequently asked questions">
<h2 id="faq">FAQ</h2>
<div class="qa">
<p class="q">What does it mean to orchestrate Claude Code agents?</p>
<p class="a">Orchestration is the layer that decides which agent does what: it reads your intent, decomposes it into tasks, routes each to the right agent, resolves routine questions between agents, and escalates only the decisions that genuinely need a human.</p>
</div>
<div class="qa">
<p class="q">Do I write the orchestration logic myself?</p>
<p class="a">You can, but you don't have to. In Munder Difflin the orchestrator is itself a Claude agent — the GOD agent — so the routing intelligence is a prompt you tune, not code you maintain. The harness provides the mechanism (messaging, git, escalation queue); the agent provides the judgment.</p>
</div>
<div class="qa">
<p class="q">How is an orchestrator different from a task queue?</p>
<p class="a">A queue hands out work in order; it doesn't reason about it. An orchestrator reads each request, decides who's best suited, writes a self-contained task spec, and adapts when an agent gets blocked or two agents conflict.</p>
</div>
</section>
<hr />
<div class="share">
<span class="lbl">Tags</span>
<a class="tag" href="/blog/tags/orchestration/">Orchestration</a><a class="tag" href="/blog/tags/multi-agent/">Multi-Agent</a><a class="tag" href="/blog/tags/claude-code/">Claude Code</a><a class="tag" href="/blog/tags/god/">GOD</a>
</div>
</div>
<aside class="toc-rail" aria-label="Table of contents">
<div class="tt">On this page</div>
<ol>
<li class="lvl-2"><a href="#what-orchestration-means-for-coding-agents">What “orchestration” means for coding agents</a></li><li class="lvl-2"><a href="#the-mechanism-vs-the-intelligence">The mechanism vs. the intelligence</a></li><li class="lvl-2"><a href="#how-a-request-flows-through-the-orchestrator">How a request flows through the orchestrator</a></li><li class="lvl-3"><a href="#1-you-describe-a-goal-to-the-orchestrator">1. You describe a goal to the orchestrator</a></li><li class="lvl-3"><a href="#2-it-decomposes-and-routes">2. It decomposes and routes</a></li><li class="lvl-3"><a href="#3-agents-work-and-message-each-other">3. Agents work, and message each other</a></li><li class="lvl-3"><a href="#4-the-orchestrator-adjudicates-the-routine-stuff">4. The orchestrator adjudicates the routine stuff</a></li><li class="lvl-3"><a href="#5-it-escalates-only-the-critical-few">5. It escalates only the critical few</a></li><li class="lvl-2"><a href="#designing-good-orchestration">Designing good orchestration</a></li><li class="lvl-2"><a href="#when-you-actually-need-an-orchestrator">When you actually need an orchestrator</a></li><li class="lvl-2"><a href="#faq">FAQ</a></li>
</ol>
</aside>
</div>
<footer class="post-foot wrap"><div class="prevnext">
<a class="pn prev" href="/blog/give-claude-code-long-term-memory/"><span class="k">← Older</span><span class="t">How to Give Claude Code Long-Term Memory</span></a>
<a class="pn next" href="/blog/coordinating-ai-coding-agents/"><span class="k">Newer →</span><span class="t">The Best Way to Coordinate AI Coding Agents</span></a>
</div>
<section class="related">
<h2>Related in Orchestration</h2>
<div class="post-grid">
<article class="card 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 & 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>