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>How to Run Multiple Claude Code Agents (Without Losing Track) — Munder Difflin Blog</title>
<meta name="description" content="Run several Claude Code agents in parallel without the chaos: give each a role, let them coordinate, and stop alt-tabbing between terminal windows." />
<link rel="canonical" href="https://munderdiffl.in/blog/how-to-run-multiple-claude-code-agents/" />
<link rel="icon" type="image/png" href="https://munderdiffl.in/logo.png" />
<link rel="apple-touch-icon" href="https://munderdiffl.in/logo.png" />
<meta name="theme-color" content="#F5F2E8" />
<!-- Open Graph -->
<meta property="og:site_name" content="Munder Difflin Blog" />
<meta property="og:type" content="article" />
<meta property="og:title" content="How to Run Multiple Claude Code Agents (Without Losing Track) — Munder Difflin Blog" />
<meta property="og:description" content="Run several Claude Code agents in parallel without the chaos: give each a role, let them coordinate, and stop alt-tabbing between terminal windows." />
<meta property="og:url" content="https://munderdiffl.in/blog/how-to-run-multiple-claude-code-agents/" />
<meta property="og:image" content="https://munderdiffl.in/blog/assets/media/how-to-run-multiple-claude-code-agents/hero.png" />
<meta property="og:image:width" content="1600" />
<meta property="og:image:height" content="900" />
<meta property="og:image:alt" content="Illustration: How to Run Multiple Claude Code Agents (Without Losing Track)" />
<meta property="og:locale" content="en_US" />
<meta property="article:published_time" content="2026-06-01T00:00:00.000Z" />
<meta property="article:author" content="Chaitanya Giri" />
<meta property="article:tag" content="Guides" />
<meta property="article:tag" content="Multi-Agent" />
<meta property="article:tag" content="Claude Code" />
<meta property="article:tag" content="Getting Started" />
<!-- Twitter -->
<meta name="twitter:card" content="summary_large_image" />
<meta name="twitter:title" content="How to Run Multiple Claude Code Agents (Without Losing Track) — Munder Difflin Blog" />
<meta name="twitter:description" content="Run several Claude Code agents in parallel without the chaos: give each a role, let them coordinate, and stop alt-tabbing between terminal windows." />
<meta name="twitter:image" content="https://munderdiffl.in/blog/assets/media/how-to-run-multiple-claude-code-agents/hero.png" />
<meta name="twitter:image:alt" content="Illustration: How to Run Multiple Claude Code Agents (Without Losing Track)" />
<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": "How to Run Multiple Claude Code Agents (Without Losing Track)",
"description": "Run several Claude Code agents in parallel without the chaos: give each a role, let them coordinate, and stop alt-tabbing between terminal windows.",
"image": ["https://munderdiffl.in/blog/assets/media/how-to-run-multiple-claude-code-agents/hero.png"],
"datePublished": "2026-06-01T00:00:00.000Z",
"dateModified": "2026-06-01T00:00:00.000Z",
"author": { "@type": "Person", "name": "Chaitanya Giri" },
"publisher": {
"@type": "Organization",
"name": "Munder Difflin",
"logo": { "@type": "ImageObject", "url": "https://munderdiffl.in/logo.png" }
},
"mainEntityOfPage": { "@type": "WebPage", "@id": "https://munderdiffl.in/blog/how-to-run-multiple-claude-code-agents/" },
"keywords": "how to run multiple claude code agents, run multiple claude code agents, claude code parallel agents, claude code multi-agent setup",
"articleSection": "Guides",
"inLanguage": "en-US",
"url": "https://munderdiffl.in/blog/how-to-run-multiple-claude-code-agents/"
}
</script>
<script type="application/ld+json">
{
"@context": "https://schema.org",
"@type": "BreadcrumbList",
"itemListElement": [
{ "@type": "ListItem", "position": 1, "name": "Home", "item": "https://munderdiffl.in/" },
{ "@type": "ListItem", "position": 2, "name": "Blog", "item": "https://munderdiffl.in/blog/" },
{ "@type": "ListItem", "position": 3, "name": "How to Run Multiple Claude Code Agents (Without Losing Track)", "item": "https://munderdiffl.in/blog/how-to-run-multiple-claude-code-agents/" }
]
}
</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-guides">
<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 Run Multiple Claude Code Agents (Without Losing Track)</h1>
<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="byline">
<span class="av" aria-hidden="true">CG</span>
<strong>Chaitanya Giri</strong>
<span class="dot" aria-hidden="true">·</span>
<time datetime="2026-06-01">Jun 1, 2026</time>
<span class="dot" aria-hidden="true">·</span>
<span>3 min read</span>
<span class="tag kind">Guides</span>
</div>
</header>
<div class="hero-wrap wrap"><figure class="fig fig-hero"><img src="/blog/assets/media/how-to-run-multiple-claude-code-agents/hero.png" alt="Illustration: How to Run Multiple Claude Code Agents (Without Losing Track)" 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>You can run
<strong>multiple Claude Code agents</strong> by opening several sessions, but the wins only show up
once you <strong>give each a role</strong>, <strong>let them coordinate</strong> (messaging + shared
memory), and <strong>watch the work</strong> instead of alt-tabbing. This guide covers the manual
way, where it breaks, and the harness that automates it.</p></div>
<p>Running one Claude Code agent is easy. Running <em>five</em> usefully is the hard part — and it’s where most
people give up, drowning in terminal tabs. Here’s how to run multiple Claude Code agents in parallel
without losing the thread.</p>
<h2 id="start-with-the-manual-approach" tabindex="-1">Start with the manual approach <a class="anchor" href="#start-with-the-manual-approach" aria-hidden="true">#</a></h2>
<p>You don’t need any tooling to begin. Open several terminals and start a <code>claude</code> session in each,
one per task:</p>
<pre class="language-bash"><code class="language-bash"><span class="token comment"># terminal 1 — the test-writer</span>
<span class="token builtin class-name">cd</span> ~/project <span class="token operator">&&</span> claude
<span class="token comment"># terminal 2 — the docs-fixer</span>
<span class="token builtin class-name">cd</span> ~/project <span class="token operator">&&</span> claude
<span class="token comment"># terminal 3 — the refactorer</span>
<span class="token builtin class-name">cd</span> ~/project <span class="token operator">&&</span> claude</code></pre>
<p>This works for two or three <strong>independent</strong> tasks. The moment they overlap, three problems appear.</p>
<figure class="fig fig-inline"><img src="/blog/assets/media/how-to-run-multiple-claude-code-agents/note-1.png" alt="Hand-drawn sketch from “How to Run Multiple Claude Code Agents (Without Losing Track)”" loading="lazy" decoding="async" /></figure>
<h2 id="where-the-manual-approach-breaks" tabindex="-1">Where the manual approach breaks <a class="anchor" href="#where-the-manual-approach-breaks" aria-hidden="true">#</a></h2>
<h3 id="1-they-collide-on-files" tabindex="-1">1. They collide on files <a class="anchor" href="#1-they-collide-on-files" aria-hidden="true">#</a></h3>
<p>Two agents editing the same file race each other; in a git repo you get <code>index.lock</code> errors and
half-applied changes. Parallel agents need a coordination rule, not just separate windows.</p>
<h3 id="2-they-dont-share-what-they-learn" tabindex="-1">2. They don’t share what they learn <a class="anchor" href="#2-they-dont-share-what-they-learn" aria-hidden="true">#</a></h3>
<p>Each session has its own context. Agent 2 can’t use what agent 1 just figured out, so you become the
courier — copy-pasting findings between windows. That’s the
<a href="/blog/give-claude-code-long-term-memory/">long-term memory problem</a>, and it compounds fast.</p>
<h3 id="3-you-cant-see-the-whole-board" tabindex="-1">3. You can’t see the whole board <a class="anchor" href="#3-you-cant-see-the-whole-board" aria-hidden="true">#</a></h3>
<p>With six tabs open, “what is everyone doing right now?” has no answer. You lose track, and lost track
is where mistakes hide.</p>
<h2 id="make-it-work-roles-coordination-visibility" tabindex="-1">Make it work: roles, coordination, visibility <a class="anchor" href="#make-it-work-roles-coordination-visibility" aria-hidden="true">#</a></h2>
<p>The fix isn’t more tabs — it’s three habits:</p>
<h3 id="give-each-agent-a-role" tabindex="-1">Give each agent a role <a class="anchor" href="#give-each-agent-a-role" aria-hidden="true">#</a></h3>
<p>Name them and scope them: <em>test-writer</em>, <em>reviewer</em>, <em>refactorer</em>. A role keeps an agent from
wandering into another’s work and makes “who should do this?” obvious.</p>
<h3 id="let-them-coordinate" tabindex="-1">Let them coordinate <a class="anchor" href="#let-them-coordinate" aria-hidden="true">#</a></h3>
<p>Agents need to pass messages and share memory <strong>without going through you</strong>. A durable mailbox
(agent A writes, agent B reads) plus a shared memory store means findings flow between agents
directly. For the coordination model, see
<a href="/blog/what-is-a-multi-agent-harness/">what is a multi-agent harness</a>.</p>
<h3 id="route-work-through-an-orchestrator" tabindex="-1">Route work through an orchestrator <a class="anchor" href="#route-work-through-an-orchestrator" aria-hidden="true">#</a></h3>
<p>Instead of hand-assigning every task, you describe intent once and a coordinator decomposes and
routes it. In Munder Difflin that’s the <a href="https://munderdiffl.in/#how">GOD orchestrator</a> — you talk to
it in plain language and it assigns the agents.</p>
<h3 id="watch-the-floor" tabindex="-1">Watch the floor <a class="anchor" href="#watch-the-floor" aria-hidden="true">#</a></h3>
<p>Seeing the team work — who’s busy, who’s idle, what messages are flying — turns a black box into
something you can supervise. Visibility is what makes running many agents feel calm instead of
chaotic.</p>
<figure class="fig fig-inline"><img src="/blog/assets/media/how-to-run-multiple-claude-code-agents/note-2.png" alt="Hand-drawn sketch from “How to Run Multiple Claude Code Agents (Without Losing Track)”" loading="lazy" decoding="async" /></figure>
<h2 id="from-tabs-to-a-team" tabindex="-1">From tabs to a team <a class="anchor" href="#from-tabs-to-a-team" aria-hidden="true">#</a></h2>
<p>The progression is always the same: one session → a few manual tabs → a coordinated team. Once you
hit the tab-juggling stage, a harness automates exactly the three habits above so you stop being the
message bus.</p>
<h2 id="next-steps" tabindex="-1">Next steps <a class="anchor" href="#next-steps" aria-hidden="true">#</a></h2>
<ul>
<li><a href="/blog/give-claude-code-long-term-memory/">How to give Claude Code long-term memory</a> — so the team
stops forgetting.</li>
<li><a href="/blog/what-is-a-multi-agent-harness/">What is a multi-agent harness?</a> — the concept behind the
coordination.</li>
</ul>
<hr>
<p>Munder Difflin runs all of this for you: roles, mailboxes, shared memory, a GOD orchestrator, and a
live office floor — locally, on your own Claude plan.
<a href="https://munderdiffl.in/#install">Download Munder Difflin</a> to run your first coordinated team; it’s
free and open source.</p>
<hr />
<div class="share">
<span class="lbl">Tags</span>
<a class="tag" href="/blog/tags/guides/">Guides</a><a class="tag" href="/blog/tags/multi-agent/">Multi-Agent</a><a class="tag" href="/blog/tags/claude-code/">Claude Code</a><a class="tag" href="/blog/tags/getting-started/">Getting Started</a>
</div>
</div>
<aside class="toc-rail" aria-label="Table of contents">
<div class="tt">On this page</div>
<ol>
<li class="lvl-2"><a href="#start-with-the-manual-approach">Start with the manual approach</a></li><li class="lvl-2"><a href="#where-the-manual-approach-breaks">Where the manual approach breaks</a></li><li class="lvl-3"><a href="#1-they-collide-on-files">1. They collide on files</a></li><li class="lvl-3"><a href="#2-they-dont-share-what-they-learn">2. They don’t share what they learn</a></li><li class="lvl-3"><a href="#3-you-cant-see-the-whole-board">3. You can’t see the whole board</a></li><li class="lvl-2"><a href="#make-it-work-roles-coordination-visibility">Make it work: roles, coordination, visibility</a></li><li class="lvl-3"><a href="#give-each-agent-a-role">Give each agent a role</a></li><li class="lvl-3"><a href="#let-them-coordinate">Let them coordinate</a></li><li class="lvl-3"><a href="#route-work-through-an-orchestrator">Route work through an orchestrator</a></li><li class="lvl-3"><a href="#watch-the-floor">Watch the floor</a></li><li class="lvl-2"><a href="#from-tabs-to-a-team">From tabs to a team</a></li><li class="lvl-2"><a href="#next-steps">Next steps</a></li>
</ol>
</aside>
</div>
<footer class="post-foot wrap"><div class="prevnext">
<a class="pn prev" href="/blog/atomic-file-mailboxes-for-agents/"><span class="k">← Older</span><span class="t">Atomic File Mailboxes: How Agents Message Each Other</span></a>
<a class="pn next" href="/blog/append-only-event-log-agents/"><span class="k">Newer →</span><span class="t">An Append-Only Event Log for a Hive of Agents</span></a>
</div>
<section class="related">
<h2>Related in Guides</h2>
<div class="post-grid">
<article class="card t-guides">
<a class="thumb t-guides" href="/blog/claude-md-best-practices/" aria-hidden="true" tabindex="-1"><img src="/blog/assets/media/claude-md-best-practices/hero.png" alt="" loading="lazy" decoding="async" /></a>
<div class="body">
<div class="meta">
<time datetime="2026-10-26">Oct 26, 2026</time>
<span class="dot" aria-hidden="true"></span>
<span>4 min</span>
</div>
<h3><a href="/blog/claude-md-best-practices/">CLAUDE.md Best Practices: What to Write, Where It Lives, How Long (Oct 2026)</a></h3>
<p class="dek">CLAUDE.md best practices from Anthropic's docs, checked 26 Oct 2026: what to put in it, where each file lives, the 200 line target and how AGENTS.md loads.</p>
<div class="foot">
<span class="tag kind">Guides</span>
<a class="more" href="/blog/claude-md-best-practices/" aria-label="Read: CLAUDE.md Best Practices: What to Write, Where It Lives, How Long (Oct 2026)">Read →</a>
</div>
</div>
</article>
<article class="card t-guides">
<a class="thumb t-guides" href="/blog/codex-computer-use/" aria-hidden="true" tabindex="-1"><img src="/blog/assets/media/codex-computer-use/hero.png" alt="" loading="lazy" decoding="async" /></a>
<div class="body">
<div class="meta">
<time datetime="2026-10-26">Oct 26, 2026</time>
<span class="dot" aria-hidden="true"></span>
<span>4 min</span>
</div>
<h3><a href="/blog/codex-computer-use/">Codex Computer Use: How to Turn It On, Plans and Limits (Oct 2026)</a></h3>
<p class="dek">Codex computer use lets the ChatGPT desktop app see and click apps on macOS and Windows. Setup, which plans get it, locked use and how Claude's compares.</p>
<div class="foot">
<span class="tag kind">Guides</span>
<a class="more" href="/blog/codex-computer-use/" aria-label="Read: Codex Computer Use: How to Turn It On, Plans and Limits (Oct 2026)">Read →</a>
</div>
</div>
</article>
<article class="card t-guides">
<a class="thumb t-guides" href="/blog/cursor-pricing/" aria-hidden="true" tabindex="-1"><img src="/blog/assets/media/cursor-pricing/hero.png" alt="" loading="lazy" decoding="async" /></a>
<div class="body">
<div class="meta">
<time datetime="2026-10-26">Oct 26, 2026</time>
<span class="dot" aria-hidden="true"></span>
<span>5 min</span>
</div>
<h3><a href="/blog/cursor-pricing/">Cursor Pricing (Oct 2026): Every Plan After the 12 Oct Change</a></h3>
<p class="dek">Cursor pricing as of 26 Oct 2026: Free, Plus $8, Premium $30, Super $100, Ultra $200, Teams seats, what changed on 12 Oct and what old plans keep.</p>
<div class="foot">
<span class="tag kind">Guides</span>
<a class="more" href="/blog/cursor-pricing/" aria-label="Read: Cursor Pricing (Oct 2026): Every Plan After the 12 Oct Change">Read →</a>
</div>
</div>
</article>
</div>
</section>
</footer>
</article>
</main>
<footer class="site-foot">
<div class="wrap">
<div class="foot-top">
<a class="foot-brand brand" href="https://munderdiffl.in" aria-label="Munder Difflin home">
<img class="brand-logo" src="https://munderdiffl.in/logo.png" width="1318" height="840" alt="Munder Difflin, Inc. — Multi-Agent Harness" />
</a>
<div class="foot-links">
<a href="/blog/">Latest</a>
<a href="/blog/topics/">Topics</a>
<a href="/blog/about/">About</a>
<a href="https://munderdiffl.in/blog/feed.xml">RSS</a>
<a href="https://github.com/chaitanyagiri/munder-difflin">GitHub</a>
<a href="https://munderdiffl.in">munderdiffl.in ↗</a>
</div>
</div>
<div class="foot-meta">
© 2026 Munder Difflin · Local-first · MIT-licensed ·
Built on <a href="https://munderdiffl.in">Electron, React, Pixi.js, xterm.js & node-pty</a>.
Run an office of agents while you sleep.
</div>
</div>
</footer>
<script>
// sticky-nav border on scroll
(function () {
var nav = document.getElementById('nav');
if (!nav) return;
var onScroll = function () { nav.classList.toggle('scrolled', window.scrollY > 8); };
onScroll(); window.addEventListener('scroll', onScroll, { passive: true });
})();
// YouTube click-to-load: thumbnail button → youtube-nocookie iframe
(function () {
document.addEventListener('click', function (e) {
var btn = e.target.closest('.yt-load');
if (!btn) return;
var box = btn.closest('.yt');
var id = box && box.getAttribute('data-yt');
// Only an 11 character YouTube video id may reach the iframe URL.
if (!id || !/^[A-Za-z0-9_-]{11}$/.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>