Overview Agent Swarm runs a lead agent that takes tasks from Slack, GitHub/GitLab, email, or an API and delegates them to worker agents, each in its own Docker container. Workers use harnesses such as Claude Code, Codex, opencode, or Cursor, and share persistent memory with vector search, identity files, schedules, and workflows. Deploy with Docker Compose (reference file runs 1 lead and 11 workers), a Helm chart, or a one-line installer.
Who it is for: Teams self-hosting a multi-agent coding workforce driven from Slack or GitHub
Strengths Supports many harnesses: Claude Code, Codex, pi, opencode, Cursor, Amp, Grok, Devin, ACP Ships Compose, Helm chart, Railway template, and cloud-init deployment options Integrates Slack, GitHub, GitLab, Linear, Jira, Azure DevOps, email, Telegram, Discord Persistent memory with hybrid search, plus schema-validated task results and deferred tasks Weaknesses Reference deployment needs at least 4 vCPU, 8 GB RAM and 40 GB disk Default example runs 12 agents, so token spend can grow quickly Installer exposes the API through a public tunnel unless --no-tunnel is passed Repo changes daily; older workers need MULTI_RUNTIME_ENABLED=false after upgrades What it needs TypeScript, Claude Code, Codex, pi, opencode Needs Docker, Docker Compose v2, Bun (installer), Slack/GitHub/other integrations (optional) Docker env example file What changed From the release notes. No flag means the note does not say so, not that the upgrade is safe.
Also in Agent and MCP starters Rank Project Score 1 deepseek-harness Plugin-based agent harness from DeepSeek with a local Web UI 279.6k stars +32,096 (+13%) in 30 days MIT98 out of 100 score 2 composio TypeScript and Python SDKs that give agents authenticated tools across 1000+ apps 31k stars +574 (+1.9%) in 30 days MIT92 out of 100 score 3 conductor Durable workflow engine that orchestrates microservices and LLM agents from JSON 32.5k stars Apache-2.091 out of 100 score # 4a2ui Protocol and renderers for agents to stream native UI instead of text
Live demo ↗
(opens in a new tab) 17.2k stars Apache-2.087 out of 100 score # 5mcp-use TypeScript framework for building MCP servers with React Views and an Inspector
Live demo ↗
(opens in a new tab) 10.9k stars +132 (+1.2%) in 30 days MIT87 out of 100 score
How to choose Choose the framework you want to live with; templates are thin and the framework is the real dependency. Check where state lives (Durable Objects, Postgres, a managed platform) and whether that fits your hosting. Favor templates that ship tests or an eval hook so agent changes can be checked. Health
Releases 100 or more in 12 monthsLast one today
Top contributor 58% of commits1,919 of 3,281 in the last 12 months
Security advisories NoneOn GitHub, in the last 12 months
OpenSSF Scorecard Not checked Read from GitHub, deps.dev and OpenSSF on 12 Nov 2026. Bots and coding-agent accounts are left out of the commit counts. Not part of the score: how we check .
License in plain words MIT Permissive
Use it at work Yes
Change it and rebrand it Yes
Sell it or host it for others Yes Your part: Keep the copyright and license notice in copies you ship.
A plain summary, not legal advice. Read the license on GitHub ↗ (opens in a new tab)
Deploy it Needs before it works: Docker, Docker Compose v2, Bun (installer), Slack/GitHub/other integrations (optional).
Buttons from the project's own README. It runs in your account on that platform; we host nothing.
Bring in an engineer who knows agent-swarm . By the hour for upkeep and fixes, or a fixed price for a build. Our own engineering service; it never changes a rank.
Where to run it Referral links: if you sign up through one, we get a commission. They never change a rank.
Ask your AI assistant The rankings as an MCP server for Claude, Cursor, ChatGPT and any MCP client. Free, no key, read-only.
Setup for other apps → Claude Code claude mcp add archestack -- npx -y @archestack/mcpCopy
Connector URL https://mcp.archestack.com/mcpCopy
Then ask: Compare agent-swarm with its top alternatives on Archestack
Share this rank #15 of 62 in Agent and MCP starters on Archestack, as of 12 Nov 2026.
Show it in your README or on your site The badge below goes in a README; a card with the rank, score and signals goes on a site or blog. Both update twice a day.
Copy for README Copy for your site
Show code README (Markdown)
[](https://archestack.com/best-of-vibe-coding/projects/agent-swarm/)Site or blog (HTML)
<iframe src="https://archestack.com/embed/best-of-vibe-coding/agent-swarm/" title="agent-swarm on Archestack" width="400" height="270" style="border:0;max-width:100%" loading="lazy"></iframe>How badges work Preview the card
Best of Vibe Coding on GitHub Each review comes from the project's README and facts we check on GitHub. The fix form opens with agent-swarm filled in.