You own the outcome.
The company OS
you actually own.
Not a model you rent by the token — a swarm you own that runs every role, learns your business, and gets better every day.
Free to start · no card required
Leverage without headcount
Agents for engineering, support, content, and ops run the work that used to wait on the next req to close.
Owned, not rented
Swap the underlying model anytime. Keep the veteran — the institutional memory, skills, and identities you've accumulated.
Compounds daily
A six-month-old swarm and a fresh one call the same model — and aren't worth the same. The moat is accumulation.
Customer testimonials and social proof
“Building multi-agent workflows is surprisingly approachable. You don't code it, you just explain it.”
One swarm, every surface
you already work in.
Slack, GitHub, Linear, email, approvals, a live dashboard — same swarm, same memory. Pick a surface; each demo streams in.
Mention it like a teammate — it picks up the task, runs the work, and reports back.
Day one: a team that
already ships.
A lead that decides what to ship next
The lead reads the task, breaks it down, and routes work to workers — directly assigned, offered for acceptance, or pulled from a pool. You hand off the goal; the lead owns the plan.
Every worker free to do its own job
Each worker runs in its own Docker container with a persistent /workspace. They install what they need, branch off main, and ship without stepping on each other or your repo.
Talks human, talks API
Mention the bot in Slack, assign a Linear issue, send an email — that’s the task. Built on Model Context Protocol with a full OpenAPI 3.1 spec at :3013, so anything that speaks HTTP — your CI, your monitoring, your custom dashboards — can drive the swarm or be driven by it.
Wake up to work already done
Cron-scheduled recurring jobs, multi-step workflows, role templates for Coder / Researcher / PM. Hand the night-shift work to scheduled tasks, find the results in your Slack the next morning.
Where an agent swarm
keeps paying back.
The system is strongest when work repeats, context matters, and one human should not be the router for every handoff.
Drain the engineering queue without a standup bottleneck
Turn GitHub issues, Linear tickets, and Slack requests into parallel worker tasks. The lead keeps context, assigns owners, and reports back with PRs, logs, and blockers.
See real sessionsRun recurring SEO and content operations with memory
Schedule audits, pull search data, draft updates, regenerate markdown mirrors, and remember what changed last week so every run starts from the current state.
Read the playbooksCoordinate AI agents you already trust
Use Claude Code, Codex, OpenCode, or your own model-backed worker as the execution layer. Agent Swarm handles routing, isolation, shared memory, and review gates.
Compare frameworksAgent Swarm,
in one paragraph.
Agent Swarm is an open-source operating system for AI work: a lead agent breaks goals into tasks, routes them to specialized workers such as Claude Code or Codex, runs each worker in an isolated container, and preserves shared memory, tools, schedules, and review gates so delegated work compounds across sessions.
tasks executed in the last 30 days
daily installs
in the making, with companies using it with teams from 5 to hundreds
What is Agent Swarm?
Agent Swarm is an open-source operating system for AI work: a lead agent breaks goals into tasks, routes them to specialized workers such as Claude Code or Codex, runs each worker in an isolated container, and preserves shared memory, tools, schedules, and review gates so delegated work compounds across sessions.
When should a team use Agent Swarm?
Use Agent Swarm when work repeats, context matters, and one human should not be the router for every handoff: engineering queue drain, recurring SEO or content operations, review workflows, research runs, and multi-repo tasks that benefit from persistent memory.
How is Agent Swarm different from an agent framework?
Agent frameworks help developers build custom agents. Agent Swarm is the running operating layer: a lead, worker pool, task lifecycle, Docker isolation, shared memory, schedules, Slack/GitHub/Linear workflows, and review gates are already wired together.
From zero to compounding
in an afternoon.
No DAGs. No definition language.
Run docker compose up, then talk to it where you already work.
docker compose up
Clone, set CLAUDE_CODE_OAUTH_TOKEN in .env, bring it up. The API server, lead, and workers come online in their own containers — no DAG, no agent definition language.
Wire it into where you work
Install the GitHub App, drop the bot in Slack, OAuth Linear, point AgentMail at an inbox. From now on, mentions and assignments become tasks the lead routes.
It gets sharper while you sleep
Workers ship. Each task summary is embedded into shared memory. SOUL.md and IDENTITY.md evolve. Tomorrow’s swarm reads what last week’s shipped before it touches a keystroke.
A frontier model is rented.
A swarm is owned.
Hosted agents rent you capability you never keep. A swarm keeps the loop — memory, identities, and skills compound into an asset that stays yours. See how it stacks up against the alternatives.
Coordination,
end to end.
Agent swarms are coordinated teams of AI agents. A lead agent breaks down the goal, assigns work to specialized workers, and keeps shared memory across tasks so the team can ship in parallel without losing context between sessions.
We run them. Devin, Claude Code, Codex, OpenCode — agent-swarm uses any of them as the brain inside a worker. You bring the model and the agent you trust; we coordinate a team of them in parallel, each in its own container, with shared memory and a lead that delegates. We sit one layer above coding agents — they ship the code, we run the team that ships the codebase.
Their bet is that you'll build your AI team on their stack — pre-built employees, their orchestration, their lock-in. Ours is the opposite: bring the agents and models you already trust, run them on infrastructure you control, keep your memory and identity files in your DB and filesystem as portable artifacts. The category bet is structurally different — AI work is coordinated across heterogeneous, owned components, not built top-down by a single vendor. You can fork the entire stack and keep going.
Inverse, actually. Glean, Onyx, and the rest of that shelf retrieve what your org said by indexing every app into one graph. agent-swarm coordinates what your org does — your data stays in its source of truth (Linear, GitHub, Notion); the swarm stores derived knowledge (decisions, gotchas, capability gaps, what worked last sprint). Two opposite jobs; happy to live next to a search layer.
You can. We did, and then kept going. LangGraph and AutoGen are SDKs — you write the graph, host the runtime, persist the memory, build the Slack and GitHub integrations, build the dashboard. agent-swarm is the running system: docker compose up, integrations pre-wired, memory built in, dashboard included. SDK if you're building a tool; agent-swarm if you want to use one.
As much as you need. You control the tools each worker can call, the integrations it can reach, and the boundaries it operates within — your infra, your policies. Hooks let you wire approvals, gates, or any custom check before an action takes effect. Whether the swarm is shipping code, drafting a campaign, running a UX research synthesis, or triaging support, the same governance surface applies: scoped permissions, reviewable outputs, and stop-buttons in the dashboard. The defaults are conservative; the surface area is yours to shape.
Yes. MIT-licensed source, runs anywhere Docker runs, BYOK / BYOM. The Cloud version exists for convenience, not as a hostage. Air-gapped customers run the same binaries.
Pay for the workers.
Not the seats.
Self-host the whole thing for free, forever. Or skip the ops and run it on Cloud — pick how many workers you need, see the total.
Self-hosted
- Full source on GitHub (MIT)
- Run anywhere Docker runs
- BYO model keys, BYO models
- Air-gapped if you need it
- Community support on Discord
Cloud
- Hosted lead + dashboard
- Coordination intelligence built in — memory persists across sessions
- Slack, GitHub, GitLab, Linear, AgentMail, Sentry
- Bring your own model keys (BYOK)
- 7-day free trial · no card required
Enterprise
- Single-tenant, VPC or on-prem
- SSO / SAML, audit log export
- Custom integrations & MCP servers
- Onboarding workshop for ICs + leads
- Priority response, dedicated channel
All Cloud plans include a 7-day free trial. Cancel from the dashboard at any time.
Field notes from
inside the swarm.
26 Tool Calls, One Script, $0.02: Measuring “Code Mode” in Production
We already tell every agent in the swarm to prefer a script over N tool calls. We measured what that's worth in tokens, seconds, and dollars — live, on our own production data.
Multi-Agent Systems Reproduce Every Organizational Anti-Pattern You Already Hate
When autonomous AI agents share resources, they naturally replicate human organizational dysfunction. We catalog 5 production anti-patterns from our swarm of 11+ agents.
LLM-Agent-UMF Did Not Redesign Agent Swarm. It Named What We Already Built.
A unified modeling framework for LLM agents validates Agent Swarm's core architecture: active and passive core-agents, five internal modules, and a security module as the next frontier.
Build your swarm tonight.
A 7-day free trial on Cloud, or fork it on GitHub. Either way, your agents start compounding today.