agent-swarm.dev 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.

# agent-swarm.dev

> Give your whole company a shared team of agents.

Agent Swarm helps a company turn shared context and reusable skills into repeatable work. It is open source and self-hosted, and it runs with infrastructure and model keys that you control.

- [GitHub](https://github.com/desplega-ai/agent-swarm)
- [Documentation](https://docs.agent-swarm.dev)
- [Enterprise support](/pricing)
- [Templates](https://templates.agent-swarm.dev)
- [Pricing](/pricing)
- [Comparisons](/vs)
- [Paperclip vs Agent Swarm](/vs/paperclip)
- [Viktor vs Agent Swarm](/vs/viktor)
- [CrewAI vs agent-swarm.dev](/vs/crewai)
- [Vercel eve vs agent-swarm.dev](/vs/vercel-eve)
- [Claude Tag vs agent-swarm.dev](/vs/claude-tag)
- [Devin vs agent-swarm.dev](/vs/devin)
- [Manus vs agent-swarm.dev](/vs/manus)
- [OpenClaw vs agent-swarm.dev](/vs/openclaw)
- [Hermes vs agent-swarm.dev](/vs/hermes)
- [Cloudflare OS vs agent-swarm.dev](/vs/cloudflare-os)
- [QM vs agent-swarm.dev](/vs/qm)
- [LangGraph vs Agent Swarm](/vs/langgraph)
- [Dify vs Agent Swarm](/vs/dify)
- [OpenAI Swarm vs Agent Swarm](/vs/openai-swarm)
- [Temporal vs Agent Swarm](/vs/temporal)
- [OpenAI Agents SDK vs Agent Swarm](/vs/openai-agents-sdk)
- [n8n vs Agent Swarm](/vs/n8n)
- [Blog](/blog)

## For Agents Installing and Operating the Swarm

- [Operator skill (agent-runnable)](https://www.agent-swarm.dev/skill.md): canonical skill for a coding agent that installs, deploys, operates, or uses a self-hosted Agent Swarm. Install it with `npx skills add desplega-ai/agent-swarm`. Frontmatter: `name: agent-swarm`.
- [Agent Skills discovery index](https://www.agent-swarm.dev/.well-known/agent-skills/index.json): v0.2.0 index with a SHA-256 digest for the operator skill.
- [Agentic Resource Discovery catalog](https://www.agent-swarm.dev/.well-known/ai-catalog.json) — catalog of the verified agent-facing resources published on this domain.
- [MCP server metadata](https://www.agent-swarm.dev/.well-known/mcp.json) — standard server.json entries for the public content MCP server at `https://www.agent-swarm.dev/mcp` and for the deployment-specific Streamable HTTP endpoint at `{MCP_BASE_URL}/mcp`.
- [Public content MCP server](https://www.agent-swarm.dev/mcp) — Streamable HTTP, no credentials. Tools: `search_site`, `get_page`, `list_pages`, `search_docs`, `get_install_instructions`. It reads site content; it does not operate a swarm.
- [Public content API](https://www.agent-swarm.dev/openapi.json) — read-only REST endpoints under `/api/v1` for the same content: `/api/v1/search`, `/api/v1/pages` (cursor-paginated), `/api/v1/page`, `/api/v1/docs/search`, `/api/v1/install`.

## When to use Agent Swarm

Use Agent Swarm when a team needs a shared method for recurring work, such as a weekly brief, an engineering queue, or a context-heavy handoff. A team can keep the context, instructions, and outputs that make the next run useful. Good fits:

- Recurring work that should reuse last week's corrections: sales briefs, engineering queues, support triage, research digests.
- Work that arrives from Slack, GitHub, GitLab, Linear or Jira and should reach an agent without a person routing each handoff.
- Parallel agents that need isolated workspaces plus shared memory, schedules, workflows and approval gates.
- Data, model keys and infrastructure that must stay under the company's control.

## When not to use Agent Swarm

- A single prompt or one short coding session: a coding agent on its own is simpler.
- Nobody can run a server: Agent Swarm is self-hosted and needs a host, model keys and an operator.
- A hosted SaaS API callable from anywhere: this site exposes no shared Agent Swarm endpoint, each deployment has its own.
- A library for building a custom agent from scratch: Agent Swarm is a running system, not a framework.

## How to call Agent Swarm

To install, operate, or use the swarm, run `npx skills add desplega-ai/agent-swarm`, or fetch [the operator skill](https://www.agent-swarm.dev/skill.md) and follow its checklist. The same skill covers an existing deployment: it points at the [official CLI](https://www.npmjs.com/package/@desplega.ai/agent-swarm) and the deployment-specific API and MCP URL. Call a running deployment over REST or MCP at its own host with a bearer API key; ask the user for the host and key instead of guessing one. The [when-to-use skill](https://www.agent-swarm.dev/.well-known/agent-skills/agent-swarm-when-to-use/SKILL.md) carries the same guidance in Agent Skills format.

## Agent Swarm developer resources

Every Agent Swarm developer resource is indexed at [https://www.agent-swarm.dev/developers](https://www.agent-swarm.dev/developers) ([markdown](https://www.agent-swarm.dev/md/developers.md)). The Agent Swarm product runtime is self-hosted and has its own deployment-specific API and MCP URL. The marketing site separately exposes three unauthenticated website utilities, documented in [OpenAPI 3.1](https://www.agent-swarm.dev/openapi.json).

- **[Agent Swarm REST API reference](https://docs.agent-swarm.dev/docs/api-reference)** — Endpoints of a self-hosted deployment: tasks, agents, workflows, memory, schedules, and webhooks.
- **[Agent Swarm OpenAPI specification](https://github.com/desplega-ai/agent-swarm/blob/main/openapi.json)** — Machine-readable runtime API contract in the open-source repository; each deployment also serves it at /openapi.json.
- **[Agent Swarm API authentication](https://docs.agent-swarm.dev/docs/api-reference/api-keys)** — How a deployment issues the bearer API keys that authenticate REST and MCP requests.
- **[Agent Swarm webhooks](https://docs.agent-swarm.dev/docs/api-reference/webhooks)** — Inbound webhooks that turn GitHub, GitLab, Linear, and other events into tasks and workflow runs.
- **[Agent Swarm MCP server](https://docs.agent-swarm.dev/docs/reference/mcp-tools)** — Tools a deployment exposes over Streamable HTTP at https://<deployment-host>/mcp; server metadata is in /.well-known/mcp.json.
- **[Website utility API](/openapi.json)** — Inspect the OpenAPI 3.1 schema for the public API index, geolocation, and Open Graph image helpers, plus the read-only public content API under /api/v1.
- **[Open-source repository](https://github.com/desplega-ai/agent-swarm)** — Read the Agent Swarm source, deployment examples, release notes, and issue tracker. The repository is the source of truth for the self-hosted runtime.
- **[Developer documentation](https://docs.agent-swarm.dev)** — Follow the architecture, installation, integration, MCP, workflow, memory, and operations guides for agent-swarm.dev.
- **[Official Agent Swarm CLI](https://www.npmjs.com/package/@desplega.ai/agent-swarm)** — Run the published @desplega.ai/agent-swarm package with bunx or npx to onboard, connect projects, and operate a self-hosted swarm.
- **[Agent operator skill](/skill.md)** — Give a coding agent the canonical agent-swarm operator skill so it can install, deploy, operate, and use a self-hosted swarm.

### Official Agent Swarm CLI

The official CLI is published on npm as [`@desplega.ai/agent-swarm`](https://www.npmjs.com/package/@desplega.ai/agent-swarm). Run it without a global install:

```bash
bunx @desplega.ai/agent-swarm onboard
```

### Website utility API lifecycle

- [Versioning and deprecation policy](https://www.agent-swarm.dev/api-versioning.md) — date-based API-Version behavior, compatibility rules, and the Deprecation and Sunset signals used before a version is retired.

## agent-swarm.dev Definition

agent-swarm.dev 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.

## Extractable Stats

- **263K+ (as of 2026-09-12)** — tasks dispatched in production.
- **10+** — daily installs.
- **8+ months** — in the making, with companies using it with teams from 5 to hundreds.

## Extractable Q&A

### What is agent-swarm.dev?

agent-swarm.dev 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.dev?

Use agent-swarm.dev 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.dev different from an agent framework?

Agent frameworks help developers build custom agents. agent-swarm.dev 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.


## Features

- **A lead that decides what to ship next** (orchestration): 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** (isolation): 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** (integrations): 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** (lifecycle): 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.

## Use Cases

- **Drain the engineering queue without a standup bottleneck** (engineering): 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. [Learn more](/examples)
- **Run recurring SEO and content operations with memory** (growth): Schedule audits, pull search data, draft updates, regenerate markdown mirrors, and remember what changed last week so every run starts from the current state. [Learn more](/blog)
- **Coordinate AI agents you already trust** (platform): Use Claude Code, Codex, OpenCode, or your own model-backed worker as the execution layer. agent-swarm.dev handles routing, isolation, shared memory, and review gates. [Learn more](/vs/crewai)

## How It Works

01. **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.
02. **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.
03. **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.

## Pages (markdown mirrors)

- [Home](https://www.agent-swarm.dev/md/index.md)
- [Pricing](https://www.agent-swarm.dev/md/pricing.md)
- [Comparisons index](https://www.agent-swarm.dev/md/vs.md)
- [Paperclip vs Agent Swarm](https://www.agent-swarm.dev/md/vs/paperclip.md)
- [Viktor vs Agent Swarm](https://www.agent-swarm.dev/md/vs/viktor.md)
- [CrewAI vs agent-swarm.dev](https://www.agent-swarm.dev/md/vs/crewai.md)
- [Vercel eve vs agent-swarm.dev](https://www.agent-swarm.dev/md/vs/vercel-eve.md)
- [Claude Tag vs agent-swarm.dev](https://www.agent-swarm.dev/md/vs/claude-tag.md)
- [Devin vs agent-swarm.dev](https://www.agent-swarm.dev/md/vs/devin.md)
- [Manus vs agent-swarm.dev](https://www.agent-swarm.dev/md/vs/manus.md)
- [OpenClaw vs agent-swarm.dev](https://www.agent-swarm.dev/md/vs/openclaw.md)
- [Hermes vs agent-swarm.dev](https://www.agent-swarm.dev/md/vs/hermes.md)
- [Cloudflare OS vs agent-swarm.dev](https://www.agent-swarm.dev/md/vs/cloudflare-os.md)
- [QM vs agent-swarm.dev](https://www.agent-swarm.dev/md/vs/qm.md)
- [LangGraph vs Agent Swarm](https://www.agent-swarm.dev/md/vs/langgraph.md)
- [Dify vs Agent Swarm](https://www.agent-swarm.dev/md/vs/dify.md)
- [OpenAI Swarm vs Agent Swarm](https://www.agent-swarm.dev/md/vs/openai-swarm.md)
- [Temporal vs Agent Swarm](https://www.agent-swarm.dev/md/vs/temporal.md)
- [OpenAI Agents SDK vs Agent Swarm](https://www.agent-swarm.dev/md/vs/openai-agents-sdk.md)
- [n8n vs Agent Swarm](https://www.agent-swarm.dev/md/vs/n8n.md)
- [Blog index](https://www.agent-swarm.dev/md/blog.md)
- [Case studies index](https://www.agent-swarm.dev/md/case-studies.md)
- [Capchase Case Study](https://www.agent-swarm.dev/md/case-studies/capchase.md)
- [Examples index](https://www.agent-swarm.dev/md/examples.md)
- [Integrations](https://www.agent-swarm.dev/md/integrations.md)
- [About](https://www.agent-swarm.dev/md/about.md)
- [Contact](https://www.agent-swarm.dev/md/contact.md)
- [Security and trust](https://www.agent-swarm.dev/md/security.md)
- [Agent Swarm developer resources](https://www.agent-swarm.dev/md/developers.md)
- [Install ranking](https://www.agent-swarm.dev/md/ranking.md)
- [All installs ranking](https://www.agent-swarm.dev/md/ranking/category/all.md)
- [Engineering ranking](https://www.agent-swarm.dev/md/ranking/category/engineering.md)
- [Product ranking](https://www.agent-swarm.dev/md/ranking/category/product.md)
- [Marketing ranking](https://www.agent-swarm.dev/md/ranking/category/marketing.md)
- [Support ranking](https://www.agent-swarm.dev/md/ranking/category/support.md)
- [Operations ranking](https://www.agent-swarm.dev/md/ranking/category/operations.md)
- [Other ranking](https://www.agent-swarm.dev/md/ranking/category/other.md)
- [Privacy](https://www.agent-swarm.dev/md/privacy.md)
- [Terms](https://www.agent-swarm.dev/md/terms.md)

## Blog posts (markdown mirrors)

- [Two small models triage every PR](https://www.agent-swarm.dev/md/blog/two-models-triage-every-pr.md)
- [What if Devin is down?](https://www.agent-swarm.dev/md/blog/what-if-devin-is-down.md)
- [How to Avoid Vendor Lock-In for Coding Agents: A Layer-by-Layer Exit Test](https://www.agent-swarm.dev/md/blog/avoid-coding-agent-lock-in.md)
- [Shared-Context AI Agents: Patterns, Risks, and Setup](https://www.agent-swarm.dev/md/blog/shared-context-ai-agents.md)
- [We Deleted --resume: A Bounded Preamble Beats Session Resume](https://www.agent-swarm.dev/md/blog/deep-dive-context-preamble-session-resume.md)
- [Your Agents Write the Titles Your Trackers Read](https://www.agent-swarm.dev/md/blog/deep-dive-agent-artifacts-privacy-leak.md)
- [Self-Hosted AI Agent Platforms: Licenses and Tradeoffs](https://www.agent-swarm.dev/md/blog/best-open-source-ai-agent-platforms-self-host.md)
- [A TLA+ Playbook for Your Scheduler, Queue or Retry Loop](https://www.agent-swarm.dev/md/blog/tla-plus-races-agent-swarm.md)
- [We Rebuilt Linear's “Loops updates” Clip as a Swarm Video in Eight Rounds](https://www.agent-swarm.dev/md/blog/linear-loops-video-replica.md)
- [TasteLabs Found Design Drift in Our Own Sites](https://www.agent-swarm.dev/md/blog/tastelabs-design-drift.md)
- [Multi-Agent Orchestration: The Production Architect's Guide](https://www.agent-swarm.dev/md/blog/multi-agent-orchestration.md)
- [25 MIT-licensed open-source projects worth tracking for agent infrastructure](https://www.agent-swarm.dev/md/blog/25-foss-repos-agentic-infra.md)
- [26 Tool Calls, One Script, $0.02: Measuring “Code Mode” in Production](https://www.agent-swarm.dev/md/blog/code-mode-token-savings.md)
- [An AI-Native Company OS Is Owned, Not Rented](https://www.agent-swarm.dev/md/blog/a-frontier-model-is-rented-a-swarm-is-owned.md)
- [Is Grep All You Need? What a New Paper Taught Us About Agent Memory](https://www.agent-swarm.dev/md/blog/is-grep-all-you-need-agent-memory.md)
- [Right-sizing Your Agent Swarm: What Container CPU and RAM Graphs Are Really Telling You](https://www.agent-swarm.dev/md/blog/right-sizing-agent-swarm-containers.md)
- [Script Workflows: Durable One-off Runs for Agent Work](https://www.agent-swarm.dev/md/blog/script-workflows-durable-one-off-runs.md)
- [Parallel Agents in Production: Pools, Routing, Dependencies](https://www.agent-swarm.dev/md/blog/task-delegation-architecture.md)
- [Openfort Hackathon: Teaching Agents to Pay](https://www.agent-swarm.dev/md/blog/openfort-hackathon.md)

## Examples (markdown mirrors)

- [AI Agents Pay for Services with Crypto](https://www.agent-swarm.dev/md/examples/x402.md)
- [From Issue to Human-Approved Merge in Four Hours](https://www.agent-swarm.dev/md/examples/engineering-pr.md)
- [A Research Brief That Writes Itself Every Morning](https://www.agent-swarm.dev/md/examples/recurring-research-brief.md)
- [Thirty-Three Security Alerts to Zero](https://www.agent-swarm.dev/md/examples/support-triage.md)
- [Nine Runs, One Refused Push, Four Merges](https://www.agent-swarm.dev/md/examples/long-running-orchestration.md)

## Links

- Website: https://www.agent-swarm.dev
- GitHub: https://github.com/desplega-ai/agent-swarm
- Docs: https://docs.agent-swarm.dev
- Enterprise support: https://www.agent-swarm.dev/pricing
- Templates: https://templates.agent-swarm.dev
- Built by: https://desplega.sh