Agent Swarm
A self-hosted operating system for coordinating AI workers with durable memory and isolated execution.
- Source repo
- desplega-ai/agent-swarm
- Stars
- ★ 1k
- Last updated
- today
- License
- MIT
- Primary language
- TypeScript
- FA score
- 47/100 · Major gaps
At a glance
- How it runs
- Works with
- Universal · cross-platformCodex · Claude Code
- Cost
- Free software; you pay for model usage
- Setup effort
- Medium · a few setup steps
- You'll need
- Typical use
- An engineering team turns a Slack feature request into delegated containerized work that produces a GitHub pull request.
- Not a fit if
- Users unwilling to configure Docker, credentials, and eight agent UUIDs
- Teams wanting a turnkey service with no self-hosted infrastructure
- Source review
- 47/100 · Major gaps
What does this agent do, and when should you use it?
Agent Swarm is a self-hosted coordination system for company AI work, with a Lead Agent that plans tasks and dispatches Workers. Tasks can arrive from Slack, GitHub, GitLab, email, Linear, Jira, WhatsApp, an API, or the CLI, while Workers run in isolated Docker containers. The system writes session learnings into shared memory and retains agent identity and context across sessions. It includes an MCP API Server, SQLite, a real-time dashboard, workflows, schedules, and human approval gates. Results can be delivered as pull requests, Slack or email replies, issue replies, and shareable pages; Docker Compose and npm/Bun CLI entry points are documented.
A Lead Agent receives a task, plans the work, and delegates subtasks to Workers. Workers run inside Docker containers with development tooling including git, Node.js, and Python; they read shared memory and identity context, write learnings back, and stream progress to the dashboard, Slack threads, or the API. DAG workflows can apply retries, structured inputs and outputs, and approval gates, while cron schedules can target agent tasks, workflows, or catalog scripts. The CLI exposes onboard, connect, api, worker, lead, e2b, x, and docs; MCP tools include memory, pages, and KV operations.
- An engineering team turns a Slack feature request into delegated containerized work that produces a GitHub pull request.
- A product team using Linear and GitHub turns synchronized tickets and discussions into trackable agent tasks.
- A customer-success team runs scheduled account reports while retaining context in per-customer working directories.
- An operations team connects Datadog, New Relic, or Sentry alerts so Workers can investigate issues or propose recurring code-health improvements.
- A marketing team runs content workflows to produce material for blogs, social channels, and website updates.
- A support team receives requests through Slack, email, or WhatsApp and has agents respond in the originating conversation channel.
How do you install or deploy this agent?
Docker and at least one supported harness credential are required. For the guided setup, run bunx @desplega.ai/agent-swarm onboard or npx @desplega.ai/agent-swarm onboard; the wizard creates a Docker Compose configuration. For manual setup, run git clone https://github.com/desplega-ai/agent-swarm.git, cd agent-swarm, and cp .env.docker.example .env. Set API_KEY and a credential for the selected harness in .env, such as CLAUDE_CODE_OAUTH_TOKEN, then run docker compose -f docker-compose.example.yml --env-file .env up -d. The API listens on port 3013, with interactive documentation at http://localhost:3013/docs.
How do you use this agent?
After deployment, create work through a Slack DM or @mention, a GitHub/GitLab issue or PR, email, or the API/CLI. The Lead plans and delegates the work, Workers execute it in containers, and outputs are sent to the relevant destination. Use bunx @desplega.ai/agent-swarm <command> or npx @desplega.ai/agent-swarm <command> to operate the system: lead runs a Lead, worker runs a Worker, and api starts the API and MCP HTTP server. Inspect the API at http://localhost:3013/docs; for local dashboard development, run bun install && bun run dev in apps/ui and open http://localhost:5274.
What are this agent's strengths and limitations?
- The Lead/Worker architecture combines centralized planning with Docker-isolated execution for parallel, reviewable delegated work.
- Shared memory, persistent identity, hybrid retrieval, and graph-linked memories preserve useful context between sessions.
- Slack, GitHub, GitLab, email, Linear, Jira, WhatsApp, API, and CLI inputs allow it to fit into several existing work channels.
- Documented harnesses include Claude Code, OpenAI Codex, pi-mono, Devin, Claude Managed Agents, raw LLMs, and opencode, reducing dependence on one harness.
- DAG workflows, cron schedules, pause/resume, retries, and HITL gates support ongoing operational automation.
- Deployment requires Docker plus credentials for a supported harness; the default quick-start example uses a Claude Code OAuth token.
- Each external channel requires its own integration setup, such as OAuth, webhooks, or service-specific credentials.
- Workers run real tasks in full development environments, so adopters must define approval gates, permitted tool routes, and infrastructure boundaries.
- Some advanced features introduce additional dependencies or co-deployments, including agent-fs, the E2B evaluation harness, and an OpenTelemetry-compatible backend.
- The supplied material does not state hosted pricing, production capacity sizing, or infrastructure cost guidance.
How does this agent compare with similar options?
Key facts side by side with the most closely related agents.
| Agent | Source review | Form / cost | Stars | Updated | Language | Full support on |
|---|---|---|---|---|---|---|
| Agent Swarm This agent | 47 · Major gaps | Agent plugin / skillFree + model costs | ★ 1k | today | TypeScript | Codex · Claude Code |
| Dagu Workflow Orchestrator | 74 · Some gaps | CLIFreemium | ★ 4.5k | today | Go | Codex · Claude Code · Claude API |
| Flock Multi-Agent Workbench | 46 · Major gaps | Desktop appFree + model costs | ★ 1.1k | 4mo ago | Rust | OpenAI API · Claude API |
| Trigger.dev | 57 · Major gaps | Library / SDKFreemium | ★ 17k | 6d ago | TypeScript | — |
How does FollowAgents rate this agent?
Why each dimension lost points
Evidence shows RBAC check scripts, API key boundary checks, audit column checks, and HITL gate patterns, but implementation details are not provided. Deductions: least privilege, user confirmation, data flow transparency are only asserted via scripts and docs, lacking code-level evidence. Sensitive data handling has OAuth and key management but no specific protection measures shown. Dependency security has lock files and CI checks but no vulnerability scanning evidence. External effects have Docker isolation and approval gates but no specific controls shown. Rollback has Swarm Apps safe rollback and deployment rollback but no specific mechanisms. Source attribution has clear author and maintainer info.
Self-consistency: README, package.json, CI workflows, and test files describe consistently, but actual execution not verified. Dependency availability: lock files and CI install steps exist, but availability not verified. Failure messages: tests cover error handling, but no user-visible failure message examples provided.
Audience and scenarios: README details multiple use cases and integrations. Capability boundaries: architecture diagram and docs exist, but no explicit limits. Trigger precision: scheduling and task triggering mechanisms exist, but no precise trigger conditions. Environment fit: supports multiple deployment methods and platforms, but not all environments detailed.
Information architecture: clear documentation structure and architecture diagram. Install notes: quick start and multiple installation methods provided. Naming stability: version numbers and CLI commands exist, but no naming conventions. Examples and FAQ: playbooks and doc links exist, but no FAQ. Known limitations: not explicitly listed. License: MIT license clear. Versioning and changelog: version numbers and CI checks exist, but no changelog. Maintenance responsibility: maintainer info present.
Output usability: CLI, API, Dashboard etc. provided. Marginal value: multiple integrations and automation features, but value not quantified. Cost-benefit: no cost analysis provided.
Claim traceability: README claims have doc links, but no specific evidence. Cross-source corroboration: CI and tests exist, but no independent verification. Fact-inference separation: docs distinguish facts and inferences, but not explicitly labeled.
- Static review cannot verify actual runtime behavior; all conclusions about security, reliability, and effectiveness are inferred from code and docs.
- Dependency security lacks vulnerability scanning evidence; check dependencies for known vulnerabilities.
- Least privilege and user confirmation mechanisms are only asserted via scripts and docs; review specific implementations.
- Rollback mechanisms lack specific implementation details; verify their effectiveness.
Recent releases
Latest entries from the project's GitHub Releases. Notes are quoted from upstream as written, not rewritten or tested by FollowAgents.
-
Release notes excerpt
Install & Run npm: ```bash npx @desplega.ai/[email protected] or install globally npm i -g @desplega.ai/[email protected] ``` bun: ```bash bunx @desplega.ai/[email protected] or install globally bun i -g @desplega.ai/[email protected] ``` Docker: ```bash Server docker pull ghcr.io/desplega-ai/agent-swarm:2.8.1 Worker docker pull ghcr.io/desplega-ai/agent-swarm-worker:2.8.1 Dashboard docker pull ghcr.io/desplega-ai/agent-swarm-ui:2.8.1 ``` E2B templates: ```bash API agent-swarm-api-2-8-1 agent-swarm-api-latest Worker / lead runtime agent-swarm-worker-2-8-1 …View on GitHub ↗ -
Release notes excerpt
Install & Run npm: ```bash npx @desplega.ai/[email protected] or install globally npm i -g @desplega.ai/[email protected] ``` bun: ```bash bunx @desplega.ai/[email protected] or install globally bun i -g @desplega.ai/[email protected] ``` Docker: ```bash Server docker pull ghcr.io/desplega-ai/agent-swarm:2.8.0 Worker docker pull ghcr.io/desplega-ai/agent-swarm-worker:2.8.0 Dashboard docker pull ghcr.io/desplega-ai/agent-swarm-ui:2.8.0 ``` E2B templates: ```bash API agent-swarm-api-2-8-0 agent-swarm-api-latest Worker / lead runtime agent-swarm-worker-2-8-0 …View on GitHub ↗ -
Release notes excerpt
Install & Run npm: ```bash npx @desplega.ai/[email protected] or install globally npm i -g @desplega.ai/[email protected] ``` bun: ```bash bunx @desplega.ai/[email protected] or install globally bun i -g @desplega.ai/[email protected] ``` Docker: ```bash Server docker pull ghcr.io/desplega-ai/agent-swarm:2.7.10 Worker docker pull ghcr.io/desplega-ai/agent-swarm-worker:2.7.10 Dashboard docker pull ghcr.io/desplega-ai/agent-swarm-ui:2.7.10 ``` E2B templates: ```bash API agent-swarm-api-2-7-10 agent-swarm-api-latest Worker / lead runtime …View on GitHub ↗