desplega-ai/agent-swarm

An engine to make your company AI Native
_{Built by desplega.sh.}

[!TIP]

This repo evolves every single day. Watch now →

_{▸ daily evolution · slack → pr · Making of}

agent-swarm.dev is an open-source operating system for AI work. A lead agent delegates goals to workers such as Claude Code or Codex. Isolated containers, shared memory, tools, schedules, and review gates preserve work across sessions.

What you get

• A lead agent that receives work from Slack, repositories, issue trackers, email, or the API
• Schema-validated task results for callers that need structured JSON output
• Deferred tasks that wake when all or any watched tasks reach an outcome, or a deadline arrives
• Dashboard file attachments by paste, drag-and-drop, or file picker
• Workers in isolated Docker containers with development environments
• Memory and identity that persist across sessions
• Workflows, schedules, scripts, and apps for recurring work
• Extensions for trusted TypeScript hooks, installed as drafts and activated by a trusted lead or operator
• Realtime rooms for shared page state, presence, and live channels
• Your choice of harness and models: Claude Code, Codex, pi, opencode, Devin, or ACP agents

flowchart LR
    subgraph IN["Tasks come in"]
        direction TB
        S["Slack"]
        G["GitHub / GitLab"]
        E["Email"]
        A["API / CLI"]
    end
LEAD(["Lead Agent
plans & delegates"])
subgraph WORKERS["Workers in Docker"]
        direction TB
        W1["Worker"]
        W2["Worker"]
        W3["Worker"]
    end
subgraph BRAIN["Persistent brain"]
        direction TB
        MEM["Memory
(vector search)"]
        ID["Identity
(SOUL, CLAUDE.md)"]
    end
subgraph OUT["Work ships"]
        direction TB
        PR["Pull Requests"]
        REPLY["Slack replies"]
        EMAIL["Email replies"]
    end
IN --> LEAD --> WORKERS
    WORKERS -->|reads context| BRAIN
    WORKERS -->|writes learnings| BRAIN
    WORKERS --> OUT

Quick Start

Give your coding agent the operator skill for Docker Compose or Kubernetes:

npx skills add desplega-ai/agent-swarm

Or install it as a plugin in your harness:

| Harness | Command | |---|---| | Claude Code | /plugin marketplace add desplega-ai/agent-swarm then /plugin install agent-swarm@agent-swarm | | Codex | codex plugin add https://github.com/desplega-ai/agent-swarm (or use npx skills above) | | Cursor | /add-plugin desplega-ai/agent-swarm | | Gemini CLI | gemini extensions install https://github.com/desplega-ai/agent-swarm | | Antigravity / Factory Droid | droid plugin marketplace add https://github.com/desplega-ai/agent-swarm then droid plugin install agent-swarm@agent-swarm | | OpenCode, pi, Devin, Kimi, others | npx skills add desplega-ai/agent-swarm |

The plugin's privacy and terms links describe the Agent Swarm website and Cloud service. The self-hosted software remains covered by the MIT License.

Or use the examples directly:

git clone https://github.com/desplega-ai/agent-swarm.git && cd agent-swarm
cp .env.docker.example .env  # Set API_KEY, a harness credential, and all eight agent UUIDs.
openssl rand -base64 32 > encryption_key
chmod 600 .env encryption_key
docker compose -f docker-compose.example.yml --env-file .env up -d

Read the Compose checklist before starting. API: http://localhost:3013, with /docs and /openapi.json. Dashboard: connect it to your API. Kubernetes: install the OCI Helm chart.

Integrations

Slack · GitHub · GitLab · Linear · Jira · AgentMail · WhatsApp (Kapso) · Composio · Sentry · Devin · Serply search. Integration guides.

Learn more

• Getting started · Architecture · Playbooks · CLI · API reference
• Agent templates
• Help: contact@desplega.sh · Discord

Contributing

Read CONTRIBUTING.md, fork the repository, create a branch, and open a PR. Discuss ideas on Discord.

Are you an agent? Run npx skills add desplega-ai/agent-swarm or read the operator skill.

Star History

License

MIT · 2025-2026 desplega.sh

Feature defaults

Fresh deployments enable Slack thread renderer v2, queued Slack steering to the lead, task steering, multi-runtime workers, RBAC, and task-tool preloading. Hybrid memory search and graph expansion are also enabled. Explicit environment/config overrides remain supported; see the environment reference. When upgrading older workers, keep MULTI_RUNTIME_ENABLED=false until they support runtime identities. Slack delegation rendering remains opt-in, and database retention continues to default to dry-run.