Swarmclaw — Self-Hosted Multi-Agent Runtime + MCP

Main

• Start with the global CLI to validate the runtime, then switch to Docker/repo mode if you need customization.

• Keep agent roles small and explicit: delegation and schedules are powerful, but only when responsibilities are clear.

• Treat MCP tools as guarded capabilities: add a tool only after you define limits, inputs, and audit expectations.

• Pin your provider settings and re-run the same workflow to compare behavior across models and budgets.

README (excerpt)

SwarmClaw

The self-hosted AI agent runtime and multi-agent framework for autonomous agents. Open-source agent swarms with durable agent memory, MCP tools, skills, delegation, schedules, and 23+ LLM providers — a practical Claude Code and LangChain alternative.

SwarmClaw is an open-source, self-hosted AI agent runtime and multi-agent framework. Run autonomous AI agents, agent swarms, and orchestrators with heartbeats, schedules, delegation, agent memory, runtime skills, and reviewed conversation-to-skill learning — across OpenClaw gateways, Claude, GPT, Gemini, OpenRouter, Ollama, and 23+ other providers. Use it as your AI agent dashboard, agent orchestration platform, and home base for self-hosted multi-agent AI workflows.

GitHub: https://github.com/swarmclawai/swarmclaw
Docs: https://swarmclaw.ai/docs
Website: https://swarmclaw.ai
Discord: https://discord.gg/sbEavS8cPV
Extension tutorial: https://swarmclaw.ai/docs/extension-tutorial

Screenshots

Source-backed notes

• README shows a global install path (npm i -g @swarmclawai/swarmclaw) and starting the server on http://localhost:3456.
• README describes durable agent memory, delegation, schedules, and MCP tool support as core features.
• GitHub topics include multi-agent and MCP-related keywords (verified via GitHub API).

FAQ

• Is it only a UI?: No—README describes a full runtime plus web dashboard and CLI entrypoint.
• Do I need Docker?: Not required for a first run; README recommends Docker for some sandbox execution paths.
• What’s a good first project?: A 2–3 agent swarm with one MCP tool and a measurable output (tests, docs, or triage).

Org chart for visualizing agent teams, delegation, and live activity.	Agent chat with durable history, tools, and operator controls.