Main
先用全局 CLI 跑通运行时;需要深度定制时再用 Docker 或从源码启动。
把 agent 角色拆小且明确:委派与调度很强,但前提是职责清晰。
把 MCP 工具当成受控能力:先定义边界与输入,再把工具接进 agent 流程。
固定 Provider 配置,重复跑同一流程对比不同模型/成本下的行为差异。
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 给出全局安装方式(
npm i -g @swarmclawai/swarmclaw)并说明服务运行在http://localhost:3456。 - README 描述持久记忆、委派/调度与 MCP 工具支持为核心能力。
- GitHub topics 包含 multi-agent 与 MCP 相关关键词(已通过 GitHub API 复核)。
FAQ
- 它只是一个 UI 吗?:不是:README 表示它包含运行时 + Web 控制台 + CLI 入口。
- 必须用 Docker 吗?:不必须:首次体验可直接用 CLI;README 提到部分沙盒能力建议配 Docker。
- 第一个练手项目做什么?:2–3 个 agent + 1 个 MCP 工具 + 可衡量产出(测试/文档/告警分拣)。
![]() |
![]() |
| Org chart for visualizing agent teams, delegation, and live activity. | Agent chat with durable history, tools, and operator controls. |
