{"data":{"slug":"aiming-lab-metaclaw","name":"MetaClaw","tagline":"Simply converse with your agent, it learns and evolves","github_url":"https://github.com/aiming-lab/MetaClaw","owner":"aiming-lab","repo":"MetaClaw","owner_avatar_url":"https://avatars.githubusercontent.com/u/186755503?v=4","primary_language":"Python","stars":3493,"forks":454,"topics":["agent","ai-agent","continual-learning","fine-tuning","llm","lora","meta-learning","metaclaw","online-learning","openclaw","reinforcement-learning","skill-learning","tinker"],"archived":false,"github_pushed_at":"2026-06-07T04:57:05+00:00","maintenance_label":"Steady","stars_delta_30d":21,"url":"https://www.graphcanon.com/tools/aiming-lab-metaclaw","markdown_url":"https://www.graphcanon.com/tools/aiming-lab-metaclaw.md","api_url":"https://www.graphcanon.com/api/graphcanon/tools/aiming-lab-metaclaw","graph_url":"https://www.graphcanon.com/api/graphcanon/graph?tool=aiming-lab-metaclaw","description":"🦞 Just talk to your agent — it learns and EVOLVES 🧬.","homepage_url":"https://arxiv.org/abs/2603.17187","license":"MIT","open_issues":17,"watchers":24,"ai_summary":"MetaClaw is an AI framework that aims to enable continuous learning and evolution of agents through interactions, fine-tuning, and reinforcement learning.","readme_excerpt":"### **One-click deployment**\nConfigure once with `metaclaw setup`, then `metaclaw start` brings up the proxy, injects skills, and wires your chosen personal agent (OpenClaw, CoPaw, or IronClaw) automatically. No manual shell scripts needed.\n\n---\n\n### 1. Install\n\n**OpenClaw (one-click):** use the [v0.4.0](https://github.com/aiming-lab/MetaClaw/releases/tag/v0.4.0) release—run the snippet below, then `metaclaw setup` and `metaclaw start`. More detail (Windows, mirrors, config, troubleshooting): [`extensions/metaclaw-openclaw/README.md`](./extensions/metaclaw-openclaw/README.md).\n\n```bash\ncurl -LO https://github.com/aiming-lab/MetaClaw/releases/download/v0.4.0/metaclaw-plugin.zip\nunzip metaclaw-plugin.zip -d ~/.openclaw/extensions\nopenclaw plugins enable metaclaw-openclaw && openclaw gateway restart\n```\n\n**pip** (PyPI or this repo):\n\n```bash\npip install -e .                        # skills_only mode (lightweight)\npip install -e \".[rl]\"                  # + RL training support (torch, transformers, tinker)\npip install -e \".[evolve]\"              # + skill evolution via OpenAI-compatible LLM\npip install -e \".[scheduler]\"           # + Google Calendar integration for scheduler\npip install -e \".[rl,evolve,scheduler]\" # recommended for full RL + scheduler setup\n```\n (Optional) WeChat integration uses the official [`@tencent-weixin/openclaw-weixin`](https://github.com/nicepkg/openclaw-weixin) plugin. MetaClaw auto-installs it when WeChat is enabled:\n\n```bash\nmetaclaw config wechat.enabled true\nmetaclaw start\n```\n\nThe plugin is installed automatically on `metaclaw start`. You can also install it manually:\n\n```bash\nnpx -y @tencent-weixin/openclaw-weixin-cli@latest install\n```\n\nTo switch WeChat accounts (re-login with a new QR code):\n\n```bash\nmetaclaw start --wechat-relogin\n```\n\nIf you want to run `rl.backend=mint`, install the MinT compatibility package separately in the same environment, for example [`mindlab-toolkit`](https://github.com/MindLab-Research/mindlab-toolkit). Similarly, for `rl.backend=weaver`, install [`nex-weaver`](https://github.com/nex-agi/weaver) separately. MetaClaw keeps these dependencies out of the default package so RL users can choose Tinker, MinT, or Weaver explicitly.\n\n---\n\n## 📄 License\n\nThis project is licensed under the [MIT License](LICENSE).","github_created_at":"2026-03-09T13:47:13+00:00","created_at":"2026-07-11T11:37:39.313868+00:00","updated_at":"2026-08-23T18:01:18.841861+00:00","categories":[{"slug":"ai-agents","name":"AI Agents","url":"https://www.graphcanon.com/categories/ai-agents","markdown_url":"https://www.graphcanon.com/categories/ai-agents.md","api_url":"https://www.graphcanon.com/api/graphcanon/categories/ai-agents"},{"slug":"model-training","name":"Model Training","url":"https://www.graphcanon.com/categories/model-training","markdown_url":"https://www.graphcanon.com/categories/model-training.md","api_url":"https://www.graphcanon.com/api/graphcanon/categories/model-training"}],"tags":[{"slug":"agent","name":"agent"},{"slug":"ai-agent","name":"ai-agent"},{"slug":"continual-learning","name":"continual-learning"},{"slug":"fine-tuning","name":"fine-tuning"},{"slug":"llm","name":"llm"},{"slug":"lora","name":"lora"},{"slug":"meta-learning","name":"meta-learning"},{"slug":"online-learning","name":"online-learning"}],"trust":{"provenance":{"is_fork":false,"github_id":1176898834,"owner_type":"Organization","methodology":"github_public_v1","parent_repo":null,"near_duplicate_slugs":[]},"computed_at":"2026-08-23T18:01:17.794Z","maintenance":{"label":"Steady","score":60,"methodology":"github_public_v1","releases_90d":0,"days_since_push":77,"last_release_at":"2026-04-11T20:04:14Z","stars_delta_30d":21,"open_issues_delta_30d":0},"security_summary":{"status":"no_lockfile","scanner":null,"low_count":0,"high_count":0,"last_scan_at":"2026-07-11T11:37:40.548Z","medium_count":0,"scan_profile":"none","critical_count":0}},"capability_facts":{"scan":{"source":"repo_scan","observed_at":"2026-08-23T18:01:18.465Z"},"has_cli":{"value":true,"source":"pyproject.toml:[project.scripts]","observed_at":"2026-08-23T18:01:18.465Z"},"languages":{"value":["python"],"source":"github.language+pyproject.toml","observed_at":"2026-08-23T18:01:18.465Z"},"license_spdx":{"value":"MIT","source":"github.license","observed_at":"2026-08-23T18:01:18.465Z"}},"decision_facts":{"hosting":null,"pricing":null,"requirements":null,"constraints":null,"when_to_use":["Need an agent that evolves and fine-tunes over time with user interactions.","Integrate MetaClaw when reinforcement learning applications require interactive evolution."],"when_not_to_use":["Avoid if you need static models without evolving capabilities based on new data.","Not suitable for scenarios requiring immediate model stability post-training, as continuous updates can vary results."],"source":"enrich:decision_facts","observed_at":"2026-07-12T18:49:23.981Z"},"constraint_facets":null,"decision_summary":[{"label":"Adopt for","value":"MetaClaw enables AI agents to evolve through continuous learning and interaction."}]}}