GraphCanon updated today · GitHub synced today
Decision brief
MetaClaw enables AI agents to evolve through continuous learning and interaction.
Good fit when
- Need an agent that evolves and fine-tunes over time with user interactions.
- Integrate MetaClaw when reinforcement learning applications require interactive evolution.
Avoid when
- 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.
Observed Jul 12, 2026 · Source: enrich:decision_facts
Verify the decision
Maintenance and security
Full trust report- Maintenance
- Steady (77d since push)
- As of today
- Provenance
- Not a fork · Organization account
- As of today
- Security (OSV)
- No lockfile
- As of 1mo
Public GitHub metadata and optional OSV scans. Signals, not a guarantee. Trust methodology.
Install
pip install MetaClawSimilar tools
Same-category neighbours. No typed graph edges are catalogued for this tool yet.
Evidence and technical details
Sourced facts, taxonomy, compatibility claims, README excerpt, and machine-readable endpoints.
Overview
MetaClaw is an AI framework that aims to enable continuous learning and evolution of agents through interactions, fine-tuning, and reinforcement learning.
Capability facts
- CLI
- CLI entrypoint
Source: pyproject.toml:[project.scripts] · Aug 23, 2026
- Languages
- python
Source: github.language+pyproject.toml · Aug 23, 2026
Categories
Compatibility
Sourced claims from the README excerpt - not unsourced marketing copy.
Source: README excerpt (regex_v1, Aug 23, 2026)
npx -y @tencent-weixin/openclaw-weixin-cli@latest installSource link
Source: README excerpt (regex_v1, Aug 23, 2026)
pip install -e . # skills_only mode (lightweight)Source link
Tags
README
One-click deployment
Configure 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.
1. Install
OpenClaw (one-click): use the 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.
curl -LO https://github.com/aiming-lab/MetaClaw/releases/download/v0.4.0/metaclaw-plugin.zip
unzip metaclaw-plugin.zip -d ~/.openclaw/extensions
openclaw plugins enable metaclaw-openclaw && openclaw gateway restart
pip (PyPI or this repo):
pip install -e . # skills_only mode (lightweight)
pip install -e ".[rl]" # + RL training support (torch, transformers, tinker)
pip install -e ".[evolve]" # + skill evolution via OpenAI-compatible LLM
pip install -e ".[scheduler]" # + Google Calendar integration for scheduler
pip install -e ".[rl,evolve,scheduler]" # recommended for full RL + scheduler setup
(Optional) WeChat integration uses the official @tencent-weixin/openclaw-weixin plugin. MetaClaw auto-installs it when WeChat is enabled:
metaclaw config wechat.enabled true
metaclaw start
The plugin is installed automatically on metaclaw start. You can also install it manually:
npx -y @tencent-weixin/openclaw-weixin-cli@latest install
To switch WeChat accounts (re-login with a new QR code):
metaclaw start --wechat-relogin
If you want to run rl.backend=mint, install the MinT compatibility package separately in the same environment, for example mindlab-toolkit. Similarly, for rl.backend=weaver, install nex-weaver separately. MetaClaw keeps these dependencies out of the default package so RL users can choose Tinker, MinT, or Weaver explicitly.
📄 License
This project is licensed under the MIT License.
For agents
This page has a .md twin and JSON over the API.