Home/AI Agents/MetaClaw

MetaClaw

aiming-lab/MetaClaw

Simply converse with your agent, it learns and evolves

GitHub Website

GraphCanon updated Sep 20, 2026 · GitHub synced Sep 20, 2026

34views this month

3.5k stars454 forksLast push Jun 7, 2026 Python MIT

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

MetaClaw alternatives Trust report

Verify the decision

Maintenance and security

Full trust report

Maintenance: Slowing (104d since push); As of Sep 19, 2026
Provenance: Not a fork · Organization account; As of Sep 19, 2026
Security (OSV): No lockfile; As of Jul 11, 2026

Public GitHub metadata and optional OSV scans. Signals, not a guarantee. Trust methodology.

Install

pip install MetaClaw

PyPI

Similar tools

Same-category neighbours. No typed graph edges are catalogued for this tool yet.

learn-claude-code

A nano claude code-like agent harness built from scratch

77k★

ai-agents-for-beginners

12 Lessons to Get Started Building AI Agents

75k★

zeroclaw

Fast, small, and fully autonomous AI personal assistant infrastructure

33k★

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] · Sep 19, 2026
Languages: python
Source: github.language+pyproject.toml · Sep 19, 2026

Compatibility

Sourced claims from the README excerpt - not unsourced marketing copy.

Node.js runtimeNode.js

Source: README excerpt (regex_v1, Sep 19, 2026)

npx -y @tencent-weixin/openclaw-weixin-cli@latest install

Source link

Python runtimePython

Source: README excerpt (regex_v1, Sep 19, 2026)

pip install -e . # skills_only mode (lightweight)

Source link

README

One click deployment Configure once with , then 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, t...

For agents

This page has a .md twin and JSON over the API.

/tools/aiming-lab-metaclaw.md GET /api/graphcanon/tools/aiming-lab-metaclaw GET /api/graphcanon/graph?tool=aiming-lab-metaclaw