MetaClaw: Just talk to your agent — it learns and EVOLVES

by aiming-lab · Codex Skill · ★ 3.5k

Last updated: · Indexed by AgentSkillsHub · Auto-synced every 8h

Security audit verdict: SAFE · quality 62/100

None of the 44 rules matched — no credential harvesting, no data exfiltration, no curl-pipe-shell installer. Scanned against 44 published rules built on the SlowMist agent-security taxonomy, refreshed every 8 hours. Full audit →

The quality score combines nine heuristic checks of the repo and its README: completeness, clarity, specificity, examples, structure, agent readiness, step-by-step content, instruction quality and security notes. It rates how well the project explains itself to an agent, not the code.

agentai-agentcontinual-learningfine-tuningllmlorameta-learningmetaclawonline-learningopenclaw

Quick Facts

Stars3,469
Forks454
LanguagePython
CategoryCodex Skill
LicenseMIT
Quality Score62/100
Open Issues18
Last Updated2026-06-07
Created2026-03-09
Platformspython
Est. Tokens~5078k

About MetaClaw

Just talk to your agent — it learns and EVOLVES. Inspired by how the brain learns. Meta-learn and evolve your 🦞 from every conversation in the wild. No GPU required. Works with Kimi, Qwen, Claude, MiniMax, and more. Kimi Qwen Claude MiniMax <a href="https://openai

Compatible Skills

These tools work well together with MetaClaw for enhanced workflows:

  • ReCall — semantic(0.46)+complementary+rare_topics+same_lang+similar_pop+shared_platform (66%)
  • LLM-Finetuning-Toolkit — semantic(0.26)+complementary+rare_topics+same_lang+similar_pop+shared_platform (63%)
  • ToolBrain — semantic(0.33)+complementary+rare_topics+same_lang+similar_pop+shared_platform (61%)

MetaClaw alternative? Top 6 similar tools

Looking for a MetaClaw alternative? If you're comparing MetaClaw with other codex skill tools, these 6 projects are the closest alternatives on Agent Skills Hub — ranked by topic overlap, star count, and community traction.

  • SkillClaw by AMAP-ML · ⭐ 2.8k

    Let Skills Evolve Collectively with Agentic Evolver

  • AI-Infra-Guard by Tencent · ⭐ 7.5k

    A full-stack AI Red Teaming platform securing AI ecosystems via OpenClaw Security Scan, Agent Scan, Skills Sca

  • semantic-router by vllm-project · ⭐ 6.5k

    A programmable Mixture-of-Models router for heterogeneous LLM inference

  • PPTAgent by icip-cas · ⭐ 5.3k

    An Agentic Framework for Reflective PowerPoint Generation

  • ReCall by Agent-RL · ⭐ 1.4k

    ReSearch: Learning to Reason with Search for LLMs via Reinforcement Learning & ReCall: Learning to Reason with

  • Mysti by DeepMyst · ⭐ 1.2k

    AI coding dream team of agents for VS Code. Claude Code + openai Codex collaborate in brainstorm mode, debate

More Codex Skill Tools

Explore other popular codex skill tools:

View all Codex Skill tools →

Popular Python Agent Tools

How this security grade is produced

Grades come from a rule-based scan built on the SlowMist agent-security taxonomy: 44 published rules, covering credential harvesting, data exfiltration, curl | sh installers and more. It is a first-layer scan, not a manual audit — we say so rather than overstate it.

The scale of the problem is documented independently: Liu et al. (2026), in a study of 31,132 agent skills, report that 26.1% contain security vulnerabilities. Our own full-catalog census is published as a citable open dataset.

Sources & who's responsible:

View on GitHub → Browse Codex Skill tools