Claude Skill

aiming-lab/MetaClaw

MetaClaw is a Claude Skill for creating AI agents that learn through conversation. This Python project supports fine-tuning, online learning, and evolution of intelligent agents.

Overview

Stars3,438
Forks442
LanguagePython
Last pushed2026-06-07
Last synced2026-06-17
View on GitHub

Repository

Owneraiming-lab
RepositoryMetaClaw
Full nameaiming-lab/MetaClaw
Repo ID1,176,898,834

Install this Skill

pip install -e . # skills_only mode (lightweight)

Registry

Typeopenclaw_skill
Quality score85/100
Verificationreadme_parsed
Last verified2026-05-30
Platforms
ClaudeOpenClawCodex
Capabilities
pdfmemorysearchterminalagentai-agentcontinual-learningfine-tuningllmlora
Detected files
README.mdexamplespyproject.tomlrequirements.txttests
Config keys
LLM_BASE_URLAPI_KEYANTHROPIC_BASE_URLANTHROPIC_API_KEYKEYTOKENURL
Install methods
  • 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

Summary

MetaClaw is a Claude Skill that enables direct conversation with an AI agent, which learns and evolves through interaction. It's a Python-based project focused on agent development, fine-tuning, and online learning.

Chinese description

直接与你的智能体对话——它会学习并不断进化。

Key features

  • Direct conversational interaction with AI agents
  • Continuous learning and evolution through use
  • Python-based implementation for AI development
  • Supports fine-tuning and online learning techniques
  • OpenAI-compatible interface for integration

Use cases

  • Developing adaptive conversational AI assistants
  • Creating self-improving agent systems
  • Research in online learning for LLMs
  • Building fine-tuned specialized AI agents
  • Experimenting with reinforcement learning for agents

README excerpt

<div align="center"> <img src="assets/new_logo2.png" alt="MetaClaw" width="600"> <br/> # Just talk to your agent — it learns and *EVOLVES*. <p>Inspired by how brains learn. Meta-learn and evolve your 🦞 from every conversation in the wild. No GPU required. <br/> <img src="assets/metaclaw_mainfig_v2.png" alt="MetaClaw Architecture" width="800"> <br/> <p> <a href="https://arxiv.org/abs/2603.17187"><img src="https://img.shields.io/badge/📄_Technical_Report-purple?style=flat-square" alt="Tech Report" /></a> <a href="https://github.com/aiming-lab/MetaClaw"><img src="https://img.shields.io/badge/github-MetaClaw-181717?style=flat&labelColor=555&logo=github&logoColor=white" alt="GitHub"></a> <a href="LICENSE"><img src="https://img.shields.io/badge/License-MIT-green?style=flat&labelColor=555" alt="License MIT"></a> <img src="https://img.shields.io/badge/⚡_Fully_Async-yellow?style=flat&labelColor=555" alt="Fully Async" /> <img src="https://img.shields.io/badge/☁️_No_GPU_Cluster-blue?style=flat&labelColor=555" alt="No GPU Cluster" /> <img src="https://img.shields.io/badge/🛠️_Skill_Evolution-orange?style=flat&labelColor=555" alt="Skill Evolution" /> <img src="https://img.shields.io/badge/🚀_One--Click_Deploy-green?style=flat&labelColor=555" alt="One-Click Deploy" /> </p> [🇨🇳 中文](./assets/README_ZH.md) • [🇯🇵 日本語](./assets/README_JA.md) • [🇰🇷 한국어](./assets/README_KO.md) • [🇫🇷 Français](./assets/README_FR.md) • [🇩🇪 Deutsch](./assets/README_DE.md) • [🇪🇸 Español](./assets/README_ES.md) • [🇧🇷 Português](./assets/README_PT.md) • [🇷🇺 Русский](./assets/README_RU.md) • [🇮🇹 Italiano](./assets/README_IT.md) • [🇻🇳 Tiếng Việt](./assets/README_VI.md) • [🇦🇪 العربية](./assets/README_AR.md) • [🇮🇳 हिन्दी](./assets/README_HI.md) <br/> [Overview](#-overview) • [Quick Start](#-

Topics

Explore more

Data from GitHub. Synced on 2026-06-17