Metaclaw Evolving Agent

If you want your AI agent to actually get better from the conversations it has, this is the infrastructure for it. MetaClaw sits as an OpenAI-compatible proxy, intercepts requests, injects learned skills into the system prompt, and runs GRPO reinforcement learning on real interactions. The clever bit is madmax mode: it defers GPU-heavy weight updates to your sleep hours, idle time, or calendar meetings so training never blocks your workflow. Supports multiple LLM providers (Kimi, Qwen, Claude, Gemini), works with or without GPU depending on mode, and includes skill summarization that extracts reusable patterns from sessions. It's meta-learning that runs in the background without getting in your way.

skills.sh installs: 1.4K
GitHub stars: 61
last updated: Jul 14, 2026

View on GitHub

Install

$ npx -y skills add aradotso/trending-skills --skill metaclaw-evolving-agent --agent claude-code

Installs into .claude/skills of the current project.

Files

MetaClaw Evolving Agent

Skill by ara.so — Daily 2026 Skills collection

MetaClaw is an OpenAI-compatible proxy agent that intercepts conversations, injects learned skills, and continuously improves itself through real-world interactions. It supports three modes: lightweight skills injection, immediate RL training, and a smart "madmax" scheduler that defers weight updates to idle/sleep windows.

Installation

# Minimal — skills injection only, no GPU required
pip install -e .

# Full RL training support (torch, transformers, tinker)
pip install -e ".[rl]"

# Skill evolution via LLM summarization
pip install -e ".[evolve]"

# Google Calendar scheduler for madmax mode
pip install -e ".[scheduler]"

# Recommended: everything
pip install -e ".[rl,evolve,scheduler]"

Quick Start

# One-time interactive config wizard
metaclaw setup

# Start in default madmax mode (skills + RL + smart scheduler)
metaclaw start

# Skills only — no GPU, no Tinker needed
metaclaw start --mode skills_only

# RL mode — trains immediately when batch is full
metaclaw start --mode rl

SKILL.md on GitHub