MetaClaw is a self-evolving agent framework by AIMING Lab (UNC-Chapel Hill) that turns live conversations into continuous training data, improving accuracy without GPU clusters.

How does MetaClaw improve agent performance?

It uses SkillRL (reinforcement learning from skills) to intercept interactions and inject relevant skills via an OpenAI-compatible proxy, advancing Kimi-K2.5 accuracy from 21.4% to 40.6%.

What is MetaClaw's Contexture layer?

Added in v0.4.0, Contexture persists cross-session memory for users and projects with adaptive memory policy and background consolidation.

How many GitHub stars does MetaClaw have?

MetaClaw has approximately 3,200 GitHub stars and 322 forks as of April 2026.

Is MetaClaw compatible with OpenClaw?

MetaClaw is built on top of OpenClaw's architecture and extends it with self-evolving capabilities, making it a complementary framework.

← Back to dashboard

clawsmith.com/signal/metaclaw-aiming-lab-self-evolving-agent

🔥 HypeUnknownAgent FrameworkLive

MetaClaw v0.4.0: self-evolving agent framework that learns from live conversations (3.2K stars)

AIMING Lab's MetaClaw turns live conversations into continuous training data without GPU clusters. Advances Kimi-K2.5 accuracy from 21.4% to 40.6%. v0.4.0 adds Contexture layer for cross-session memory persistence.

Product Idea from this Signal

A feedback loop system that teaches OpenClaw agents to improve their own skills and rules from real conversation corrections

3.5k ▲

Every OpenClaw user repeats the same corrections to their agent dozens of times. 'Stop using em dashes.' 'Always run tests first.' 'Never suggest manual steps.' MetaClaw showed that self-evolving agents are possible with 3.2K stars, but it requires a custom framework. This tool plugs into any existing OpenClaw or Claude Code setup, watches your conversations for corrections and feedback patterns, and automatically updates CLAUDE.md, skills, and agent rules so the agent never makes the same mistake twice.

CLIDEVTOOLAI-AGENTSOPEN-SOURCE

UnderservedView Opportunity →