aiming-lab/MetaClaw
#370 of 783 by Stars among GitHub repos
🦞 Just talk to your agent — it learns and EVOLVES 🧬.
About
Inspired by how brains learn. Meta-learn and evolve your 🦞 from every conversation in the wild. No GPU required.
MetaClaw is an agent that meta-learns and evolves in the wild. Just talk to your agent as you normally would — MetaClaw turns every live conversation into a learning signal, enabling the agent to continuously improve through real-world deployment rather than offline training alone.
Under the hood, it places your model behind a proxy that intercepts interactions from your personal agent (OpenClaw, CoPaw, IronClaw, PicoClaw, ZeroClaw, NanoClaw, NemoClaw, or any OpenAI-compatible client), injects relevant skills at each turn, and meta-learns from accumulated experience. For…
Excerpted from github.com/aiming-lab/MetaClaw
Latest metrics
| Stars | 3.5k | 2026-07-16 |
|---|---|---|
| Forks | 446 | 2026-07-16 |
| Commits | 189 | 2026-07-16 |
| Releases | 8 | 2026-07-16 |
| Watchers | 24 | 2026-07-16 |
| Open issues | 6 | 2026-07-16 |
| Open PRs | 10 | 2026-07-16 |