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. After metaclaw start , a local OpenAI-compatible proxy is running. Point your client (OpenClaw or any OpenAI SDK consumer) at instead of the upstream LLM endpoint. metaclaw setup writes a config file (default: ~/.metaclaw/config.yaml ). You can also edit it directly: Point any OpenAI SDK client at the MetaClaw proxy: Skills are injected transparently — the client code does not change. The scheduler ensures RL weight updates never interrupt active use: MetaClaw separates experience into support and query sets to prevent stale rewards from polluting updates: Proxy not reachable after metaclaw start rl mode: "No training backend available" Skills not persisting between sessions Madmax mode never trains Google Calendar integration fails OPD teacher distillation errors - Check port conflicts: lsof -i :8080 - Change proxy.port in config and restart - Ensure pip install -e ".[rl]" completed successfully - Verify METACLAW_TINKER_API_KEY or METACLAW_MINT_API_KEY is set - Try rl.backend: tinker explicitly instead of auto...