MetaClaw Evolving Agent Skill by [ara.so](https://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 Quick Start After metaclaw start , a local OpenAI compatible proxy is running. Point your client (OpenClaw or any OpenAI SDK consumer) at http://localhost:<port instead of the upstream LLM endpoint. Configuration metaclaw setup writes a config file (default: ~/.metaclaw/config.yaml ). You can also edit it directly: Environment Variables Operating Modes Mode Command GPU Required Description skills only metaclaw start mode skills only No Proxy + skills injection + auto summarization rl metaclaw start mode rl Via API Skills + GRPO training when batch fills madmax metaclaw start Via API Skills + RL + scheduler (trains only during idle/sleep/meetings) Python API Programmatic startup Manual skill injection Intercepting and recording conversations Triggering RL training manually Reward modeling Skills Lifecycle Integration: OpenAI SDK as Client Point any OpenAI SDK client at the MetaClaw proxy: Skills are injected transparently — the client code does not change. Scheduler (MadMax Mode) The scheduler ensures RL weight updates never interrupt active use: Google Calendar Setup Support/Query Set Separation MetaClaw separates experience into support and query sets to prevent stale rewards from polluting updates: RL Backends Tinker (default) MinT Auto detection Troubleshooting Proxy not reachable after metaclaw start Check port conflicts: lsof i :8080 Change proxy.port in config and restart rl mode: "No training backend available" 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 Skills not persisting between sessions Confirm skills.summarize after session: true in config Check write permissions on ~/.metaclaw/skills/ Run metaclaw skills list to inspect stored skills Madmax mode never trains Verify scheduler.sleep hours covers your timezone's night Lower scheduler.idle timeout minutes for testing (e.g., 1 ) Check scheduler logs: ~/.metaclaw/logs/scheduler.log Google Calendar integration fails Re run OAuth flow: delete ~/.metaclaw/token.json and restart Ensure Calendar API is enabled in your Google Cloud project OPD teacher distillation errors Only supported with rl.backend: tinker Requires a separate teacher model endpoint in config: CLI Reference

metaclaw-evolving-agent