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.