MetaClaw fork: self-hosted GPU training (GRPO + LoRA + vLLM), per-agent skill isolation, multi-agent mode routing, training engine bug fixes. Train your AI agent on your own A100s. No cloud dependency.
reinforcement-learning multi-agent lora meta-learning peft fastapi gpu-training ai-agent llm vllm qwen grpo agent-isolation openclaw metaclaw skill-evolution per-agent-skills self-hosted-training
-
Updated
Apr 2, 2026 - Python