Claude Skill
Gen-Verse/OpenClaw-RL
OpenClaw-RL is a Python framework that trains agents via conversation, using RL and on-policy distillation to personalize Claude Skill. Supports GRPO, RLHF, async coding, and GUI.
Overview
Repository
Install this Skill
git clone https://github.com/Gen-Verse/OpenClaw-RL.gitRegistry
Summary
OpenClaw-RL is a Python-based framework that lets you train any agent simply by talking, using reinforcement learning and on-policy distillation to personalize Claude Skill without manual coding.
OpenClaw-RL:通过对话轻松个性化你的Claude Skill
Key features
- Train agents via natural language conversation
- On-policy distillation for efficient skill learning
- Integrated GRPO and RLHF support
- Async coding and memory systems
- GUI application for easy interaction
- SGLang and Slime integration for scalable training
Use cases
- Personalizing Claude Skill through conversation
- Rapid prototyping of RL-based agents
- Educational demonstrations of reinforcement learning
- Building custom AI assistants with minimal code
- Research in on-policy distillation and skill learning
README excerpt
<div align="center"> <h1 align="center"> <img src="assets/spacer.png" alt="" width="23" height="40" align="absmiddle" /> OpenClaw-RL<!-- --><sup> <img src="assets/clawistool.png" alt="Claw-RL logo" width="23" height="40" align="absmiddle" /> <sup> </h1> <p><b>Empowering OpenClaw with RL — Train a personalized agent simply by talking to it.</b></p> <p><b>Scalable RL in real-world settings — Agentic RL for terminal, GUI, SWE, and tool-call settings.</b></p> </div> <p align="center"> <img src="https://img.shields.io/badge/⚡_Fully_Async-yellow?style=for-the-badge" alt="Fully Async" /> <img src="https://img.shields.io/badge/💰_Zero_API_or_Zero_GPU-blue?style=for-the-badge" alt="Zero API or Zero GPU" /> <img src="https://img.shields.io/badge/🤖_Personalized-success?style=for-the-badge" alt="Personalized" /> <img src="https://img.shields.io/badge/🛠️_Auto_Optimization-orange?style=for-the-badge" alt="Auto" /> <img src="https://img.shields.io/badge/💬_Language_Feedback-purple?style=for-the-badge" alt="Language Feedback" /> <img src="https://img.shields.io/badge/🧠_Hybrid_RL-red?style=for-the-badge" alt="Hybrid RL" /> <img src="https://img.shields.io/badge/🌍_Real_World_Agentic_RL-green?style=for-the-badge" alt="General Agentic RL" /> <br><br> <a href="https://arxiv.org/abs/2603.10165"><img src="https://img.shields.io/badge/📄_Tech_Report-red?style=flat-square" alt="Tech Report" /></a> <a href="https://yinjjiew.github.io/projects/openclawrl1"><img src="https://img.shields.io/badge/Blog-Page-blue?style=flat-square" alt="OpenClaw-RL Blog" /></a> <a href="https://openclaw.ai"><img src="https://img.shields.io/badge/OpenClaw-Plugin-orange?style=flat-square" alt="OpenClaw Plugin" /></a> <a href="https://github.com/THUDM/slime"><img src="http