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

Stars5,503
Forks597
LanguagePython
Last pushed2026-05-23
Last synced2026-06-17
View on GitHub

Repository

OwnerGen-Verse
RepositoryOpenClaw-RL
Full nameGen-Verse/OpenClaw-RL
Repo ID1,167,576,951

Install this Skill

git clone https://github.com/Gen-Verse/OpenClaw-RL.git

Registry

Typeopenclaw_skill
Quality score75/100
Verificationreadme_parsed
Last verified2026-05-29
Platforms
OpenClaw
Capabilities
pdfmemorysearchimagevideoterminalasynccodinggrpogui-application
Detected files
README.mdrequirements.txt
Config keys
SGLANG_API_KEY

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.

Chinese description

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

Topics

Explore more

Data from GitHub. Synced on 2026-06-17