+0
Daily
5,746
stars
612
forks
42
watchers
59
prs
64
issues
0
releases
README
OpenClaw-RL
Empowering OpenClaw with RL — Train a personalized agent simply by talking to it.
Scalable RL in real-world settings — Agentic RL for terminal, GUI, SWE, and tool-call settings.
📰 News
- [2026/4/15] 🙌 We sincerely thank Fireworks AI for its generous support of this project, which has enabled more experiments and faster iteration.
- [2026/4/11] ✨ Qwen3.5-4B/9B/27B is supported now, both text and multi-modal!
- [2026/4/4] 👨👦👦 We support optimizing a single model based on feedback from a group of people.
- [2026/3/25] 🙌 We sincerely thank Tinker for its generous support of this project, which has enabled more experiments and faster iteration.
- [2026/3/20] 💻 You can use your own openclaw now, simply install this extension.
- [2026/3/13] ☁️ OpenClaw-RL now supports both local GPU and cloud (Tinker) deployment. Launch with one line of code — Hybrid RL, OPD, and Binary RL all supported!
- [2026/3/12] ⚡ We support LoRA training now!
- [2026/3/10] 📃 We have released our Technical Report! 🏆 Ranked 1 on HuggingFace Daily Papers!
- [2026/3/10] 🔥 Huge updates today! We released a new combination method, along with an interesting evaluation of these OpenClaw-RL methods. Track 2 is released too, featuring scalable RL implementations for general agent settings across terminal, GUI, SWE, and tool-call scenarios. We only focus on real-world settings!
- [2026/3/3] 🙌 Working with the authors of SDFT and SDPO, we have integrated their methods into openclaw-opd. We welcome the integration of novel and effective methods!
- [2026/3/3] 📺 Check out these community tutorial videos on OpenClaw-RL: Video 1 | Video 2
- [2026/2/26] 🔥 We release OpenClaw-RL v1 — a fully asynchronous RL framework for training personalized AI agents from natural conversation feedback.
---
💡 TL;DR
OpenClaw-RL is a fully asynchronous reinforcement learning framework that turns everyday conversations into training signals for personalized AI agents, and supports training general agents with large-scale environment parallelization.
Most RL-for-LLM systems assume centralized, batch-mode training with pre-collected datasets. OpenClaw-RL takes a fundamentally different approach: it wraps your self-hosted model in OpenClaw as an OpenAI-compatible API, intercepts live multi-turn conversations, and continuously optimizes the policy in the background — all without interrupting your usage.
Highlights: Fully async 4-component loop · Self-hosted & private · Zero manual labeling · Three learning paradigms (Binary RL / OPD / Combine) · Personal + General agent support
🌈 Features
Fully Asynchronous 4-Component Architecture
OpenClaw-RL decouples agent serving, rollout collection, PRM/judge evaluation, and policy training into independent async loops. None of them block one another: the model continues serving requests while training runs in the background, and judging happens concurrently with newTop issues
#69train/train_rollout_logprob_abs_diff 值过大12 comments · 2026-04-09#88rollout阶段很慢10 comments · 2026-04-16#68训练效果问题9 comments · 2026-04-09#113关于 Personal Agent GSM8K 实验中 Student/Teacher 场景训练方式8 comments · 2026-05-11#7Why teacher top-k8 comments · 2026-03-10#63No module named 'megatron.bridge.models.conversion'7 comments · 2026-04-04#62tool call training question7 comments · 2026-04-03#48Absence of evaluation tools for Personal Agent Track scores7 comments · 2026-03-26