← Back to Leaderboard
Openrlhf
An Easy-to-use, Scalable and High-performance Agentic RL Framework based on Ray (PPO & DAPO & REINFORCE++ & VLM & TIS & vLLM & Ray & Async RL)
⭐
9.5K
Stars
🍴
941
Forks
👥
86
Contributors
💚
53
Health Score
Star History
Not enough data for chart
Health Score Breakdown
Star Momentum
0
Commit Frequency
21
Issue Health
40
Contributors
100
Release Cadence
80
Documentation
100
Community Signal
100
Project Info
- Language
- Python
- License
- Apache-2.0
- Last Commit
- 5d ago
- Last Release
- v0.10.3 (8d ago)
- Open Issues
- 329
- Bus Factor
- 8
- Commits/Week
- 4.2
- Avg Issue Close
- 21.3 days
large-language-modelsproximal-policy-optimizationraylibreinforcement-learningreinforcement-learning-from-human-feedbacktransformersvisual-language-modelsvllm
Project Badge
Embed a live health badge in a README or docs page.
[](https://www.ai-tools-scout.com/projects/openrlhf)Compare Openrlhf
See how this project stacks up against other agent tools.
Weekly AI open-source movers
Get the fastest-growing projects, useful MCP servers, and technical reads in one weekly email.