OpenRLHF

An Easy-to-use, Scalable and High-performance Agentic RL Framework based on Ray (PPO & DAPO & REINFORCE++ & VLM & TIS & vLLM & Ray & Async RL)

OpenRLHF/OpenRLHF

View on GitHub ↗

An Easy-to-use, Scalable and High-performance Agentic RL Framework based on Ray (PPO & DAPO & REINFORCE++ & VLM & TIS & vLLM & Ray & Async RL)

OpenRLHF grew +0.6% in the last 30 days, ranks 1st of 92 in Reinforcement Learning / RLHF, actively maintained, last commit 11 days ago.

Star trajectory

134 days tracked
2026-07-0210.2k stars today2026-11-14
Momentum

+0.6% in 30d, below the Reinforcement Learning / RLHF median of +0.8%.

Maintenance

Last commit 11 days ago, fresher than the median of 34d.

How it compares in Reinforcement Learning / RLHF

OpenRLHF
10.2k
stars
+0.6% 30d
commit 11 days ago
Reinforcement Learning / RLHF median
290
stars
+0.8% 30d
commit ~34d ago
Category leader
10.2k
stars
- 30d
you lead

Ranked 1st of 92 by stars.

Ranked by shared tags, then keywords, then stars
  1. Democratizing Reinforcement Learning for LLMs

    +33 (+0.6%) in 30d · Committed 28d ago · Python · Apache-2.0

    Shares Reinforcement Learning / RLHF, Training Toolkits

  2. Halo is an open-source framework built by White Circle for training large language and multimodal models

    +36 (+4.4%) in 30d · Committed today · Python · Other license

    Shares Training Toolkits, Reinforcement Learning / RLHF

  3. An Asynchronous Reinforcement Learning Engine for Omni-Modal Post-Training at Scale

    +31 (+4.8%) in 30d · Committed today · Python · Apache-2.0

    Shares Reinforcement Learning / RLHF, Training Toolkits

  4. Single File, Single GPU, From Scratch, Efficient, Full Parameter Tuning library for "RL for LLMs"

    +7 (+1.1%) in 30d · Committed 402d ago · Jupyter Notebook · MIT

    Shares Training Toolkits, Reinforcement Learning / RLHF

  5. AxisRL is an agentic RL post-training framework built on SGLang rollout, Megatron training, and real-world…

    +0 (+0.0%) in 30d · Committed 102d ago · Python · Apache-2.0

    Shares Reinforcement Learning / RLHF, Training Toolkits

  6. LightRFT: Light, Efficient, Omni-modal & Reward-model Driven Reinforcement Fine-Tuning Framework

    -17 (-4.3%) in 30d · Committed 67d ago · Python · Apache-2.0

    Shares Training Toolkits, Reinforcement Learning / RLHF

  7. Super-Efficient RLHF Training of LLMs with Parameter Reallocation

    +0 (+0.0%) in 30d · Committed 569d ago · Python · Apache-2.0

    Shares Reinforcement Learning / RLHF, Training Toolkits

  8. MiroRL is an MCP-first reinforcement learning framework for deep research agent.

    -1 (-0.4%) in 30d · Committed 443d ago · Python · Apache-2.0

    Shares Reinforcement Learning / RLHF, Training Toolkits

  9. Cutting-edge platform for LLM agent tuning. Deliver RL tuning with flexibility, reliability, speed…

    +2 (+0.8%) in 30d · Committed 80d ago · Python · Apache-2.0

    Shares Reinforcement Learning / RLHF, Training Toolkits

  10. Comprehensive toolkit for Reinforcement Learning from Human Feedback (RLHF) training, featuring instruction…

    +1 (+0.5%) in 30d · Committed 22d ago · Python

    Shares Training Toolkits, Reinforcement Learning / RLHF

Language
Python
License
Apache License 2.0
Contributors
97
Forks
1.1k
Watchers
52
Open issues
317
Releases
110
Created
2023-07-30
Stars this week
+8

You've seen where OpenRLHF stands today.

Get the moves before everyone else: the 5 Reinforcement Learning / RLHF repos climbing fastest, every Tuesday.

Free weekly digest. Double opt-in, unsubscribe anytime.

Maintain OpenRLHF?

Claim this page to add your own call-to-action.

Claim this page