Open Source
OpenRLHF
An Easy-to-use, Scalable and High-performance Agentic RL Framework based on Ray (PPO & DAPO & REINFORCE++ & VLM & TIS & vLLM & Ray & Async RL)
Our verdict
We have not reviewed OpenRLHF yet
No one at Enterprise DNA has checked this listing against its sources. The description comes from public listings gathered automatically. Any fact below shows where it came from and when it was last checked.
From the listing
About OpenRLHF
OpenRLHF is an open-source framework for agentic reinforcement learning with language and vision-language models. It is built on Ray for distributed scaling and supports multiple RL algorithms including PPO, DAPO, and REINFORCE++. The framework integrates with vLLM for efficient inference and enables asynchronous RL training.
Best for
Developers building large-scale RL training systems for language and vision-language models
Use cases
- Training LLMs with reinforcement learning from human feedback (RLHF) at scale
- Implementing agentic RL workflows that require distributed compute and async execution
- Experimenting with policy gradient methods like PPO or REINFORCE++ on multimodal models
Notes
9,583 stars on GitHub. Last updated 2026-05-28. Licensed Apache-2.0.
Pros
- Uses Ray for seamless distributed computing across clusters
- Supports a broad range of modern RL algorithms out of the box
- Integrates with vLLM for fast LLM inference during training
Cons
- Requires familiarity with Ray and distributed system concepts
- Community-maintained, so support and documentation are limited
- Steep learning curve for developers new to RL frameworks
Key facts
What we have checked
- Latest version
- 0.11.2 (released 14 Sept 2026)
- GitHub stars
- 10,045
Each value shows when we last confirmed it and where it came from. Values we have not confirmed are left out, never guessed.
Stars and usage
How OpenRLHF is growing
9,583 to 10,045
Alternatives
Alternatives to OpenRLHF
| Record | Type | How we know | Checked |
|---|---|---|---|
| AxolotlAlternative to this | Open source | Named in the listing | Not dated |
| ROLLAlternative to this | Open source | Named in the listing | Not dated |
| TRLAlternative to this | Open source | Named in the listing | Not dated |
| veRLAlternative to this | Open source | Named in the listing | Not dated |
| open-r1This is an alternative to it | Open source | Named in the listing | Not dated |
| TinyZeroThis is an alternative to it | Open source | Named in the listing | Not dated |
Compare
Compare OpenRLHF side by side
Sources
Where this comes from
- GitHubOfficial
- github api via nightly crawl, recovered from git history 20e874270887c1008f860ee0198e461a23c9e438Registry
A source shows what was published when we checked it. It does not certify security, performance or a working installation. Read our method.
Changelog
What changed
Released 0.11.2
Released 0.11.1
Released 0.11.0
Released 0.10.4
Released 0.10.3
Released 0.10.2
Released 0.10.1.post2
Released 0.10.1
Released 0.10.0
Released 0.9.10
Open-source & AI alternatives
Swap-in tools that solve the same job. Weigh the trade-offs before you commit.
Axolotl
Community
Go ahead and axolotl questions
ROLL
Community
An Efficient and User-Friendly Scaling Library for Reinforcement Learning with Large Language Models
TRL
Community
We’re on a journey to advance and democratize artificial intelligence through open source and open science.
veRL
Community
verl/HybridFlow: A Flexible and Efficient RL Post-Training Framework
Pairs with
Other entries in the index that connect to this one. Click through to see the chain.
Get the free Developer’s Field Guide
A 27-page field guide to the AI coding workflow with Claude. Claude Code, MCP servers, the prompt patterns that work, and what to delegate. Free.
Enter your work email. We send it straight over, plus a few short notes worth knowing. Unsubscribe any time.