OpenRLHF

license

Apache-2.0(OSI)

source

public(OpenRLHF/OpenRLHF)

core features withheld

no

Apache-2.0, an OSI license, with the full source public and no proprietary tier. The license text, the README and the repository page all agree, and nothing is held back from the published code.

• https://github.com/OpenRLHF/OpenRLHF recorded 2026-08-09

  Repo page's embedded data records "license":{"spdxId":"Apache-2.0","name":"Apache License 2.0"} and "isArchived":false, with a top-level tree containing the openrlhf package directory itself (plus dockerfile, docs, examples, tests) -- the repo is the shipped code, not a stand-in for it.

• https://raw.githubusercontent.com/OpenRLHF/OpenRLHF/main/LICENSE recorded 2026-09-09

  The unmodified Apache License, Version 2.0 template -- opens "Apache License" / "Version 2.0, January 2004" and the standard TERMS AND CONDITIONS, ending with the generic placeholder "Copyright [yyyy] [name of copyright owner]" rather than a custom notice. No altered terms, no NOASSERTION trap.

• https://raw.githubusercontent.com/OpenRLHF/OpenRLHF/main/README.md recorded 2026-09-09

  The Installation section gives "pip install openrlhf" and, for the source route, "git clone https://github.com/OpenRLHF/OpenRLHF.git" followed by "pip install -e ." -- the thing you run builds from this repo. No enterprise, pricing, hosted-service, or paid-tier section appears anywhere in the file.

OpenRLHF's repository lists named adopters -- Google, ByteDance, Tencent, Alibaba, Baidu, China Telecom, Vivo, Allen AI, NexusFlow and Jülich -- rather than publishing a download count. It reads as a specialist RLHF tool used by research and training teams, and that named-adopter list is the basis used here rather than GitHub stars, which measure attention only.

• https://github.com/OpenRLHF/OpenRLHF recorded 2026-08-09

  Repo page reports "stargazerCount":9896 -- attention in the high thousands.

• https://raw.githubusercontent.com/OpenRLHF/OpenRLHF/main/README.md recorded 2026-10-08

  The "Companies and Organizations using OpenRLHF" section still lists Google, ByteDance, Tencent, Alibaba, Baidu, China Telecom, Vivo, Allen AI, NexusFlow, and Jülich Supercomputing Centre (JSC), among others -- the same named adopters the score's note cites, unchanged. No download-count badge or PyPI figure appears anywhere in the file.

Deep, production-grade distributed RLHF: PPO, REINFORCE++, GRPO and RLOO, orchestrated with Ray scheduling, vLLM-accelerated rollout and DeepSpeed, scaling to 70B+ models across many GPUs, with multi-turn agent RL as well. Its method scope is RL-centric rather than full-spectrum, and it does not reach Megatron-LM's frontier scale, so it sits one step below the top.

• https://raw.githubusercontent.com/OpenRLHF/OpenRLHF/main/README.md recorded 2026-10-07

  Architecture section describes Ray separating "the Actor, Reward, Reference, and Critic models across different GPUs, enabling scalable training for models up to", vLLM rollout and DeepSpeed training; the RL algorithms entry lists "PPO, REINFORCE++, GRPO, RLOO", with single-turn and "Multi-Turn Agent" sections. A "New Backend" callout offers Molt as an alternative to DeepSpeed.