OpenRLHF alternatives

The 12 products closest to OpenRLHF in what they do and who they're for, best match first.

RLinf — Scalable open-source framework supporting real-world robots and simulators. (Code, Free)
rLLM — Enables reinforcement learning training for AI agents with minimal code changes. (Code, Free)
ART — Enhances LLM agent performance and reliability using reinforcement learning techniques. (Code, Free)
Agent Lightning — Train existing artificial intelligence agents with reinforcement learning and zero code changes. (Code, Free)
OpenVLHarness — Lifts six multimodal model backbones by 9.7 to 12.6 points across 22 benchmarks. (Research, Free)
AReaL — Bridges foundation model training with modern agent-based applications. (Code, Free)
Unsloth — Runs and trains models locally with lower memory usage. (Code, Free)
AirLLM — Runs massive 70B+ parameter models on small 4GB consumer GPUs. (Code, Free)
XTuner — High-efficiency training for 200B+ scale MoE models without expert parallelism. (Code, Free)
EasyR1 — It supports vision-language models and high-performance RL training algorithms. (Code, Free)
Karotte — It runs tasks in isolated virtual machines for safety and consistency. (Research, Free)
Stable Baselines3 — Provides reliable, standard PyTorch implementations for reinforcement learning. (Code, Free)