open-thought/reasoning-gym
[NeurIPS 2025 Spotlight] Reasoning Environments for Reinforcement Learning with Verifiable Rewards
- Stars
- 1.5k
- Forks
- 134
- Open issues
- 7
- Last push
- 6mo ago
About reasoning-gym
reasoning-gym is a free, open-source LLM chat app by open-thought, written mainly in Python. [NeurIPS 2025 Spotlight] Reasoning Environments for Reinforcement Learning with Verifiable Rewards. It has 1.5k GitHub stars and 134 forks, and was last updated 6mo ago. It's released under the Apache-2.0 license, a standard open-source license.
- License
- Apache-2.0
- Language
- Python
- Stars
- 1,536
- Last update
- 6mo ago
- Runs on Mac
- Not stated
- GPU
- Not stated
- Paid API key
- Not stated
- Self-hostable
- Yes
Similar free tools
Hands-On-Large-Language-Models30k stars · Official code repo for the O'Reilly Book - "Hands-On Large Language Models"
FinGPT21k stars · FinGPT: Open-Source Financial Large Language Models! Revolutionize 🔥 We release the trained model on HuggingFace.
Qwen22k stars · The official repo of Qwen (通义千问) chat & pretrained large language model proposed by Alibaba Cloud.
OpenRLHF10k stars · An Easy-to-use, Scalable and High-performance Agentic RL Framework based on Ray (PPO & DAPO & REINFORCE++ & VLM & TIS & vLLM & Ray & Async RL)
HRM13k stars · Hierarchical Reasoning Model Official Release
MOSS12k stars · An open-source, tool-augmented conversational language model from Fudan University
reasoning-gym FAQ
Is reasoning-gym free?
Yes. reasoning-gym is open source and free to use. It's released under the Apache-2.0 license, a standard open-source license.
Does reasoning-gym run on a Mac?
The project doesn't say. Check its installation guide before you start.
Does reasoning-gym need a GPU?
The project doesn't state hardware needs. AI models generally run much faster with a GPU.
Is reasoning-gym still maintained?
It was last updated 6mo ago. Check recent issues on GitHub to judge how active it is.
What are alternatives to reasoning-gym?
Similar free, open-source tools include Hands-On-Large-Language-Models, FinGPT, Qwen, OpenRLHF.