open-thought/reasoning-gym

[NeurIPS 2025 Spotlight] Reasoning Environments for Reinforcement Learning with Verifiable Rewards

gymlarge-language-modelsreinforcement-learning

License & maintenance

Apache-2.0 is a permissive license: free to use commercially with attribution.

Last code push 6 months ago.

	Repository	Stars	Language	License	Activity
1	langflow-ai/langflowLangflow is a powerful tool for building and deploying AI-powered agents and workflows.	★ 155.8k	Python	MIT	Active
2	hiyouga/LlamaFactoryUnified Efficient Fine-Tuning of 100+ LLMs & VLMs (ACL 2024)	★ 75.6k	Python	Apache-2.0	Active
3	binary-husky/gpt_academic为GPT/GLM等LLM大语言模型提供实用化交互接口，特别优化论文阅读/润色/写作体验，模块化设计，支持自定义快捷按钮&函数插件，支持Python和C++等项目剖析&自译解功能，PDF/LaTex论文翻译&总结功能，支持并行问询多种LLM模型，支持chatglm3等本地模型。接入	★ 71.5k	Python	GPL-3.0	Slowing
4	FlowiseAI/FlowiseBuild AI Agents, Visually	★ 55.5k	TypeScript	Other	Archived
5	bojieli/ai-agent-book《深入理解 AI Agent：设计原理与工程实践》（李博杰著）开源主仓库：全书正文、编译版 PDF 与按章配套代码	★ 54.8k	Python	Apache-2.0	Active
6	ray-project/rayRay is an AI compute engine. Ray consists of a core distributed runtime and a set of AI Libraries for accelerating ML workloads.	★ 44.1k	Python	Apache-2.0	Active
7	HKUDS/LightRAG[EMNLP2025] LightRAG: Simple and Fast Retrieval-Augmented Generation	★ 40.2k	Python	MIT	Active
8	google/langextractA Python library for extracting structured information from unstructured text using LLMs with precise source grounding and interactive visua	★ 39k	Python	Apache-2.0	Active