AReaL

Repository facts

Stars

5,841

Forks

630

Open issues and pull requests

139

Primary language

Python

License

Apache License 2.0 (Apache-2.0)

Owner

areal-project · Organization

Created

Feb 24, 2025

Last push

Oct 16, 2026

Topics

• agent
• llm
• llm-agent
• llm-reasoning
• machine-learning-systems
• mlsys
• reinforcement-learning
• rl

Rank #1,391 of 9,507 in AI on GitHub, by stars. Data from the GitHub API, fetched Oct 18, 2026; star counts change daily. Stars measure popularity, not quality or safety, and a listing is not an endorsement. How this list is made

Related projects

Projects that share this one’s GitHub topics.

• 5,850

  Rank 5,850: JudgmentLabs/judgeval

  The Continuous-Improvement Stack for Agents. Our environment data and evals power agent improvement and monitoring.

  1,068 starsPythonApache-2.0Last push Oct 18, 2026

• 6,931

  Rank 6,931: Purewhiter/mobilegym

  [EMNLP 2026] MobileGym: A Verifiable and Highly Parallel Simulation Platform for Mobile GUI Agent Research · 浏览器里运行的安卓模拟器 · Browser-hosted Android Simulator · Verifiable Evaluatio…

  825 starsPythonApache-2.0Last push Oct 9, 2026

• 8,053

  Rank 8,053: Gen-Verse/Open-AgentRL

  RLAnything (ICML 2026) & AutoTool (ICML 2026), DemyAgent: Open-Source RL for LLMs and Agentic Scenarios

  655 starsPythonApache-2.0Last push Jun 12, 2026

• 3,703

  Rank 3,703: FareedKhan-dev/all-rl-algorithms

  Implementation of all RL algorithms in a simpler way

  1,972 starsJupyter NotebookMITLast push Aug 29, 2025

• 750

  Rank 750: OpenPipe/ART

  Agent Reinforcement Trainer: train multi-step agents for real-world tasks using GRPO. Give your agents on-the-job training. Reinforcement learning for Qwen3.6, GPT-OSS, Llama, and…

  10,807 starsPythonApache-2.0Last push Oct 15, 2026

• 1,546

  Rank 1,546: hiyouga/EasyR1

  EasyR1: An Efficient, Scalable, Multi-Modality RL Training Framework based on veRL

  5,198 starsPythonApache-2.0Last push Sep 19, 2026