by areal-project · Agent Tool · ★ 5.2k
AReaL: A Large-Scale Asynchronous Reinforcement Learning System WeChat (微信) Group | AReaL is a reinforcement learning (RL) infrastructure designed to bridge foundation model training with modern agent-based applications. It was originally developed by researchers and engineers from Tsinghua IIIS and the AReaL Team at Ant Group. Built on a fully asynchronous RL training paradigm, AReaL is optimized for efficiency and scalability, making it particularly well-suited for training large-scale reasoning and agentic models.
| Stars | 5,204 |
| Forks | 501 |
| Language | Python |
| Category | Agent Tool |
| License | Apache-2.0 |
| Quality Score | 49.022/100 |
| Open Issues | 75 |
| Last Updated | 2026-05-22 |
| Created | 2025-02-24 |
| Platforms | python |
| Est. Tokens | ~19261k |
These tools work well together with AReaL for enhanced workflows:
Explore other popular agent tool tools:
AReaL is The RL Bridge for LLM-based Agent Applications. Made Simple & Flexible.. It is categorized as a Agent Tool with 5.2k GitHub stars.
AReaL is primarily written in Python. It covers topics such as agent, llm, llm-agent.
You can find installation instructions and usage details in the AReaL GitHub repository at github.com/areal-project/AReaL. The project has 5.2k stars and 501 forks, indicating an active community.
AReaL is released under the Apache-2.0 license, making it free to use and modify according to the license terms.