mll-lab-nu/RAGEN

RAGEN

✅ Recently maintained

Agent RL framework for LLM agents: multi-turn reinforcement learning with StarPO and reasoning-collapse diagnostics

2,835Stars
227Forks
+57-day stars

Python · MIT · Last push 2026-10-28

Official repository & installation ↗
agent-rlagentic-aillm-agentsreinforcement-learningrl-frameworkmulti-turn-rl

GitValue · Value evidence

Unscored · Evidence coverage 0%

Provisional rubric; documentation and runtime testing are separate. Missing evidence does not imply low value.

Star history

2025-09-292026-11-03
View historical data
DateStars
2026-10-052,811
2026-10-062,811
2026-10-072,815
2026-10-082,817
2026-10-092,817
2026-10-102,817
2026-10-112,820
2026-10-122,822
2026-10-132,823
2026-10-142,823
2026-10-152,823
2026-10-162,823
2026-10-172,823
2026-10-182,823
2026-10-192,823
2026-10-202,824
2026-10-212,825
2026-10-222,825
2026-10-232,826
2026-10-242,827
2026-10-252,829
2026-10-262,830
2026-10-272,831
2026-10-282,831
2026-10-292,832
2026-10-302,832
2026-10-312,832
2026-11-012,832
2026-11-022,833
2026-11-032,835

Get the project

git clone https://github.com/mll-lab-nu/RAGEN.git

Cloning downloads the source. For dependencies and installation, follow the project README.

Related projects & alternative candidates

Related domains do not imply feature parity. Review official documentation and licenses.

agenticSeek

Fully Local Manus AI. No APIs, No $200 monthly bills. Enjoy an autonomous agent that thinks, browses the web, and code for the sole cost of electricity.

★ 27,606hindsight

A memory layer that lets AI agents remember and learn from past experience.

★ 58,167nanobot

Lightweight swarm intelligence experimental platform for micro-agents.

★ 49,776