RAGEN
RAGEN leverages reinforcement learning to train LLM reasoning agents in interactive, stochastic environments.
RAGEN scores 5.1/10 (Solid) in Fine-Tuning.
Language Python License MIT Stars 2.7k★ Type library Self-host Yes Repo RAGEN-AI/RAGEN Homepage https://ragen-ai.github.io
Quality
Solid 5.1
Adoption 36
Activity 39
Maturity 84
Community 35
Capability 50
Show the math
Overall 5.1/10
value = 5.1/10
score = value
Adoption 4.2/10
value = 35.9/100
score = 1 + 9 * value / 100
Activity 4.5/10
value = 39.1/100
score = 1 + 9 * value / 100
Maturity 8.5/10
value = 83.7/100
score = 1 + 9 * value / 100
Community 4.1/10
value = 34.9/100
score = 1 + 9 * value / 100
Capability 5.5/10
value = 50/100
score = 1 + 9 * value / 100
Key metrics
2.7k★ GitHub stars
10/90d Recent commits
2 devs/90d Recent contributors
1.4y Project age
3mo ago Last commit
Gotchas
No gotchas documented yet. Contribute one if you know a constraint we missed.
Labels
- Self-hosted
Self-hosted
You deploy and operate it yourself; there is no hosted option here.
agent-rl reasoning multi-turn environments research