AReaL
The RL Bridge for LLM-based Agent Applications. Made Simple & Flexible.
AReaL scores 6.7/10 (Solid) in Fine-Tuning.
Language Python License Apache-2.0 Stars 5.5k★ Type heavyweight Self-host Yes Repo inclusionAI/AReaL Homepage https://github.com/inclusionAI/AReaL
Quality
Solid 6.7
Adoption 43
Activity 80
Maturity 85
Community 44
Capability 50
Show the math
Overall 6.7/10
value = 6.7/10
score = value
Adoption 4.9/10
value = 43.4/100
score = 1 + 9 * value / 100
Activity 8.2/10
value = 79.5/100
score = 1 + 9 * value / 100
Maturity 8.7/10
value = 85.1/100
score = 1 + 9 * value / 100
Community 5/10
value = 44/100
score = 1 + 9 * value / 100
Capability 5.5/10
value = 50/100
score = 1 + 9 * value / 100
Key metrics
5.5k★ GitHub stars
166/90d Recent commits
29 devs/90d Recent contributors
1.4y Project age
active 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.
- Heavyweight
Heavyweight
Resource-heavy to run (GPU, large memory, or multi-service stack).
async-rl agentic post-training distributed reasoning