rLLM
Agentica's framework for post-training language agents with RL, used to train reasoning and coding agents like DeepCoder.
rLLM scores 3/10 (Emerging) in Fine-Tuning.
Language Jupyter Notebook License Apache-2.0 Stars 400★ Type library Self-host Yes Repo agentica-project/rllm Homepage https://github.com/agentica-project/rllm
Quality
Emerging 3.0
Adoption 15
Activity 5
Maturity 61
Community 14
Capability 50
Show the math
Overall 3/10
value = 3/10
score = value
Adoption 2.4/10
value = 15.1/100
score = 1 + 9 * value / 100
Activity 1.4/10
value = 5/100
score = 1 + 9 * value / 100
Maturity 6.5/10
value = 61.1/100
score = 1 + 9 * value / 100
Community 2.2/10
value = 13.6/100
score = 1 + 9 * value / 100
Capability 5.5/10
value = 50/100
score = 1 + 9 * value / 100
Key metrics
400★ GitHub stars
0/90d Recent commits
0 devs/90d Recent contributors
11mo Project age
10mo ago Last commit
Gotchas
No gotchas documented yet. Contribute one if you know a constraint we missed.
Labels
- New project
New (11mo)
Created within the last year — promising but less battle-tested.
- Self-hosted
Self-hosted
You deploy and operate it yourself; there is no hosted option here.
agent-rl reasoning coding-agent post-training research