SkyRL logo

SkyRL

Fine-Tuning 6.4/10 Solid

SkyRL: A Modular Full-stack RL Library for LLMs

SkyRL scores 6.4/10 (Solid) in Fine-Tuning.

Language Python License Apache-2.0 Stars 2.1k★ Type library Self-host Yes Repo NovaSky-AI/SkyRL Homepage https://github.com/NovaSky-AI/SkyRL

Quality

Solid 6.4
Adoption 33
Activity 81
Maturity 84
Community 40
Capability 50
Show the math
Overall 6.4/10
value = 6.4/10
score = value
Adoption 4/10
value = 32.8/100
score = 1 + 9 * value / 100
Activity 8.3/10
value = 80.6/100
score = 1 + 9 * value / 100
Maturity 8.5/10
value = 83.5/100
score = 1 + 9 * value / 100
Community 4.6/10
value = 39.7/100
score = 1 + 9 * value / 100
Capability 5.5/10
value = 50/100
score = 1 + 9 * value / 100

Key metrics

2k★ GitHub stars
225/90d Recent commits
19 devs/90d Recent contributors
1.2y 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.

agent-rl multi-turn long-horizon async training