NovaSky-AI/SkyRL
SkyRL: A Modular Full-stack RL Library for LLMs
Build with Backblaze B2
SDKs, agent skills, IDE extensions, and reference pipelines from Backblaze Labs. All open source.
Loading star history...
Where it stands
Rank, growth pace and release cadence relative to everything GStars tracks.
1 release in the last 90 days, the latest 33 days ago, with 115 contributors on GitHub.
Use Cases & Benefits
- Provides a modular full-stack reinforcement learning library tailored for training and deploying long-horizon agents with large language models.
- Enables efficient, scalable RL training and inference on local hardware with unified APIs and support for multi-turn, real-world tasks.
- Use for developing and training RL agents that perform complex, multi-step tool use in real environments using LLMs.
- Use for integrating and benchmarking custom RL environments via a Gymnasium-compatible interface focused on math, coding, search, and SQL tasks.
- Use for building and optimizing agentic pipelines that require long-horizon planning and multi-turn interactions with external tools.
Should you depend on it?
License terms, project hygiene and risks, from GitHub metadata and GStars' snapshots.
License
Apache 2.0
Permissive: commercial use, modification and redistribution are allowed with attribution; includes an explicit patent grant from contributors.
Community files
- README: present
Watch-outs
No watch-outs from GStars' checks.
General guidance from repository metadata, not legal advice. How we score
From the README
For a guide on developing with SkyRL, take at look at our Development Guide docs.
For model training, checkout
skyrlto start using, modifying, or building on top of the SkyRL training stack. See our quickstart docs to ramp up!For building environments, checkout
skyrl-gymto integrate your task in the simple gymnasium interface.For agentic pipelines, check out
skyrl-agentfor our work on optimizing and scaling pipelines for multi-turn tool use LLMs on long-horizon, real-environment tasks.For a list of supported models, see our Supported Models docs.
Daily snapshots
Stars gained per day, and how forks and open issues moved, from GStars' daily snapshots
Forks
477+78
Open issues
583+188
Compared with peers in Backend
Fastest-growing repositories GStars tracks in this cohort for the week of Nov 1, by 7-day star growth
| Repository | Stars | +7d | Health | Last release |
|---|---|---|---|---|
| anthropics/skills | 187.8K | +2.9K | 15 | — |
| DuarteSantos8/openGym | 19.7K | +2.4K | 60 | 2 days ago |
| shiyu-coder/Kronos | 47.0K | +2.3K | 16 | — |
| NationalSecurityAgency/ghidra | 98.2K | +2.3K | 64 | 14 days ago |
| microsoft/VibeVoice | 56.0K | +1.1K | 29 | — |
| NovaSky-AI/SkyRL | 2.5K | — | 53 | 33 days ago |
| Category median | 56.0K | +2.3K | 29 | — |
Discover Repositories
Search across tracked repositories by name or description