# SkyRL

> Modular reinforcement-learning stack with a training engine, long-horizon agent layer and Gymnasium-style tool-use environments for LLMs.

- id: `skyrl`
- category: Infrastructure (`infrastructure`)
- url: https://github.com/NovaSky-AI/SkyRL
- repo: https://github.com/NovaSky-AI/SkyRL
- status: active
- pricing: open-source
- license: Apache-2.0
- tags: infrastructure, open-source
- auth: none
- access notes: Public source repository; local library. Model services and compute have separate requirements and costs.
- related: Harbor (https://indexagentica.com/entries/harbor/)
- sources: https://github.com/NovaSky-AI/SkyRL , https://github.com/NovaSky-AI/SkyRL/blob/main/LICENSE
- added: 2026-11-07
- updated: 2026-11-07
- last verified: 2026-11-07
- featured in: RL environment libraries compared — NeMo Gym, OpenEnv and Verifiers (https://indexagentica.com/compare/rl-environment-libraries/); Fine-tuning frameworks compared — Axolotl, LLaMA-Factory and Unsloth (https://indexagentica.com/compare/fine-tuning-frameworks/); Agent RL stacks compared — verl, SkyRL, Agent Lightning and ART (https://indexagentica.com/compare/agent-reinforcement-learning-stacks/); Post-training a tool-use model — TRL, PEFT, and scale-out RL (https://indexagentica.com/stacks/post-training-tool-use-model/)
- submitted by: agentica-curator
- page: https://indexagentica.com/entries/skyrl/
- json: https://indexagentica.com/api/entries/skyrl.json

Public Apache-2.0 source. The unified skyrl library combines skyrl-train and skyrl-tx and supports a Tinker API backend on hardware you control. skyrl-agent handles multi-turn long-horizon training and evaluation; skyrl-gym supplies math, coding, search and SQL environments. Repository development and quickstart guides cover source setup and model/compute dependencies. The README documents Harbor integration and an October 16, 2026 Beam support recipe. This is software access, not free hosted GPU capacity.
