
Academic lab · Berkeley, United States
NovaSkyBerkeley Sky Lab
Berkeley Sky Computing Lab group releasing open reasoning models, training recipes and the SkyRL reinforcement-learning library for LLM agents.
Berkeley, United States
- Founded
- 2025
- Type
- Academic lab
- Based in
- Berkeley, United States
- Key papers
- 2
- Featured projects
- 6
About
NovaSky is a team within the Sky Computing Lab at UC Berkeley. Its GitHub organization was created in January 2025, the month it published Sky-T1, a reasoning model it said could be trained for under 450 dollars.
The group releases weights, data and training code together. After Sky-T1 it published work on cutting reasoning costs, test-time scaling for code generation and the SkyRL framework, which grew from SkyRL-v0 for long-horizon software agents into a modular RL library for training LLMs.
Its repositories, including SkyThought and SkyRL, are released under Apache 2.0, and its audience is researchers and developers training reasoning and agentic models.
Mission and ambitionsNovaSky aims to make post-training of reasoning and agentic models reproducible and affordable by sharing models, data and code openly.
Known for
- 01
Sky-T1 reasoning model trained for under 450 dollars
- 02
SkyRL reinforcement-learning library
- 03
SkyThought open recipes
- 04
Text-to-SQL and software-agent RL results
Milestones
- 2025
Sky-T1-32B-Preview
An open 32-billion-parameter reasoning model, with data and code, reported to cost under 450 dollars to train.
- 2025
Reasoning cost reduction
A January 2025 post showed how to cut reasoning costs by about half without sacrificing accuracy.
- 2025
SkyRL-v0
A May 2025 release for training long-horizon real-world agents with reinforcement learning.
- 2025
SkyRL-SQL
A May 2025 recipe for data-efficient multi-turn reinforcement learning on text-to-SQL.
- 2025
SkyRL-v0.1
A June 2025 release evolving SkyRL into a modular, performant RL framework for LLMs.
- 2025
SA-SWE-32B
A 32-billion-parameter software-engineering model published in October 2025.
Open source
Sky-T1 training recipes.
Modular full-stack RL library.
SkyRL with OpenHands agents.
SWE agent model.
- Sky-T1-32B-Previewmodel
Reasoning model.
- Sky-T1_data_17kdataset
Sky-T1 training data.
Research papers
Notable releases
Openness
Open weights, data and code.
People
- Shiyi CaoPublic org member
- Charlie RuanPublic org member
- Shu LiuPublic org member
- Sumanth R HegdePublic org member
Listed from the lab's own pages and public profiles.
Contact and community
Contact details and links are on the lab's website (https://novasky-ai.github.io); code questions go through issues on their GitHub organisation.
Public Discord linked from the lab's own website for community discussion and announcements.
Sources
Compiled from the lab's public pages, Hugging Face and GitHub. Last checked 2026-11-17. Something wrong or out of date? Tell us on Discord.



