# ZeroGUI

Online RL framework for GUI agents in which VLMs generate the training tasks and judge success from trajectory screenshots, with OSWorld and AndroidLab checkpoints trained from UI-TARS-7B-DPO.

- Catalog URL: https://awesomecua.github.io/resources/github-opengvlab-zerogui/
- Original source: https://github.com/OpenGVLab/ZeroGUI
- Kind: framework
- Review: curated
- Scope: core
- Environments: cross-platform
- Topics: reinforcement-learning, data-generation
- Evidence checked: 2026-10-16T06:36:04Z
- ID: github:opengvlab/zerogui

## Limitations

Inclusion does not establish reproducibility or endorsement.

- Record JSON: https://awesomecua.github.io/resources/github-opengvlab-zerogui/record.json

## License declarations

- code: Apache-2.0 — https://raw.githubusercontent.com/OpenGVLab/ZeroGUI/HEAD/LICENSE
- data: not recorded
- document: not recorded
- weights: not recorded

## Primary evidence

- https://raw.githubusercontent.com/OpenGVLab/ZeroGUI/HEAD/README.md (retrieved 2026-10-16T06:36:04Z; SHA-256 033d2de815e11c208862c5c5601b78d58668b79cadd37a750cad9edd4dacabed)
- https://raw.githubusercontent.com/OpenGVLab/ZeroGUI/HEAD/LICENSE (retrieved 2026-10-16T06:42:05Z; SHA-256 c71d239df91726fc519c6eb72d318ec65820627232b2f796219e87dcf35d0ab4)