# ScreenAgent

Environment and agent in which a vision-language model controls real desktops over VNC with mouse and keyboard in plan, act and reflect stages, plus a hand-annotated dataset of daily computer tasks.

- Catalog URL: https://awesomecua.github.io/resources/github-niuzaisheng-screenagent/
- Original source: https://github.com/niuzaisheng/ScreenAgent
- Kind: agent
- Review: curated
- Scope: core
- Environments: desktop
- Topics: planning
- Evidence checked: 2026-10-16T06:36:02Z
- ID: github:niuzaisheng/screenagent

## Limitations

Inclusion does not establish reproducibility or endorsement.

- Record JSON: https://awesomecua.github.io/resources/github-niuzaisheng-screenagent/record.json

## License declarations

- code: not recorded
- data: not recorded
- document: not recorded
- weights: not recorded

## Primary evidence

- https://raw.githubusercontent.com/niuzaisheng/ScreenAgent/HEAD/README.md (retrieved 2026-10-16T06:36:02Z; SHA-256 2248b2048b9166ce0348b24e81b2587fdf373a958fd86ab870ba85825425b02f)