# OmniParser

Screenshot parser that detects interactable regions and captions icons so vision-language models can ground actions, released as V1.5 and V2 weights alongside OmniTool for driving a Windows 11 VM.

- Catalog URL: https://awesomecua.github.io/resources/github-microsoft-omniparser/
- Original source: https://github.com/microsoft/OmniParser
- Kind: tool
- Review: curated
- Scope: core
- Environments: cross-platform
- Topics: screen-understanding, grounding
- Evidence checked: 2026-10-16T06:36:04Z
- ID: github:microsoft/omniparser

## Limitations

Inclusion does not establish reproducibility or endorsement.

- Record JSON: https://awesomecua.github.io/resources/github-microsoft-omniparser/record.json

## License declarations

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

## Primary evidence

- https://raw.githubusercontent.com/microsoft/OmniParser/HEAD/README.md (retrieved 2026-10-16T06:36:04Z; SHA-256 f4ebaafcc0ab0b9e9cc55cb587678e5c83a5bbd64469fb2cc52bc63843c5cc6d)