# Tarsier

Perception utilities for web agents that tag interactable elements with typed IDs an LLM can act on, and use OCR to render page screenshots as whitespace-structured text for models without vision.

- Catalog URL: https://awesomecua.github.io/resources/github-reworkd-tarsier/
- Original source: https://github.com/reworkd/tarsier
- Kind: tool
- Review: curated
- Scope: core
- Environments: web
- Topics: screen-understanding
- Evidence checked: 2026-10-16T06:36:04Z
- ID: github:reworkd/tarsier

## Limitations

Inclusion does not establish reproducibility or endorsement.

- Record JSON: https://awesomecua.github.io/resources/github-reworkd-tarsier/record.json

## License declarations

- code: MIT — https://raw.githubusercontent.com/reworkd/tarsier/HEAD/LICENSE
- data: not recorded
- document: not recorded
- weights: not recorded

## Primary evidence

- https://raw.githubusercontent.com/reworkd/tarsier/HEAD/README.md (retrieved 2026-10-16T06:36:04Z; SHA-256 2a313a5a1c433c0609067c6d875d5ff69493e8792d2173e458eb5db8bf232977)
- https://raw.githubusercontent.com/reworkd/tarsier/HEAD/LICENSE (retrieved 2026-10-16T06:42:06Z; SHA-256 f4ff2ba0f16e8abb7087071651c217ced6421e224313755c5d88433e324f19a1)