typesafe-computer-use
awlevin
Builds candidate actions from OCR and UI state for Jev to control macOS, calling a text model only when writing is needed.
- License
- MIT
- GitHub Stars
- 302
- Source reviewed
- 2026-09-19
Where Jev makes a decision
Selects the next step from deterministically extracted controls and actions before desktop execution.
What this project offers
Separates screen reading, action selection, and text generation.
Review scope
README cost and speed comparisons use the author’s limited screenshot and goal setup, with some reasoning supplied by deterministic code. They are not general savings multipliers and were not independently retested.
Sources and implementation
Related projects
jev-ultrafast
browser-use · Browser & OS Action
A browser Agent that uses Jev to choose actions and page controls, calling a text model only when input is needed.
jev-desktop
lahfir · Browser & OS Action
An optional Jev skill for agent-desktop that chooses controls and actions from native accessibility data.
jev-browser
jkudish · Browser & OS Action
Drives a browser from a task and URL, returning the final page, screenshot and action trace.
AskJev
ranjan2829 · Browser & OS Action
Connects Agents to a browser over MCP, using Jev to choose page actions with confirmation gates for actions such as payment or deletion.