awlevin /
Browser & OS Actiontypesafe-computer-use
Builds candidate actions from OCR and UI state for Jev to control macOS, calling a text model only when writing is needed.
What Jev Does in this Architecture
Key Architecture Benefit
Separates screen reading, action selection, and text generation.
Reviewed Source Code Evidence
Verified fixed-commit source files demonstrating genuine Jev integration:
Inspect on GitHub
Check out the upstream repository README, issues, and commit log.
awlevin/typesafe-computer-useArchitecture Category
Browser & OS Action
Browser automation and desktop OS control with bounded action candidate selection.
View all in this category →Related Projects in Browser & OS Action
browser-use
jev-ultrafast
A browser Agent that uses Jev to choose actions and page controls, calling a text model only when input is needed.
Chooses an action and its matching DOM element in one request; a text model generates input text.
↳ Separates UI choices, text generation, and browser execution so each step can be inspected.
lahfir
jev-desktop
An optional Jev skill for agent-desktop that chooses controls and actions from native accessibility data.
Jev selects a target and action and estimates presence and risk; local policy decides whether to execute.
↳ Keeps the full UI tree out of the main Agent context while exposing the selected action.
jkudish
jev-browser
Drives a browser from a task and URL, returning the final page, screenshot and action trace.
Chooses DOM actions and judges goal completion or stalled progress; a separate model can supply typed text.
↳ Records proposed actions, execution and stop reasons for inspection.