What you can build with it

Purpose

typesafe-computer-use turns a written goal into desktop actions using OCR and accessibility controls on a Mac.

Evidence 1 ↗ · Evidence 2 ↗

Jev’s role

TypeSafe Jev chooses the action, target and site; code supplies facts, while a separate writer handles free text.

Evidence 1 ↗

How to use it

Provide a TypeSafe key and screen-recording and accessibility permissions. The CLI offers a dry run before real mouse and keyboard control.

Evidence 1 ↗ · Evidence 2 ↗

Limits to consider

The project is beta, requires macOS 14 and Python 3.12 or newer, and describes Windows support as experimental.

Evidence 1 ↗ · Evidence 2 ↗

Repository description

Computer use for about $0.0002 a step: OCR the screen, classify the next action with TypeSafe, click. macOS.

Project facts

Relationship to Jev
Jev application
Evidence
Documented
Language
Python
License
MIT
Origin
Original repository
Repository status
Not archived
Created
2026-09-16
Last code update
2026-09-23
GitHub stars
1,042
Evidence checked
Sep 30, 2026
Metadata checked
Sep 28, 2026
Check status
Up to date

Stars measure the whole repository, including work unrelated to Jev.

Evidence and scope

Documented records the linked documentation or source. JevHunt has not independently run or benchmarked this project.

Evidence commit: d2df97dbc243b951023e94c574d41f1feab8ee33

Discovered through: awesome-jev.

How we review →

Suggest a correction · Claim this listing · Submit a project