Repo · Agents & browsers

Computer Use

Translate screen text into mouse actions.

Open github.com ↗

From the repository

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

ai-agentsautomationcomputer-usemacosocrtypesafe

How builders describe it

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

Use this experimental macOS CLI to study how local screen reading and Jev decisions can select the next click, scroll, or text-entry action.

Computer use on macOS, with one Jev decision per step.

A macOS computer-use loop that OCRs the screen, asks Jev for the next action with typed Choices, and clicks, at about $0.0002 per decision without sending screenshots to a frontier model.

The decision Jev makes

Pick the next click, field or navigation from the legal actions on screen.

Where it fits

Browser agents need to choose an action on every step. With Jev each step is a choice from the actions actually available on the page, which keeps agents fast and on the rails. All 299 agents & browsers projects →

Related projects