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.

Someone built a working computer-use loop using Jev alone to take actions. Small use of LLM when text needs to be generated (like filling in forms or URLs). Repo X Post

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 193 agents & browsers projects →

Related projects