# typesafe-computer-use

> MIT macOS computer-use loop — OCR + TypeSafe Jev decisions, ~$0.0002/step

**Category:** AI Agents  
**Pricing:** open-source  
**URL:** https://github.com/awlevin/typesafe-computer-use  
**GitHub:** https://github.com/awlevin/typesafe-computer-use  
**Added:** 2026-09-19

---

## The Hook

typesafe-computer-use drives a Mac toward a plain-English goal without shipping screenshots to a frontier model — OCR the screen, classify the next action with TypeSafe Jev, click.

## What's Good

MIT (awlevin/typesafe-computer-use). Deterministic screen read + calibrated Choice classifier instead of full multimodal computer-use. Author-measured ~$0.0002 per decision and ~1.5s end-to-end steps vs multi-second frontier screenshot loops. Python 3.12+ / uv / macOS 14+. Honest README: rebuild frontier free reasoning as deterministic state.

## The Catch

The decision brain is closed TypeSafe Jev (paid input tokens, early-access/waitlist) — the loop is OSS, the classifier is not. macOS only. Vs Open Interpreter / browser-use / SemIf: this is GUI clicker + paid System One decisions, not a coding REPL, browser agent, or local logit SemIf gate. A separate writing model is still needed when a text field needs free text.

## Verdict

Cheap macOS computer-use around TypeSafe Jev. OSS loop; paid/waitlisted decision API is the real dependency.