typesafe-computer-use
A macOS tool that drives your computer toward a plain-English goal by reading the screen and picking the next click with a cheap classifier instead of a big AI model, about 150x cheaper per step than frontier computer-use.
View awlevin/typesafe-computer-use on GitHub- GitHub stars
- 1,301
- Forks
- —
- Language
- Python
Project details
- Repository
- awlevin/typesafe-computer-use
- Licence
- MIT
- Primary language
- Python
- Catalog status
- Available
- Catalog check
- 2026-11-13
Repository description
Computer use for about $0.0002 a step: OCR the screen, classify the next action with TypeSafe, click. macOS.
Explore by topic
More tools in Automation & workflows
- agent-desktop
vercel-labs · Apache-2.0
Lets an AI agent see and click on real desktop app elements via the OS accessibility tree instead of guessing from screenshots, so it can reliably operate macOS,…
- bama
daveebbelaar · MIT
BAMA gives AI coding agents a set of skills to research, clone, design, build and test a native Mac app from scratch.
- macos-harness
browser-use · MIT
macOS Harness gives an AI agent direct, raw control of a Mac, letting it see, click, type into, and script real running apps itself instead of relying on a library of…
- useagent
useagenthq · AGPL-3.0
A self-hosted platform that turns coding agents into team coworkers with their own cloud computer, returning finished decks, reports, and pull requests rather than just…