awlevin/typesafe-computer-use

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

Open original source ↗

Older snapshot: check the original source for current information.

From the publisher

README & documentation

Source preview

Read the project’s overview, installation instructions and usage examples. The original README is the source of truth.

typesafe-computer-use (jev for short) drives a Mac toward a goal you type in plain English, for about a fiftieth of a cent per step. It reads the screen deterministically, asks a small classifier which action comes next, and only calls a writing model when a text field genuinely needs free text or the classifier has stopped and the screen needs reading. One idea runs through it: the classifier picks, code decides facts, and the writer only writes free text. Anything a model would have to work out (a date, whether a field is focused, whether a URL is clean) is computed in code and handed over as state. VISION.md says what it is for in a dozen lines. Frontier-model computer use is capable and expensive: every step ships a screenshot and waits several seconds for a plan. Most steps do not need a plan. They need one choice from a…

awlevin/typesafe-computer-use on GitHub A short preview, not the full document.

Read the full README ↗ · Preview checked 2026-10-29T02:39:44.672Z

Inside the original README — Document outline
  1. Why a classifier
  2. Install
  3. First run
  4. How a step works
  5. Benchmark
  6. Read more
  7. Contributing
  8. License

Headings are captured from the source. Links open the publisher’s document, not a locally hosted copy.

Links from the README

References supplied by the publisher, not independently verified endorsements. Check the destination before downloading files or entering credentials.

Documentation belongs to its respective authors. Reported project/model license: MIT. A listing is not a grant of reuse or training rights. Confirm the document’s own terms at the source.

What this repository does

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

Repository facts

Owner
awlevin
Primary language
Python
Stars
1,174
Forks
113
Open issues + pull requests
35
License
MIT
Archived
No
Default branch
main
Created
2026-09-16T17:48:45.000Z
Last push
2026-09-29T23:33:46.000Z

Topics and intended use

Owner-supplied topics: ai-agents, automation, computer-use, macos, ocr, typesafe

Review the README for scope, installation, examples and limitations. We do not run repository code or certify it.

Evaluate before installing

Review licensing and dependencies, inspect recent commits and unresolved issues, and test in an isolated environment before production use. Stars and forks alone cannot answer these questions.

README and project files

Issues and maintenance discussion

Releases and changelog

Source and freshness

Source: GitHub. Metadata observed 2026-10-06T12:06:59.213Z. Daily imports are snapshots, not real-time monitoring.

Popularity and source listings do not establish security, suitability, licensing rights or benchmark performance.

Open original source

Related repositories

public-apis/public-apis

EbookFoundation/free-programming-books

donnemartin/system-design-primer

vinta/awesome-python

practical-tutorials/project-based-learning

NousResearch/hermes-agent