# browser-use/macos-harness

> A thin Python harness giving an LLM agent direct control of macOS through six primitives (see, key, type, click, ax, script) to drive apps, the browser, and files. The agent writes any missing logic in plain Python mid-task.

- Magnitude: 0.5 out of 10 — Steady
- Stars: 888 total · +0 stars on 2026-09-25 (UTC), ≈ 1 by evening
- Star trust: star growth looks organic
- Category: AI agents · Language: Python · License: MIT · Created: 2026-08-17 · Last push: 2026-08-17
- GitHub: https://github.com/browser-use/macos-harness · Homepage: https://github.com/browser-use/macos-harness · Page: https://gitnova.dev/en/r/browser-use/macos-harness

## Useful for

- Run an agent that controls Spotify or another app via screenshots and clicks
- Automate actions in an already logged-in Chrome through CDP without a fresh profile
- Build a script that reads background app windows and home directory files in one Python process

## Why it’s here

- 0 stars so far today, about 1 expected by the end of the day.
- The repository is 39 days old and already has 888 stars.

## Star trust

Star growth looks organic.

Star-trust labels are heuristics based on the repository’s behavior, not a check of every stargazer.

## Numbers

- Forks: 61
- Issues and pull requests: 12
- Watchers: 1
- Average over the last week: 2 per day
- Usual pace: 7 per day
- Latest release: v0.1.2 (2026-08-17)

## Stars per day, last 30 days (oldest → newest, today is partial)

2026-09-30 … 2026-10-29: None, None, None, None, None, None, None, None, None, None, None, None, None, None, None, None, None, None, None, None, None, None, None, None, None, None, None, None, None, None

## Magnitude by day, last 12 days

09-14 1.6, 09-15 0.9, 09-16 0.8, 09-17 0.8, 09-18 0.9, 09-19 0.8, 09-20 0.5, 09-21 0.5, 09-22 0.5, 09-23 0.7, 09-24 0.7, 09-25 0.6

---

Magnitude (0–10) measures how fast and how unusually interest in a repository is growing right now. It is not a quality score.
Days are UTC. “So far today” is a fact; “expected by the end of the day” is a forecast.
Summaries and use cases are written by an LLM (DeepSeek V4.1 Flash) from the README and may be inaccurate: verify specific claims (benchmarks, speed, hardware) in the repository itself.
Data as of 2026-09-25 04:59 UTC, updated every 30 minutes.