# browser-use/macOS-use

Make Mac apps accessible for AI agents

Repository: https://github.com/browser-use/macOS-use
Canonical: https://ross.abutalabs.com/products/macos-use
Language: Python
License: MIT
License Family: permissive
Last push: 2025-03-05T19:13:33+00:00

## Health v2 (maintenance only)
Score: 25/100 (v2, computed 2026-09-03T02:20:16.233290+00:00)
- activity 9, release rhythm 35, longevity 42
- inputs: {"age_days": 588, "days_push": 546, "days_rel": null, "gap_med": null, "n_releases_24m": 0}
- flags: no_releases
- formula: round(0.45*activity + 0.35*rhythm + 0.20*longevity); archived -> min(score, 10)

## Adoption (not part of the score)
Stars 1973, forks 190 (observed 2026-08-28T04:06:01.141231+00:00)

## What it is
A Python library that lets LLM-powered AI agents control and interact with any macOS application via the accessibility layer, from the makers of browser-use. It translates natural-language prompts into actions across native Mac apps.

## Use cases
- let an AI agent operate any Mac app
- automate calculator or native app tasks with a prompt
- have an agent log into websites via Google auth on macOS
- control my MacBook with natural language commands
- build computer-use agents for macOS
- automate repetitive desktop workflows with LLMs

## When to choose
- you want LLM agents to drive native macOS apps, not just browsers
- you're building on top of browser-use and need desktop control
- you're prototyping computer-use agents on a Mac

## When to avoid
- you need Windows or Linux desktop automation
- you need a production-hardened, stable automation tool
- you can't grant accessibility permissions or share an LLM API key

## Facets
- artifact type: library
- maturity: experimental
- function: agent-framework, machine-learning, llm-inference, workflow-automation
- domain: artificial-intelligence, large-language-models, apple-ecosystem
- platform: python
- tags: computer-use, gui-automation, accessibility-api, browser-use, llm-agents, ai-agents, automation, macos

## Member repositories
- browser-use/macOS-use (main) score 25

## Provenance
- Observed fields: from GitHub, fetched 2026-08-28T04:06:01.141231+00:00.
- Health v2: computed from the inputs above; adoption is never an input.
- Inferred fields (summary, facets, guidance): AI-extracted, prompt v1, taxonomy v1, on 2026-08-30T03:04:57.856174+00:00, confidence not recorded.
  - readme: https://github.com/browser-use/macOS-use (fetched 2026-08-28T04:06:01.141231+00:00, sha abfc8615aecf)
- Data as of 2026-08-30T08:39:29.467469+00:00.