GitHub radar
macOS Harness: Give Your LLM Full Mac Control
Announcing macOS Harness — a small Python wrapper that enables an LLM to interact with any application on Mac by taking screenshots, typing, using mouse and scripting.
A new project by browser-use: A small Python service that provides 6 low level APIs for interacting with macOS to a LLM: Screenshot windows, Send keyboard/mouse events to an application with a given PID (using Apple Accessibility), Access to AppleScript, A complete web browser through CDP, Local File System. The model will learn as it interacts and generate the required code. No tools for any particular app required. Exclusive to macOS. Licensed under MIT License. Anonymous Data Collection.
Why a vibe-coder should care
When you assign your agent to perform tasks on a Mac, it will figure out how to do it by itself. Even if there isn’t any tool for a particular app. Simply copy & paste the below code into Claude Code and watch your agent do its magic!
How to install
Copy this and send it to your agent — Claude Code, Codex, any of them:
Install macOS Harness from https://github.com/browser-use/macos-harness with uv on Python 3.12, register the skill printed by `macos-harness skill`, run `macos-harness doctor`, explain any missing macOS permissions and ask me before requesting them.
Mac only — a regular one, no GPU needed; install it as a Python package.
Open on GitHub▌ More finds