AI Computer Use — AI skill for Claude Code
A tool that allows Claude to control Mac and iOS devices through the Anthropic API.
How to install AI Computer Use
This entry records only its repository, not the path inside it, so there is no
exact command to give. Open rohitg00/ai_computer_use and copy the folder into
~/.claude/skills/, or the file into ~/.claude/agents/.
What AI Computer Use does
A tool that allows Claude to control Mac and iOS devices through the Anthropic API.
Alternatives in AI
- Deepreasoning — A high-performance LLM inference API and Chat UI that integrates DeepSeek R1's CoT reasoning traces with Anthr 5.4k ★
- Claude To ChatGPT — This project converts the API of Anthropic's Claude model to the OpenAI Chat API format 1.3k ★
- Claude Code Switch — One-command model switcher for Claude Code (Only for Anthropic API) 655 ★
README
Mac & iOS Anthropic Control
A tool that allows Claude to control Mac and iOS devices through the Anthropic API.
Acknowledgments
This project builds upon and was inspired by the excellent [Anthropic Computer Use Demo](https://github.com/anthropics/anthropic-quickstarts/tree/main/computer-use-demo). The original demo provides a robust foundation for computer control through Claude, and we've extended it to support native macOS and iOS automation.
We highly recommend checking out the original demo to understand the core concepts and implementation patterns.
Features
- Control Mac OS through native commands and GUI automation
- Control iOS devices through Appium/XCUITest
- Streamlit-based interface for interaction
- Support for multiple LLM providers (Anthropic, Bedrock, Vertex)
- Automatic screen resolution scaling
- File system interaction capabilities
Prerequisites
- macOS Sonoma 15.7 or later
- Python 3.12+
- Homebrew
- Xcode and iOS Simulator/Device
- Node.js and npm (for Appium)
Installation
- Install system dependencies:
# Install Homebrew if not installed
/bin/bash -c "$(curl -fsSL https://raw.githubusercontent.com/Homebrew/install/HEAD/install.sh)"
# Install required packages
brew install python@3.12 cliclick node
# Install Appium and dependencies
npm install -g appium
npm install -g appium-xcuitest-driver
- Install Python dependencies:
python -m venv venv
source venv/bin/activate
pip install -r requirements.txt
- Configure environment:
cp .env.example .env
# Edit .env with your settings
Usage
- Start the Streamlit interface:
streamlit run src/ui/streamlit_app.py
- Access the interface at http://localhost:8501
Environment Variables
ANTHROPIC_API_KEY: Your Anthropic API keyAPI_PROVIDER: anthropic/bedrock/vertexSCREEN_WIDTH: Display width (default: 1280)SCREEN_HEIGHT: Display height (default: 800)IOS_DEVICE_ID: iOS device UDID (optional)
Sec
Related Skills
AgentPilot
LLM-powered macOS computer control. AgentPilot lets AI agents see your screen, move the mouse, type text, pres
Agentic KVM
Give AI agents (Claude Code/Cowork, ChatGPT/Codex, Gemini/Antigravity) bare-metal, out-of-band control of any
OmniPilot
Cross-platform LLM computer-use agent — OpenAI, Anthropic, Gemini, NVIDIA NIM and more control your PC behind
Jarhead
Voice-first Mac assistant that uses the computer for you. GPT-Live-1 full-duplex voice behind an on-device wak
Use Crew Gateway
Route an OpenAI/Anthropic-compatible client through the portable farmd control plane's virtual crew model, for
Slipwright Agent
Lends a computer to a Slipwright account: writes phases with your own model (Claude Code, Codex or a key), bui
Related Agents
Launcher
Build the Mac daemon and iOS app, launch both (daemon on host, app in Simulator), and seed the dev endpoint to
LLM Orchestrator
Use this agent for LLM integration work — prompt engineering, multi-provider abstraction (OpenRouter, Gemini,
AI ML
AI/ML 통합 전문가 + LLM API 최신 모델/SDK 코딩 가이드. RAG 시스템, 문서 분석, OpenAI/Anthropic/Gemini/Ollama 최신 API 보장. "AI integra