Mobile Use

Active
GitHub Python Apache-2.0

Description

Framework enabling AI agents to use real Android and iOS apps just like a human, supporting autonomous operation and interaction with mobile interfaces.

Key Features

  • Natural language control of Android and iOS devices
  • UI-aware automation with accessibility tree navigation
  • Data scraping from any app into structured JSON format
  • Extensible LLM configuration with multiple provider support
  • Docker quick-launch for rapid setup on Android
  • AndroidWorld benchmark leader with 100% completion

Use Cases

💡 Automate repetitive mobile tasks like sending messages and navigating apps
💡 Extract structured data from mobile apps for analytics or reporting
💡 Test mobile application UI flows end-to-end using natural language
💡 Build AI-powered assistants that operate real mobile interfaces
💡 Prototype mobile automation scripts without writing platform-specific code

Quick Start

1. Install via pip: pip install minitap-mobile-use
2. Clone the repo and copy .env.example to .env
3. Add your LLM API key to .env
4. Connect an Android device via USB with USB debugging enabled
5. Run: python -m mobile_use "Open Gmail, find first 3 unread emails" --output-description "JSON list with sender and subject"

Related Projects