Roubao

Roubao is an open-source AI-powered mobile automation agent that operates an iPhone through natural language instructions. It observes the screen, interprets application interfaces, and performs actions such as tapping, swiping, typing, and navigating between apps. Users can connect compatible AI models through configurable API endpoints. The agent supports information searches, product comparisons, and generating PDF reports with tables and screenshots. Long-running tasks include progress tracking, checkpoints, and resumable execution. Interactive confirmation cards allow users to approve decisions before sensitive actions. Its experimental features include authorized messaging app interactions and streaming voice input. The iOS developer preview requires initial Mac and USB setup but can subsequently operate without a connected computer.