PhoneDriver

Overview

PhoneDriver is a Python based mobile automation agent that uses Qwen vision language models to understand Android screens through visual analysis. It interacts with devices using ADB commands and allows users to describe tasks in natural language. The system includes a built in Gradio web interface with live screenshots and execution logs for real time feedback.

Key features

• Vision powered automation
• ADB device control
• Natural language tasks
• Built in web UI
• Real time feedback