AI-powered, vision-driven UI automation for every platform.
-
Updated
Jul 3, 2026 - TypeScript
AI-powered, vision-driven UI automation for every platform.
This is the repo for the paper "OS Agents: A Survey on MLLM-based Agents for Computer, Phone and Browser Use" (ACL 2025 Oral).
OpenGUI is an Android GUI agent framework for phone-use AI that can see, plan, and operate real mobile apps through the GUI.
Source code of the paper "V-Droid: Advancing Mobile GUI Agent Through Generative Verifiers"
Scripts for the analysis of EMA and longitudinal data on virtual media use and well-being during the pandemic
把操作手机点外卖封装成给 AI agent 调用的工具——文本进文本出(markdown表格)、对非视觉/远程 LLM 友好、可 MCP 封装或原生 tool 直用。基于 Open-AutoGLM。
AI-powered app that detects distracted or unsafe driving and rewards safe driving behavior to eliminate driver distractions.
Add a description, image, and links to the phone-use topic page so that developers can more easily learn about it.
To associate your repository with the phone-use topic, visit your repo's landing page and select "manage topics."