Plain-AyI
← All projects
AI models & research

Mobile-Agent

Research AI agents and models from Alibaba's Tongyi Lab that can operate phones and computers by looking at the screen.

Research-backedNew this week

What it does

Mobile-Agent is a family of research projects about GUI agents: AI that uses apps the way a person does, by looking at the screen and tapping, typing and scrolling.

It includes the GUI-Owl models, which understand screens on phones, computers and the web, and several agent systems built on top of them for planning, checking progress and remembering steps.

The team publishes papers, code and model files, and offers online demos and a paid cloud API through Alibaba Cloud.

Who it's for

AI researchers and developers working on agents that control phones or computers.

Can I use it without coding?

Developers only. The code and models are for researchers; the online demo is the easiest way to try it. New to this? Start here.

Can I run it?

API key
Not needed

Try it

  1. Try the online demo the project links to: type an instruction and watch the agent operate a phone or computer.

Using Claude Code, Cursor or another AI coding assistant? Paste the prompt and it will walk you through the setup.New to this?

Before you install

  • Only download from the official GitHub page. Copies with similar names exist for many popular projects.
  • License (MIT): Very permissive: free to use, change and share, including for business.
  • More on staying safe

Where people are talking about it