X-PLUG/MobileAgent
A multimodal AI agent framework that automates mobile GUI interactions using vision-language models.
Not currently ranked — collecting fresh signals.
star history
Mobile-Agent is an autonomous agent system designed to control mobile device interfaces through multimodal large language models. It leverages visual understanding to navigate apps, execute tasks, and perform GUI automation without direct user input. The project includes specialized GUI-Owl models (7B and 32B variants) trained for mobile interface understanding and control.
Frequently asked
- What is X-PLUG/MobileAgent?
- A multimodal AI agent framework that automates mobile GUI interactions using vision-language models.
- Is MobileAgent open source?
- Yes — X-PLUG/MobileAgent is open source, released under the MIT license.
- What language is MobileAgent written in?
- X-PLUG/MobileAgent is primarily written in Python.
- How popular is MobileAgent?
- X-PLUG/MobileAgent has 9k stars on GitHub.
- Where can I find MobileAgent?
- X-PLUG/MobileAgent is on GitHub at https://github.com/X-PLUG/MobileAgent.