What it does
Mobilerun is a framework that lets AI agents operate a phone: reading what is on screen, tapping, swiping and typing to complete multi-step tasks you describe in plain words.
It works with many AI providers, including OpenAI, Anthropic, Gemini and local models through Ollama. You can drive it from a command line, a terminal screen, Docker or Python code.
Suggested uses include testing mobile apps, automating repetitive phone tasks and pulling information out of apps. A separate paid cloud service offers managed phones.
Who it's for
Developers and testers who want to automate tasks on mobile devices.
Can I use it without coding?
With some setup. It's installed and run from the command line, and you need to connect a phone or emulator. New to this? Start here.
Can I run it?
- Cost
- Free, with optional paid extrasThe open-source version is free; the makers also sell a hosted or pro version.
- Runs on
- Phone
- Privacy
- Your choice: run it on your device or use an online service
- API key
- Not needed
Try it
- Install Mobilerun with Python's tools, following the README.
- Connect an Android or iOS device by following the device setup guide.
- Give it a task in plain words and watch it work on the phone.
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