Agents
OpenGUI
Android GUI agent framework: AI that sees, plans, and taps real mobile apps.
★ 1.8k starsCustom
View guide →// agents · minitap-ai/mobile-use
mobile-use
mobile-use is an open-source ai agents project by minitap-ai (minitap-ai/mobile-use on GitHub). It has 3,234 GitHub stars and 295 forks, is released under the Apache-2.0 license, and was last updated on GitHub on 14 September 2026.
AI agents that use real Android and iOS apps like a human — from minitap.
★ 3.2k stars⑂ 295 forksApache-2.0updated 2026-09
▦ visual — this project's README ships no embeddable screenshot,
so here's a placeholder. The guide below is complete regardless.
so here's a placeholder. The guide below is complete regardless.
// project facts
Project facts
- Repository
- minitap-ai/mobile-use
- GitHub stars
- 3,234
- Forks
- 295
- License
- Apache-2.0
- Last updated on GitHub
- 14 September 2026
- Category
- AI Agents
- Listing
- Full install guide
- Official site
- Official site
// how it works
How it works
- Clarify your goal
Decide the first concrete outcome you want from it, so you can pick the right example, template or mode instead of exploring everything at once.
- Get the project
Clone the repository (or install the published package) and skim its README quick start for the requirements for your platform.
- Install and configure
Run the documented install step and set any required configuration — such as provider keys, data sources or local services — before the first run.
- Run your first task
Execute the smallest documented example end to end, confirm the output is what you expected, then adapt it to your real data or workflow.
// features
Why people love it
Real devices and simulators
Physical Android phones over USB, Android emulators, and iOS simulators on macOS.
Natural-language control
Describe the task in plain language; the agent plans and acts on the live UI.
Docker quick launch
A containerised launch path, with troubleshooting docs for device-IP and image-pull issues.
Development mode
uv venv + uv sync gives a locked, reproducible local setup.
Benchmarked
The README reports benchmark results for the agent's mobile task performance.
LangGraph-based system
An agentic system overview in the README explains the perception/action loop.
Advertisement
// run it
Run it yourself
- Clone the repository
Get the source so you can inspect, configure and run it locally.
git clone https://github.com/minitap-ai/mobile-use.git cd mobile-use - Clone and set up locally
Clone, create the uv environment from the project's Python version, activate it and sync locked dependencies.
git clone https://github.com/minitap-ai/mobile-use.git && cd mobile-use uv venv source .venv/bin/activate # Windows: .venv\Scripts\activate uv sync - Run a task
Connect a device (ADB for Android, fb-idb for iOS) and give the agent a goal.
python ./minitap/mobile_use/main.py "Go to settings and tell me my current battery level"
// use cases
What you can build
- Automate QA flows on a real Android phone from a sentence
- Run repetitive in-app tasks like checking settings or filling forms
- Test an app on both an Android emulator and an iOS simulator
- Benchmark agents on realistic mobile tasks
Advertisement
// faq
Questions, answered
Who maintains mobile-use?
It is maintained by minitap-ai on GitHub (minitap-ai/mobile-use), where the source, issues and releases live.
Is it free to use?
Yes — it is free and open source under Apache-2.0, which permits use, modification and commercial redistribution, with licence/notice retention.
Does it need a paid API key?
Yes — the agent reasons with an LLM, so you configure a provider key as the README describes; devices themselves are your own hardware/emulators.
How does it compare to Appium scripts or desktop browser-use agents?
Compared with Appium scripts or desktop browser-use agents, mobile-use's distinguishing focus is: aI agents that use real Android and iOS apps like a human — from minitap. Pick it when that focus matches your need; the alternative may suit you better if its broader or different scope is the priority.
How do I get started?
Clone https://github.com/minitap-ai/mobile-use (or install its published package), follow the README quick start to install and configure it, then run the smallest documented example — the Run section on this page mirrors those steps.
// keep exploring
Similar tools
AI Agents
agent-desktop
Reliable computer use for any agent: drive real apps through accessibility trees, not pixel guessing.
★ 1.8k starsApache-2.0
View guide →AI Agents
mobilerun
Control Android and iOS devices with natural language — an LLM-agnostic mobile agent framework and CLI.
★ 9.6k starsMIT
View guide →AI Agents
Tutti
Tutti — a real-time shared workspace where people and multiple AI agents build in tune, sharing context, files, apps and tasks
★ 3.8k starsApache-2.0
View guide →AI Agents
browser-use
The open-source library that lets AI agents control a real browser.
★ 117.4k starsMIT
View guide →AI Agents
OSWorld-V2
Benchmark computer-use agents on long, real-world desktop tasks.
★ 353 starsApache-2.0
View guide →// alternatives
Alternatives in AI Agents
The most-starred other AI Agents projects in the LibreAI catalogue — the realistic shortlist if mobile-use is not the right fit.
- openclaw★ 391.6k
A personal AI that really does things — on any OS, with your data staying yours.
- superpowers★ 294.9k
An agentic skills framework & software development methodology that works.
- ECC★ 275.2k
Agent harness optimization system with skills, memory and security for Claude Code, Codex and more
- hermes-agent★ 252.0k
The agent that grows with you — a Python framework for adaptive AI agents.
- deepseek-harness★ 245.5k
DeepSeek's plugin-based agent harness where everything is a plugin.
// more in agents
More in AI Agents
Nearby AI Agents projects in the catalogue, closest in stars to mobile-use — keep exploring the shelf either side of it.
- google_workspace_mcp★ 3.3k
Control Gmail, Calendar, Docs, Sheets, Drive and more from AI — a full Google Workspace MCP server.
- AP2★ 3.2k
An open protocol for secure AI-driven payments.
- EvoAgentX★ 3.4k
EvoAgentX — a framework for building self-evolving ecosystems of AI agents.
- arxiv-mcp-server★ 3.2k
A local MCP server for serious arXiv work — LaTeX section reads, BibTeX and topic watches.
- beeai-framework★ 3.4k
Build production-ready AI agents in both Python and Typescript.
- OSWorld★ 3.2k
OSWorld — benchmark multimodal agents on open-ended tasks in real computer environments.
Get mobile-use
Free and open — grab the source, star the repo, and start creating.