Skip to content
Back to search

mobile-use

AI agents can now use real Android and iOS apps, just like a human.

Safety scan

A static text scan, not a guarantee. Select the badge to see what was scanned and every finding.

Checked today

Check it deeper on your machine

It has changed since its scan on 11 Nov 2026.

As a Claude Code plugin, install it and then ask Claude Code:

/plugin marketplace add keithmackay/mackayi/plugin install scanskillsafety@mackayiDo a deep scan of https://github.com/minitap-ai/mobile-use with scanskillsafety

Or from a terminal, clone it and run it:

git clone https://github.com/keithmackay/scanskillsafety-skill ~/.claude/skills/scanskillsafetynode ~/.claude/skills/scanskillsafety/cli.cjs --deep 'https://github.com/minitap-ai/mobile-use'

It checks the exact commit: every file, its packages against OSV (api.osv.dev), how it compares with this page's scan (findsafeskills.com receives the repository's address), and, if you agree, Claude reading every file with your own Claude subscription. It never runs the code.

Badge for your README
findsafeskills safety rating

Markdown

[![findsafeskills safety rating](/api/listings/minitap-ai--mobile-use/badge.svg)](/listings/minitap-ai--mobile-use)

HTML

<a href="/listings/minitap-ai--mobile-use"><img src="/api/listings/minitap-ai--mobile-use/badge.svg" alt="findsafeskills safety rating" /></a>

Install

i

Install instructions from the README

As written by the repo's author. findsafeskills has not verified these steps.

Ready to automate your mobile experience? Follow these steps to get mobile-use up and running.

πŸ› οΈ Run locally

Mobile-use runs on your own Android or iOS device with your choice of supported LLM provider. Start with the [local quickstart](https://docs.minitap.ai/mobile-use-sdk/quickstart).

1. **Set up Environment Variables:** Copy the example `.env.example` file to `.env` and add your API keys.

```bash cp .env.example .env ```

2. **(Optional) Customize LLM Configuration:** To use different models or providers, create your own LLM configuration file.

```bash cp llm-config.override.template.jsonc llm-config.override.jsonc ```

Then, edit `llm-config.override.jsonc` to fit your needs.

You can also use local LLMs or any other openai-api compatible providers :

1. Set `OPENAI_BASE_URL` and `OPENAI_API_KEY` in your `.env` 2. In your `llm-config.override.jsonc`, set `openai` as the provider for the agent nodes you want, and choose a model supported by your provider.

**Using MiniMax:**

[MiniMax](https://www.minimaxi.com/) provides high-performance, OpenAI-compatible LLMs for agentic and coding tasks. To use MiniMax as your provider:

1. Set `MINIMAX_API_KEY` in your `.env` 2. Copy the contents of the `minimax` preset object from `llm-config.defaults.jsonc` into your `llm-config.override.jsonc`, or set `"provider": "minimax"` on individual agent nodes.

Available models: `MiniMax-M2.7` (200K context, recommended), `MiniMax-M2.7-highspeed` (200K context, faster inference).

**Using Anthropic Claude:**

[Anthropic](https://www.anthropic.com/) provides Claude β€” a capable, safety-focused model family. To use it:

1. Set `ANTHROPIC_API_KEY` in your `.env` 2. Copy the contents of the `anthropic` preset object from `llm-config.defaults.jsonc` into your `llm-config.override.jsonc`, or set `"provider": "anthropic"` on individual agent nodes.

Available models: `claude-sonnet-4-6` (200K context, recommended), `claude-haiku-4-5-20251001` (200K context, faster/cheaper).

> [!NOTE] > If you want to use Google Vertex AI, you must either: > > - Have credentials configured for your environment (gcloud, workload identity, etc…) > - Store the path to a service account JSON file as the GOOGLE_APPLICATION_CREDENTIALS environment variable > > More information: - [Credential types](https://cloud.google.com/docs/authentication/application-default-credentials#GAC) - [google.auth API reference](https://googleapis.dev/python/google-auth/latest/reference/google.auth.html#module-google.auth)

Quick Launch (Docker)

> [!NOTE] > This quickstart, is only available for Android devices/emulators as of now, and you must have Docker installed.

First:

- Either plug your Android device and enable USB-debugging via the Developer Options - Or launch an Android emulator

Then run in your terminal:

1. For Linux/macOS:

chmod +x mobile-use.sh
bash ./mobile-use.sh \
  "Open Gmail, find first 3 unread emails, and list their sender and subject line" \
  --output-description "A JSON list of objects, each with 'sender' and 'subject' keys"

2. For Windows (inside a Powershell terminal):

powershell.exe -ExecutionPolicy Bypass -File mobile-use.ps1 `
  "Open Gmail, find first 3 unread emails, and list their sender and subject line" `
  --output-description "A JSON list of objects, each with 'sender' and 'subject' keys"

> [!NOTE] > If using your own device, make sure to accept the ADB-related connection requests that will pop up on your device.

🧰 Troubleshooting

The script will try to connect to your device via IP. Therefore, your device **must be connected to the same Wi-Fi network as your computer**.

1. No device IP found

If the script fails with the following message:

Could not get device IP. Is a device connected via USB and on the same Wi-Fi network?

What was scanned

The files the safety scan read, as written by the repository's author and shown as plain text. Lines with a finding are marked.

README.md Β· README Β· 313 lines

View this file on GitHub (read at the repository's current version: the scan did not record which commit it read)

  1. # mobile-use: automate your phone with natural language
  2. <div align="center">
  3. ![mobile-use in Action](./doc/banner-v2.png)
  4. </div>
  5. <div align="center">
  6. [![Discord](https://img.shields.io/discord/1403058278342201394?color=7289DA&label=Discord&logo=discord&logoColor=white&style=for-the-badge)](https://discord.gg/6nSqmQ9pQs)
  7. [![GitHub stars](https://img.shields.io/github/stars/minitap-ai/mobile-use?style=for-the-badge&color=e0a8dd)](https://github.com/minitap-ai/mobile-use/stargazers)
  8. <h3>
  9. <a href="https://docs.minitap.ai/v2/mcp-server/introduction"><b>πŸ“š Documentation</b></a> β€’
  10. <a href="https://arxiv.org/abs/2602.07787"><b>πŸ“ƒ Paper</b></a>
  11. </h3>
  12. <p align="center">
  13. <a href="https://discord.gg/6nSqmQ9pQs"><b>Discord</b></a> β€’
  14. <a href="https://x.com/minitap_ai?t=iRWtI497UhRGLeCKYQekig&s=09"><b>Twitter / X</b></a>
  15. </p>
  16. [![PyPI version](https://img.shields.io/pypi/v/minitap-mobile-use.svg?color=blue)](https://pypi.org/project/minitap-mobile-use/)
  17. [![Python Version](https://img.shields.io/badge/python-3.12%2B-blue)](https://www.python.org/downloads/)
  18. [![License](https://img.shields.io/badge/license-Apache%202.0-blue)](https://github.com/minitap-ai/mobile-use/blob/main/LICENSE)
  19. </div>
  20. Mobile-use is a powerful, open-source AI agent that controls your Android or IOS device using natural language. It understands your commands and interacts with the UI to perform tasks, from sending messages to navigating complex apps.
  21. > Mobile-use is quickly evolving. Your suggestions, ideas, and reported bugs will shape this project. Do not hesitate to join in the conversation on [Discord](https://discord.gg/6nSqmQ9pQs) or contribute directly, we will reply to everyone! ❀️
  22. ## ✨ Features
  23. - πŸ—£οΈ **Natural Language Control**: Interact with your phone using your native language.
  24. - πŸ“± **UI-Aware Automation**: Intelligently navigates through app interfaces (note: currently has limited effectiveness with games as they don't provide accessibility tree data).
  25. - πŸ“Š **Data Scraping**: Extract information from any app and structure it into your desired format (e.g., JSON) using a natural language description.
  26. - πŸ”§ **Extensible & Customizable**: Easily configure different LLMs to power the agents that power mobile-use. Supports OpenAI, Google, xAI, OpenRouter, MiniMax, and more.
  27. ## Benchmarks
  28. <p align="center">
  29. <a href="https://minitap.ai/benchmark">
  30. <img src="https://files.peachworlds.com/website/2b590171-669d-42ce-b4b5-ce6eae83a9d8/scorerank-140126.webp" alt="Project banner" />
  31. </a>
  32. </p>
  33. We stand as the top performers and the first to have completed 100% of the AndroidWorld benchmark.
  34. Get more info about how we reached this milestone here: [Minitap Benchmark](https://minitap.ai/benchmark).
  35. The official leaderboard is available [here](https://docs.google.com/spreadsheets/d/1cchzP9dlTZ3WXQTfYNhh3avxoLipqHN75v1Tb86uhHo/edit?pli=1&gid=0#gid=0).
  36. Check out our research paper [here](https://arxiv.org/abs/2602.07787).
  37. ## πŸš€ Getting Started
  38. Ready to automate your mobile experience? Follow these steps to get mobile-use up and running.
  39. ### πŸ› οΈ Run locally
  40. Mobile-use runs on your own Android or iOS device with your choice of supported LLM provider. Start with the [local quickstart](https://docs.minitap.ai/mobile-use-sdk/quickstart).
  41. 1. **Set up Environment Variables:**
  42. Copy the example `.env.example` file to `.env` and add your API keys.
  43. ```bash
  44. cp .env.example .env
  45. ```
  46. 2. **(Optional) Customize LLM Configuration:**
  47. To use different models or providers, create your own LLM configuration file.
  48. ```bash
  49. cp llm-config.override.template.jsonc llm-config.override.jsonc
  50. ```
  51. Then, edit `llm-config.override.jsonc` to fit your needs.
  52. You can also use local LLMs or any other openai-api compatible providers :
  53. 1. Set `OPENAI_BASE_URL` and `OPENAI_API_KEY` in your `.env`
  54. 2. In your `llm-config.override.jsonc`, set `openai` as the provider for the agent nodes you want, and choose a model supported by your provider.
  55. **Using MiniMax:**
  56. [MiniMax](https://www.minimaxi.com/) provides high-performance, OpenAI-compatible LLMs for agentic and coding tasks. To use MiniMax as your provider:
  57. 1. Set `MINIMAX_API_KEY` in your `.env`
  58. 2. Copy the contents of the `minimax` preset object from `llm-config.defaults.jsonc` into your `llm-config.override.jsonc`, or set `"provider": "minimax"` on individual agent nodes.
  59. Available models: `MiniMax-M2.7` (200K context, recommended), `MiniMax-M2.7-highspeed` (200K context, faster inference).
  60. **Using Anthropic Claude:**
  61. [Anthropic](https://www.anthropic.com/) provides Claude β€” a capable, safety-focused model family. To use it:
  62. 1. Set `ANTHROPIC_API_KEY` in your `.env`
  63. 2. Copy the contents of the `anthropic` preset object from `llm-config.defaults.jsonc` into your `llm-config.override.jsonc`, or set `"provider": "anthropic"` on individual agent nodes.
  64. Available models: `claude-sonnet-4-6` (200K context, recommended), `claude-haiku-4-5-20251001` (200K context, faster/cheaper).
  65. > [!NOTE]
  66. > If you want to use Google Vertex AI, you must either:
  67. >
  68. > - Have credentials configured for your environment (gcloud, workload identity, etc…)
  69. > - Store the path to a service account JSON file as the GOOGLE_APPLICATION_CREDENTIALS environment variable
  70. >
  71. > More information: - [Credential types](https://cloud.google.com/docs/authentication/application-default-credentials#GAC) - [google.auth API reference](https://googleapis.dev/python/google-auth/latest/reference/google.auth.html#module-google.auth)
  72. ### Quick Launch (Docker)
  73. > [!NOTE]
  74. > This quickstart, is only available for Android devices/emulators as of now, and you must have Docker installed.
  75. First:
  76. - Either plug your Android device and enable USB-debugging via the Developer Options
  77. - Or launch an Android emulator
  78. Then run in your terminal:
  79. 1. For Linux/macOS:
  80. ```bash
  81. chmod +x mobile-use.sh
  82. bash ./mobile-use.sh \
  83. "Open Gmail, find first 3 unread emails, and list their sender and subject line" \
  84. --output-description "A JSON list of objects, each with 'sender' and 'subject' keys"
  85. ```
  86. 2. For Windows (inside a Powershell terminal):
  87. ```powershell
  88. powershell.exe -ExecutionPolicy Bypass -File mobile-use.ps1 `
  89. "Open Gmail, find first 3 unread emails, and list their sender and subject line" `
  90. --output-description "A JSON list of objects, each with 'sender' and 'subject' keys"
  91. ```
  92. > [!NOTE]
  93. > If using your own device, make sure to accept the ADB-related connection requests that will pop up on your device.
  94. #### 🧰 Troubleshooting
  95. The script will try to connect to your device via IP.
  96. Therefore, your device **must be connected to the same Wi-Fi network as your computer**.
  97. ##### 1. No device IP found
  98. If the script fails with the following message:
  99. ```
  100. Could not get device IP. Is a device connected via USB and on the same Wi-Fi network?
  101. ```
  102. Then it couldn't find one of the common Wi-Fi interfaces on your device.
  103. Therefore, you must determine what WLAN interface your phone is using via `adb shell ip addr show up`.
  104. Then add the `--interface <YOUR_INTERFACE_NAME>` option to the script.
  105. ##### 2. Failed to connect to <DEVICE_IP>:5555 inside Docker
  106. This is most probably an issue with your firewall blocking the connection. Therefore there is no clear fix for this.
  107. ##### 3. Failed to pull GHCR docker images (unauthorized)
  108. Since UV docker images rely on a `ghcr.io` public repositories, you may have an expired token if you used `ghcr.io` before for private repositories.
  109. Try running `docker logout ghcr.io` and then run the script again.
  110. ### Manual Launch (Development Mode)
  111. For developers who want to set up the environment manually:
  112. #### 1. Device Support
  113. Mobile-use currently supports the following devices:
  114. - **Physical Android Phones**: Connect via USB with USB debugging enabled.
  115. - **Android Simulators**: Set up through Android Studio.
  116. - **iOS Simulators**: Supported for macOS users.
  117. > [!NOTE]
  118. > Physical iOS devices are not yet supported.
  119. #### 2. Prerequisites
  120. **For Android:**
  121. - **[Android Debug Bridge (ADB)](https://developer.android.com/studio/releases/platform-tools)**: A tool to connect to your device.
  122. **For iOS (macOS only):**
  123. - **[Xcode](https://developer.apple.com/xcode/)**: Apple's IDE for iOS development.
  124. - **[fb-idb](https://fbidb.io/docs/installation/)**: Facebook's iOS Development Bridge for device automation.
  125. ```bash
  126. # Install via Homebrew (macOS)
  127. brew tap facebook/fb
  128. brew install idb-companion
  129. ```
  130. > [!NOTE]
  131. > `idb_companion` is required to communicate with iOS simulators. Make sure it's in your PATH after installation.
  132. **Common requirements:**
  133. Before you begin, ensure you have the following installed:
  134. - **[uv](https://github.com/astral-sh/uv)**: A lightning-fast Python package manager.
  135. #### 3. Installation
  136. 1. **Clone the repository:**
  137. ```bash
  138. git clone https://github.com/minitap-ai/mobile-use.git && cd mobile-use
  139. ```
  140. 2. [**Setup environment variables**](#-getting-started)
  141. 3. **Create & activate the virtual environment:**
  142. ```bash
  143. # This will create a .venv directory using the Python version in .python-version
  144. uv venv
  145. # Activate the environment
  146. # On macOS/Linux:
  147. source .venv/bin/activate
  148. # On Windows:
  149. .venv\Scripts\activate
  150. ```
  151. 4. **Install dependencies:**
  152. ```bash
  153. # Sync with the locked dependencies for a consistent setup
  154. uv sync
  155. ```
  156. ## πŸ‘¨β€πŸ’» Usage
  157. To run mobile-use, simply pass your command as an argument.
  158. **Example 1: Basic Command**
  159. ```bash
  160. python ./minitap/mobile_use/main.py "Go to settings and tell me my current battery level"
  161. ```
  162. **Example 2: Data Scraping**
  163. Extract specific information and get it back in a structured format. For instance, to get a list of your unread emails:
  164. ```bash
  165. python ./minitap/mobile_use/main.py \
  166. "Open Gmail, find all unread emails, and list their sender and subject line" \
  167. --output-description "A JSON list of objects, each with 'sender' and 'subject' keys"
  168. ```
  169. > [!NOTE]
  170. > If you haven't configured a specific model, mobile-use will prompt you to choose one from the available options.
  171. ## πŸ”Ž Agentic System Overview
  172. <div align="center">
  173. ![Graph Visualization](doc/graph.png)
  174. _This diagram is automatically updated from the codebase. This is our current agentic system architecture._
  175. </div>
  176. ## ❀️ Contributing
  177. We love contributions! Whether you're fixing a bug, adding a feature, or improving documentation, your help is welcome. Please read our **[Contributing Guidelines](CONTRIBUTING.md)** to get started.
  178. ## ⭐ Star History
  179. <p align="center">
  180. <a href="https://star-history.dera.page/#minitap-ai/mobile-use&Date">
  181. <img src="https://star-history.dera.page/svg?repos=minitap-ai/mobile-use&type=Date" alt="Star History Chart" />
  182. </a>
  183. </p>
  184. ## πŸ† Attribution & Licensing
  185. `mobile-use` is the first agentic framework to achieve **100% on the AndroidWorld benchmark**.
  186. This project is licensed under the **Apache License 2.0**.
  187. If you use this code, or are inspired by the architecture used to reach our benchmark results, we kindly request that you credit Minitap, Inc.
  188. ### How to Cite
  189. If you use this work in research or a commercial product, please use the following:
  190. > Pierre-Louis Favreau, Jean-Pierre Lo, Clement Guiguet, Charles Simon-Meunier,
  191. Nicolas Dehandschoewercker, Allen G. Roush, Judah Goldfeder, Ravid Shwartz-Ziv.
  192. _Do Multi-Agents Dream of Electric Screens? Achieving Perfect Accuracy on AndroidWorld Through Task Decomposition._
  193. arXiv preprint arXiv:2602.07787 (2026).
  194. https://arxiv.org/abs/2602.07787
  195. #### Bibtex
  196. ```bibtex
  197. @misc{favreau2026multiagentsdreamelectricscreens,
  198. title = {Do Multi-Agents Dream of Electric Screens? Achieving Perfect Accuracy on AndroidWorld Through Task Decomposition},
  199. author = {Pierre-Louis Favreau and Jean-Pierre Lo and Clement Guiguet and Charles Simon-Meunier and Nicolas Dehandschoewercker and Allen G. Roush and Judah Goldfeder and Ravid Shwartz-Ziv},
  200. year = {2026},
  201. eprint = {2602.07787},
  202. archivePrefix= {arXiv},
  203. primaryClass = {cs.AI},
  204. url = {https://arxiv.org/abs/2602.07787}
  205. }

Ratings and comments

Sign in to rate this skill.

Sign in

Free to use. If it’s helped, pass it on.