---
title: "mobilerun"
type: "tool"
slug: "droidrun-mobilerun"
canonical_url: "https://www.graphcanon.com/tools/droidrun-mobilerun"
github_url: "https://github.com/droidrun/mobilerun"
homepage_url: "https://mobilerun.ai/framework"
stars: 8709
forks: 924
primary_language: "Python"
license: "MIT"
categories: ["developer-tools", "ai-agents"]
tags: ["ios-automation", "natural-language-processing", "android-automation", "ai-agents"]
updated_at: "2026-07-07T18:35:55.69703+00:00"
---

# mobilerun

> Mobilerun is an open-source framework for controlling Android and iOS devices with LLM agents.

Automate mobile devices using natural language commands via various LLM models. Offers direct task execution or reasoning mode for intricate workflows, accessible through CLI, terminal UIs, and the Dock.

## Facts

- Repository: https://github.com/droidrun/mobilerun
- Homepage: https://mobilerun.ai/framework
- Stars: 8,709 · Forks: 924 · Open issues: 29 · Watchers: 49
- Primary language: Python
- License: MIT
- Last pushed: 2026-07-06T18:32:45+00:00

## Categories

- [Developer Tools](/categories/developer-tools.md)
- [AI Agents](/categories/ai-agents.md)

## Tags

ios-automation, natural-language-processing, android-automation, ai-agents

## Related tools

- [ECC](/tools/affaan-m-ecc.md) - The agent harness performance optimization system (★ 226,962)
- [hermes-agent](/tools/nousresearch-hermes-agent.md) - The self-improving AI agent built by Nous Research (★ 210,880)
- [AutoGPT](/tools/significant-gravitas-autogpt.md) - AutoGPT: Build, Deploy, and Run AI Agents (★ 185,417)
- [ollama](/tools/ollama-ollama.md) - Get up and running with Kimi-K2.6, GLM-5.1, MiniMax, DeepSeek, gpt-oss, Qwen, Gemma and other models. (★ 175,659)
- [prompts.chat](/tools/f-prompts-chat.md) - The world's largest open-source prompt library for AI (★ 165,019)
- [JavaGuide](/tools/snailclimb-javaguide.md) - Snailclimb/JavaGuide: 面试 & 后端通用面试指南，覆盖计算机基础、数据库、分布式、高并发、系统设计与 AI 应用开发 (★ 156,863)
- [langflow](/tools/langflow-ai-langflow.md) - Langflow is a powerful platform for building and deploying AI-powered agents and workflows. (★ 151,298)
- [dify](/tools/langgenius-dify.md) - Production-ready platform for agentic workflow development (★ 148,070)

## README (excerpt)

```text
<picture align="center">
  <source media="(prefers-color-scheme: dark)" srcset="./static/mobilerun-dark.png">
  <source media="(prefers-color-scheme: light)" srcset="./static/mobilerun.png">
  <img src="./static/mobilerun.png"  width="full">
</picture>

<p align="center">
  <strong>Mobilerun is an open-source framework for controlling Android and iOS devices with LLM agents.</strong><br>
  It gives agents mobile-native tools to inspect UI state, understand screenshots, tap, swipe, type, plan multi-step workflows, and return results through a CLI or Python API.
</p>

<div align="center">

<a href="https://docs.mobilerun.ai">📕 Documentation</a>
·
<a href="https://cloud.mobilerun.ai">☁️ Mobilerun Cloud</a>









<picture>
  <source media="(prefers-color-scheme: dark)" srcset="https://api.producthunt.com/widgets/embed-image/v1/top-post-badge.svg?post_id=983810&theme=dark&period=daily&t=1753948032207">
  <source media="(prefers-color-scheme: light)" srcset="https://api.producthunt.com/widgets/embed-image/v1/top-post-badge.svg?post_id=983810&theme=neutral&period=daily&t=1753948125523">
  <a href="https://www.producthunt.com/products/droidrun-framework-for-mobile-agent?embed=true&utm_source=badge-top-post-badge&utm_medium=badge&utm_source=badge-droidrun" target="_blank"><img src="https://api.producthunt.com/widgets/embed-image/v1/top-post-badge.svg?post_id=983810&theme=neutral&period=daily&t=1753948125523" alt="Droidrun - Give&#0032;AI&#0032;native&#0032;control&#0032;of&#0032;physical&#0032;&#0038;&#0032;virtual&#0032;phones&#0046; | Product Hunt" style="width: 200px; height: 54px;" width="200" height="54" /></a>
</picture>


[Deutsch](https://zdoc.app/de/droidrun/mobilerun) | 
[Español](https://zdoc.app/es/droidrun/mobilerun) | 
[français](https://zdoc.app/fr/droidrun/mobilerun) | 
[日本語](https://zdoc.app/ja/droidrun/mobilerun) | 
[한국어](https://zdoc.app/ko/droidrun/mobilerun) | 
[Português](https://zdoc.app/pt/droidrun/mobilerun) | 
[Русский](https://zdoc.app/ru/droidrun/mobilerun) | 
[中文](https://zdoc.app/zh/droidrun/mobilerun)

</div>


<p align="center">
  <img src="./static/mobilerun-demo.gif" alt="Mobilerun automating a phone with natural language" width="320">
</p>

- 🤖 Control Android and iOS devices with natural language commands
- 🔀 Use OpenAI, Anthropic, Gemini, Ollama, DeepSeek, OpenRouter, and OpenAI-compatible models
- 🧠 Run direct tasks or enable reasoning mode for complex multi-step automation
- 💻 Automate from the CLI, a terminal UI, Docker, or Python code
- 🐍 Extend agents with custom tools, structured output, app cards, and credentials
- 📸 Combine accessibility trees with screenshots for visual understanding
- 🫆 Trace execution with Arize Phoenix or Langfuse

Use the framework when you want to run the agent on your machine. Use [Mobilerun Cloud](https://cloud.mobilerun.ai) when you want a ready-to-go solution for your local phones or cloud-hosted virtual/physical phones, managed infrastructure, and API-driven device workflows without running the agent on your local machine. [Check out our benchmark results](https://mobilerun.ai/benchmark).

## 📦 Installation

> **Note:** Python 3.14 is not currently supported. Please use Python `>=3.11,<3.14`.

Install Mobilerun with [`uv`](https://docs.astral.sh/uv/):

```bash
# CLI usage
uv tool install mobilerun
```

```bash
# CLI + Python integration
uv pip install mobilerun
```

Most LLM providers are included by default. For Anthropic support, install the optional extra:

```bash
uv tool install "mobilerun[anthropic]"
```

## 🚀 Quickstart

```bash
uv tool install mobilerun
mobilerun setup
mobilerun configure
mobilerun run "Open settings and turn on dark mode"
```

Before starting, make sure you have [ADB](https://developer.android.com/studio/releases/platform-tools) installed and an Android device with Developer options and USB debugging enabled. iOS setup is supported separately through the iOS Portal flow.

### 1. Install the Portal on your device

```bash
mobi
```

---

**Machine-readable endpoints**

- JSON: [`/api/graphcanon/tools/droidrun-mobilerun`](/api/graphcanon/tools/droidrun-mobilerun)
- LLM index: [/llms.txt](/llms.txt)
- Full corpus: [/llms-full.txt](/llms-full.txt)

_GraphCanon - The knowledge graph for AI development. https://www.graphcanon.com/_