app-use 0.0.1

Make mobile apps accessible for AI agents

Enable AI to control your mobile apps 🤖

📱 App Use is the easiest way to connect AI agents with mobile applications.

Our goal is to provide a powerful yet simple interface for AI agent app automation.

Quick start

With pip (Python>=3.11):

pip install app-use

For memory functionality (requires Python<3.13 due to PyTorch compatibility):

pip install "app-use[memory]"

Install and the necessary drivers (XCUITest and UiAutomator2): Appium

Define the app and mobile device you want to target:

    app = App(
        platform_name="ios",
        device_name='Your Device Name',
        bundle_id="com.apple.calculator",
        appium_server_url='http://localhost:4723',
        {"udid": 'device-id'},
    )

Spin up your agent:

import asyncio
from dotenv import load_dotenv
load_dotenv()
from app_use import Agent
from langchain_openai import ChatOpenAI

async def main():
    agent = Agent(
        task="What is 2+2?",
        llm=ChatOpenAI(model="gpt-4o"),
        app=app

    )
    await agent.run()

asyncio.run(main())

Add your API keys for the provider you want to use to your .env file.

OPENAI_API_KEY=
ANTHROPIC_API_KEY=
AZURE_OPENAI_ENDPOINT=
AZURE_OPENAI_KEY=
GOOGLE_API_KEY=
DEEPSEEK_API_KEY=
GROK_API_KEY=
NOVITA_API_KEY=

DEMOS

Ordering Shorts from the Lululemon App (iOS)

Ordering some tacos and a drink on DoorDash (IOS)

Community & Support

Contributions are welcome! Please feel free to submit a Pull Request.

App Use is actively maintained and designed to make mobile app control as simple and reliable as possible.

Made with ❤️ by Erick Torres