Skip to content

Automate your mobile devices with natural language commands - an LLM agnostic mobile Agent πŸ€–

License

Notifications You must be signed in to change notification settings

zhaopufeng/droidrun

Β 
Β 

Repository files navigation

Docs Cloud

GitHub stars droidrun.ai Twitter Follow Discord Benchmark

Droidrun - Give AI native control of physical & virtual phones. | Product Hunt

DroidRun is a powerful framework for controlling Android and iOS devices through LLM agents. It allows you to automate device interactions using natural language commands. Checkout our benchmark results

Why Droidrun?

  • πŸ€– Control Android and iOS devices with natural language commands
  • πŸ”€ Supports multiple LLM providers (OpenAI, Anthropic, Gemini, Ollama, DeepSeek)
  • 🧠 Planning capabilities for complex multi-step tasks
  • πŸ’» Easy to use CLI with enhanced debugging features
  • 🐍 Extendable Python API for custom automations
  • πŸ“Έ Screenshot analysis for visual understanding of the device
  • πŸ«† Execution tracing with Arize Phoenix

πŸ“¦ Installation

pip install 'droidrun[google,anthropic,openai,deepseek,ollama,dev]'

πŸš€ Quickstart

Read on how to get droidrun up and running within seconds in our docs!

Quickstart Video

🎬 Demo Videos

  1. Accommodation booking: Let Droidrun search for an apartment for you

    Droidrun Accommodation Booking Demo


  1. Trend Hunter: Let Droidrun hunt down trending posts

    Droidrun Trend Hunter Demo


  1. Streak Saver: Let Droidrun save your streak on your favorite language learning app

    Droidrun Streak Saver Demo

πŸ’‘ Example Use Cases

  • Automated UI testing of mobile applications
  • Creating guided workflows for non-technical users
  • Automating repetitive tasks on mobile devices
  • Remote assistance for less technical users
  • Exploring mobile UI with natural language commands

πŸ‘₯ Contributing

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

πŸ“„ License

This project is licensed under the MIT License - see the LICENSE file for details.

Security Checks

To ensure the security of the codebase, we have integrated security checks using bandit and safety. These tools help identify potential security issues in the code and dependencies.

Running Security Checks

Before submitting any code, please run the following security checks:

  1. Bandit: A tool to find common security issues in Python code.

    bandit -r droidrun
  2. Safety: A tool to check your installed dependencies for known security vulnerabilities.

    safety scan

About

Automate your mobile devices with natural language commands - an LLM agnostic mobile Agent πŸ€–

Resources

License

Contributing

Stars

Watchers

Forks

Releases

No releases published

Packages

No packages published

Languages

  • Python 93.9%
  • Jinja 6.0%
  • Shell 0.1%