The Dawn of GUI Agent: A Preliminary Case Study with Claude 3.5 Computer Use

If you like our project, please give us a star ⭐ on GitHub for the latest update.

[](https://arxiv.org/abs/2411.10323) [](https://hits.seeyoufarm.com/api/count/incr/badge.svg?url=https%3A%2F%2Fgithub.com%2Fshowlab%2Fcomputer_use_ootb&count_bg=%2379C83D&title_bg=%23555555&icon=&icon_color=%23E7E7E7&title=hits&edge_flat=false)

🌟 Overview

This is an out-of-the-box (OOTB) solution for Claude's new Computer Use APIs.

No Docker is required, and it supports both Windows and macOS. This project provides a user-friendly interface based on Gradio. 🎨

For more information, you can visit our project page. 🌐

Update

• [2024/11/20] We've added some examples to help you get hands-on experience with Claude 3.5 Computer Use.
• [2024/11/19] Forget about the single-display limit set by Anthropic - you can now use multiple displays 🎉!
• [2024/11/18] We've released a deep analysis of Claude 3.5 Computer Use: https://arxiv.org/abs/2411.10323.
• [2024/11/11] Forget about the low-resolution display limit set by Anthropic — you can now use any resolution you like and still keep the screenshot token cost low 🎉!
• [2024/11/11] Now both Windows and macOS platforms are supported 🎉!
• [2024/10/25] Now you can Remotely Control your computer 💻 through your mobile device 📱 — No Mobile App Installation required! Give it a try and have fun 🎉.

Demo Video

https://github.com/user-attachments/assets/333e536e-93d0-4a97-8c9b-8f0722c29d51

🚀 Getting Started

0. Prerequisites

• Instal Miniconda on your system through this link. (Python Version: >= 3.11).

1. Clone the Repository 📂

Open the Conda Terminal. (After installation Of Miniconda, it will appear in the Start menu.) Run the following command on Conda Terminal.

git clone https://github.com/showlab/computer_use_ootb.git
cd computer_use_ootb

2. Install Dependencies 🔧

pip install -r dev-requirements.txt

3. Start the Interface ▶️

python app.py

If you successfully start the interface, you will see two URLs in the terminal:

* Running on local URL:  http://127.0.0.1:7860
* Running on public URL: https://xxxxxxxxxxxxxxxx.gradio.live (Do not share this link with others, or they will be able to control your computer.)

4. Control Your Computer with Any Device can Access the Internet

• Computer to be controlled: The one installed software.
• Device Send Command: The one opens the website.

Open the website at http://localhost:7860/ (if you're controlling the computer itself) or https://xxxxxxxxxxxxxxxxx.gradio.live in your mobile browser for remote control.

Enter the Anthropic API key (you can obtain it through this website), then give commands to let the AI perform your tasks.

Mobile Interface

Desktop Interface

🖥️ Supported Systems

• Windows ✅
• macOS ✅

⚠️ Risks

• Potential Dangerous Operations by the Model: The models' performance is still limited and may generate unintended or potentially harmful outputs. Recommend continuously monitoring the AI's actions.
• Cost Control Challenges: Each task may cost a few dollars. We'll optimize this in the future. 💸

📅 Roadmap

• [ ] Explore available features
  • [ ] The Claude API seems to be unstable when solving tasks. We are investigating the reasons: resolutions, types of actions required, os platforms, or planning mechanisms. Welcome any thoughts or comments on it.
• [ ] Interface Design
  • [x] Support for Gradio ✨
  • [ ] Simpler Installation
  • [ ] More Features... 🚀
• [ ] Platform
  • [x] Windows
  • [x] Mobile (Send command)
  • [x] macOS
  • [ ] Mobile (Be controlled)
• [ ] Support for More MLLMs
  • [x] Claude 3.5 Sonnet 🎵
  • [ ] GPT-4o
  • [ ] Qwen2-VL
  • [ ] ...
• [ ] Improved Prompting Strategy
  • [ ] Optimize prompts for cost-efficiency. 💡

Join Discussion

Welcome to discuss with us and continuously improve the user experience of Computer Use - OOTB. Reach us using this Discord Channel or the WeChat QR code below!