hanzo-operator 0.0.1

A framework to enable multimodal models to operate a computer

Hanzo Operator

Self-Operating Computer Framework

A framework to enable multimodal models to operate a computer.

Using the same inputs and outputs as a human operator, the model views the screen and decides on a series of mouse and keyboard actions to reach an objective. Hanzo Operator is a powerful framework for computer automation using multimodal AI models.

Key Features

• Compatibility: Designed for various multimodal models.
• Integration: Currently integrated with GPT-4o, o1, Gemini Pro Vision, Claude 3, Qwen-VL and LLaVa.
• Future Plans: Support for additional models.

Demo

https://github.com/OthersideAI/self-operating-computer/assets/42594239/9e8abc96-c76a-46fb-9b13-03678b3c67e0

Run Self-Operating Computer

1. Install the project

pip install hanzo-operator

2. Run the project

hanzo

3. Enter your OpenAI Key: If you don't have one, you can obtain an OpenAI key here. If you need you change your key at a later point, run vim .env to open the .env and replace the old key.

4. Give Terminal app the required permissions: As a last step, the Terminal app will ask for permission for "Screen Recording" and "Accessibility" in the "Security & Privacy" page of Mac's "System Preferences".

Using hanzo Modes

OpenAI models

The default model for the project is gpt-4o which you can use by simply typing hanzo. To try running OpenAI's new o1 model, use the command below.

hanzo -m o1-with-ocr

Multimodal Models -m

Try Google's gemini-pro-vision by following the instructions below. Start hanzo with the Gemini model

hanzo -m gemini-pro-vision

Enter your Google AI Studio API key when terminal prompts you for it If you don't have one, you can obtain a key here after setting up your Google AI Studio account. You may also need authorize credentials for a desktop application. It took me a bit of time to get it working, if anyone knows a simpler way, please make a PR.

Try Claude -m claude-3

Use Claude 3 with Vision to see how it stacks up to GPT-4-Vision at operating a computer. Navigate to the Claude dashboard to get an API key and run the command below to try it.

hanzo -m claude-3

Try qwen -m qwen-vl

Use Qwen-vl with Vision to see how it stacks up to GPT-4-Vision at operating a computer. Navigate to the Qwen dashboard to get an API key and run the command below to try it.

hanzo -m qwen-vl

Try LLaVa Hosted Through Ollama -m llava

If you wish to experiment with the Self-Operating Computer Framework using LLaVA on your own machine, you can with Ollama!
Note: Ollama currently only supports MacOS and Linux. Windows now in Preview

First, install Ollama on your machine from https://ollama.ai/download.

Once Ollama is installed, pull the LLaVA model:

ollama pull llava

This will download the model on your machine which takes approximately 5 GB of storage.

When Ollama has finished pulling LLaVA, start the server:

ollama serve

That's it! Now start hanzo and select the LLaVA model:

hanzo -m llava

Important: Error rates when using LLaVA are very high. This is simply intended to be a base to build off of as local multimodal models improve over time.

Learn more about Ollama at its GitHub Repository

Voice Mode --voice

The framework supports voice inputs for the objective. Try voice by following the instructions below. Clone the repo to a directory on your computer:

git clone https://github.com/OthersideAI/self-operating-computer.git

Cd into directory:

cd self-operating-computer

Install the additional requirements-audio.txt

pip install -r requirements-audio.txt

Install device requirements For mac users:

brew install portaudio

For Linux users:

sudo apt install portaudio19-dev python3-pyaudio

Run with voice mode

hanzo --voice

Optical Character Recognition Mode -m gpt-4-with-ocr

The Self-Operating Computer Framework now integrates Optical Character Recognition (OCR) capabilities with the gpt-4-with-ocr mode. This mode gives GPT-4 a hash map of clickable elements by coordinates. GPT-4 can decide to click elements by text and then the code references the hash map to get the coordinates for that element GPT-4 wanted to click.

Based on recent tests, OCR performs better than som and vanilla GPT-4 so we made it the default for the project. To use the OCR mode you can simply write:

hanzo or hanzo -m gpt-4-with-ocr will also work.

Set-of-Mark Prompting -m gpt-4-with-som

The Self-Operating Computer Framework now supports Set-of-Mark (SoM) Prompting with the gpt-4-with-som command. This new visual prompting method enhances the visual grounding capabilities of large multimodal models.

Learn more about SoM Prompting in the detailed arXiv paper: here.

For this initial version, a simple YOLOv8 model is trained for button detection, and the best.pt file is included under model/weights/. Users are encouraged to swap in their best.pt file to evaluate performance improvements. If your model outperforms the existing one, please contribute by creating a pull request (PR).

Start hanzo with the SoM model

hanzo -m gpt-4-with-som

Contributions are Welcomed!:

If you want to contribute yourself, see CONTRIBUTING.md.

Feedback

For any input on improving this project, feel free to reach out to Josh on Twitter.

Join Our Discord Community

For real-time discussions and community support, join our Discord server.

• If you're already a member, join the discussion in #self-operating-computer.
• If you're new, first join our Discord Server and then navigate to the #self-operating-computer.

Follow HyperWriteAI for More Updates

Stay updated with the latest developments:

• Follow HyperWriteAI on Twitter.
• Follow HyperWriteAI on LinkedIn.

Compatibility

• This project is compatible with Mac OS, Windows, and Linux (with X server installed).

OpenAI Rate Limiting Note

The gpt-4o model is required. To unlock access to this model, your account needs to spend at least $5 in API credits. Pre-paying for these credits will unlock access if you haven't already spent the minimum $5.
Learn more here