A secure cloud Linux computer powered by E2B Desktop Sandbox and controlled by open-source LLMs.

• Uses Llama 3.2, 3.3 and OS-Atlas
• Operates the computer via a combination of keyboard, mouse, and shell commands
• Live streams the display of the sandbox on the client computer
• The user can pause the agent and provide feedback and any time
• Designed to work on any operating system or platform
• Supports multiple inference providers, including Hugging Face, Fireworks, OpenRouter and Llama AI

The details of the design are laid out in this article: How I taught an AI to use a computer

• Python 3.10 or later
• git
• E2B API key
• LLM API keys:
  • Option 1: OpenRouter API key + Fireworks API key
  • Option 2: Llama API key

In your terminal:

brew install poetry ffmpeg

In your terminal:

git clone https://github.com/e2b-dev/open-computer-use/

Enter the project directory:

cd open-computer-use

Create a .env file in open-computer-use and set the following:

# Get your API key here - https://e2b.dev/
E2B_API_KEY="your-e2b-api-key"
LLAMA_API_KEY="your-llama-api-key"

or

# Get your API key here - https://e2b.dev/
E2B_API_KEY="your-e2b-api-key"
OPENROUTER_API_KEY="your-openrouter-api-key"
FIREWORKS_API_KEY="your-fireworks-api-key"

Run the following command to start the agent:

poetry install

poetry run start

The agent will start and prompt you for its first instruction.