E2B Desktop Sandbox is an isolated cloud environment with a desktop-like interface powered by E2B. Ready for AI Computer Use - check out the example.
Launching E2B Sandbox takes about 300-500ms. You can customize the desktop environment and preinstall any dependencies you want using our custom sandbox templates.
Work in progress This repository is a work in progress. We welcome feedback and contributions. Here's the list of features we're working on:
- JavaScript SDK
- Streaming live desktop
- Tests
- Docstrings
The E2B Desktop Sandbox is built on top of E2B Sandbox.
Sign up at E2B and get your API key.
Set environment variable E2B_API_KEY with your API key.
Python
pip install e2b-desktopJavaScript
Coming soonfrom e2b_desktop import Sandbox
desktop = Sandbox()from e2b_desktop import Sandbox
desktop = Sandbox()
desktop.double_click()
desktop.left_click()
desktop.right_click()
desktop.middle_click()
desktop.scroll(10) # Scroll by the amount. Positive for up, negative for down.
desktop.mouse_move(100, 200) # Move to x, y coordinatesfrom e2b_desktop import Sandbox
desktop = Sandbox()
# Find "Home" text on the screen and return the coordinates
x, y = desktop.locate_on_screen("Home")
# Move the mouse to the coordinates
desktop.mouse_move(x, y)from e2b_desktop import Sandbox
desktop = Sandbox()
desktop.write("Hello, world!") # Write text at the current cursor position
desktop.hotkey("ctrl", "c") # Press ctrl+cfrom e2b_desktop import Sandbox
desktop = Sandbox()
# Take a screenshot and save it as "screenshot.png" locally
desktop.screenshot("screenshot.png")from e2b_desktop import Sandbox
desktop = Sandbox()
# Open file with default application
desktop.files.write("/home/user/index.js", "console.log('hello')") # First create the file
desktop.open("/home/user/index.js") # Then open itfrom e2b_desktop import Sandbox
desktop = Sandbox()
# Run any bash command
desktop.commands.run("ls -la /home/user")from e2b_desktop import Sandbox
desktop = Sandbox()
# Run any PyAutoGUI command
desktop.pyautogui("pyautogui.click()")You can use PyAutoGUI to control the whole environment programmatically.
The desktop-like environment is based on Linux and Xfce at the moment. We chose Xfce because it's a fast and lightweight environment that's also popular and actively supported. However, this Sandbox template is fully customizable and you can create your own desktop environment. Check out the sandbox template's code here.