Desktops for AI agents 💻
Explore the docs »
View Demo
·
Report Bug
·
Request Feature
AgentDesk provides full-featured desktop environments which can be programatically controlled by AI agents. Spin them up locally or in the cloud.
▶ Built on agentd a runtime daemon which exposes a REST API for interacting with the desktop.
▶ Implements the DeviceBay Protocol.
pip install agentdesk
from agentdesk import Desktop
# Create a desktop container
desktop = Desktop.docker()
# Launch the UI for it
desktop.view(background=True)
# Open a browser to Google
desktop.open_url("https://google.com")
# Take actions on the desktop
desktop.move_mouse(500, 500)
desktop.click()
img = desktop.take_screenshots()from agentdesk import Desktop
desktop = Desktop.docker()$ agentdesk create --provider docker*requires docker
desktop = Desktop.kube()$ agentdesk create --provider kubedesktop.view()$ agentdesk view old_mckinny*requires docker
Desktop.find()$ agentdesk getDesktop.delete("old_mckinny")$ agentdesk delete old_mckinnydesktop.open_url("https://google.com")
coords = desktop.mouse_coordinates()
desktop.move_mouse(500, 500)
desktop.click()
desktop.type_text("What kind of ducks are in Canada?")
desktop.press_key('Enter')
desktop.scroll()
img = desktop.take_screenshots()Process images to make them more accessible to LMMs.
Add a coordinate grid on top of the image
from agentdesk.processors import GridProcessor
img = desktop.take_screenshots()
processor = GridProcessor()
grid_img = processor.process_b64(img)Come join us on Discord.
Please open an issue before creating a PR.
Changes to the VM happen in agentd.