trycua/cua

Source: https://github.com/trycua/cua

Build, benchmark, and deploy agents that use computers

Choose Your Path

Cua Driver - Background computer-use on macOS

Drive any native macOS app in the background — agents click, type, and verify without stealing the cursor, focus, or Space, even on non-AX surfaces like Chromium web content and canvas-based tools (Blender, Figma, DAWs, game engines). Use with the CLI or MCP server for Claude Code, Cursor, and custom clients. Every session records as a replayable trajectory.

/bin/bash -c "$(curl -fsSL https://raw.githubusercontent.com/trycua/cua/main/libs/cua-driver/scripts/install.sh)"

Full tool reference, architecture notes, and the Claude Code skill ship with the package: libs/cua-driver/README.md.

Cua - Agent-Ready Sandboxes for Any OS

Build agents that see screens, click buttons, and complete tasks autonomously. One API for any VM or container image — cloud or local.

pip install cua

# Requires Python 3.11 or later
from cua import Sandbox, Image

# Same API regardless of OS or runtime
async with Sandbox.ephemeral(Image.linux()) as sb:   # or .macos() .windows() .android()
    result = await sb.shell.run("echo hello")
    screenshot = await sb.screenshot()
    await sb.mouse.click(100, 200)
    await sb.keyboard.type("Hello from Cua!")
    await sb.mobile.gesture((100, 500), (100, 200))  # multi-touch gestures

Get Started | Examples | API Reference

CuaBot - Co-op computer-use for any agent

cuabot gives any coding agent a seamless sandbox for computer-use. Individual windows appear natively on your desktop with H.265, shared clipboard, and audio.

npx cuabot                 # Setup onboarding

# Run any agent in a sandbox
cuabot claude              # Claude Code
cuabot openclaw            # OpenClaw in the sandbox

# Run any GUI workflow in a sandbox
cuabot chromium
cuabot --screenshot
cuabot --type "hello"
cuabot --click <x> <y> [button]

Built-in support for agent-browser and agent-device (iOS, Android) out of the box.

Get Started | Installation | First spotted at ClawCon

Cua-Bench - Benchmarks & RL Environments

Evaluate computer-use agents on OSWorld, ScreenSpot, Windows Arena, and custom tasks. Export trajectories for training.

# Install and create base image
cd cua-bench
uv tool install -e . && cb image create linux-docker

# Run benchmark with agent
cb run dataset datasets/cua-bench-basic --agent cua-agent --max-parallel 4

Get Started | Partner With Us | Registry | CLI Reference

Lume - macOS Virtualization

Create and manage macOS/Linux VMs with near-native performance on Apple Silicon using Apple’s Virtualization.Framework.

# Install Lume
/bin/bash -c "$(curl -fsSL https://raw.githubusercontent.com/trycua/cua/main/libs/lume/scripts/install.sh)"

# Pull & start a macOS VM
lume run macos-sequoia-vanilla:latest

Get Started | FAQ | CLI Reference

Packages

Resources

• Documentation — Guides, examples, and API reference
• Blog — Tutorials, updates, and research
• Discord — Community support and discussions
• GitHub Issues — Bug reports and feature requests

Contributing

We welcome contributions! See our Contributing Guidelines for details.

License

MIT License — see LICENSE for details.

Third-party components have their own licenses:

• Kasm (MIT)
• OmniParser (CC-BY-4.0)
• Optional cua-agent[omni] includes ultralytics (AGPL-3.0)

Trademarks

Apple, macOS, Ubuntu, Canonical, and Microsoft are trademarks of their respective owners. This project is not affiliated with or endorsed by these companies.

Thank you to all our GitHub Sponsors!