cua

Choose your path

• Cua Fleets: Provision a Linux desktop, run a command, and save a screenshot.
• Cua SDK, CLI and Spaces: Install cua, create a sandbox locally or in the cloud, and share desktops as Spaces.
• CUA-S1: Explore small, specialized models for computer-use decisions.
• Cua Driver: Operate Calculator and verify its result.
• Lume: Create a Tahoe VM and connect over SSH.
• Cua Bench: Create and verify a simulated task.

Bring your own agent and model, or explore CUA-S1 for specialized decisions. Cua provides the computer and automation tools. Computer-Use 2.0 describes an agent moving between code, APIs, and graphical interfaces within the same task.

See Cua Driver in action

Two Cua Driver sessions select cells in LibreOffice Calc and objects in Inkscape on an Omarchy desktop while a terminal stays in the foreground. Watch the 50-second demo, then explore Omarchy on Fleet.

https://github.com/user-attachments/assets/b4e5517c-d2db-4758-b4cf-07131b0753b2

---

Sandboxes

Run any image as an isolated computer or container, on your machine or in the cloud at run.cua.ai. Only where it runs changes:

from cua_sandbox import Image, Sandbox

async with Sandbox.ephemeral(Image.linux(), local=True) as sb:  # local=False for the cloud
    print((await sb.shell.run("uname -a")).stdout)

Commands, environment, named services, readiness probes, public URLs, port forwards and MCP servers work the same on both. See the backend notes for limits.

Sandboxes | Quickstart | Your first cloud sandbox | Sandbox SDK reference

---

Cua SDK, CLI and Spaces

One SDK and one cua command for every sandbox: cloud desktops, local VMs and containers, or any machine that runs cua-spacesd.

macOS / Linux

curl -fsSL https://cua.ai/install.sh | sh

Windows (PowerShell)

irm https://cua.ai/install.ps1 | iex

In a terminal the script shows a short checklist: the cua CLI, the Cua Spaces app (default on macOS), the cua-driver MCP and skill for your agents, and hosting this machine. It then runs cua auth login: it signs you in and offers to install cua skills and the cua MCP server into your AI coding agents (Claude Code, Codex, Cursor, and others). Preselect items with sh -s -- --select cua-driver, or skip the checklist with --only cua-driver. The Spaces app installers (dmg/pkg, msi/exe, deb/AppImage) do the same graphically. See the installer options.

cua sb create ubuntu --name dev          # local: a gVisor container, set up on first use
cua sb exec dev uname -a
cua sb screenshot dev
cua sb rm dev
cua sb create ubuntu --on cloud          # the same image in the Cua cloud
cua config set default.on cloud          # make the cloud the default (--on local still works)

• SDK: the same API in Python (pip install cua), TypeScript (@trycua/cua), Swift (Cua) and Kotlin (generated bindings), running embedded in your process or through a shared cua daemon.
• Sandboxes need no agent inside. Readiness comes from the runtime and optional port probes. Images that ship cua-spacesd (port 3211) add processes, files, screenshots, input through cua-driver, and low-latency video and audio streaming.
• Spaces are sandboxes or machines with cua-spacesd that you and your agents share: live desktop and window streams, presence, file send, teleporting an app session from your machine, and agent threads. cua host setup makes this machine reachable through the cua.ai relay with no port forwarding.

SDK README | CLI reference | Example Spaces app

---

Cua Driver

Give your agent tools to inspect and operate native desktop apps and browsers on macOS, Windows, and Linux. Connect through the CLI, MCP, or typed SDKs. Background delivery lets agents work without moving your pointer or taking focus when the app and platform support it; see platform support for the boundaries.

macOS / Linux

/bin/bash -c "$(curl -fsSL https://cua.ai/driver/install.sh)"

Windows (PowerShell)

irm https://cua.ai/driver/install.ps1 | iex

Your first result: connect your agent, ask it to compute 6 × 7 in Calculator, and have it verify that the app displays 42. The tutorial covers platform setup, permissions, and agent connection.

Drive your first app | Installation | CLI Reference

Using Claude Code, Codex, Cursor, OpenClaw, or another agent? Find your integration. Source documentation and architecture notes live in libs/cua-driver/README.md.

---

CUA-S1

CUA-S1 is our family of small, specialized System 1 models for computer use. We use "System 1" as an engineering analogy for fast, bounded decisions, such as choosing which value belongs in a field or whether to leave an element alone. It is not a strict classification of model architectures or a replacement for a general-purpose agent's planning and reasoning.

The first research profile focuses on forms: scoring decisions from structured interface elements and document values rather than generating a response token by token. Application code orders the actions, and the optional Cua Driver integration handles execution with explicit action boundaries.

The project includes Python model code, synthetic-data generation, training, and evaluation. The GitHub component is an early, source-only research release; model weights are hosted separately on Hugging Face. The source is MIT-licensed. Check each model and dataset card for its scope, limitations, and artifact-specific license.

Explore CUA-S1 | Model card | Safety and deployment guidance

CUA-S1-FORMS on Hugging Face: Model weights | Dataset

---

Lume

Create and manage local macOS and Linux VMs on Apple Silicon using Apple's Virtualization.Framework.

/bin/bash -c "$(curl -fsSL https://cua.ai/lume/install.sh)"

Your first result: create a vanilla macOS Tahoe VM from an Apple restore image, start it, and connect over SSH. The tutorial uses the Lume CLI directly and explains the unattended setup defaults.

Create your first Lume VM | Installation | CLI reference

---

Cua Bench

Build computer-use tasks, evaluate agents, and export trajectories for training. Start with a simulated task that requires no VM, Docker, or model API key.

With Python 3.12 or 3.13 and uv installed:

uv tool install 'cua-bench[browser]'
uv tool run --from 'cua-bench[browser]' playwright install chromium

Your first result: create a small task, run its reference solution, and verify that its evaluator reports a reward of 1.0. Then try the same task yourself.

Build your first task | What is Cua-Bench? | CLI reference | Partner with us

---

Packages

Package	Description
cua-driver	Background computer-use agent for macOS, Windows, and Linux
cua SDK and CLI	Rust core and the cua command: sandboxes, Fleet, local runtimes, images, Spaces
cua (Python)	The cua SDK for Python (pip install cua)
@trycua/cua	The cua SDK for Node and the browser, plus @trycua/cua/spaces
Cua (Swift)	The cua SDK for Swift (SwiftPM, XCFramework)
cua-sandbox	High-level Python Sandbox/Image/Pool API, a thin wrapper over the cua SDK
cua-spacesd	In-sandbox daemon on port 3211: processes, files, desktop, streaming (gRPC)
Cua Spaces	Desktop app for Spaces: live streams, PiP, teleport, agent threads
cua-agent	AI agent framework for computer-use tasks
cua-bench	Benchmarks and RL environments for computer-use
lume	macOS/Linux VM management on Apple Silicon
lumier	Docker-compatible interface for Lume VMs

---

Resources

• Documentation: guides, examples, and API reference
• Blog: tutorials, updates, and research
• Discord: community support and discussions
• GitHub Issues: bug reports and feature requests
• Security: private vulnerability reporting

Citation

If Cua supports your research, please cite the software:

@software{cua2025,
  author  = {{Cua AI, Inc.}},
  title   = {Cua},
  year    = {2025},
  url     = {https://github.com/trycua/cua},
  license = {MIT}
}

For reproducibility, include the Cua release or commit used in your experiments. Citation metadata is also available in CITATION.cff.

Contributing

We welcome contributions! See our Contributing Guidelines for details.

Licensing

Cua is open source under the MIT License (LICENSE): the cua SDK and its Python, TypeScript, Swift and Kotlin packages, the cua command and cua daemon, Cua Driver, Lume and the rest of this repository unless a directory says otherwise. Cua Spaces is source-available under FSL-1.1-MIT: the Spaces apps, cua-spacesd, the Cua Keyvault, teleport, Cua Volume (cua-volume) and the streaming client, codecs and viewers. The streaming wire protocol stays MIT. It is free to use, self-host and build on, with no competing hosted service, and each release becomes MIT two years after it ships. The MIT parts never depend on the FSL parts. Some subdirectories carry their own licence; LICENSING.md lists each one and how the two fit together. Offering Spaces as a hosted or managed service? See COMMERCIAL.md. For use of our names and logo, see TRADEMARKS.md.

Third-party components have their own licenses:

• Kasm (MIT)
• cua-som is an optional package licensed under AGPL-3.0-or-later. Its Ultralytics dependency retains its own license; inspect the resolved dependency version and its notices before redistribution.
• The Microsoft OmniParser repository states CC-BY-4.0 for its repository content. Model files downloaded from the separate OmniParser model repository are distinct artifacts; verify the terms published with the exact model revision before redistributing them.
• The optional cua-perception extension is installed separately from the MIT Cua Driver, from the signed assets of a cua-perception-v<version> GitHub release. Each release combines an AGPL-3.0-only OmniParser model artifact, Apache-2.0 PP-OCR model artifacts, and a separately packaged ONNX Runtime. The extension is not MIT licensed. Redistributing it, or offering it to users over a network, can trigger AGPL-3.0 source obligations. Cua does not relicense the detector and cannot grant other terms for it. Read the perception third-party notices and precautions before you install, redistribute, or host an extension artifact.

Trademarks

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

---

Sponsors