Skip to content
AgentRadar
Cua

Cua

Scale Linux, Windows, macOS, and Android computer fleets for computer-use agents with one open-source MCP/CLI driver

DevOps Agents Open Source

Last Updated

2026-06-15

GitHub Stars

18,169

Last Updated

2026-07

About Cua

Drive native desktop apps in the background. Agents click, type, and verify without stealing the cursor or focus. Use the same CLI and MCP server on macOS, Windows, and Linux from Claude Code, Cursor, Codex, OpenClaw, and custom clients. Linux supports X11 and compositor-specific Wayland routes with explicit limits for raw background input. Windows (PowerShell) Then wire it into Claude Code as an MCP server and your agent can drive the desktop in the background: Full tool reference, architecture notes, and the optional agent skill pack live here: libs/cua-driver/README.md. Build agents that see screens, click buttons, and complete tasks autonomously. One API for any VM or container image — cloud or local.

Features

Optional

Detailed Ratings

Ease of Use
6.7
Value for Money
7.3
Features
6.9
Support
6.5
Performance
7.1
Overall Rating
7.0 /10

Pros & Cons

Pros

  • Active community with 18.2k GitHub stars
  • Optional

Use Cases

Incident responseMonitoringDeploymentObservability

Who Is It For?

Teams and individuals looking for DevOps and infrastructure automation who value open-source flexibility and control.

#agent#ai-agent#apple#computer-use#computer-use-agent#choose

Frequently Asked Questions

What is Cua?

Scale Linux, Windows, macOS, and Android computer fleets for computer-use agents with one open-source MCP/CLI driver.

How much does Cua cost?

Cua is open-source and free to self-host. See https://github.com/trycua/cua for installation instructions.

Is Cua open source?

Yes — Cua is open source with 18.2k stars. The source code is on GitHub at https://github.com/trycua/cua.

Who should use Cua?

Teams and individuals looking for DevOps and infrastructure automation who value open-source flexibility and control.

Related Agents

Links & Resources

AR Reviewed by AgentRadar · Reviewed on · How we rate

Profiles are AI-assisted from public information — not independently hands-on tested.