Stack Gems
Menu
WorkbenchBestNewSkillsLogAboutSubmit
← Catalog

Cua

Open computer-use drivers, sandboxes, MCP, and CUA-S1 decision models

AI Agents / Browser Automation · AGPL-3.0 · 30.2k

Reviewed 2026-09-20 · last push 2026-10-19 · repo checked 2026-10-19

Visit siteGitHub

What's Good

MIT (trycua/cua). The stack covers computer-use drivers across OS/desktop surfaces, local sandboxes, MCP integration, and the CUA-S1 model line when an agent needs a decision loop rather than a text-only tool call. It is a useful bridge from browser automation to the wider desktop.

The Catch

Vs BrowserSkill, Stagehand, and Browser Use: Cua is the broader computer-use driver/sandbox/model stack, not only browser automation or a browser-session attach bridge. Optional `omni` extras pull AGPL Ultralytics; cloud fleets are paid. Audit extras and treat a fleet as infrastructure spend, not as part of the MIT core.

Verdict

MIT computer-use stack with CUA-S1. Reach for desktop/OS control and sandboxes; audit the AGPL omni extra and paid cloud fleet boundary.

Embed

Maintainer? Add the badge to your README. It is free, links to this review, and there is no paid version.

Reviewed on Stack Gems

Markdown

[![Reviewed on Stack Gems](https://stackgems.com/badge/cua.svg)](https://stackgems.com/gems/cua)

HTML

<a href="https://stackgems.com/gems/cua"><img src="https://stackgems.com/badge/cua.svg" alt="Cua reviewed on Stack Gems" height="20"></a>

Related

AI Agents →