Cua logo

Cua

Cua AI Agent
Rating:
Rate it!

Overview

Computer-use infrastructure for connecting agents to desktop workspaces, virtual machines and automation tools.

Cua provides desktop environments and interaction tools for an agent and model you choose. Current components include Spaces for workspaces, Driver for computer interaction and Lume for local macOS virtual machines. CLI, MCP and language interfaces let developers connect these components to their own automation.

Check the operating-system and hardware requirements of the selected component; Spaces targets macOS 26 or later. Licences and access terms differ across the project. The controlling model, credentials, task instructions and human approval policy remain part of your application.

Product overview

Capabilities, pricing and fit

Cua supplies computer environments and automation interfaces for an agent and model you choose.

Information as of September 22, 2026

What it can do

  • Desktop interaction

    Driver exposes computer actions through CLI, MCP and language interfaces.[1]

  • Local virtual machines

    Lume provides a path to macOS virtual machines.[1]

  • Agent workspaces

    Spaces organizes desktop workspaces; its current release requires macOS 26 or later.[1]

Where it fits best

  • Developers connecting an existing agent to desktop applications.[1]

Pricing and availability

Access and licences differ by component. Individual Spaces access is free; model usage and machine resources remain separate costs.[1]

Access: Choose the component for your operating system and hardware.[1]

Sources (1)
  1. Cua components and accessGitHub · checked 2026-10-12

Autonomy level

79/100

Our subjective rating of how independently the product carries out its documented tasks, considering the human setup, input, approval and review it needs. This is not a measured success rate.

Reasoning: Cua enables configured agents to perform multistep desktop work through computer-control interfaces and managed or local environments. The score describes what an agent built on that infrastructure can execute: the chosen external model supplies decisions. Developers provide goals, machines, credentials and permissions, and people approve consequen...

Comparisons


Custom Comparisons

Some of the use cases of Cua:

  • building computer-use agents
  • desktop automation experiments
  • agent evaluation and benchmarking
  • provisioning isolated desktops for agent workflows
  • testing GUI interaction tasks

Loading Community Opinions...

Pricing model:

Code access:

Popularity level: 87%

Free credibility widget

Turn this profile into a trust signal

Show prospects that Cua has a public place where they can check product details, pricing, ratings, and reviews.

Build confidence

Give buyers a third-party profile to explore.

Reduce hesitation

Put validation beside your strongest CTA.

Earn discovery

Every badge links prospects to your listing.

Choose your style

Preview it, then copy the complete embed code.

Live previewReady to embed

Shows buyers where to validate your product, pricing, and reputation.

Plain HTML. No signup, script, or maintenance required.

Make it work for you

Describe the job. Get an AI worker you can actually message.

We create the setup, keep it running after your laptop closes, and save its memory. Test in the browser, then add Telegram, WhatsApp, or Slack.

Runs without your laptopBrowser + messaging appsCredits, keys, or subscriptionsMemory survives restarts

Plans start at $29/month. Cancel anytime.

Hosted agent

OpenClaw or Hermes

saved state
Browser
WhatsApp
Telegram
Slack
“I checked the inbox, handled the routine messages, and sent you the one question that needs a decision.”
Create an AI worker that keeps running after this tab closes.
Open Agent Teams

Did you find this page useful?

Not useful
Could be better
Neutral
Useful
Loved it!