Skip to content

AgentCua

Cua

Open-source infrastructure for computer-use agents across full desktops.

Categories
AgentAutomation
Pricing
FREEMIUM
Source
Open core
Hosting
Hybrid
Platforms
macOSLinuxCLIAPI
Models
Model-agnostic
Verified
Jun 20, 2026

Cua (also styled c/ua) is infrastructure for building and scaling computer-use agents. One API boots Linux, Windows, macOS, and Android machines in lightweight, isolated virtual containers, and SDKs plus benchmarks let agents observe and control full operating systems — clicking, typing, browsing, and running real apps. On Apple Silicon it reaches near-native speed via Apple's Virtualization.framework and the Lume CLI, and it runs locally with any LLM or on Cua's managed cloud.

Capabilities 4

What it actually does — grouped by capability family.

  • Sandboxed code execution (secondary capability)
  • Agent framework (primary capability)
  • Browser automation (secondary capability)
  • LLM evaluation (primary capability)

Pros & cons

  • Isolated VMs across four OS families
  • Agents control full desktops, not just browsers
  • SDKs and benchmarks included
  • Run locally with any LLM
  • Cloud, BYOC, or on-prem hosting
  • Cloud hosting is paid/commercial
  • Developer/infra tool, not an end-user app
  • Computer-use agents are still error-prone

Tags

Further reading

Alternatives to Cua (3)

View all Agent →
  • View Browser Use details
    AgentFREEMIUMOpen core

    Browser Use

    Browser Use

    Open-source browser automation for AI agents.

    MIT-licensed Python framework that connects AI agents to a real browser to navigate, fill forms, extract data, and run multi-step web workflows. It parses the live DOM into a structured view so any model — Claude, GPT, Gemini, Qwen, DeepSeek — can act on it. A hosted Browser Use Cloud adds managed sessions and a fully-hosted agent.

    Top open-source WebVoyager score (~89%)
    Success drops on bot-protected sites
    • browser-automation
    • open-source
    • web-agent
    • playwright
    Open
  • View Stagehand details
    AutomationFREEOSS

    Stagehand

    Browserbase

    Open-source SDK for building reliable AI browser agents.

    Stagehand is an SDK from Browserbase for building browser agents in TypeScript or Python. It exposes act(), extract(), and observe() primitives so you can drive a page with natural language while keeping deterministic code wherever you need it. v3 dropped its hard Playwright dependency for a modular Chrome DevTools Protocol driver.

    CDP-native v3 driver, no Playwright lock-in
    SDK, not a no-code tool
    • browser-automation
    • web-agents
    • sdk
    • open-source
    Open
  • View Skyvern details
    AutomationFREEMIUMOpen core

    Skyvern

    Skyvern

    Automate browser-based workflows on any website with AI.

    An AI agent that completes browser workflows — form fills, logins, data extraction, multi-step flows — by combining computer vision with LLMs rather than hand-written selectors, so a single agent generalizes across sites it has never seen. Run it via the cloud app and API or self-host the open-source engine; bring your own model (OpenAI, Anthropic, Gemini, or local Ollama).

    Vision+LLM, no hand-written selectors
    AGPL-3.0 limits commercial reuse
    • browser-automation
    • computer-vision
    • open-source
    • agents
    • +1
    Open
Open Cua