convez.ai
PluginAutomaçãoAvançado
trycua

Cua - Infraestrutura para Agentes de Computer-Use

trycua/cua

Treina e deploy agentes que controlam computadores full-stack

Ver no GitHub
Muito bomPluginScore · de 0 a 100

Framework open-source para construir, treinar e avaliar agentes de IA que controlam desktops completos (macOS, Linux, Windows). Oferece sandboxes agnósticos, SDKs, drivers de automação em background e benchmarks para avaliar performance de agentes autônomos.

Instalação

$npx convez-ai trycua/cua

1 comando no terminal: detecta o formato do repositório (marketplace ou plugin avulso) e instala via Claude Code. Requer Node 18+ e o Claude Code instalado.

Métricas

Estrelas
33 mil
Forks
2,5 mil
Acompanhando
98
Saúde
50%
Último commit
há 22 horas
Versão
cua-spaces-v0.38.8
Issues abertas
1,6 mil
Contribuidores
70

Casos de uso

  • Treinar agentes autônomos capazes de controlar interfaces gráficas
  • Avaliar e fazer benchmarking de modelos de computer-use
  • Automatizar tarefas complexas que requerem interação com desktop
  • Desenvolver assistentes que clicam, digitam e verificam sem interferir no usuário

Veredito

Cua é um projeto maduro e bem-estruturado que resolve um problema real: dar agentes capacidade de usar computadores como humanos fazem. A arquitetura modular (drivers, sandbox, bench) permite casos de uso desde automação simples até pesquisa de RL — ferramenta séria para quem trabalha com agentes autônomos.

README

A tradução para o português deste README ainda está na fila.

Choose Your Path


Cua Drivers - Background computer-use on macOS and Windows, with Linux pre-release

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 and Windows from Claude Code, Cursor, Codex, OpenClaw, and custom clients. Linux support is available as a pre-release backend while platform testing is still in progress.

macOS / Linux

/bin/bash -c "$(curl -fsSL https://raw.githubusercontent.com/trycua/cua/main/libs/cua-driver/scripts/install.sh)"

Windows (PowerShell)

irm https://raw.githubusercontent.com/trycua/cua/main/libs/cua-driver/scripts/install.ps1 | iex

Then wire it into Claude Code as an MCP server and your agent can drive the desktop in the background:

claude mcp add --transport stdio cua-driver -- cua-driver mcp

Full tool reference, architecture notes, and the optional agent skill pack live here: libs/cua-driver/README.md.


Cua - Agent-Ready Sandboxes for Any OS

Build agents that see screens, click buttons, and complete tasks autonomously. One API for any VM or container image — cloud or local.

pip install cua
# Requires Python 3.11 or later
from cua import Sandbox, Image

# Same API regardless of OS or runtime
async with Sandbox.ephemeral(Image.linux()) as sb:   # or .macos() .windows() .android()
    result = await sb.shell.run("echo hello")
    screenshot = await sb.screenshot()
    await sb.mouse.click(100, 200)
    await sb.keyboard.type("Hello from Cua!")
    await sb.mobile.gesture((100, 500), (100, 200))  # multi-touch gestures
Linux containerLinux VMmacOSWindowsAndroidBYOI (.qcow2, .iso)
Cloud (cua.ai)✅✅✅✅✅🔜 soon
Local (QEMU)✅✅✅✅✅✅

Get Started | Examples | API Reference


Cua-Bench - Benchmarks & RL Environments

Evaluate computer-use agents on OSWorld, ScreenSpot, Windows Arena, and custom tasks. Export trajectories for training.

# Clone, install, and create base image
git clone https://github.com/trycua/cua && cd cua/cua-bench
uv tool install -e . && cb image create linux-docker

# Run benchmark with agent
cb run dataset datasets/cua-bench-basic --agent cua-agent --max-parallel 4

Get Started | Partner With Us | Registry | CLI Reference


Lume - macOS Virtualization

Create and manage macOS/Linux VMs with near-native performance on Apple Silicon using Apple's Virtualization.Framework.

# Install Lume
/bin/bash -c "$(curl -fsSL https://raw.githubusercontent.com/trycua/cua/main/libs/lume/scripts/install.sh)"

# Pull & start a macOS VM
lume run macos-sequoia-vanilla:latest

Get Started | FAQ | CLI Reference


Packages

PackageDescription
cua-driverBackground computer-use agent for macOS, Windows, and Linux
cua-agentAI agent framework for computer-use tasks
cua-sandboxSDK for creating and controlling sandboxes
cua-computer-serverDriver for UI interactions and code execution in sandboxes
cua-benchBenchmarks and RL environments for computer-use
lumemacOS/Linux VM management on Apple Silicon
lumierDocker-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

Contributing

We welcome contributions! See our Contributing Guidelines for details.

License

MIT License — see LICENSE for details.

Third-party components have their own licenses:

  • Kasm (MIT)
  • OmniParser (CC-BY-4.0)
  • Optional cua-agent[omni] includes ultralytics (AGPL-3.0)

Trademarks

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


Stargazers over time

Thank you to all our GitHub Sponsors!

Ver o original no GitHub

Bom para

Relacionados