evaluation securityQuick Start ↓
Get Started with cua
Open-source infrastructure for training and evaluating AI agents to control full desktop environments.
Getting Started
1
Read the official documentation
The cua team maintains comprehensive docs that cover installation, configuration, and common patterns.
Open cua Docs↗2
Create an account
Visit the cua website to create your account and explore pricing options.
Visit cua↗3
Review strengths, tradeoffs, and alternatives
Our full tool profile covers cua's strengths, weaknesses, pricing, and how it compares to alternatives.
View full profile→Best For
Researchers looking to evaluate the performance of AI agents in controlling desktop environments across multiple operating systems.
Developers building automation tools that need to interact with a wide range of desktop applications and interfaces.