Open-source infrastructure for Computer-Use Agents. Sandboxes, SDKs, and benchmarks to train and evaluate AI agents that can control full desktops (macOS, Linux, Windows).
-
Updated
Apr 27, 2026 - HTML
Open-source infrastructure for Computer-Use Agents. Sandboxes, SDKs, and benchmarks to train and evaluate AI agents that can control full desktops (macOS, Linux, Windows).
[NeurIPS 2025] Official repository of RiOSWorld: Benchmarking the Risk of Multimodal Computer-Use Agents
Entorno de pruebas diseñado para validar y depurar la interacción de agentes autónomos (CUA) con elementos web mediante el árbol de accesibilidad y MCP.
Add a description, image, and links to the cua topic page so that developers can more easily learn about it.
To associate your repository with the cua topic, visit your repo's landing page and select "manage topics."