trycua/cua
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).
agentai-agentapplecomputer-usecomputer-use-agentcontainerizationcuadesktop-automationhacktoberfestlumemacosmanusoperatorswiftvirtualizationvirtualization-frameworkwindowswindows-sandbox
Agent quality
57%
Agent quality score.
Reputation70%
Cross-source presence, stars, and recency.
has 16847 stars; actively maintained; credible author
Usability80%
Docs, license, auth, and clear capabilities.
Usability based on documentation, license, auth/pricing clarity, structured capabilities, and public repository presence.
Functionality39%
Predicted functionality, speed, and reliability.
Scored on specificity, consistency, reliability, speed, and scope clarity.