Open Computer Use

CUA provides open-source infrastructure for Computer-Use Agents, including sandboxes, SDKs, and benchmarks to train and evaluate AI agents that control full desktops (macOS, Linux, Windows).

Open-source AI sandbox infrastructure for code execution, browser use, and AI agent runtimes.

Sandboxed code execution for AI agents, locally or on the cloud. Massively parallel, easy to extend. Powering SWE-agent and more.

Interactive sandboxes for AI agent evaluations and reinforcement learning on third-party APIs like Slack, LinkedIn, and more.