Open-source infrastructure for computer-use agents — virtualized macOS, Linux, and Windows sandboxes, SDKs, and benchmarks for agents that control full desktop environments.
Use it now
Keep it with up to 9 other tools you're setting up, then share them all as one link.
Try this first
Ask your coding agent:
- VM Sandboxes
Use Cua to spin up virtualized macOS, Linux, or Windows environments: ‹what you need›
- Agent Benchmarks
Use Cua to evaluate computer-use agents on standardized tasks across operating systems: ‹what you need›
Call the API
Auth An API key from trycua
Its page: github.com/trycua/cua
Compare
Press Compare to add it to the tray at the bottom of the window, then pick up to 2 others anywhere on the site.
- Access
- API
- Auth
- API Key
- Skills
- 3
Skills
VM Sandboxes
Spin up virtualized macOS, Linux, or Windows environments for computer-use agent tasks safely
Desktop Control
Give AI agents full GUI control over desktop apps, browsers, and system interfaces in sandboxes
Agent Benchmarks
Evaluate computer-use agents on standardized tasks across operating systems with repeatable test suites