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).
Cost / License
- Freemium (Pay once)
- Open Source (MIT)
Platforms
- Online
- Docker
- GitHub
- Linux
- Windows
- Mac
- Android
- Android Tablet
- Node.JS



Cua
Features
- CI/CD
- AI-Powered
- Virtualization
- Task Automation
- Sandbox
- Workflow Automation
Cua information
What is Cua?
Drive any native macOS app in the background — agents click, type, and verify without stealing the cursor, focus, or Space, even on non-AX surfaces like Chromium web content and canvas-based tools (Blender, Figma, DAWs, game engines). Use with the CLI or MCP server for Claude Code, Cursor, and custom clients. Every session records as a replayable trajectory.
Agent-ready sandboxes for any OS
Build agents that see screens, click buttons, and complete tasks autonomously. One API for any VM or container image — cloud or local.
Co-op computer-use for any agent
cuabot gives any coding agent a seamless sandbox for computer-use. Individual windows appear natively on your desktop with H.265, shared clipboard, and audio.
Benchmarks & RL environments
Evaluate computer-use agents on OSWorld, ScreenSpot, Windows Arena, and custom tasks. Export trajectories for training.
macOS virtualization
Create and manage macOS/Linux VMs with near-native performance on Apple Silicon using Apple's Virtualization.Framework.
