cua
Cua is an open-source platform designed for building, benchmarking, and deploying AI agents capable of interacting with any computer. It provides isolated, self-hostable sandboxes using technologies like Docker, QEMU, and Apple Vz for agentic UI automation and secure code execution.
cua is currently grouped under LLM Infra, which makes it easier to evaluate through workflow fit instead of isolated features alone. Based on the available data, it leans most heavily toward Build AI agents for desktop UI automation and interaction. and Developing and deploying AI agents for autonomous desktop interaction and task completion.. The listed license is MIT, which is useful when adoption constraints matter. It also shows measurable community traction with 19.9k GitHub stars.
Features
Why choose it
Trade-offs
Compatibility
Use cases
How it compares
Alternatives
Related searches
Comments
- ?usr_seed_0054May 10, 2026
Good for researchers building and evaluating computer-use AI systems.
- ?usr_seed_0798Apr 8, 2026
Sandbox isolation makes it safe to run agents that control a computer.
- ?usr_seed_0866Mar 25, 2026
Open-source computer-use agent infrastructure with sandboxes and benchmarks.
- ?usr_seed_0577Mar 13, 2026
Benchmark suite enables reproducible comparison of computer-use agent approaches.