CUA provides infrastructure for computer-use agents that need reproducible access to operating systems and desktop applications. Its current product surface includes Cua Driver for background computer control, Cua Sandbox for local or cloud machine environments, Cua Run for scaling fleets of machines, Cua Bench for evaluation, and Verified Data for curated trajectories. The project is MIT licensed and its GitHub repository remains active with roughly 18.6K stars.
The platform targets cross-OS agent development across Linux, Windows, macOS, and Android. Developers can work through Python or TypeScript SDKs, the CUA CLI, MCP tools, and documentation for sandbox lifecycles, snapshots, secrets, parallel sandboxes, and benchmark integrations such as ScreenSpot and OSWorld-style tasks. This makes CUA more than a simple VM wrapper: it is a development and evaluation layer for agents that click, type, inspect interfaces, execute commands, and collect trajectories.
Current pricing language starts with the open-source GitHub stack and moves into hosted, BYOC, on-prem, or dedicated fleets as concurrency, OS mix, and compliance needs grow. That makes CUA best for teams that need controlled computer fleets for evals, RL loops, data generation, or batch rollouts, rather than buyers looking for a simple fixed-price SaaS tier. Procurement teams should confirm hosted and dedicated-fleet terms before using old per-resource pricing assumptions.
