Cloud desktops for AI agents — give Claude Code, Codex or any computer-use agent its own isolated macOS or Linux VM.
Cloud desktops for AI agents — give Claude Code, Codex or any computer-use agent its own isolated macOS or Linux VM.
Cua (short for 'Computer Use Agent') gives every AI agent its own cloud desktop so the agent can browse, open apps, fill forms and run tools without being trapped behind a chat-only interface. Where most computer-use stacks tie you to a single model and a single sandbox, Cua provides on-demand macOS, Linux and Windows VMs that are pre-wired for Claude Code, OpenAI Codex, OpenClaw, Anthropic Computer Use and the open-source cua-driver CLI. Agents drive the desktop through an MCP-compatible API that exposes accessibility-tree snapshots, screen pixels, mouse and keyboard, file-system access and bring-your-own credentials via a secrets vault. Each session is isolated, recorded and revocable, which solves the biggest blocker for production computer-use: letting an agent into a real browser session without leaking cookies or breaking compliance. Cua is used by indie hackers prototyping browser agents, by RPA teams replacing brittle scripts with LLM-driven flows, and by teams building consumer products on top of computer use without operating their own VM fleet. It is one of the few infra products that is genuinely native to MCP, with first-class servers for desktop control and built-in clients for the major agent runtimes.
Was this helpful?
Feature information is available on the official website.
View Features →$0
Hourly metered
Contact sales
Ready to get started with Cua?
View Pricing Options →Weekly insights on the latest AI tools, features, and trends delivered to your inbox.
No reviews yet. Be the first to share your experience!
Get started with Cua and see if it's the right fit for your needs.
Get Started →Take our 60-second quiz to get personalized tool recommendations
Find Your Perfect AI Stack →Explore 20 ready-to-deploy AI agent templates for sales, support, dev, research, and operations.
Browse Agent Templates →AI agents without memory restart from zero every conversation, wasting time and money. Here's how the three types of agent memory work, why they matter for your business, and which tools actually deliver results in 2026.
Deploy AI agents to production with confidence. Covers containerization, cloud deployment on AWS/Azure/GCP, Kubernetes orchestration, observability, cost control, and security best practices.
Running an online store means juggling product listings, customer questions, inventory, pricing, and marketing — all at once. AI agents can now handle most of it for you. Here's exactly how to automate your e-commerce business without hiring a team.
Compare GPT-4o, Claude 3.5 Sonnet, Gemini 2.0, Llama 4, and more for AI agent workloads. Covers tool calling, reasoning, cost, latency, and which model fits your use case.