aicoolies logo
CUA (Computer-Use Agent) logo

CUA (Computer-Use Agent)

Open-source sandboxes and SDKs for AI agents that control desktops

Share
freemium
Visit Website →

Open-source computer-use infrastructure for agents that need to drive desktop environments in the background. CUA includes Cua Driver, Sandbox, Run, Bench, and Verified Data across Linux, Windows, macOS, and Android, with MCP and CLI surfaces for screenshots, accessibility trees, keyboard/mouse actions, shell commands, task evaluation, and fleet execution.

We have a review for this tool

A detailed review by the aicoolies team — click to read

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.

Pricing

Open-source GitHub tier; hosted, BYOC, on-prem, and dedicated fleets by request as concurrency, OS mix, and compliance needs grow

Platforms

macOS, Linux, Windows, Android; Docker, QEMU, Apple Virtualization

Categories

Agent FrameworksAgent Skills & PromptsTesting & QA

Tags

Computer-UseSandboxPythonDockerSelf-Hosted

Use Cases

Agentic DevelopmentTesting & QA Automation

Alternatives

CrabTalk

The 5MB open-source agent daemon that hides nothing

CrabTalk is a lightweight five-megabyte daemon that streams every AI agent event to your client in real time including text deltas, tool calls, and thinking steps. It provides complete transparency into agent operations with one-curl installation and bring-your-own-model support. Designed as the observable alternative to opaque agent runtimes where you cannot see what the AI is actually doing.

open-sourceOpen Source

adk-go

Google's official Agent Development Kit for building AI agents in Go

adk-go is Google's official Agent Development Kit for the Go programming language, providing the tools and abstractions needed to build production AI agents. It supports tool calling, multi-turn conversations, structured outputs, and integration with Google's Gemini models. With 7,300 GitHub stars and Apache 2.0 license, it brings first-class AI agent development capabilities to the Go ecosystem.

open-sourceOpen Source

Spring AI Alibaba

Alibaba's Spring framework for building AI applications in Java

Spring AI Alibaba is Alibaba's open-source framework that brings AI capabilities to Java Spring Boot applications. It provides auto-configuration for AI model providers, RAG pipeline components, agent frameworks, and tool integration following Spring conventions. With 9,100 GitHub stars and 220+ contributors, it is the most mature AI framework for Java enterprise developers building production AI features.

open-sourceOpen Source

Memori

SQL-native memory infrastructure for AI agents and applications

Memori is an AI memory engine that provides persistent, queryable memory for agents and applications using SQL-native storage. It stores structured memories with semantic search, temporal awareness, and relationship tracking, enabling AI systems to remember user preferences, past interactions, and contextual facts across sessions. With 12,900 GitHub stars, it offers a database-native approach to the agent memory problem.

open-sourceOpen Source

Related Tools

Hermes Agent logo

Hermes Agent

Top Pick

Open-source AI agent framework with persistent memory, reusable skills, tools, and messaging gateways

Hermes Agent is an open-source AI agent framework with persistent memory, reusable skills, 40+ tools, cron jobs, and messaging gateways.

open-sourceOpen Source

Accomplish Coworker

Open-source desktop AI coworker for browsing and code execution.

Accomplish Coworker is an MIT-licensed open-source AI coworker that runs on the desktop, combining computer-use style browsing with code execution so agents can research, implement, run, and debug workflows in one local environment.

open-sourceOpen SourceTelemetry

Safari MCP Server

Apple's Safari-native MCP server for web debugging agents

Safari MCP Server is Apple's safaridriver-based MCP server in Safari Technology Preview, giving compatible coding agents local access to Safari page content, console logs, network requests, screenshots, JavaScript evaluation, interactions, viewport controls, and accessibility/performance checks.

freeTelemetry

Headroom

Context compression for LLM apps and coding agents

Headroom is an Apache-2.0 context compression layer for LLM apps and coding agents. It compresses tool output, logs, files, RAG chunks, and agent history through a local library, proxy, wrapper, or MCP server, with retrieval hooks for bringing originals back when needed. Treat its savings numbers as Headroom-reported benchmarks, not independent aicoolies measurements.

open-sourceOpen SourceTelemetry

Codebase Memory MCP

Codebase knowledge graph MCP server for AI coding agents

Codebase Memory MCP is an MIT-licensed MCP server that turns a repository into a persistent code knowledge graph for AI coding agents. It gives Claude Code, Cursor, Codex-style agents, and other MCP clients structural queries for functions, classes, call chains, routes, and architecture, helping them explore large projects without repeatedly rereading files or relying only on broad search.

open-sourceOpen SourceTelemetry
BeeAI Framework logo

BeeAI Framework

Python and TypeScript framework for production multi-agent systems

BeeAI Framework is an Apache-2.0 toolkit for building production-ready AI agents and multi-agent systems in Python and TypeScript. Its docs cover agents, tools, RAG, memory, workflows, backend providers, serving, and A2A/MCP integration surfaces, making it a vendor-neutral option for teams comparing LangGraph, CrewAI, Mastra, and related agent runtimes.

open-sourceOpen SourceTelemetry

Used in Stacks

AI Agent Infrastructure Stack

A complete open-source stack for building, sandboxing, and deploying autonomous AI agents that can control computers, browse the web, and access production infrastructure securely. Combines sandboxed execution environments, headless browsing, web data extraction, and zero-trust infrastructure access.

varies

Comparisons

CUA vs OpenHands: Computer-Use Agent Infrastructure Compared

CUA and OpenHands both enable AI agents to autonomously control computers, but they target different layers of the stack. CUA provides sandboxed VM infrastructure where any agent can operate safely, while OpenHands is a complete autonomous coding platform with its own agent logic. The choice depends on whether you need infrastructure for custom agents or a ready-to-use coding assistant.

CUA (Computer-Use Agent)OpenHands