Overview
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).
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). 17,103 GitHub stars · HTML.
17,103 GitHub stars
Written in HTML
Topics: agent, ai-agent, apple, computer-use
Features & capabilities
Everything it does, in plain English.
The honest take
Where it shines, where it stumbles.
✓ Pros
- ✓Active open-source community
- ✓Code is publicly auditable
! Watch-outs
- !Requires manual review before publishing
Who it's for
Where Cua pays for itself fast.
AI-assisted development
Integration into agentic workflows
Community reviews
Share your take on Cua
Sign in to leave a verified review.
Alternatives
Similar tools worth comparing.

Awesome Claude Skills
A curated list of awesome Claude Skills, resources, and tools for customizing Claude AI workflows

n8n
Open-source workflow automation platform connecting apps and APIs

Claude Mem
Persistent Context Across Sessions for Every Agent – Captures everything your agent does during sessions, compresses it with AI, and injects relevant context back into future sessions. Works with Claude Code, OpenClaw...
Claude Code
Anthropic's agentic coding tool — runs in your terminal and autonomously writes, edits and tests code across your entire codebase.

Ollama
Simple tool to download and run large language models locally on Mac, Windows, and Linux.

DeepSeek
Chinese open-source AI models rivaling GPT-4 at fraction of cost
