---
title: "Cua"
pageType: "tool-profile"
schemaVersion: "1.0"
snapshotId: "tv-20260911-8ab5e3f1311b"
generatedAt: "2026-09-11T07:01:56.000Z"
canonicalUrl: "https://toolvitals.com/tools/cua/"
jsonUrl: "https://toolvitals.com/api/agent/tools/cua"
indexable: true
---

# Cua

Open-source infrastructure for computer-use agents, with sandboxes, SDKs, and benchmarks.

## Decision context

- Status: active
- ToolVitals score: 98/100
- Health score: 97/100
- Shipping score: 98/100
- Score mode: verdict
- Data confidence: 90/100
- Source coverage: 100/100
- Last evidence check: 2026-09-10

## Classification

- Use case: AI Agent Tools (ai-agent-tools)
- Category: Developer Tools (developer-tools)
- Tool mode: Library Framework
- Openness: OSI-approved OSS
- License: MIT
- Tags: computer-use, agents, sandbox, sdk, benchmarks, open-source, agent, ai-agent, apple, computer-use-agent, containerization, cua, desktop-automation, hacktoberfest, lume, macos

## Public repository signals

- Repository: [trycua/cua](https://github.com/trycua/cua)
- Stars: 22429 (adoption context only)
- Forks: 1553
- Open issues: 834
- Last commit date: 2026-09-10
- Releases in 90 days: 30

## Source receipts

- [Official website](https://cua.ai/) — checked 2026-09-10
- [Source repository](https://github.com/trycua/cua) — checked 2026-09-10

## Discovery status

- Search indexable: yes
- Reason: sufficient tool evidence

## Interpretation limits

- ToolVitals scores summarize bounded public maintenance, shipping, openness, and evidence signals. They are not user-review ratings.
- GitHub stars and related popularity metrics are adoption context, not quality evidence.
- Missing values mean not collected or not confidently established; they do not mean zero.
- Public signals do not prove security, uptime, support quality, customer satisfaction, or production suitability.
- Verify material decisions against the linked first-party sources and your own requirements.