macOS-use — security grade SAFE, quality 65/100

Security audit verdict: SAFE · quality 65/100

No red flags found in any of the 11 categories — no credential harvesting, no data exfiltration, no curl-pipe-shell installer. Scanned against the SlowMist agent-security taxonomy, refreshed every 8 hours. Full audit →

by browser-use · Agent Tool · ★ 2.0k

Last updated: · Indexed by AgentSkillsHub · Auto-synced every 8h

🔒 Is macOS-use safe to install? View the security audit →

About macOS-use

Tell your MacBook what to do, and it's done—across ANY app. Created by Ofir Ozeri ♥️ migrated in collaboration with Magnus and Gregor macOS-use enables AI agents to interact with your Macbook see it in action! Quick start ⚠️ Important: Review the Warning section before proceeding. With pip: From github Clone first Don't forget API key Supported providers: [OAI](https://pl

Quick Facts

Stars1,996
Forks192
LanguagePython
CategoryAgent Tool
LicenseMIT
Quality Score65.023311450624/100
Open Issues16
Last Updated2025-03-05
Created2025-01-23
Platformspython
Est. Tokens~15k

Compatible Skills

These tools work well together with macOS-use for enhanced workflows:

  • joinly — semantic(0.23)+complementary+same_lang+similar_pop+shared_platform (58%)
  • pivotnacci — semantic(0.21)+complementary+same_lang+similar_pop+shared_platform (57%)
  • kicad-mcp — semantic(0.15)+complementary+same_lang+similar_pop+shared_platform (55%)

macOS-use alternative? Top 6 similar tools

Looking for a macOS-use alternative? If you're comparing macOS-use with other agent tool tools, these 6 projects are the closest alternatives on Agent Skills Hub — ranked by topic overlap, star count, and community traction.

  • notebooklm-skill by PleasePrompto · ⭐ 7.8k

    Use this skill to enable Claude Code to communicate directly with your Google NotebookLM notebooks. Query your

  • agent-skills by tech-leads-club · ⭐ 6.5k

    The secure, validated skill registry for professional AI coding agents. Extend Antigravity, Claude Code, Curso

  • excalidraw-diagram-skill by coleam00 · ⭐ 4.3k

    Skill to give Claude Code (and any coding agent) the ability to generate beautiful and practical Excalidraw di

  • raptor by gadievron · ⭐ 3.8k

    Raptor turns Claude Code into a general-purpose AI offensive/defensive security agent. By using Claude.md and

  • playwright-skill by lackeyjb · ⭐ 3.0k

    General-purpose Playwright automation for coding agents

  • chinese-novelist-skill by PenglongHuang · ⭐ 2.8k

    🎭 AI 写小说:从零生成 10-50 章完整中文小说,三层问答 · 创作记忆 · 悬念钩子 · 自动校验,长篇网文连载皆宜|开源免费,适配主流 coding agent|AI novel writing skill

More Agent Tool Tools

Explore other popular agent tool tools:

View all Agent Tool tools →

Popular Python Agent Tools

Frequently Asked Questions

What is macOS-use?

macOS-use is Make Mac apps accessible for AI agents. It is categorized as a Agent Tool with 2.0k GitHub stars.

What programming language is macOS-use written in?

macOS-use is primarily written in Python.

How do I install or use macOS-use?

You can find installation instructions and usage details in the macOS-use GitHub repository at github.com/browser-use/macOS-use. The project has 2.0k stars and 192 forks, indicating an active community.

What license does macOS-use use?

macOS-use is released under the MIT license, making it free to use and modify according to the license terms.

What are the best alternatives to macOS-use?

The top alternatives to macOS-use on Agent Skills Hub include notebooklm-skill, agent-skills, excalidraw-diagram-skill. Each offers a different approach to the same problem space — compare them side-by-side by stars, quality score, and community activity.

How this security grade is produced

Grades come from a rule-based scan built on the SlowMist agent-security taxonomy, covering 11 red-flag categories including credential harvesting, data exfiltration, and curl | sh installers. It is a first-layer scan, not a manual audit — we say so rather than overstate it.

The scale of the problem is documented independently: Liu et al. (2026), in a study of 31,132 agent skills, report that 26.1% contain security vulnerabilities. Our own full-catalog census is published as a citable open dataset.

Sources & who's responsible:

View on GitHub → Browse Agent Tool tools