claude-overlay — security grade SAFE, quality 69/100

Security audit verdict: SAFE · quality 69/100

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 shengyanlin · Agent Tool · ★ 92

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

🔒 Is claude-overlay safe to install? View the security audit →

About claude-overlay

Claude Overlay ### Talk to Claude Code without ever leaving the app you're in — and let it actually see your screen. Windows 10 / 11 only (for now) · runs on your existing Claude subscription — no API key Claude Overlay is a frameless, always-on-top chat window that floats over everything you do. Ask a question, and Claude looks at your real screen — every monitor — to answer. No copy-pasting error messages, no describing what you're staring at, no alt-tabbing to a browser. And because it runs the full [Claude Code](https://docs.clau

aiai-assistantalways-on-topanthropicclaudeclaude-agent-sdkclaude-codedesktop-appdeveloper-toolsllm

Quick Facts

Stars92
Forks15
LanguagePython
CategoryAgent Tool
LicenseMIT
Quality Score69.116214571167/100
Last Updated2026-09-16
Created2026-05-31
Platformsclaude-code, python
Est. Tokens~17k

claude-overlay alternative? Top 6 similar tools

Looking for a claude-overlay alternative? If you're comparing claude-overlay 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.

  • repopack-py by abinthomasonline · ⭐ 121

    Python version of 📦 repopack (https://github.com/yamadashy/repopack) by yamadashy (https://github.com/yamadas

  • OmoiOS by kivo360 · ⭐ 71

    Turn feature specs into merged PRs with a self-supervising swarm of coding agents — parallel execution, isolat

  • aipointer by gonemedia · ⭐ 267

    AI cursor assistant for macOS, Windows, Linux. Hold a hotkey, ask a question about what's on your screen, get

  • lazy-bird by yusufkaraaslan · ⭐ 234

    Universal development automation for ANY project. Claude Code implements features, runs tests, creates PRs aut

  • navigator by alekspetrov · ⭐ 232

    Finish What You Start — Context engineering for Claude Code. Sessions last 20+ exchanges instead of cr

  • claude-historian-mcp by Vvkmnn · ⭐ 177

    📜 An MCP server for conversation history search and retrieval in Claude Code

More Agent Tool Tools

Explore other popular agent tool tools:

View all Agent Tool tools →

Popular Python Agent Tools

Frequently Asked Questions

What is claude-overlay?

claude-overlay is A floating, screen-aware Claude Code chat for Windows - it reads your screen to answer, and runs on your own Claude subscription (no API key).. It is categorized as a Agent Tool with 92 GitHub stars.

What programming language is claude-overlay written in?

claude-overlay is primarily written in Python. It covers topics such as ai, ai-assistant, always-on-top.

How do I install or use claude-overlay?

You can find installation instructions and usage details in the claude-overlay GitHub repository at github.com/shengyanlin/claude-overlay. The project has 92 stars and 15 forks, indicating an active community.

What license does claude-overlay use?

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

What are the best alternatives to claude-overlay?

The top alternatives to claude-overlay on Agent Skills Hub include repopack-py, OmoiOS, aipointer. 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