AgathOS — AI skill for Claude Code
The good daemon for your AI agents.
How to install AgathOS
This entry records only its repository, not the path inside it, so there is no
exact command to give. Open laaielichter/AgathOS and copy the folder into
~/.claude/skills/, or the file into ~/.claude/agents/.
What AgathOS does
The good daemon for your AI agents. Free, open-source Windows and macOS app that shows every AI agent, MCP server and model on your PC, scores the risk in plain words, warns before damage happens and gives you a real stop button. Offline, no account, no telemetry.
Alternatives in AI
- Agmsg — Cross-vendor messaging for CLI AI coding agents — let Claude Code, Codex, Gemini & Copilot talk to each other 1.5k ★
- Gtm Engineer Skills — Claude Code skill for improving website AEO (AI Engine Optimization) and GEO (Generative Engine Optimization) 761 ★
- OpenGhost — Open desktop AI agent for Windows, macOS and Linux, written from scratch: its own agent engine, its own browse 266 ★
README
AgathOS
**The good guardian for your local AI agents.**
[](https://github.com/laaielichter/AgathOS/actions/workflows/tests.yml)
**[Download the latest version](https://github.com/laaielichter/AgathOS/releases/latest)** for Windows (Intel/AMD and ARM) and macOS (Apple chip and Intel). See [Install](#install).

*All screenshots in this README show demo data, not a real PC.*
*Agathos* is Greek for *good*. AgathOS is a free, open-source app for Windows and macOS that quietly keeps watching the AI agents on your PC, warns you before they do damage, and gives you a real stop button.
Nothing leaves your PC. No account, no cloud, no telemetry. The one thing AgathOS asks the internet is whether a newer version is on GitHub: once a day, without any data about your PC, and one switch (Settings > Updates) turns it off.
Why
In 2025 and 2026 most real harm from AI agents on personal computers did not come from an AI that "wanted" evil. It came from:
- poisoned packages, skills and MCP servers that stole keys and wallets
(Nx "s1ngularity", Shai-Hulud,
postmark-mcp, malicious ClawHub skills) - agents in "allow everything" mode that wiped folders or whole drives
- hidden instructions in repos, web pages and rules files, including invisible Unicode
- local AI servers left open to the network (Ollama on
0.0.0.0:11434) - agents that say "all tests pass" when they did not
Prompt injection is not solved, and nobody can reliably read an AI's mind. AgathOS does not pretend otherwise. It makes every AI on your PC visible, scores the risk in plain words, predicts the next step from the actions it sees, and limits the damage.
What it does
**Six watchers**
| Watcher | Looks for |
|---|---|
| Gatekeeper | MCP servers in every app's config: known-bad packages, unpinned versions, inline secrets, plain-http servers. Appro |
Related Skills
Vibe Sensei
AI Trading Terminal — 68 historical masters watch your trades. Buffett warns on risk, Soros spots reflexivity,
Loomwatch
Put your AI apps to work as a team. Connect Claude Code, Codex and OpenCode on one canvas, ask in plain words,
SentriPet AI
A desktop pet that shows how much of your AI plan is left (Claude, Codex, Copilot…) and nudges you to use it b
Free247editor
Free, open-source personal AI video editor for Claude. Drop in a raw video, say "edit this", give notes in pla
Ebay Finder
Say what you want on eBay in plain words (any language) — get a ranked hunt. The open, keyless AI agent skill
Cc Mod Waitwhat
Retell what Claude Code just said, in plain words, above the prompt. Nothing enters the transcript or the mode
Related Agents
Electron Menubar Engineer
Builds and fixes Electron macOS menu-bar (tray) apps — main/renderer IPC, tray icons, windows, open-at-login,
Byok Token Security Expert
BYOK (Bring-Your-Own-Key) and OAuth token security expert. Deep on cross-platform OS keychain integration (mac
macOS UI Designer
Use this agent when you need to plan, design, or evaluate macOS application user interfaces from a UI/UX persp