by 201Harsh
IRIS 👁️ — A "God Mode" AI operator that controls your entire OS 💻 via voice. Automates coding 👨💻, deep focus 🛡️, remote access 📲, and context recall ⏳. No mouse, no keyboard → complete intelligent execution 🚀.
# Add to your Claude Code skills
git clone https://github.com/201Harsh/IRIS-AILast scanned: 5/30/2026
{
"issues": [],
"status": "PASSED",
"scannedAt": "2026-05-30T16:34:41.911Z",
"npmAuditRan": false,
"pipAuditRan": true
}IRIS-AI is an open-source ai agents skill for AI coding assistants such as Claude Code, Codex CLI, and ChatGPT, built by 201Harsh. IRIS 👁️ — A "God Mode" AI operator that controls your entire OS 💻 via voice. Automates coding 👨💻, deep focus 🛡️, remote access 📲, and context recall ⏳. No mouse, no keyboard → complete intelligent execution 🚀. It has 120 GitHub stars.
Yes. IRIS-AI passed SkillsLLM's automated security scan — a dependency vulnerability audit plus prompt-injection heuristics — with no high-severity issues. You can read the full report in the Security Report section on this page.
Clone the repository with "git clone https://github.com/201Harsh/IRIS-AI" and add it to your Claude Code skills directory (see the Installation section above).
IRIS-AI is primarily written in TypeScript. It is open-source under 201Harsh on GitHub, so you can review or fork the full source.
Yes. SkillsLLM lists many other AI Agents skills you can browse and compare side by side. Open the AI Agents category from the badge at the top of this page, or use the Related Skills and comparison links further down to weigh IRIS-AI against similar tools.
No comments yet. Be the first to share your thoughts!

A local-first neural execution system that turns intent into real OS actions.
IRIS is not a chatbot.
It is a local-first AI Operating System layer that executes real-world actions across your system, applications, and devices.
Speak your command. IRIS executes it.
Ctrl+Alt+Space).window.electron.ipcRenderer.invoke('tool-name', payload)
IRIS is forged using a high-performance stack combining web technologies with deep native OS access and state-of-the-art AI models.
@google/genai).@huggingface/inference, @xenova/transformers).loudness (master audio), clipboardy (phantom typing), screenshot-desktop (visual context).pdf-parse, mammoth (docx), cheerio (HTML DOM).git clone https://github.com/201Harsh/IRIS-AI.git
cd IRIS-AI
npm install
npm run dev
IRIS operates locally, but requires specific API keys to bridge the gap to large language models and search engines. Your keys are encrypted and stored locally on your machine. They are never sent to our servers.
.env.example to .env in the root directory and place your keys there for local testing.The Neural OS requires these core engines to process logic and execute actions.
GEMINI_API_KEY)