Back to browse
GitHub Repository

Open-source AI chat app powered by Apple Foundation Models. Runs in any browser. Self-hosted. Private. No cloud.

42 starsTypeScript

Open-sourced a web client that lets any device use Apple's on-device AI

by tayarndt·Mar 4, 2026·10 points·1 comment

AI Analysis

●●●BangerZero to OneSolve My Problem

Apple Intelligence in the browser, streaming from your Mac, nothing leaves network.

Strengths
  • Genuinely novel architecture: local macOS AI exposed as networked service via browser
  • 8 specialized agents with auto-routing removes friction of manual tool selection
  • Complete stack (Next.js auth, PostgreSQL, streaming) ships as working product today
Weaknesses
  • Requires Apple Silicon Mac (excludes Intel, Windows, Linux servers as compute)
  • Depends on Perspective Server menu bar app; setup complexity for non-technical users
Category
Target Audience

macOS users with Apple Silicon who want to share local AI inference across home/office devices securely

Similar To

Ollama web UI · LM Studio

Post Description

I use Claude every day but there are things I will not type into a cloud service. I have a Mac with Apple Silicon running Apple Foundation Models locally and privately. But I was not always at my Mac. So we built Perspective Intelligence Web. One Mac runs Perspective Server. Any device on your network opens a browser and chats with Apple Intelligence through it. Phone, Windows laptop, Chromebook, Linux machine. Streaming responses, token by token. Nothing leaves your network. MIT License. Next.js, TypeScript, Tailwind. Full writeup: https://taylorarndt.substack.com/p/i-opened-claude-and-then-...

Similar Projects