Open-sourced a web client that lets any device use Apple's on-device AI
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:…
In plain words
Perspective Intelligence Web is an open-source browser-based client that allows any device on a home network to access Apple's on-device AI models running on a Mac with Apple Silicon. One Mac runs the server while phones, laptops, and other devices connect through a web browser to chat with Apple Foundation Models locally, with responses streaming token by token. All processing stays within the network and nothing is sent to external services. Built with Next.js, TypeScript, and Tailwind, it is available under the MIT License.
written from the facts on this page · September 2026
From the sources
In the maker’s words, at launch
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-...
More ai this month
the category →
I trained a 125M-parameter transformer to autocomplete piano performances in real time (~108 notes/sec on an iPhone 15). The idea is basically GitHub Copilot or Tabnine, except instead of prompting it with code, you prompt it by playing a few notes on a MIDI piano. The model then continues what you played, entirely on-device. The app is free if anyone wants to try it. Happy to answer questions about the model, training, Core ML, or the many things that didn't work.
AI · 17d ago · simedw.com
Astute▲585Automate your B2B brand going viral, with new media creators
AI · 18d ago · company-app.joinastute.com
Hey HN, Henry from Cactus here! We previously released Cactus Needle, a 14MB agentic LLM for tool call, device use, and structured extraction for phones, wearables, smart homes, small robots and microcontrollers. We got really great feedback here, and have now incorporated the suggestions to release Needle 2. The whole model is a single 14MB binary that runs a full session in 28MB of RAM; 45m parameters at 2bit compression. Needle hits 500 tokens/sec decode speed on a Raspberry Pi 5, sits between 400-1,500 tokens/sec on VR devices like Meta Quest 3S and Apple Vision Pro, and ranges…
AI · 26d ago · cactuscompute.com
Launched alongside, March 2026
the whole month →
Switch from ChatGPT to Claude with import memory feature
AI · Mar 2026 · claude.com
