LLM Pigeon

Put a full-featured AI assistant in your pocket—without sending a single word to any outside cloud.

LLM Pigeon works together with LLM Pigeon Server on your Mac.

• Type a message on your iPhone.

• The text is stored inside your private iCloud files.

• Your Mac picks it up, runs the large-language model locally, writes the reply, and CloudKit delivers the answer back to the phone.

Why you’ll love it

• 100 % privacy: messages never leave your own iCloud container; no analytics, no ads, no accounts. You can optionally add a search-engine API.

• Real LLMs: choose from a set of built-in models or point the server at LM Studio or Ollama to swap in any model you prefer.

How it works

1. Install LLM Pigeon Server (free) on a Mac that’s signed in with the same iCloud account.

2. Download the models you want and, if you’d like web search, enter a Serper API key.

3. Start a new chat in the iOS app.

4. Receive answers in seconds, even on hotel Wi-Fi.

Zero data collection

• No personal information

• No usage analytics

• No crash logs—everything stays on your devices

• If you enable web search, only the queries your LLM generates are sent to Serper.

Requirements

• iPhone running iOS 17 or later

• Mac running macOS 14 (Sonoma) or later with LLM Pigeon Server installed

• iCloud Drive enabled on both devices