microAI vs LLM Pigeon

AI ON YOUR PHONE. POWERED BY YOUR DEVICES. Run private AI directly on your phone. Need more power? Connect your own computer and let it handle the heavy AI work while you keep using microAI from your phone. No sign-up. No cloud AI account required. Ask questions. Talk instead of type. Show AI a photo. Read a file. Work on a project. Save something for later. microAI brings local AI, your devices, and your private context together in one workspace. YOUR PHONE. YOUR COMPUTER. YOUR AI. Your phone can run compatible local AI models on its own. When you need more power, connect your own computer. Scan a QR code and your approved Mac or browser can run the model while you continue using microAI from your phone. That means you can move heavier AI work off your phone—reducing the load, heat, and battery use caused by demanding on-device inference. Use your phone when that is enough. Use your computer when you want more power. You choose where your AI runs. NO SIGN-UP. NO CLOUD AI REQUIRED. Local AI should not require another account. microAI can run compatible models directly on your devices without requiring a cloud AI account. Your computer can also become your own AI compute node. Open the microAI website on your computer, load a compatible local model, scan the QR code, and connect. No separate website account is required. DIFFERENT AI FOR DIFFERENT JOBS Not every task needs the same AI. microAI includes task-focused AI helpers: • Private Chat — Ask, write, plan, brainstorm, or talk. • Image Chat — Ask questions about photos and screenshots. • Voice Chat — Talk instead of typing. • Review Writer — Turn your experience into a clear review. • Photo Tagger — Create titles, descriptions, and keywords for photos. Choose which compatible model powers each job. Use a small model for quick everyday tasks, a vision model for images, or a stronger model running on your computer when you need more capability. TALK. SEE. READ. AI should work with more than a text box. Talk naturally with Voice Chat. Add a photo or screenshot and ask questions about what you see. Add a supported PDF, TXT, or Markdown file and ask questions about its contents. Use microAI for writing, research, documents, photos, ideas, and everyday questions. COME BACK WITHOUT STARTING OVER Your useful context should not disappear into old chats. Create Projects to keep related conversations, files, instructions, and context together. Save quick thoughts in Journal. microAI can remember useful context and bring it back when relevant. Memory Map gives you a visual way to explore your conversations, projects, journals, models, and memories. LOCAL AI WITHOUT THE USUAL SETUP You should not need to be an AI engineer to start using local AI. Find a compatible model, download it, and start. microAI keeps model discovery, downloads, switching, and resource management in one place. Advanced users can also import compatible GGUF models. Actual performance depends on your device, model, and connection. YOUR AI. YOUR DEVICES. YOUR DATA. When AI runs on your phone, compatible models process requests directly on your device. When you connect your own computer, the model runs on the computer you approve while you continue using microAI from your phone. Your model files stay on the device running them. You decide when a remote compute node is connected and used. Internet access may still be required for model discovery and downloads, purchases, ratings, app services, and certain system features. RUN AI YOUR WAY. On your phone when you want portability. On your computer when you want more power. No sign-up. No cloud AI account required. Your AI. Your devices. Your choice. Want to use your computer with microAI? Visit: https://linklocalai.com/ By using microAI, you agree to Apple's Standard End User License Agreement (EULA). Apple EULA: https://www.apple.com/legal/internet-services/itunes/dev/stdeula/

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