nowfound

AI · March 11, 2024

Offline Chat: Private AI

On-Device LLM with RAG

What it does

AI ChatBot that runs entirely on iPhones, iPads and Macs without the Internet. Use it anywhere, and your data stays private and secure. In addition to asking general questions, you can also load your private documents and ask questions about their content.

Does a similar job

all alternatives →
  • Haplo AI2025 · apps.apple.com · ▲98

    Secure & local AI chatbot for iOS and macOS

  • Lekh AIJan 2026 · apps.apple.com · ▲80

    Private, offline AI for iPhone, and iPad

  • Ragna2024 · ▲130

    100% private AI chatbot for desktop

  • LapisNov 2025 · lapis.lvrpiz.com · ▲79

    Secure, offline AI chat assistant on your device

  • Local AI Chat: Pocket LLMOct 2025 · apps.apple.com · ▲8

    Private & Offline AI Assistant

  • LocalChatAIApr 2026 · remi.geeketfier.fr · ▲4

    Private, Offline AI Chatbot powered by Apple Intelligence.

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 · 19d ago · simedw.com

  • Astute585

    Automate your B2B brand going viral, with new media creators

    AI · 20d ago · company-app.joinastute.com

  • Grok Bot547

    AI teammates that you can give real work to

    AI · 27d ago · x.ai

  • 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 · 28d ago · cactuscompute.com

  • Monid479

    One wallet, every paid tool your agent needs

    AI · 8d ago · monid.ai

  • Turn website visitors into qualified pipeline

    AI · 21d ago · clarasdr.ai

Source: Product Hunt launch

Launched alongside, March 2024

the whole month →
  • Dub.co1,475

    Short links with superpowers

    Dev tools · 2024 · dub.co

  • 3Y
  • Microlaunch1,116

    Launch and get feedback on both the idea and product

    Dev tools · 2024 · microlaunch.net

  • Milestone1,113

    Interactive, gamified product tours for SaaS

    Growth · 2024 · milestoneflow.io

  • Hunted Space1,004

    Insights on Product Hunt launches

    Growth · 2024 · hunted.space

  • Creatie850

    The one-stop product design tool amplified by AI

    AI · 2024 · creatie.ai