Passion Livres
L'app qui connecte lecteurs, auteurs et livres grâce à l'IA
What it does
Passion Livres repense l'expérience du lecteur moderne. Importez votre bibliothèque depuis Goodreads ou Babelio, recevez des recommandations IA selon votre humeur, découvrez votre portrait littéraire et rejoignez des Tribus de lecteurs. Auteurs, éditeurs et libraires connectés dans un seul écosystème. Interviews d'auteurs exclusives. PWA, mobile-first, zéro installation. 100% gratuit.
Does the same job
all alternatives →
- L1LibreRead 1.0 – Self-Hosted Free Ebook Reader2017 · libreread.org · ▲210
- AIAn immersive, social reading app for book nerds2025 · ▲5
This is a first draft of an app that I am working on that is the "anti blinkist (the book summarization app)". I call it Augre (aug-ur - short for augmented reader) and the whole idea is that I want to immerse more, not less in a book. I want to dive deeper into the text, chat with others who are reading the book and get into delicious discussions. It's still early but here are a couple of features: 1. A really solid cross platform epub reader 2. Left sidebar which augments the reading experience with tables, images, maps (and other artifacts coming soon) 3. Book chat where you can chat with…
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 · 27d ago · cactuscompute.com
