Archivia: AI Notebooks
Turn any lecture into a learning plan
What it does
In school I had a teacher who’d talk for an hour then spell out a tight learning plan at the end. I studied faster in that class than any other. I never found that in university. Recording lectures meant hours of audio I never revisited. So I built Archivia — record a lecture, get a structured study plan and flashcards back in minutes. No cloud. No ads. Your notes stay on your phone.
Does the same job
all alternatives →
- IMI made an AI that turn live lecture into structured notes,mind-maps,PDF2025 · notorium.app · ▲27
Hi HN, University lectures are long, dense, and fast-paced. Like many students, I used to record them thinking I’d revisit them later — but that never really worked. Even transcripts felt like raw logs. So I built [Notorium](https://www.notorium.app) — an AI assistant that records live lectures and automatically turns them into structured notes, flowcharts, and mind maps— within minutes after class. What it does: - Record lectures inside the app (in-person, live) - Transcribe using Whisper - Send the full transcript to LLM - Use a custom system prompt to: - Summarize the lecture -…
Resonate Learning24d ago · resonatelearn.app · ▲2Record the lecture. Know exactly what you didn't understand.
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
