Open-Source NotebookLM Alternative
Open Notebook is a tool where you can upload your own sources - PDFs (textbooks, research papers), Github repos, documentation websites, and other URLs. Once uploaded, you can either chat with an AI about them or run “apps” on top of those sources. Apps can be anything. Right now, I’ve built the following: - turn articles into short video overviews - create a mind map of the source - create summaries or other reports about the source - generate quizzes or flashcards to help study the source You can also remix existing apps or create one from scratch. I built this because I wanted to make…
What it does
In the maker’s words, at launch
Open Notebook is a tool where you can upload your own sources - PDFs (textbooks, research papers), Github repos, documentation websites, and other URLs. Once uploaded, you can either chat with an AI about them or run “apps” on top of those sources. Apps can be anything. Right now, I’ve built the following: - turn articles into short video overviews - create a mind map of the source - create summaries or other reports about the source - generate quizzes or flashcards to help study the source You can also remix existing apps or create one from scratch. I built this because I wanted to make self-learning less painful. I enjoy diving into new subjects (electronics, space, math), but the usual options feel limited: long lectures, repetitive ChatGPT chats, or slogging through PDFs and textbooks. NotebookLM looked promising in this space, but I found it too rigid - the outputs weren’t bad, but they weren’t adaptable to how I wanted to learn. Open Notebook takes a different approach: it exposes the full workflows behind the AI outputs (LLM prompts, steps, formats). That means you can see exactly how a video, podcast, or summary is generated, change the process, or share your own workflows with others. That is why I consider Open Notebook to be the "open source" version of NotebookLM. I’d be interested in feedback on what’s useful, what’s missing, or how you’d want to adapt it for your own learning.
Does the same job
all alternatives →
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 · 26d ago · cactuscompute.com
Launched alongside, November 2025
the whole month →
- IB
Life & fun · Nov 2025 · bitsnpieces.dev
- BBoing▲782
Life & fun · Nov 2025 · boing.greg.technology