Napkinbook, a smart canvas for discovering, and sharing insights
Napkinbook is a smart canvas for collaboration, sharing, and discovering insights. I think of it as a more computational version of Excalidraw or Miro: a flexible canvas where you can think, build, present, and collaborate without constantly moving between different tools. Since my first Show HN, I’ve added: * Much better mobile support * AI-assisted brainstorming * Presentation decks with animations * Shareable reports * Live collaboration * Actual Git history The goal is to make the canvas itself the workspace, rather than treating whiteboarding, presenting, reporting, and version history…
What it does
A computational whiteboard that closes the gap between data and decisions. Cloud-first, collaborative, and built for durable work.
NapkinBook is a digital and computational whiteboard for people who make data driven decisions. Start from the evidance, and update with your beliefs over time. The board does recomputes as you work. Wire in real evidence, then share it so sharper people can try to break it. Circles hold values, squares do the math, wires carry the numbers between them. Nudge any input, and everything downstream, including your final number, recomputes the moment you let go. Send one link and someone sharper picks up your board with every number still live: same canvas, live cursors, live ink, no accounts to create. The link doubles as the key, so boards stay end-to-end encrypted and the server never sees…from desk.napkinbook.com
In the maker’s words, at launch
Napkinbook is a smart canvas for collaboration, sharing, and discovering insights. I think of it as a more computational version of Excalidraw or Miro: a flexible canvas where you can think, build, present, and collaborate without constantly moving between different tools. Since my first Show HN, I’ve added: * Much better mobile support * AI-assisted brainstorming * Presentation decks with animations * Shareable reports * Live collaboration * Actual Git history The goal is to make the canvas itself the workspace, rather than treating whiteboarding, presenting, reporting, and version history as separate products. I’d love feedback, especially on the interaction model and where this feels meaningfully different from existing canvas tools.
Does the same job
all alternatives →
- NANapkinbook – an infinite computational whiteboard/dashboardJul 2026 · napkinbook.com · ▲5
I am a superforecaster and napkinbook is a tool I have used to do forecasts and to organize my thoughts and to plan for the future. I built this originally so I could make videos on prediction markets and break down my ideas so I wanted to share it with all of you :)
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
Launched alongside, August 2026
the whole month →- TL
Life & fun · 10d ago · louisabraham.github.io
- SA
Hello HN! I found that picking out plausible but diverse skin tones for my digital art and game development projects was kind of difficult, and I got curious about if there was a way to define a color space that made it easy. I've built a color picker and procedural generation algorithm based on the space as well as a bunch of other fun js features and demos throughout the page that use the equations. If you find it interesting, I have lots of explanations of how I built it and what properties the space has. The methodology might be a bit shaky, but hopefully the result is as helpful for…
Life & fun · Aug 2026 · toneyalexander.github.io
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