Lumen
medicine, made legible
What it does
Clinical information is written for clinicians. Lumen translates it for the person holding it. Photograph your medicine boxes to see what each is for and which combinations to ask a pharmacist about—quoted word for word from the official FDA label. Paste your lab results for every value in plain language, including how many were normal. Describe a symptom for how urgently to seek care and where to go. Clinical facts never come from the model. It doesn't diagnose you and stores nothing.
Understand what your medications actually do and which combinations to ask about, read your own lab results in plain language, or practise clinical reasoning against simulated patients.
Understand what you're taking, what your results mean, and whether that symptom needs a doctor tonight — in plain language, from real sources. Photograph the boxes. Lumen quotes the official FDA label word-for-word, so you can see exactly where every warning comes from. Clinics are shut. Nobody wants to be the person who overreacted. And the internet is very good at telling you the worst thing it could possibly be. You don't know if this matters. You don't want to wake anyone over nothing, and you don't want to sit in a waiting room until dawn over nothing either. So you search it instead — and somewhere around the third result is the word you were afraid of. Now you're not sleeping…from lumen-virid-sigma.vercel.app
Does the same job
all alternatives →
ClinicFrame Jul 2026 · clinicframe.com · ▲191Like Granola, but for healthcare. Fully HIPAA-compliant.
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, 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