IngrediCheck – An "AI-Native" Food Scanning App
Hello HN, longtime lurker, finally I have something to show :) IngrediCheck is a Food Scanning App. It is meant to help with Grocery Shopping, for people who have unique dietary restrictions or preferences. I made it because we were reading too many food labels when Grocery Shopping. If you are shopping for a family, the list of dietary restrictions can get long. The way it works is 1. You enter your dietary restrictions or preferences in natural language. This can be quite flexible. Examples: - I am allergic to oats and peanuts. - I want to avoid seed oils. - Dr Berg on YouTube said avoid…
What it does
In the maker’s words, at launch
Hello HN, longtime lurker, finally I have something to show :) IngrediCheck is a Food Scanning App. It is meant to help with Grocery Shopping, for people who have unique dietary restrictions or preferences. I made it because we were reading too many food labels when Grocery Shopping. If you are shopping for a family, the list of dietary restrictions can get long. The way it works is 1. You enter your dietary restrictions or preferences in natural language. This can be quite flexible. Examples: - I am allergic to oats and peanuts. - I want to avoid seed oils. - Dr Berg on YouTube said avoid Maltodextrin. 2. When Grocery Shopping, scan the Barcode of a packaged food item to get an instant analysis whether it meets your dietary preferences. Hope someone finds it useful! I had fun using LLMs for: 1. Validating dietary preference entered in natural language. 2. Matching natural language dietary preferences to an ingredients list. 3. Extracting structured ingredients list from OCR of package product images. 4. And now I plan to use Agents to scour the web for Packaged Food Item details. PS: - only works for Ingredients right now, not Nutrition label. - only on iPhone right now. - only in US, Canada, UK, India right now. - code is on Github: https://github.com/IngrediCheck
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 · 27d ago · cactuscompute.com
