What I Built?
I built Safe Plate for my roommate, Mayur, who is allergic to nuts.
Whenever we cook together, we spend a long time reading labels and googling whether a recipe is safe. Most recipe sites also don't know what's in our kitchen.
With Safe Plate, you tick the dietary needs, type the ingredients you have (like "rice, tomato, spinach, onion"), and get 3 recipes. If a recipe has anything unsafe, like almonds or peanuts, the app removes it automatically.
Example: I selected "Nut allergy", entered "rice, tomato, spinach, onion", and got 3 recipes. The page also showed "1 recipe(s) removed by the safety filter" because one suggestion had cashews.
GitHub: https://github.com/JAYMS07/Diet-App.git[](https://github.com/JAYMS07/Diet-App.git)
How I Built It
Frontend: HTML, CSS, and JavaScript
Backend: Node.js and Express
AI: Gemma 3 running locally with Ollama
The AI suggests the recipes. Then my code checks every ingredient against a list of banned foods (for nuts: almond, cashew, peanut, walnut, and more) and removes any recipe that matches. I didn't want to trust the AI alone with allergies, because it can make mistakes.
Why Does Open Innovation Matter?
Allergy and health details are private. Because the model runs on my own laptop, Riya's information never goes to anyone else's server. It's also free, with no API key.
Since the project is open source, anyone can make it safer by adding more foods to the banned list, like shellfish, soy or local ingredient names.


Top comments (0)