ShelfLife-KIMS
This is a submission for the Hacktoberfest Weekend Challenge: Build for a Friend What I Built I built ShelfLife-KIMS, a smart kitchen management system that helps a household decide what to cook based on the people in the house, their food restrictions and preferences, and the ingredients they already have. The main things I built are: Household management — create a household and add different…
This submission for the Hacktoberfest Weekend Challenge is ShelfLife-KIMS, a smart kitchen management system designed to assist households in deciding what to cook based on their members, dietary restrictions, ingredient availability, and personal preferences. The application's core components include household management, food profiles, inventory management, food usage history, and persistent data storage.
To create ShelfLife-KIMS, a full-stack web application was developed using React and TypeScript for the frontend, and FastAPI and Python for the backend. MongoDB Atlas served as the data layer, storing household members, food preferences, inventory, and usage history. The AI component of the system is planned to utilize open-weight Gemma models with Mastra as the agent orchestration layer, functioning as a "kitchen brain" that understands household constraints, preferences, and available ingredients.
The current foundation of ShelfLife-KIMS focuses on ensuring the reliability of household data, food profiles, inventory management, and data persistence. The AI architecture is built to enhance these foundations by generating intelligent recommendations, validating food choices, and automating certain processes. The current prototype emphasizes addressing the household problem of food waste by providing a practical and personalized experience, rather than reinventing infrastructure that already exists.
Written by urgent.news from Dev.to's reporting — not their text. Machine-written — may contain errors; check the original before relying on it.
