AllergyGuard — Open-Source Offline Dietary Safety & Recipe Transformation Engine

Description and use

AllergyGuard is an offline, client‑side tool that transforms conventional recipes into hypoallergenic versions using AI, ensuring safety for users with severe food allergies.

Problem

Shared living arrangements create friction when a roommate has severe immunological food sensitivities; commercial cooking platforms often suggest unsafe substitutions such as almond flour for wheat, risking anaphylaxis.

Outcome

AllergyGuard enables safe, offline recipe transformation for users with severe food allergies, eliminating risky substitutions and providing real‑time audio guidance.

Workflow

• 1. Load a conventional recipe or food label into AllergyGuard.
• 2. The parsing engine isolates allergen vectors (gliadin, casein, nut antigens).
• 3. The engine computes drop‑in structural equivalents for each allergen.
• 4. The industrial nomenclature inspector checks packaged food labels against a 40+ token lexicon for hidden wheat derivatives and tree‑nut derivatives.
• 5. The user receives a transformed recipe with safe ingredient substitutions and audio narration via the Web Speech API.
• 6. The transformed recipe is executed offline in the browser without external APIs.

Evidence

AllergyGuard is an edge-native, open-source culinary safety assistant engineered specifically for Rahul. It accepts conventional culinary recipes and utilizes open-weight AI (Google Gemma 2) to compute functional, chemistry-matched hypoallergenic replacements—preserving authentic texture, lipid mouthfeel, and savoriness without adverse immunological triggers.

Source

The platform executes entirely client-side, translating conventional recipes into biochemically matched hypoallergenic formulations without reliance on external cloud APIs.

Source

Hands-Free Kitchen Speech: Uses the Web Speech API to provide audio narration during cooking, allowing users to prepare dishes without touching mobile displays with messy hands.

Source