Predict it. Rate it. Count it.

Three pillars of x-brain — cannabis (BudBrain), wine (WineBrain), and now food. Same engine, food-domain features.

What FoodBrain does

• Snap a plate, get items. Multi-item plate decomposition: one photo → many ratings, each with portion-aware calories.
• Estimate calories. Always overrideable. USDA → Open Food Facts → recipe inference cascade.
• Restaurant context matters. "I love chicken parm but not from XYZ" — the predictor learns your preferences per venue.
• Track health goals. Daily calorie + macro targets via Mifflin–St Jeor BMR.
• Mood-aware. What you crave when you're stressed isn't what you want when you're celebrating. Tag the context, get smarter predictions.
• Cross-brain pairings. Friends who loved this dish drank these wines (powered by the x-brain knowledge graph).

How the prediction works

Same hybrid engine that powers BudBrain and WineBrain: a 15-question onboarding ladder, k-means cohort assignment, content-based fallback, and a per-user XGBoost model that takes over after ~20 ratings.