{"slug": "hostmeal-an-ai-meal-assistant-i-built-for-my-hosteller-brother", "title": "HostMeal — An AI Meal Assistant I Built for My Hosteller Brother😋🥣", "summary": "A developer built HostMeal, an open-source AI meal assistant that suggests recipes to hostel students based on the ingredients, budget, time, servings, dietary preferences and cooking equipment they enter. The React and Node/Express app uses the open-weight Gemma model via Hugging Face for structured meal recommendations and the YouTube Data API for recipe videos, with the developer noting that prompt and response structuring was needed so suggestions respect constraints like a 20-minute cook time or a gas stove only.", "body_md": "*This is a submission for the Hacktoberfest Weekend Challenge: Build for a Friend.*\n\n**What I Built**\n\nMy brother is currently staying in a hostel, and one of the small problems he deals with is deciding what to cook.\n\nWhen you're staying in a hostel, you usually don't have a fully equipped kitchen or a lot of ingredients. Sometimes you have a few things in your room, a small budget, and maybe 20–30 minutes to cook something.\n\nSo I thought, instead of searching for recipes every time, why not make something where you can simply enter what you already have and get some ideas?\n\nThat's how I came up with HostMeal.\n\nHostMeal is a small AI-powered meal assistant that helps hostel students decide what they can cook based on their available ingredients and situation.\n\nYou can enter things like:\n\nIngredients you already have\n\nYour budget\n\nHow much time you have\n\nNumber of servings\n\nDietary preference\n\nCooking equipment\n\nTaste preference\n\nType of meal\n\nThe app then gives you meal suggestions that match those requirements.\n\nIt also shows which ingredients are missing, provides the recipe, creates a shopping list, and finds a relevant YouTube cooking video.\n\nThe main idea is pretty simple:\n\nTell HostMeal what you have, and it helps you figure out what you can make.\n\nI originally made it for my brother, but while working on it I realized that this could also be useful for other students living away from home.\n\n**Demo**\n\nLive Application: [https://hostmeal.netlify.app/](https://hostmeal.netlify.app/)\n\n**Code**\n\nGitHub Repository: [https://github.com/reyan3/HostMeal_Hacktoberfest01](https://github.com/reyan3/HostMeal_Hacktoberfest01)\n\nThe project has a React frontend and a Node/Express backend.\n\nI've kept the project open source so that other developers can look at the code, suggest improvements, or contribute new features.\n\n**How I Built It**\n\nI used:\n\nReact for the frontend\n\nTailwind CSS for styling\n\nNode.js + Express for the backend\n\nGemma for generating meal recommendations\n\nHugging Face for hosted model inference\n\nYouTube Data API for finding recipe videos\n\nNetlify for the frontend\n\nRender for the backend\n\nHow it works\n\nThe user first enters their ingredients and preferences in the React app.\n\nFor example:\n\nEggs, bread, onion\n\nBudget: ₹80\n\nTime: 20 minutes\n\nEquipment: Gas stove\n\nThe frontend sends this information to my Express backend.\n\nThe backend creates a prompt with these requirements and sends it to Gemma. I ask the model to return the meal information in a structured format so that I can use it directly in the frontend.\n\nThe response contains things like the meal name, ingredients, missing ingredients, and cooking instructions.\n\nFor the YouTube videos, I didn't ask the AI to generate video links. Instead, my backend uses the YouTube Data API to search for an actual recipe video based on the generated meal.\n\nSo the basic flow is:\n\nUser\n\n  ↓\n\nReact\n\n  ↓\n\nExpress Backend\n\n  ↓\n\nGemma\n\n  ↓\n\nMeal Suggestions\n\n  ↓\n\nReact\n\n  ↓\n\nYouTube Data API\n\n  ↓\n\nRecipe Video\n\nOne of the more challenging parts was making the AI consider multiple things at once.\n\nFor example, a recipe might use the right ingredients but take 45 minutes to prepare when the user only has 20 minutes. Or it might require an oven when the user only has a gas stove.\n\nSo I had to spend some time working on the prompt and the structure of the response.\n\nThis was also one of my first projects where I used an open-weight AI model as an actual part of the application rather than just experimenting with AI separately.\n\n**Why Does Open Innovation Matter?**\n\nFor this project, using Gemma gave me the chance to work with an open-weight model and understand how it can be used inside a real application.\n\nI liked that I could experiment with the model and think about different ways of running it in the future instead of building the whole project around a single closed AI service.\n\nThere are also things I'd like to try later, such as using a smaller model locally, improving the recommendations for Indian hostel food, and adding more regional recipes.\n\nMaking the project open source also means I'm not the only person who has to decide where it goes next.\n\nSomeone could add a better recommendation system, improve the UI, add more meal options, or completely change how the recipe generation works.\n\nThat's one of the reasons I wanted to build this as an open-source project.\n\n**Prize Categories**\n\nBest Use of Render - \n\nI'm using Render to deploy and host the Express backend for HostMeal.\n\nBest Use of Gemma - \n\nI'm using Gemma as the AI model that generates the personalized meal recommendations.\n\n**Why I Built It**\n\nI didn't start this project with the idea of building a huge platform.\n\nIt started with my brother being in a hostel and me thinking about a very simple problem:\n\n\"What can he cook with the stuff he already has?\"\n\nThat was enough of an idea for me to start building.\n\nI also wanted to use Hacktoberfest as an opportunity to build something that wasn't just another practice project, but something that could actually be useful to someone close to me.\n\nSo, this is HostMeal — a small project I built for my brother, and hopefully something that can help other hostel students too.", "url": "https://wpnews.pro/news/hostmeal-an-ai-meal-assistant-i-built-for-my-hosteller-brother", "canonical_source": "https://dev.to/reyan3/hostmeal-an-ai-meal-assistant-i-built-for-my-hosteller-brother-2jmi", "published_at": "2026-10-03 11:06:15+00:00", "updated_at": "2026-10-03 11:08:48.726824+00:00", "lang": "en", "topics": ["artificial-intelligence", "ai-tools", "ai-products", "generative-ai", "developer-tools"], "entities": ["HostMeal", "Gemma", "Hugging Face", "YouTube Data API", "React", "Node.js", "Express", "Netlify"], "also_reported_by": [], "alternates": {"html": "https://wpnews.pro/news/hostmeal-an-ai-meal-assistant-i-built-for-my-hosteller-brother", "markdown": "https://wpnews.pro/news/hostmeal-an-ai-meal-assistant-i-built-for-my-hosteller-brother.md", "text": "https://wpnews.pro/news/hostmeal-an-ai-meal-assistant-i-built-for-my-hosteller-brother.txt", "jsonld": "https://wpnews.pro/news/hostmeal-an-ai-meal-assistant-i-built-for-my-hosteller-brother.jsonld"}}