MealMatch is an intelligent web application that suggests recipes based on the ingredients you already have at home. It leverages a multi-agent architecture using MESA and integrates with the Spoonacular API to retrieve real-world recipes.
- Input ingredients in various languages (e.g., Romanian, Italian)
- Automatic translation & simplification using
googletrans
( translation_agent.py ) - Ingredient validation using a dedicated agent ( ingredient_agent.py )
- Live recipe search from Spoonacular API ( recipe_agent.py )
- Paginated recipe results with images and missing item list ( user_agent.py )
- Agent-based modular architecture with logging and monitoring ( monitor_agent.py )
This project is implemented using the MESA framework (Python-based agent simulation library). It features several specialized agents:
IngredientInputAgent
– Captures raw input from the userTranslationAgent
– Translates and simplifies ingredientsIngredientRecognitionAgent
– Normalizes and validates ingredient namesRecipeSuggestionAgent
– Queries Spoonacular API for recipe suggestionsShoppingAgent
– Builds a list of missing ingredientsUserInteractionAgent
– Sends recipe results to the user interfaceMonitoringAgent
– Logs system actions and flow state
Agents are scheduled using SimultaneousActivation
for proper coordination.
git clone https://github.com/hurr13ane/MealMatch.git
cd MealMatch
mesa==1.1.1
python-dotenv
requests>=2.31.0
googletrans==4.0.0-rc1
Flask
To install the required packages, run the following command:
pip install -r requirements.txt
Run the Flask application
python flask_app.py
Diana-Maria Iercosan |
Alexandru Becher |
For any questions or support, please contact us ^^ .
This project is licensed under the MIT License. This project was created for educational purposes.