EcoMealAI

EcoMealAI helps you plan sustainable meals with AI, offering low-carbon recipes, weekly planners, and shopping lists. Built with Kiro’s tools, it educates on carbon footprints.

Comment

Project Story

Inspiration

As a final-year Computer Engineering student passionate about AI and sustainability, I was inspired by the growing need to combat climate change through daily choices. Seeing friends struggle with meal planning, I wanted to create an educational tool that makes eco-friendly eating accessible and fun – that’s how EcoMealAI was born for the Kiro Hackathon!

What it does

EcoMealAI is a Streamlit app that helps users plan sustainable meals. It offers personalized preferences (e.g., Vegetarian), recipe searches via TheMealDB API, a weekly planner with unique low-carbon suggestions, and shopping list exports (CSV/PDF). Users can save, load, or upload plans with a unique UID, all while learning about their carbon footprint.

How we built it

I leveraged @Kiro's AI tools to kickstart the project, using spec-to-code to define user stories in Markdown. The app integrates TheMealDB API for recipes, ClimatIQ for carbon estimates (heuristic), and Streamlit for the UI. Python handled logic, with caching to optimize performance, and reportlab generated PDF exports. GitHub hosted the repo, and Streamlit Cloud deployed the live version.

Challenges we ran into

Streamlit Cloud’s latency slowed recipe loading and page switches, while TheMealDB API rate limits delayed suggestions. Fixing UI bugs (e.g., image loading errors) and ensuring smooth save/load functionality tested my problem-solving skills, especially under the hackathon’s tight timeline.

Accomplishments that we're proud of

I’m thrilled to have built a fully functional app from scratch in days, integrating AI and sustainability seamlessly. The preloaded recipe feature reduced delays, and the MIT-licensed GitHub repo showcases my work – a personal milestone!

What we learned

I deepened my understanding of Streamlit deployment, API integration, and performance optimization (e.g., caching with lru_cache). Collaboration with Kiro’s AI taught me to iterate quickly, and troubleshooting taught resilience under pressure.

What's next for EcoMealAI

Next, I’d love to add real-time carbon data via a paid ClimatIQ API, support multiple languages, and introduce a community feature for shared recipes. Expanding to mobile with a PWA is also on the horizon – excited to grow this impact!

Inspiration...

This project reflects my journey from coding passion to real-world impact, fueled by Kiro’s support and my love for sustainable living. Let’s keep the conversation going – what eco-tips do you have? 🌱

Built With

Share this project:

Updates