Skip to content

Jam-Cai/replate

 
 

Folders and files

NameName
Last commit message
Last commit date

Latest commit

 

History

66 Commits
 
 
 
 
 
 
 
 
 
 
 
 
 
 

Repository files navigation

🥡 Replate

Replate is a generative AI-powered sustainability app that turns the world into your fridge. It connects users to surplus food from local restaurants while adjusting to dietary preferences and restrictions. Built by students at GenAI Genesis 2025 to combat food waste, promote sustainable eating, and deliver a futuristic, AI-assisted experience.

MIT License Built with TypeScript Made with ❤️ at GenAI Genesis


🌍 Inspiration

Billions of tons of food go to waste every year—meanwhile, students and families struggle to afford meals. We built Replate to connect these dots using generative AI, creating a smart, sustainable food recovery system that works for everyone.


🚀 What It Does

  • 🌱 Recommends surplus meals based on dietary needs, religious restrictions, and user preferences
  • 🤝 Uses Gemini + Cohere in a multi-agent LLM pipeline to interpret ambiguous, human-like meal requests
  • 🛍️ Sources food from local restaurants using the Too Good To Go API
  • 📡 Streams real-time updates to the frontend via Socket.io
  • 🗺️ Maps nearby meal deals on an interactive Leaflet.js map
  • 🤖 Envisions robot-based last-mile delivery for a greener future

🧠 AI Stack

  • Gemini API – Natural language understanding
  • Cohere API – Contextual RAG + semantic search
  • Multi-agent architecture – Gemini and Cohere reach consensus for accurate recommendations

⚙️ Tech Stack

🧑‍💻 Languages

  • TypeScript
  • JavaScript
  • Python

🧰 Frameworks and Libraries

  • Node.js
  • React
  • Next.js
  • Express.js
  • Flask
  • Socket.io
  • Leaflet.js
  • Twilio

☁️ Platforms & APIs

  • Google Cloud Platform (GCP)
  • Gemini API
  • Cohere API
  • Too Good To Go API
  • Twilio

🛠️ Tools

  • Git & GitHub
  • Postman
  • Liveshare
  • Node.js

About

No description, website, or topics provided.

Resources

Stars

Watchers

Forks

Releases

No releases published

Packages

No packages published

Languages

  • Python 53.5%
  • TypeScript 43.2%
  • JavaScript 2.6%
  • CSS 0.7%