BudgetBuddy — AI-Powered Personal Finance Tracker

Author: Ahmed Furkhan Class: CS 5610 Web Development — Northeastern University Class link: https://johnguerra.co/classes/webDevelopment_online_summer_2026/

Project Objective

BudgetBuddy helps people track spending without manual categorization. When a user logs a transaction, the Groq API automatically assigns a spending category, and the app shows a live dashboard of spending vs. monthly budgets plus savings-goal tracking.

Screenshot

Features

• User accounts with secure password hashing (bcrypt) and sessions
• Transaction logging with AI auto-categorization (Groq, llama-3.3-70b-versatile)
• Monthly budgets per category with full CRUD
• Spending-vs-budget dashboard with aggregation
• Savings goals with contribution tracking

Tech Stack

• Node.js + Express (ESM)
• MongoDB (native driver — no Mongoose)
• Vanilla ES6 frontend (client-side rendering)
• Groq API for categorization

Build & Run Instructions

1. Clone the repo and install dependencies:

   npm install
   

2. Copy .env.example to .env and fill in your values:

   MONGO_URI=...
   GROQ_API_KEY=...
   SESSION_SECRET=...
   

3. Seed the database with 1,000+ sample transactions:

   npm run seed
   

4. Start the server:

   npm start
   

5. Open http://localhost:3000 Demo login: james@northeastern.edu / demo1234

GenAI Disclosure

This project uses the Groq API (llama-3.3-70b-versatile) as a runtime feature for transaction categorization. Generative AI tools were also used to assist with scaffolding and boilerplate; all code was reviewed and understood by the author.

License

MIT — see LICENSE.