StudyMate — An AI Study Partner Built for a Friend

This is a submission for the Hacktoberfest Weekend Challenge: Build for a Friend

What I Built

I built StudyMate, an AI-powered study partner for a friend who struggles with managing lecture notes, PDFs, and a large amount of study material before exams.

Instead of switching between notes, search engines, YouTube, and different AI tools, StudyMate brings everything into one place.

With StudyMate, students can:

• 📚 Upload and organize study materials
• 🤖 Ask questions about their notes
• 🔎 Get answers grounded in their study material
• 📝 Generate quizzes for practice
• 📅 Create personalized study plans
• 🔄 Revise important concepts
• 📊 Track their learning progress

The goal is simple:

Turn scattered study material into a personal, interactive AI study partner.

I built StudyMate to solve a real problem: having plenty of study material but not knowing how to effectively learn, practice, revise, and prepare from it.

Demo

🚀 Live Demo:

https://study-mate-one-psi.vercel.app/

Explore StudyMate and experience the AI-powered study workflow.

Code

💻 GitHub Repository:

https://github.com/azmolwasimhussain-ops/StudyMate

The complete source code is open-source and available on GitHub.

How I Built It

StudyMate is built with Next.js, React, and TypeScript, with a modular architecture for AI, document processing, RAG, database operations, and study features.

For the AI layer, I used Google Gemma 2 2B, an open-weight model, running locally through Ollama.

The core workflow is:

Study Material
      ↓
Document Processing
      ↓
Chunking & Retrieval
      ↓
Relevant Context
      ↓
Gemma 2 2B
      ↓
Grounded Response

This AI architecture powers the main StudyMate features:

• 🤖 AI study chat
• 🔎 RAG-based answers from study materials
• 📝 Quiz generation
• 📅 Personalized study planning
• 🔄 Revision assistance
• 📊 Learning progress I built the AI layer using a provider-based architecture, so the application is not tightly coupled to a single model or AI provider. This makes it easier to experiment with different open-weight models in the future. I also used AI coding agents during development to help with implementation, debugging, refactoring, and organizing the codebase into a maintainable structure. The main idea was to make the open-weight model the core intelligence behind StudyMate rather than simply adding AI as a separate feature.

Why Does Open Innovation Matter?

Open innovation matters because it gives developers more control, flexibility, and freedom to experiment with the technology behind their products.

For StudyMate, this is especially important because the application is designed around students' personal study materials such as lecture notes, PDFs, and assignments.

Instead of building the entire AI experience around a closed API, I used an open-weight model, Gemma 2 2B, running through Ollama. This allowed me to build the AI layer around a model that I can run and experiment with locally.

Open innovation made it possible for me to:

• 🔓 Experiment with open-weight AI models
• 🖥️ Run the model locally through Ollama
• 🔧 Customize prompts and AI behavior
• 🔎 Build my own RAG pipeline
• 🔄 Change or experiment with different models
• 🧩 Create a modular AI provider architecture
• 🚀 Have more control over how the AI layer is developed

A closed API can be convenient, but open-weight AI gives developers the ability to understand, customize, and evolve the technology behind their applications.

For StudyMate, open innovation wasn't just about using an AI model — it allowed me to build the AI layer around the product rather than building the product around a single closed AI provider.

That flexibility is what makes open innovation valuable for projects like StudyMate.

Prize Categories

• 🏆 Best Use of Gemma — StudyMate uses Google Gemma 2 2B, an open-weight model running through Ollama, as the core AI intelligence behind its study assistant, RAG-based question answering, quiz generation, planning, and revision features.