DEV Community

Varun Ahuja
Varun Ahuja

Posted on

StudyMate AI: I Built an Open-Source AI Study Partner for My College Friend 📚

Hacktoberfest Weekend Challenge: Build for a Friend Submission 🤝

My submission for the Hacktoberfest Weekend Challenge: Build for a Friend.

What I Built

Meet StudyMate AI, an open-source AI study assistant I built for a college friend who struggles with managing study time, organizing notes, and preparing for exams.

College life can get overwhelming. Between multiple subjects, assignments, deadlines, and exams, knowing what to study next can be just as difficult as studying itself.

I wanted to build something that would help my friend spend less time figuring out how to study and more time actually learning.

StudyMate AI brings study planning, notes-based question answering, practice quizzes, and progress tracking into one place.

What it does:

  • Adaptive study planning: Creates a study schedule based on subjects, available time, and upcoming exams.
  • Ask Your Notes: Lets students ask questions about uploaded study materials and receive answers grounded in those materials.
  • AI-generated quizzes: Turns notes into practice questions and flashcards.
  • Weak-topic detection: Uses quiz results to identify concepts that need more revision.
  • Progress tracking: Helps students understand their study habits and keep track of completed tasks.

Rather than acting as another general-purpose chatbot, StudyMate AI is designed around a student's actual syllabus, schedule, and learning progress.

Most importantly, I built it for a real person, not just for a demo.

Demo

Live demo: [Add deployed application URL]

Demo video: [Add video URL]

The demo shows the complete workflow, from adding subjects and uploading notes to generating a study plan and practicing with AI-generated questions.

Code

GitHub repository: [Add your repository URL]

The project is open source, and I welcome contributions, feedback, and ideas for making personalized AI learning tools more accessible.

How I Built It

StudyMate AI uses a modern web application with an AI-powered backend.

The frontend is built with Next.js, TypeScript, and Tailwind CSS. The backend uses Python and FastAPI to process study materials and coordinate AI features.

For its AI capabilities, I use [insert the actual open-weight model and inference method].

The notes assistant retrieves relevant passages from uploaded documents before generating an answer. This helps keep responses grounded in the student's own material instead of relying entirely on the model's general knowledge.

The quiz workflow generates practice questions from relevant study content. Quiz results are then used to identify topics that deserve more revision.

The study planner combines the student's deadlines, available study time, and incomplete tasks to recommend what to work on next.

I focused on building a useful end-to-end workflow rather than adding AI features just for the sake of having AI.

Why Does Open Innovation Matter?

Education is personal. Students have different syllabuses, learning speeds, budgets, and privacy requirements.

Building with open-weight models and open-source tools gives developers the freedom to experiment with different models, customize the learning experience, and potentially run AI locally.

For StudyMate AI, local inference can help keep private notes on a student's own device when the entire workflow is configured for local processing. It can also reduce dependence on paid proprietary model APIs.

Open innovation also means other developers can inspect the code, improve retrieval quality, add support for more languages, and adapt the application to different subjects and learning styles.

I want tools like this to be accessible to students who cannot afford expensive subscriptions but still deserve useful learning technology.

What I Learned

Building StudyMate AI helped me explore how open-weight models, document retrieval, and personalized workflows can work together in a practical application.

It also reinforced an important lesson: useful AI is not just about generating answers. It is about understanding the user's context and helping them take the next useful action.

My Agent Session

[Add your DevRelay agent session link, if available.]

Prize Categories

  • Best Use of Gemma — [Include only if the project genuinely uses Gemma.]
  • Best Use of Render — [Include only if Render is used in a qualifying way.]

I am only entering partner categories whose technologies I actually use in the project.


Built with ❤️ for a college friend, with the hope of making studying a little less stressful and a lot more organized.

devchallenge #weekendchallenge #hf26challenge #hacktoberfest #opensource #AI

Top comments (0)