This is a submission for the Hacktoberfest Weekend Challenge: Build for a Friend
StudyMate: An AI Study Partner That Tells You What to Do Next
What I Built
I built StudyMate, an AI study partner for a friend who is a real student. She has plenty of study material, but when she gets stuck on a topic she often doesn't know what to do next: re-read, watch a video, practice, or revise.
Most AI tools work like this: Ask → Get answer. Then the student is on their own again.
StudyMate works like this:
Ask → Understand → Practice → Revise → Improve
It looks at what the student asked and offers the right next actions.
- Concept question ("Explain electromagnetic induction"): Explain simply, Use an analogy, Real-world example, Quiz me.
- Numerical ("Calculate the induced emf…"): Give me a hint, Show formula, Solve step-by-step, Similar problem.
- Revision: Quick revision, Flashcards, Common mistakes, Quiz, Exam practice.
The options are adaptive, not fixed. The same app gives different next steps depending on what the student is doing.
Demo
Video Demo
Screenshot
StudyMate's chat interface. After each answer, it offers adaptive next actions based on what the student asked.
Code
chanveersinghdev
/
Studymate
AI study assistant that explains topics, adapts to your goals and level (Beginner to Advanced), and remembers context so you don't repeat yourself. Built with FastAPI, Ollama Cloud, and GPT-OSS. Privacy-first: it only uses what you provide or allow it to remember. Get quizzes, follow-ups, and clear answers in your style.
StudyMate — Ollama Cloud Edition
Personalized AI study partner with contextual learning actions.
AI provider
This version uses Ollama Cloud by default. The default configurable model is gpt-oss:120b.
Setup
1. Backend
cd backend
python -m venv .venv
.venv\\Scripts\\activate
pip install -r requirements.txt
copy .env.example .env
Open backend/.env and add your Ollama Cloud API key:
AI_PROVIDER=ollama_cloud
OLLAMA_HOST=https://ollama.com
OLLAMA_API_KEY=YOUR_KEY_HERE
OLLAMA_MODEL=gpt-oss:120b
Then:
uvicorn app.main:app --reload --port 8000
Check:
http://127.0.0.1:8000/api/health
2. Frontend
In a second terminal:
cd frontend
npm install
npm run dev
Open the Vite URL shown in the terminal.
Included
- Rounded Claude-inspired chat UI
- Hover and message animations
- Dark/light mode
- Responsive layout
- Context-aware study actions
- Learning-phase detection
- Ollama Cloud API integration
- Configurable model
- Server-side API key handling
- Fallback UI when no key is configured
Security
Never commit backend/.env. It contains your private API key.
The React frontend does…
The repo has the React + Vite frontend, the FastAPI backend, and a .env.example with setup instructions.
📧 Contact: chanveersinghdev@gmail.com
How I Built It
Student (question / doubt)
│
▼
React + Vite (UI)
│
▼
FastAPI backend
│
▼
Context / prompt engine
│
▼
Ollama Cloud ─► gpt-oss:120b
│
▼
Answer + adaptive actions
Tech stack
| Part | Tool |
|---|---|
| Frontend | React + Vite |
| Backend | FastAPI |
| AI | gpt-oss:120b (open-weight) via Ollama Cloud |
| Storage | SQL database for user data |
| Built with | Claude Code |
Learning phases
StudyMate is designed around how people actually learn:
Discover → Understand → Practice → Revise → Exam prep
The prompt engine detects the question type and phase, then chooses which actions to show.
Why open-weight AI is the core
The AI is an open-weight model (gpt-oss:120b) running through Ollama Cloud, not a closed proprietary API. The learning logic is separated from the provider and model:
StudyMate learning logic → AI provider → Model
The model is set in .env, so I can switch models or providers, or move to local inference later, without rewriting the product. That means less vendor lock-in and more control over the AI layer.
Security
The Ollama API key stays on the FastAPI backend (.env). The browser never sees it, and only .env.example is committed to GitHub.
Honest about PYQs
StudyMate never calls AI-generated questions "PYQs." They are labelled Practice question. Real previous-year questions will come from a verified database (year + exam + subject + chapter), so students can trust what they study.
UI
I designed the interface like a real product: dark theme, rounded chat and composer, contextual action buttons, hover animations, chat history, and a responsive layout.
Challenges
- Adaptive actions: making the options change correctly by question type (concept vs numerical vs revision) instead of showing the same buttons every time.
- Keeping the key safe: routing every AI call through the backend so the Ollama key never reaches the browser.
- Academic trust: separating AI-generated practice questions from real PYQs so the app never misleads a student.
- Model independence: keeping the learning logic separate from the model so changing models doesn't mean a rewrite.
What's Next
- PDF and notes upload with RAG, so students can ask questions about their own material
- Verified PYQ database and NCERT integration, with chapter-wise and exam filters
- Quiz engine, flashcards, progress tracking, and weak-topic detection
- Web sources and book/resource recommendations
- Streaming responses, image-based question solving, and a personalized learning profile
Final Thoughts
The biggest lesson was that a good study tool shouldn't stop at the answer. Knowing what to do next is what turns an answer into learning. StudyMate is the foundation for that, and I want to keep building it with my friend's feedback.
Top comments (1)
🚀 StudyMate is live!
I built StudyMate for a real student problem: getting an answer isn't always enough — you also need to know what to do next.
StudyMate uses Ollama Cloud + GPT-OSS + FastAPI + React to provide contextual actions like explanations, hints, quizzes, revision, and practice.
🔓 GitHub: github.com/chanveersinghdev/Studymate
🎥 Demo: youtu.be/Cn-L-TjlGUA
Would love to hear what you think and what feature I should build next!
Hacktoberfest #BuildForAFriend #OpenSource #AI #Ollama #React #Python