LexiSAT is a mobile-first SAT vocabulary practice app that uses an agentic loop to adapt reading passages to a student’s vocabulary weaknesses. It combines a FastAPI backend, SQLAlchemy + SQLite persistence, and a React/Vite frontend.
- Adaptive vocabulary practice based on failed words and spaced repetition
- Dynamic passage generation for lexical inference practice
- Dashboard with current reading level and mastered words
- Demo mode for showcasing the scaffolding logic
- Frontend: React, Vite
- Backend: FastAPI, SQLAlchemy, SQLite
- LLM layer: local Ollama-compatible fallback with deterministic mock response
cd backend
python -m pip install -r requirements.txt
python -m seed_db
python -m uvicorn main:app --reload --port 8000cd frontend
npm install
npm run dev- backend/: FastAPI app, models, database, seed script, and LLM helper
- frontend/: Vite + React app for the student experience