DeepTutor and TutorAI
Both are RAG-based tutoring systems that complement each other by targeting different implementation approaches—DeepTutor emphasizes personalized AI-driven instruction while TutorAI focuses on curriculum-grounded retrieval with explicit source citation—making them interoperable choices depending on whether priority is given to adaptive learning or transparent, textbook-anchored responses.
About DeepTutor
HKUDS/DeepTutor
"DeepTutor: AI-Powered Personalized Learning Assistant"
Implements a dual-loop multi-agent architecture combining RAG, web search, and code execution for problem-solving with cited sources. Built on FastAPI (backend) and Next.js/React (frontend), it supports pluggable LLM and embedding providers with a unified prompt management system. Core modules handle document ingestion with Docling support, interactive visualization with session-based tracking, exam-style question generation, and cross-domain knowledge synthesis through deep research workflows.
About TutorAI
CogitoNTNU/TutorAI
TutorAI is a RAG system capable of assisting with learning academic subjects and using the curriculum and citing it. The project revolves around building an application that ingests a textbook in most formats and facilitates efficient learning of the course material.
Builds a full-stack learning platform with Django backend and Node.js frontend, leveraging OpenAI's language models integrated with MongoDB for persistent storage of processed documents and user progress. Beyond RAG retrieval, it generates adaptive learning plans, auto-grades quizzes, creates exportable flashcards (Anki/Quizlet compatible), and tracks study streaks—transforming raw textbooks into structured, gamified learning experiences. Containerized deployment via Docker Compose enables quick local setup while supporting multiple document formats through multimodal processing.
Related comparisons
Scores updated daily from GitHub, PyPI, and npm data. How scores work