OpenTutor

The first block-based adaptive learning workspace that runs locally. Upload any material → get AI-generated notes, quizzes, flashcards, and an adaptive tutor. O

What is OpenTutor?

The first block-based adaptive learning workspace that runs locally. Upload any material → get AI-generated notes, quizzes, flashcards, and an adaptive tutor. Open source, self-hosted, 10+ LLM providers.

Overview of OpenTutor

What it is

OpenTutor is a self-hosted, local-first AI learning platform. It is described as the first block-based adaptive learning workspace that runs locally. Users upload course material (PDF, DOCX, PPTX, or connect Canvas LMS) and within 30 seconds receive structured notes, flashcards, quizzes, and an AI tutor — all running on the user's machine. The platform is open source and supports 10+ LLM providers.

Key features

  • Block-based adaptive workspace with 12 composable learning blocks (notes, quiz, flashcards, knowledge graph, study plan, analytics, etc.) that adapts layout based on user behavior - AI tutor with source citations; adapts depth based on behavioral signals (fatigue detection, error patterns, message brevity) and supports Socratic questioning mode - 30-second content ingestion from PDF, DOCX, PPTX, or Canvas LMS; generates structured notes, AI-generated flashcards, and quiz questions with 7 question types (MCQ, short answer, fill-in-blank, true/false, matching, ordering, coding)
  • Adaptive quiz with wrong-answer tracking and diagnostic feedback; difficulty adapts based on performance - Study plan and calendar with task tracking and deadline management - Spaced repetition using FSRS 4.5; tracks forgetting and proactively reminds review - Knowledge graph (LOOM, experimental) and semantic review (LECTOR, experimental) for concept mastery and review prioritization - Support for 10+ LLM providers: Ollama (default, local), OpenAI, Anthropic, DeepSeek, Gemini, Groq, vLLM, LM Studio, OpenRouter, or any OpenAI-compatible endpoint

Use cases

OpenTutor is designed for local single-user learning. It can be used for self-study, course material review, exam preparation, and adaptive tutoring without sending data to the cloud. The platform is currently in public beta targeting macOS and Linux (Windows is community-supported).

Getting started

bash git clone https://github.com/zijinz456/OpenTutor.git && cd OpenTutor cp .env.example .env docker compose up -d --build Open http://localhost:3001. Without Docker, use bash scripts/quickstart.sh or manual setup: bash # Backend cd apps/api python3 -m venv .venv && source .venv/bin/activate pip install -r requirements-core.txt uvicorn main:app --reload --port 8000 # Frontend (separate terminal) cd apps/web && npm install && npm run dev Prerequisites: Python 3.11+, Node.js 20+, Docker (optional).

License and pricing

The project is open source under the MIT license. It is free to use and self-hosted. Pricing type is open source.

Based on the project's public README and repository metadata.

Add this badge to your README

Featured on YunoDB Badge styles & help

Maintain this project? Show that it is featured on YunoDB.

Markdown[![Featured on YunoDB](https://yunodb.com/badge/zijinz456opentutor.svg)](https://yunodb.com/tools/zijinz456opentutor?utm_source=github&utm_medium=badge)
HTML<a href="https://yunodb.com/tools/zijinz456opentutor?utm_source=github&utm_medium=badge"><img src="https://yunodb.com/badge/zijinz456opentutor.svg" alt="Featured on YunoDB" height="20"></a>