OpenTutor

OpenTutor is a local AI learning workspace for students who want to study their own course materials with a tutor that adjusts to their progress. It targets individual study rather than shared classroom use.

• Course material conversion: Generate notes, flashcards and quiz questions from PDF, DOCX and PPTX files or material from Canvas LMS.
• Source-based tutoring: Ask questions with citations to your material, use Socratic questioning, and get explanations whose depth adapts to signals such as error patterns and fatigue.
• Adaptive practice and review: Take quizzes that adjust difficulty to your performance, get feedback on wrong answers, and review flashcards with FSRS spaced repetition and reminders.
• Study workspace: Arrange notes, practice and planning in blocks, with suggested layout changes based on your activity and a calendar for tasks and deadlines.

OpenTutor is free and open source under the MIT license. It runs on macOS, including Apple Silicon and Intel, and Linux; Windows has community support. Docker is optional. Mobile layouts aren't fully optimized across all views.

Ollama is the default model backend, and local models can keep your study data on your machine without API keys. It also supports LM Studio, vLLM and OpenAI-compatible endpoints. Optional cloud providers include OpenAI, Anthropic, DeepSeek and Gemini; using them sends model requests to the selected service. Local response quality and speed depend on your model runtime and hardware.