DeepTutor
DeepTutor: Lifelong Personalized Tutoring. https://deeptutor.info/.
What is DeepTutor?
DeepTutor: Lifelong Personalized Tutoring. https://deeptutor.info/.
Overview of DeepTutor
What it is
DeepTutor is an open-source project for lifelong personalized tutoring, published in the HKUDS/DeepTutor repository. The README describes a learning environment built around learning workspaces, knowledge bases, generated books, video lessons, and practice activities, and its release notes document a continuous series of versions from v1.5.x through v1.7.1. The project metadata also references an arXiv paper about the work.
Key features
- Folder-based learning workspaces that organize study material, chats, and activity in one place.
- Knowledge bases built from documents, with selectable parsing engines (for example MinerU, Apache Tika, LiteParse, and self-hosted PageIndex OSS) and retrieval options that include LightRAG and GraphRAG indexing.
- Book generation and reading, including EPUB reading with annotations, streaming compilation, progress tracking, and Markdown export.
- Practice and assessment tools: question banks, quizzes, daily practice, grouped assessments, and Mastery Path modes that gate the tutor's tools.
- Tutoring chat with bounded memory, traceable citations, immersive reading of a document beside the thread, and narrated video lessons.
- Per-account MCP services and CLI apps the tutor can run, plus plugins for third-party tools and capabilities.
- Exports to Anki and calendar, and interfaces localized into several languages, including German, French, Ukrainian, and Polish.
Use cases
- Learners who study documents and books with a tutor that cites pages and sources.
- Users assembling personal knowledge bases from PDFs, EPUBs, Office files, and web sources.
- Practicing with question banks and assessments tied to a learning path.
- Developers extending the system through plugins, MCP servers, and additional model and search providers.
Getting started
The README excerpt provided here does not include installation or quick-start commands. See the repository README for setup instructions.
License and pricing
Licensed under Apache-2.0. The project is open source; no pricing is stated.
Based on the project's public README and repository metadata.