HKUDS /
DeepTutor
A self-hosted AI tutor that learns from your documents and tracks your progress
- 42.2k stars
- 1.6k stars since 3 Oct
- Python
- Updated 3 days ago
- Some experience
- Productivity & personal
DeepTutor is a learning workspace built around large language models. You load in documents, books, folders or other sources, and the tutor answers from them, cites where answers came from, and keeps track of your progress across sessions.
It is a Python backend with a Next.js web interface. It builds knowledge bases with retrieval engines such as LightRAG and PageIndex, and connects to many model and search providers. The README also mentions a command-line interface that agents can use, and partners you can reach through chat apps such as Mattermost and WeChat.
The README excerpt is mostly a release log, so the details here come from those notes. There is an arXiv paper, and the project is under active development, with several releases in September 2026.
What it does
Knowledge bases with citations
Upload documents, point it at folders, or sync sources such as GitHub repos and web pages. The tutor retrieves from them and cites its sources.
Immersive reading
Open a document beside the chat and read it with the tutor, with annotations and page-by-page citations. EPUB and Office previews are supported.
Books, quizzes and guided learning
The release notes describe Books generated from your material, Courses, quizzes, daily practice and Mastery Paths that track progress.
Bring your own models and tools
Connect many LLM providers, embedding models and web search services, including OpenAI Codex sign-in. MCP servers and CLI apps give the tutor extra tools.
Accounts and interface languages
Learner and guardian accounts are supported, and the interface is available in several languages, including German, French and Ukrainian.
What you could build
- Turn a textbook or set of lecture PDFs into a knowledge base you can question and get cited answers from.
- Generate quizzes and daily practice from your own study material.
- Read a paper or EPUB alongside a tutor that answers about the exact page.
- Run a private tutoring setup for a family or class using separate learner accounts.
- Connect a tutor to a chat app so you can ask questions away from the browser.
Get started
The README excerpt provided cuts off before its Get Started section, so no commands are listed here. Check the project's docs at deeptutor.info or the Get Started section of the README for install steps, which include Python 3.11 or newer.
Commands are copied from the project's README. Read it on GitHub for the full setup.
More in Productivity & personal
meetily
Desktop app that records, transcribes and summarizes meetings on your own machine
cleanyourtv
Disable ad and telemetry apps on an Android TV over Wi-Fi and add a clean launcher
tolaria
Desktop app for keeping notes as plain markdown files in a git repository
omi
Open-source app and wearable that records your screen and talks, then summarizes them
inbox-zero
Self-hostable AI email assistant that sorts your inbox and drafts replies
FluidVoice
Open-source macOS dictation app that transcribes speech on your Mac
presenton
Self-hosted AI tool that turns a prompt or document into an editable slide deck
clicky
A Mac menu bar AI teacher that sees your screen, talks, and points at things
VoiceInk
Mac dictation app that turns speech into text using models on your device
birdclaw
Local SQLite archive of your Twitter/X history with a web app, CLI and MCP server