hkuds/deeptutor is an agent-native learning workspace that unifies tutoring, problem solving, quiz generation, research, and visualization tasks in a single runtime. It provides a command-line interface and a multi-engine retrieval system that processes user documents and queries while allowing local or cloud-based language models.
Project overview
The project consolidates multiple isolated learning and research workflows into a single agent loop, reducing the need to switch between standalone tools and lose context.
Project type
AI Agent · Learning Resources
Use cases
Search & Research · Learning & Education
Deployment
Refer to project documentation
License
Apache-2.0
Best for
General users and educators who need a single command-line driven workspace to unify tutoring, problem solving, quiz generation, research, and document visualization tasks.
Key capabilities
Provides a single runtime where Chat, Quiz, Research, Visualize, Solve, and Mastery Path operate on the same agent loop.
Provides versioned retrieval libraries that work across LlamaIndex, PageIndex, GraphRAG, LightRAG, or a linked Obsidian vault.
Provides a 'deeptutor' binary featuring an interactive REPL and structured JSON output designed for consumption by other agents.
Provides L1 traces, L2 surface summaries, and L3 synthesis alongside a Memory Graph to trace generated claims back to source evidence.
Provides built-in skills for docx, pdf, pptx, and xlsx files that execute model-generated code to produce documents and spreadsheets.
Limitations and risks
Telemetry practices and data collection policies are not documented in the available facts.
Minimum hardware requirements and GPU necessities are not documented.
Getting started
Setup is rated easy due to pre-built PyPI and Docker installation paths. Users can initialize the system by creating a directory, running 'pip install -U deeptutor', executing 'deeptutor init', and starting it with 'deeptutor start'.
Alternatives and comparisons
A suite of Claude Code skills for a human-in-the-loop academic research pipeline handling reference hunting and citation formatting.
An interactive application for chatting with books, exploring topics, and discussing ideas with agent-simulated thinkers.
README: DeepTutor is an agent-native learning workspace that connects tutoring, problem solving, quiz generation, research, visualization, and mastery practice in one extensible system.
README: 2026-04-19 🎉 20k stars in 111 days! Thank you for the support toward truly personalized, intelligent tutoring.
README: GA cut of v1.4: Auto Mode, three-layer Memory, agentic Deep Research / Solve / Question, LlamaIndex RAG refactor, Visualize/Animator merge, and restart-safe turn runtime.
README: One `deeptutor` binary, two ways in: an interactive **REPL** for people who live in the terminal, and structured **JSON** for other agents that drive DeepTutor as a tool.