DeepTutor

The Panel's Take

DeepTutor is an open-source AI tutoring platform from HKUDS that just shipped v1.0.3. Unlike ChatGPT wrappers dressed up as learning tools, DeepTutor is architected around a genuine agent-native philosophy: "not chatbots — autonomous tutors." The system runs five integrated modes within a single continuous thread — Chat (with RAG and web search), Deep Solve (multi-agent problem solving with source citations), Quiz Generation, Deep Research (parallel agents with cited reports), and Math Animator (Manim-powered visual explanations of mathematical concepts). Context flows between modes, so a question in Chat can escalate to Deep Solve without losing thread history. The standout feature is TutorBots — persistent AI tutors that maintain their own memory, personality, and skill sets across sessions. Combined with a RAG-ready knowledge base where you can upload your own PDFs and notes, DeepTutor effectively becomes a personalized learning environment that evolves with you. A Co-Writer feature turns any document into a collaborative editing session with AI as a genuine co-author. An Agent-Native CLI exposes every capability as structured JSON for autonomous agent pipelines, complete with a SKILL.md spec. The platform supports 25+ LLM providers including OpenAI, Anthropic, DeepSeek, Groq, and local models via Ollama or llama.cpp. It ships under Apache 2.0, installs via Docker, and launched v1.0.3 on April 13, 2026 with question notebooks and Mermaid diagram support. For students, researchers, or anyone building on top of a learning platform, this is the most architecturally serious open alternative to closed tutoring products.

DeepTutor verdict: SHIP 🚀

3 ships · 1 skip from the expert panel

Full review: shiporskip.io/tool/deeptutor-hkuds-agent-native-personalized-learning-five-modes-math-animator-2026

Compare DeepTutor with Others

Looking for DeepTutor alternatives?

Compare DeepTutor with every other Education tool reviewed by our panel.

Builder

Ship

“The Agent-Native CLI with SKILL.md spec is what separates DeepTutor from every other 'AI learning' product. You can actually pipe its capabilities into larger agent workflows, not just use it as a chat UI. FastAPI backend, Next.js 16 frontend, Docker deployment, 25+ LLM providers — this is built by people who've thought about production systems, not just demos.”

Skeptic

Skip

“The technical paper is 'coming soon' — so the pedagogical claims about learning outcomes are completely unvalidated. Running 25+ integrations with a FastAPI backend requires real infrastructure to keep stable. TutorBot 'personality persistence' sounds compelling but in practice these systems tend to drift or feel inconsistent over time. v1.0.3 just launched today; I'd wait a few months for the rough edges to smooth out.”

Futurist

Ship

“The persistent, memory-bearing TutorBot model is an early prototype of what personalized education will look like at scale — a tutor that genuinely knows you, evolves with you, and can meet you anywhere across modalities. The math visualization capability hints at a future where abstract concepts are always accompanied by dynamic, personalized visual proofs generated on demand.”

Creator

Ship

“The Guided Learning mode that converts personal materials into visual multi-step learning journeys is genuinely exciting for content creators who want to build courses without painful authoring tools. The Co-Writer with AI as a first-class collaborator in a Markdown editor is a cleaner experience than most writing AI tools I've tried.”