# HKUDS/DeepTutor

DeepTutor: Lifelong Personalized Tutoring. https://deeptutor.info/.

Repository: https://github.com/HKUDS/DeepTutor
Canonical: https://ross.abutalabs.com/products/deeptutor
Homepage: http://arxiv.org/abs/2604.26962
Language: Python
License: Apache-2.0
License Family: permissive
Topics: ai-tutor, deepresearch, interactive-learning, large-language-models, multi-agent-systems, rag, ai-agents, clawdbot, cli-tool
Last push: 2026-08-25T18:41:02+00:00

## Health v2 (maintenance only)
Score: 78/100 (v2, computed 2026-09-03T02:39:23.370411+00:00)
- activity 99, release rhythm 87, longevity 17
- inputs: {"age_days": 248, "days_push": 8, "days_rel": 9, "gap_med": 1.0, "n_releases_24m": 71}
- flags: none
- formula: round(0.45*activity + 0.35*rhythm + 0.20*longevity); archived -> min(score, 10)

## Adoption (not part of the score)
Stars 37574, forks 4710 (observed 2026-08-28T04:12:01.449134+00:00)

## What it is
DeepTutor is an open-source agentic AI tutoring framework that combines citation-grounded problem tutoring with difficulty-calibrated question generation, using a hybrid personalization engine that couples static knowledge grounding with dynamic learner memory. It extends to adaptive learning workflows, interactive books, and multi-channel tutoring agents, and ships with the TutorBench evaluation benchmark.

## Use cases
- get personalized tutoring on university coursework with an ai tutor
- generate practice questions calibrated to my skill level
- build a tutoring chatbot that cites sources for its answers
- create adaptive learning materials and interactive textbooks
- track a learner's progress and adapt explanations over time
- benchmark personalized tutoring agents
- run deep research on a topic with guided feedback

## When to choose
- you want an open-source, self-hostable personalized AI tutor grounded in citations
- you need adaptive question generation tied to learner profiles
- you're researching agentic personalization and need a benchmark like TutorBench

## When to avoid
- you need a simple static Q&A bot without learner memory or personalization
- you require a turnkey commercial LMS rather than a research-grade framework
- you can't run LLM-backed Python services or lack API access to backbone models

## Facets
- artifact type: application
- maturity: active
- function: rag, agent-framework, llm-inference, chatbot, cli
- domain: education, large-language-models
- platform: python, cli, cross-platform
- tags: ai-tutor, personalized-learning, multi-agent, deep-research, question-generation, tutorbench, interactive-learning, learner-memory, ai-agents, retrieval-augmented-generation, natural-language-processing, web-server

## Member repositories
- HKUDS/DeepTutor (main) score 78

## Provenance
- Observed fields: from GitHub, fetched 2026-08-28T04:12:01.449134+00:00.
- Health v2: computed from the inputs above; adoption is never an input.
- Inferred fields (summary, facets, guidance): AI-extracted, prompt v1, taxonomy v1, on 2026-08-29T16:25:37.750942+00:00, confidence not recorded.
  - readme: https://github.com/HKUDS/DeepTutor (fetched 2026-08-28T04:12:01.449134+00:00, sha 675dad48cb8e)
  - homepage: http://arxiv.org/abs/2604.26962 (fetched 2026-08-29T07:47:15.791257+00:00, sha f0788dc5c1e5)
  - site_page: https://info.arxiv.org/about/ourmembers.html (fetched 2026-08-29T07:47:15.806207+00:00, sha 47cbc55ff1de)
  - site_page: https://info.arxiv.org/about/donate.html (fetched 2026-08-29T07:47:15.801413+00:00, sha cca9c3a11c56)
  - site_page: https://info.arxiv.org/about (fetched 2026-08-29T07:47:15.808752+00:00, sha a1f16f915a9a)
  - site_page: https://info.arxiv.org/labs/index.html (fetched 2026-08-29T07:47:15.803990+00:00, sha b14a8d05a0ec)
- Data as of 2026-08-30T08:39:29.467469+00:00.