LibreAI / Produtividade / DeepTutor
// productivity · HKUDS/DeepTutor

DeepTutor

DeepTutor é um projeto de produtividade de código aberto de HKUDS (HKUDS/DeepTutor no GitHub). Tem 40.946 estrelas no GitHub e 5.172 forks, é publicado sob a licença Apache-2.0 e foi atualizado pela última vez no GitHub em 8 de outubro de 2026.

DeepTutor: lifelong personalized tutoring with multi-agent RAG, a CLI and an interactive workspace

★ 40,9 mil estrelas⑂ 5,2 mil forksApache-2.0atualizado out 2026
▦ visual: o README deste projeto não inclui nenhuma captura incorporável,
então aqui vai um marcador. O guia abaixo está completo mesmo assim.
// dados do projeto

Dados do projeto

Repositório
HKUDS/DeepTutor
Estrelas no GitHub
40.946
Forks
5.172
Licença
Apache-2.0
Última atualização no GitHub
8 de outubro de 2026
Categoria
Produtividade
Tipo de ficha
Guia de instalação completo
Site oficial
Official site
// como funciona

Como funciona

  1. Clarify your goal

    Decide what you want from DeepTutor and check the README and requirements to confirm it fits your setup and Python environment.

  2. Get the code

    Clone the repository from GitHub (github.com/HKUDS/DeepTutor) or use the documented install channel if you do not need the source.

  3. Install and configure

    Follow the README quickstart to install dependencies and set any required configuration or credentials.

  4. Run your first task

    Work through the README's first example end to end, then adapt it to your own project or data.

// recursos

Por que as pessoas gostam tanto

Personalized tutoring

AI tutoring that adapts to the learner over time, from the HKUDS team.

Multi-agent design

Uses multi-agent systems and RAG for deep research-style learning support.

One-command Docker trial

Try it with a single docker run command publishing the app on port 3782.

Agent-native CLI

A DeepTutor CLI designed for agents, plus a content workspace.

pip install

Also installable with pip: `pip install -U deeptutor`, then `deeptutor init` and `deeptutor start`.

Ecosystem

Connects to an EduHub skills community ecosystem.

Advertisement
// execute você mesmo

Execute você mesmo

  1. Clone the repository

    Start by getting the source and entering the project directory.

    git clone https://github.com/HKUDS/DeepTutor.git
    cd DeepTutor
  2. Try it with Docker

    The one-command trial runs the published image with a persistent data volume.

    docker run --rm --name deeptutor -p 127.0.0.1:3782:3782 -v deeptutor-data:/app/data ghcr.io/hkuds/deeptutor:latest
  3. Or install with pip

    Install, initialize with your LLM provider, and start the app.

    pip install -U deeptutor
    deeptutor init
    deeptutor start
// casos de uso

O que você pode criar

  • Personalized self-study with an AI tutor that tracks progress
  • A tutoring assistant for a course's reading materials
  • Research-style deep dives into a subject with sources
  • Setting up a learning workspace for students
Advertisement
// perguntas frequentes

Perguntas frequentes

Who maintains DeepTutor?

It is maintained by HKUDS and contributors on GitHub, where the repository github.com/HKUDS/DeepTutor is the canonical home for code, issues and releases.

Is DeepTutor free to use?

Yes — it is open source under the Apache-2.0 license. Read the license in the repository for what is permitted, including any conditions on redistribution or commercial use.

Does it need a paid API key?

Yes — setup prompts for an LLM provider, so you need your own provider key or a local model endpoint.

How does DeepTutor compare to alternatives?

Compared with ChatGPT alone: DeepTutor structures tutoring with a workspace, persistent learner context and multi-agent research, rather than one-off chat answers.

How do I get started?

Clone github.com/HKUDS/DeepTutor, follow the README quickstart to install it, and run the documented first example before adapting it to your own work.

// continue explorando

Ferramentas semelhantes

Produtividade

CowAgent

Open-source personal AI assistant & Agent Harness. Plans tasks, runs tools and skills, self-evolves with memory and knowledge. Multi-agent, multi-model, mult…

★ 47,2 mil estrelasMIT
Ver o guia →
Produtividade

lark-cli

Token-efficient CLI designed for Lark/Feishu APIs.

★ 54 estrelasMIT
Ver o guia →
Produtividade

llm-for-zotero

An open-source research agent system that lives inside your Zotero library.

★ 3,2 mil estrelasAGPL-3.0
Ver o guia →
Produtividade

obsidian-second-brain

Persistent memory for Claude Code and other CLI agents, stored as plain Markdown in your Obsidian vault

★ 4,7 mil estrelasMIT
Ver o guia →
Produtividade

WebCode

WebCode is a browser-based AI coding system that lets you remotely run CLI assistants

★ 278 estrelasNOASSERTION
Ver o guia →
// alternativas

Alternativas em Produtividade

Os outros projetos de Produtividade com mais estrelas no catálogo do LibreAI — a lista realista de alternativas se DeepTutor não for o ideal para você.

  • worldmonitor★ 88,1 mil

    Real-time global intelligence dashboard: AI news aggregation, geopolitics and infrastructure tracking

  • Memos★ 63,9 mil

    Memos — a personal timeline for quick notes: capture short memos in seconds, find them later by search, tag or date; open source and self-hosted

  • Joplin★ 56,8 mil

    Joplin — the privacy-focused note-taking app: Markdown notes and to-dos on every platform, offline-first, with end-to-end encrypted sync you control

  • CowAgent★ 47,2 mil

    Open-source personal AI assistant & Agent Harness. Plans tasks, runs tools and skills, self-evolves with memory and knowledge. Multi-agent, multi-model, mult…

  • Logseq★ 45,3 mil

    Logseq — a privacy-first platform for knowledge management: an outliner over your local Markdown files, with a graph, journals and spaced repetition built in

// mais em productivity

Mais em Produtividade

Projetos de Produtividade próximos no catálogo, os mais próximos em estrelas de DeepTutor: continue explorando dos dois lados dele.

  • Logseq★ 45,3 mil

    Logseq — a privacy-first platform for knowledge management: an outliner over your local Markdown files, with a graph, journals and spaced repetition built in

  • Trilium★ 38,4 mil

    Trilium — build your personal knowledge base: a hierarchical notes app with strong encryption, scripting and sync, maintained by the TriliumNext community

  • CowAgent★ 47,2 mil

    Open-source personal AI assistant & Agent Harness. Plans tasks, runs tools and skills, self-evolves with memory and knowledge. Multi-agent, multi-model, mult…

  • prompt-optimizer★ 36,9 mil

    Optimize, test and compare AI prompts — web app, desktop app, Chrome extension and Docker

  • Joplin★ 56,8 mil

    Joplin — the privacy-focused note-taking app: Markdown notes and to-dos on every platform, offline-first, with end-to-end encrypted sync you control

  • meetily★ 31,5 mil

    Privacy-first AI meeting assistant: live transcription and summaries, 100% local on your machine

Baixe o DeepTutor

Grátis e aberto: pegue o código-fonte, dê uma estrela no repositório e comece a criar.