> **[2026.4.8]** [v1.0.0-beta.3](https://github.com/HKUDS/DeepTutor/releases/tag/v1.0.0-beta.3) — Native OpenAI/Anthropic SDK (drop litellm), Windows Math Animator support, robust JSON parsing, and full Chinese i18n.
> **[2026.1.23]** [v0.6.0](https://github.com/HKUDS/DeepTutor/releases/tag/v0.6.0) — Session persistence, incremental document upload, flexible RAG pipeline import, and full Chinese localization.
> **[2026.1.18]** [v0.5.2](https://github.com/HKUDS/DeepTutor/releases/tag/v0.5.2) — Docling support for RAG-Anything, logging system optimization, and bug fixes.
> **[2026.1.15]** [v0.5.0](https://github.com/HKUDS/DeepTutor/releases/tag/v0.5.0) — Unified service configuration, RAG pipeline selection per knowledge base, question generation overhaul, and sidebar customization.
> **[2026.1.9]** [v0.4.0](https://github.com/HKUDS/DeepTutor/releases/tag/v0.4.0) — Multi-provider LLM & embedding support, new home page, RAG module decoupling, and environment variable refactor.
> **[2026.1.5]** [v0.3.0](https://github.com/HKUDS/DeepTutor/releases/tag/v0.3.0) — Unified PromptManager architecture, GitHub Actions CI/CD, and pre-built Docker images on GHCR.
> **[2026.4.4]** Long time no see! ✨ DeepTutor v1.0.0 is finally here — an agent-native evolution featuring a ground-up architecture rewrite, TutorBot, and flexible mode switching under the Apache-2.0 license. A new chapter begins, and our story continues!
> **[2026.2.6]** 🚀 We've reached 10k stars in just 39 days! A huge thank you to our incredible community for the support!
> **[2026.1.1]** Happy New Year! Join our [Discord](https://discord.gg/eRsjPgMU4t), [WeChat](https://github.com/HKUDS/DeepTutor/issues/78), or [Discussions](https://github.com/HKUDS/DeepTutor/discussions) — let's shape the future of DeepTutor together!
> **[2025.12.29]** DeepTutor is officially released!
- **Unified Chat Workspace** — Five modes, one thread. Chat, Deep Solve, Quiz Generation, Deep Research, and Math Animator share the same context — start a conversation, escalate to multi-agent problem solving, generate quizzes, then deep-dive into research, all without losing a single message.
- **Personal TutorBots** — Not chatbots — autonomous tutors. Each TutorBot lives in its own workspace with its own memory, personality, and skill set. They set reminders, learn new abilities, and evolve as you grow. Powered by [nanobot](https://github.com/HKUDS/nanobot).
- **AI Co-Writer** — A Markdown editor where AI is a first-class collaborator. Select text, rewrite, expand, or summarize — drawing from your knowledge base and the web. Every piece feeds back into your learning ecosystem.
- **Guided Learning** — Turn your materials into structured, visual learning journeys. DeepTutor designs multi-step plans, generates interactive pages for each knowledge point, and lets you discuss alongside each step.
- **Knowledge Hub** — Upload PDFs, Markdown, and text files to build RAG-ready knowledge bases. Organize insights across sessions in color-coded notebooks. Your documents don't just sit there — they actively power every conversation.
- **Persistent Memory** — DeepTutor builds a living profile of you: what you've studied, how you learn, and where you're heading. Shared across all features and TutorBots, it gets sharper with every interaction.
- **Agent-Native CLI** — Every capability, knowledge base, session, and TutorBot is one command away. Rich terminal output for humans, structured JSON for AI agents and pipelines. Hand DeepTutor a [`SKILL.md`](SKILL.md) and your agents can operate it autonomously.
You'll also need an **API key** from at least one LLM provider (e.g. [OpenAI](https://platform.openai.com/api-keys), [DeepSeek](https://platform.deepseek.com/), [Anthropic](https://console.anthropic.com/)). The Setup Tour will walk you through entering it.
A **single interactive script** that walks you through everything: dependency installation, environment configuration, live connection testing, and launch. No manual `.env` editing needed.
- **Web mode** (recommended) — Installs all dependencies (pip + npm), spins up a temporary server, and opens the **Settings** page in your browser. A four-step guided tour walks you through LLM, Embedding, and Search provider setup with live connection testing. Once complete, DeepTutor restarts automatically with your configuration.
- **CLI mode** — A fully interactive terminal flow: choose a dependency profile, install dependencies, configure providers, verify connections, and apply — all without leaving the shell.
> **Daily launch** — The tour is only needed once. From now on, start DeepTutor with:
>
> ```bash
> python scripts/start_web.py
> ```
>
> This boots both the backend and frontend in one command and opens the browser automatically. Re-run `start_tour.py` only if you need to reconfigure providers or reinstall dependencies.
Docker wraps the backend and frontend into a single container — no local Python or Node.js required. You only need [Docker Desktop](https://www.docker.com/products/docker-desktop/) (or Docker Engine + Compose on Linux).
Edit `.env` and fill in at least the required fields (same as [Option B](#option-b--manual-local-install) above).
**2a. Pull official image (recommended)**
Official images are published to [GitHub Container Registry](https://github.com/HKUDS/DeepTutor/pkgs/container/deeptutor) on every release, built for `linux/amd64` and `linux/arm64`.
```bash
docker compose -f docker-compose.ghcr.yml up -d
```
To pin a specific version, edit the image tag in `docker-compose.ghcr.yml`:
Five distinct modes coexist in a single workspace, bound by a **unified context management system**. Conversation history, knowledge bases, and references persist across modes — switch between them freely within the same topic, whenever the moment calls for it.
| Mode | What It Does |
|:---|:---|
| **Chat** | Fluid, tool-augmented conversation. Choose from RAG retrieval, web search, code execution, deep reasoning, brainstorming, and paper search — mix and match as needed. |
| **Deep Solve** | Multi-agent problem solving: plan, investigate, solve, and verify — with precise source citations at every step. |
| **Quiz Generation** | Generate assessments grounded in your knowledge base, with built-in validation. |
| **Deep Research** | Decompose a topic into subtopics, dispatch parallel research agents across RAG, web, and academic papers, and produce a fully cited report. |
| **Math Animator** | Turn mathematical concepts into visual animations and storyboards powered by Manim. |
Tools are **decoupled from workflows** — in every mode, you decide which tools to enable, how many to use, or whether to use any at all. The workflow orchestrates the reasoning; the tools are yours to compose.
> Start with a quick chat question, escalate to Deep Solve when it gets hard, generate quiz questions to test yourself, then launch a Deep Research to go deeper — all in one continuous thread.
Co-Writer brings the intelligence of Chat directly into a writing surface. It is a full-featured Markdown editor where AI is a first-class collaborator — not a sidebar, not an afterthought.
Select any text and choose **Rewrite**, **Expand**, or **Shorten** — optionally drawing context from your knowledge base or the web. The editing flow is non-destructive with full undo/redo, and every piece you write can be saved straight to your notebooks, feeding back into your learning ecosystem.
Guided Learning turns your personal materials into structured, multi-step learning journeys. Provide a topic, optionally link notebook records, and DeepTutor will:
1.**Design a learning plan** — Identify 3–5 progressive knowledge points from your materials.
2.**Generate interactive pages** — Each point becomes a rich visual HTML page with explanations, diagrams, and examples.
3.**Enable contextual Q&A** — Chat alongside each step for deeper exploration.
4.**Summarize your progress** — Upon completion, receive a learning summary of everything you've covered.
Sessions are persistent — pause, resume, or revisit any step at any time.
### 📚 Knowledge Management — Your Learning Infrastructure
Knowledge is where you build and manage the document collections that power everything else in DeepTutor.
- **Knowledge Bases** — Upload PDF, TXT, or Markdown files to create searchable, RAG-ready collections. Add documents incrementally as your library grows.
- **Notebooks** — Organize learning records across sessions. Save insights from Chat, Guided Learning, Co-Writer, or Deep Research into categorized, color-coded notebooks.
Your knowledge base is not passive storage — it actively participates in every conversation, every research session, and every learning path you create.
DeepTutor maintains a persistent, evolving understanding of you through two complementary dimensions:
- **Summary** — A running digest of your learning progress: what you've studied, which topics you've explored, and how your understanding has developed.
- **Profile** — Your learner identity: preferences, knowledge level, goals, and communication style — automatically refined through every interaction.
Memory is shared across all features and all your TutorBots. The more you use DeepTutor, the more personalized and effective it becomes.
TutorBot is not a chatbot — it is a **persistent, multi-instance agent** built on [nanobot](https://github.com/HKUDS/nanobot). Each TutorBot runs its own agent loop with independent workspace, memory, and personality. Create a Socratic math tutor, a patient writing coach, and a rigorous research advisor — all running simultaneously, each evolving with you.
- **Soul Templates** — Define your tutor's personality, tone, and teaching philosophy through editable Soul files. Choose from built-in archetypes (Socratic, encouraging, rigorous) or craft your own — the soul shapes every response.
- **Independent Workspace** — Each bot has its own directory with separate memory, sessions, skills, and configuration — fully isolated yet able to access DeepTutor's shared knowledge layer.
- **Proactive Heartbeat** — Bots don't just respond — they initiate. The built-in Heartbeat system enables recurring study check-ins, review reminders, and scheduled tasks. Your tutor shows up even when you don't.
- **Full Tool Access** — Every bot reaches into DeepTutor's complete toolkit: RAG retrieval, code execution, web search, academic paper search, deep reasoning, and brainstorming.
- **Skill Learning** — Teach your bot new abilities by adding skill files to its workspace. As your needs evolve, so does your tutor's capability.
- **Multi-Channel Presence** — Connect bots to Telegram, Discord, Slack, Feishu, WeChat Work, DingTalk, Email, and more. Your tutor meets you wherever you are.
- **Team & Sub-Agents** — Spawn background sub-agents or orchestrate multi-agent teams within a single bot for complex, long-running tasks.
```bash
deeptutor bot create math-tutor --persona "Socratic math teacher who uses probing questions"
DeepTutor is fully CLI-native. Every capability, knowledge base, session, memory, and TutorBot is one command away — no browser required. The CLI serves both humans (with rich terminal rendering) and AI agents (with structured JSON output).
Hand the [`SKILL.md`](SKILL.md) at the project root to any tool-using agent ([nanobot](https://github.com/HKUDS/nanobot), or any LLM with tool access), and it can configure and operate DeepTutor autonomously.
**One-shot execution** — Run any capability directly from the terminal:
```bash
deeptutor run chat "Explain the Fourier transform" -t rag --kb textbook
deeptutor run deep_solve "Prove that √2 is irrational" -t reason
deeptutor run deep_question "Linear algebra" --config num_questions=5
deeptutor run deep_research "Attention mechanisms in transformers"
```
**Interactive REPL** — A persistent chat session with live mode switching:
```bash
deeptutor chat --capability deep_solve --kb my-kb
# Inside the REPL: /cap, /tool, /kb, /history, /notebook, /config to switch on the fly
```
**Knowledge base lifecycle** — Build, query, and manage RAG-ready collections entirely from the terminal:
```bash
deeptutor kb create my-kb --doc textbook.pdf # Create from document
deeptutor kb add my-kb --docs-dir ./papers/ # Add a folder of papers
| `deeptutor run <capability> <message>` | Run any capability in a single turn (`chat`, `deep_solve`, `deep_question`, `deep_research`, `math_animator`) |
