### DeepTutor First-Time Setup

Source: https://github.com/hkuds/deeptutor/blob/main/SKILL.md

Installs DeepTutor and initiates an interactive guided setup process.

```bash
cd DeepTutor
pip install -e .
deeptutor init    # Interactive guided setup
```

--------------------------------

### Install DeepTutor from Source

Source: https://github.com/hkuds/deeptutor/blob/main/site/src/content/docs/docs/get-started/from-source.md

Clone the repository, set up a Python virtual environment, install backend and frontend dependencies, and initialize and start the application.

```bash
git clone https://github.com/HKUDS/DeepTutor.git
cd DeepTutor

# Create a venv (macOS / Linux)
# Windows PowerShell:
#   py -3.11 -m venv .venv ; .\.venv\Scripts\Activate.ps1
python3 -m venv .venv && source .venv/bin/activate
python -m pip install --upgrade pip

# Install backend + frontend deps
python -m pip install -e .
( cd web && npm ci --legacy-peer-deps )

deeptutor init
deeptutor start
```

--------------------------------

### Initialize deeptutor setup

Source: https://github.com/hkuds/deeptutor/blob/main/site/src/content/docs/docs/cli/commands.md

Use `deeptutor init` for guided setup. Options allow for full setup, CLI-only setup, or specifying a custom home directory.

```bash
deeptutor init                # Full setup (asks ports + LLM + embedding + search)
```

```bash
deeptutor init --cli          # CLI-only (skips port questions)
```

```bash
deeptutor init --home /path   # Use a non-default workspace
```

--------------------------------

### Python: Start Tour Script

Source: https://github.com/hkuds/deeptutor/blob/main/assets/releases/ver1-2-4.md

This Python script initiates a 7-step fresh-install tour for DeepTutor. It handles environment detection, dependency installation for both backend and frontend, and guides the user through provider configuration.

```python
import scripts.start_tour

scripts.start_tour.run()
```

--------------------------------

### Install and Initialize DeepTutor

Source: https://github.com/hkuds/deeptutor/blob/main/site/src/content/docs/docs/get-started/pypi.md

Install the deeptutor package using pip, initialize its configuration, and start the application. The application requires Python 3.11+ and Node.js 20+.

```bash
mkdir -p my-deeptutor && cd my-deeptutor
pip install -U deeptutor
deeptutor init     # prompts for ports + LLM provider + optional embedding
deeptutor start    # starts backend + frontend; keep the terminal open
```

--------------------------------

### Install TutorBot Python Extras

Source: https://github.com/hkuds/deeptutor/blob/main/site/src/content/docs/docs/tutorbot/index.md

Commands to install the TutorBot extra for a full server or CLI-only installation. Also shows installation from PyPI.

```bash
# Full server + TutorBot
pip install -e ".[tutorbot]"

# CLI-only + TutorBot
pip install -e "./packaging/deeptutor-cli[tutorbot]"

# From PyPI (already includes tutorbot)
pip install deeptutor
```

--------------------------------

### Install Dependencies

Source: https://github.com/hkuds/deeptutor/blob/main/site/README.md

Installs all the necessary dependencies for your project.

```bash
npm install
```

--------------------------------

### New Contributors Example

Source: https://github.com/hkuds/deeptutor/blob/main/assets/releases/ver0-3-0.md

Example of listing new contributors and their first contributions in the release notes.

```git
* @oshliaer made their first contribution in https://github.com/HKUDS/DeepTutor/pull/27
* @LouisACR made their first contribution in https://github.com/HKUDS/DeepTutor/pull/28
* @ahmedjawedaj made their first contribution in https://github.com/HKUDS/DeepTutor/pull/34
```

--------------------------------

### Start WhatsApp Bridge

Source: https://github.com/hkuds/deeptutor/blob/main/site/src/content/docs/docs/tutorbot/whatsapp.md

Commands to navigate to the bridge directory, install dependencies, and run the Node.js bridge script.

```bash
cd multi-user/whatsapp-bridge
npm install
node bridge.js
```

--------------------------------

### Install TutorBot SDKs

Source: https://github.com/hkuds/deeptutor/blob/main/site/src/content/docs/docs/get-started/troubleshooting.md

Install the necessary Python packages for TutorBot integration. This command installs the generic TutorBot SDK, or specific ones for platforms like Telegram, Slack, Zulip, and Matrix.

```bash
# Generic
pip install -e ".[tutorbot]"

# Or one specific (rarely needed)
pip install python-telegram-bot   # Telegram
pip install slack-sdk              # Slack
pip install zulip                  # Zulip
pip install matrix-nio             # Matrix (no E2EE)
```

--------------------------------

### DeepTutor System and Configuration Commands

Source: https://github.com/hkuds/deeptutor/blob/main/SKILL.md

Commands for viewing configuration, listing plugins, getting plugin details, logging into providers, and starting the DeepTutor API server.

```bash
deeptutor config show                          # Print current configuration
deeptutor plugin list                          # List registered tools and capabilities
deeptutor plugin info <name>                   # Show tool/capability details
deeptutor provider login <provider>            # OAuth login (openai-codex, github-copilot)
deeptutor serve [--port 8001] [--reload]       # Start API server
```

--------------------------------

### Start Local Development Server

Source: https://github.com/hkuds/deeptutor/blob/main/site/README.md

Starts a local development server, typically accessible at `localhost:4321`.

```bash
npm run dev
```

--------------------------------

### Installing Pre-commit

Source: https://github.com/hkuds/deeptutor/blob/main/CONTRIBUTING.md

Install the pre-commit tool for managing Git hooks.

```bash
pip install pre-commit
# Or: conda install -c conda-forge pre-commit
```

--------------------------------

### Summarize Configuration Example

Source: https://github.com/hkuds/deeptutor/blob/main/deeptutor/tutorbot/skills/summarize/SKILL.md

Shows an example of a local configuration file for the summarize CLI. This file can be used to set default options, such as the AI model to use.

```json
{
  "model": "openai/gpt-5.2"
}
```

--------------------------------

### Install All DeepTutor Features

Source: https://github.com/hkuds/deeptutor/blob/main/AGENTS.md

Installs the complete DeepTutor application with all available features and addons. This is the most comprehensive installation option.

```bash
pip install deeptutor.[all]
```

--------------------------------

### Install Full Server Runtime

Source: https://github.com/hkuds/deeptutor/blob/main/requirements.txt

This command installs the complete server runtime, including the CLI, API, and TutorBot. It recursively includes dependencies from requirements/tutorbot.txt. Requires Python 3.11 or higher.

```bash
-r requirements/tutorbot.txt
```

--------------------------------

### Development Setup and Pre-commit Hooks

Source: https://github.com/hkuds/deeptutor/blob/main/site/src/content/docs/docs/contributing.md

This snippet details the steps to set up a local development environment for DeepTutor, including forking, cloning, installing dependencies, and configuring pre-commit hooks for code quality checks. Ensure you sync with the 'dev' branch before branching.

```bash
git checkout dev && git pull origin dev

git checkout -b feature/your-feature-name

pip install -e ".[all]"

pip install pre-commit
pre-commit install

pre-commit run --all-files

```

--------------------------------

### Start a Bot

Source: https://github.com/hkuds/deeptutor/blob/main/README.md

Initiate a previously created TutorBot instance.

```bash
deeptutor bot start <id>
```

--------------------------------

### Installing Git Hooks

Source: https://github.com/hkuds/deeptutor/blob/main/CONTRIBUTING.md

Install the pre-commit Git hooks into your local repository.

```bash
pre-commit install
```

--------------------------------

### Install DeepTutor CLI

Source: https://github.com/hkuds/deeptutor/blob/main/site/src/content/docs/docs/get-started/cli-only.md

Clone the repository, set up a virtual environment, and install the CLI-only package. This is the primary installation method for CLI-only usage.

```bash
git clone https://github.com/HKUDS/DeepTutor.git
cd DeepTutor

# Create a venv (macOS / Linux)
# Windows PowerShell:
#   py -3.11 -m venv .venv-cli ; .\.venv-cli\Scripts\Activate.ps1
python3 -m venv .venv-cli && source .venv-cli/bin/activate
python -m pip install --upgrade pip

python -m pip install -e ./packaging/deeptutor-cli
deeptutor init --cli
deeptutor chat
```

--------------------------------

### Install DeepTutor for Development

Source: https://github.com/hkuds/deeptutor/blob/main/AGENTS.md

Installs the full DeepTutor application along with tools for testing and linting. This is recommended for developers contributing to the project.

```bash
pip install deeptutor.[dev]
```

--------------------------------

### Installing Project Dependencies

Source: https://github.com/hkuds/deeptutor/blob/main/CONTRIBUTING.md

Install the project's dependencies, including optional extras, in editable mode.

```bash
pip install -e ".[all]"
```

--------------------------------

### Start deeptutor Server

Source: https://github.com/hkuds/deeptutor/blob/main/site/src/content/docs/docs/cli/server-api.md

Starts the deeptutor server. You can specify custom host and port, or enable hot reloading for development.

```bash
deeptutor serve
```

```bash
deeptutor serve --host 127.0.0.1 --port 18001
```

```bash
deeptutor serve --reload
```

--------------------------------

### Install TutorBot Extras

Source: https://github.com/hkuds/deeptutor/blob/main/site/src/content/docs/docs/get-started/cli-only.md

Install the necessary extras for TutorBot functionality within the CLI-only environment. This includes channel SDKs for integrations.

```bash
pip install -e "./packaging/deeptutor-cli[tutorbot]"
```

--------------------------------

### Create and Start a New Bot

Source: https://github.com/hkuds/deeptutor/blob/main/README.md

Instantiate and launch a new TutorBot, with options for name, persona, and model.

```bash
deeptutor bot create <id>
```

--------------------------------

### Install Frontend Dependencies

Source: https://github.com/hkuds/deeptutor/blob/main/site/src/content/docs/docs/get-started/from-source.md

Install or update frontend dependencies after adding or upgrading them. Ensure to commit both package.json and package-lock.json.

```bash
cd web
npm install --legacy-peer-deps
# commit both web/package.json and web/package-lock.json
```

--------------------------------

### Install a Skill

Source: https://github.com/hkuds/deeptutor/blob/main/deeptutor/tutorbot/skills/clawhub/SKILL.md

Installs a skill from ClawHub into your nanobot workspace. Replace `<slug>` with the skill's identifier obtained from search results. Always include `--workdir` to ensure skills are installed in the correct location.

```bash
npx --yes clawhub@latest install <slug> --workdir ~/.nanobot/workspace
```

--------------------------------

### Install Full DeepTutor Application

Source: https://github.com/hkuds/deeptutor/blob/main/AGENTS.md

Installs the complete DeepTutor application, including the CLI, Web/API, and packaged Web assets. Use this for a full-featured experience.

```bash
pip install deeptutor
```

--------------------------------

### Install All DeepTutor Features

Source: https://github.com/hkuds/deeptutor/blob/main/requirements.txt

Install all available features and components of DeepTutor from a source checkout. Requires Python 3.11 or higher.

```bash
pip install -e ".[all]"
```

--------------------------------

### Session JSON Output Example

Source: https://github.com/hkuds/deeptutor/blob/main/site/src/content/docs/docs/cli/commands.md

Example of the full JSON output for a session, showing its metadata, messages, and preferences.

```json
{
  "id": "sess_abc123",
  "title": "Chain rule explanation",
  "capability": "chat",
  "status": "completed",
  "messages": [
    {"role": "user", "content": "..."},
    {"role": "assistant", "content": "..."}
  ],
  "preferences": {
    "tools": ["rag", "reason"],
    "knowledge_bases": ["math"],
    "language": "en"
  },
  "created_at": "2026-05-21T14:23:01Z",
  "updated_at": "2026-05-21T14:24:38Z"
}
```

--------------------------------

### Start DeepTutor API Server

Source: https://github.com/hkuds/deeptutor/blob/main/README.md

Initiate the DeepTutor API server for external access.

```bash
deeptutor serve
```

--------------------------------

### Install DeepTutor with TutorBot Agent

Source: https://github.com/hkuds/deeptutor/blob/main/requirements.txt

Install DeepTutor with the TutorBot agent engine from a source checkout. Requires Python 3.11 or higher.

```bash
pip install -e ".[tutorbot]"
```

--------------------------------

### Install Full DeepTutor with TutorBot Engine

Source: https://github.com/hkuds/deeptutor/blob/main/AGENTS.md

Installs the full DeepTutor application along with the TutorBot agent engine and channel SDKs. Use this to enable advanced agent functionalities.

```bash
pip install deeptutor.[tutorbot]
```

--------------------------------

### Install Matrix Dependencies

Source: https://github.com/hkuds/deeptutor/blob/main/site/src/content/docs/docs/tutorbot/matrix.md

Install the necessary Python extras for Matrix support. Use '.[matrix]' for base support or '.[matrix-e2e]' for end-to-end encryption, which also requires libolm.

```bash
pip install -e ".[matrix]"
```

```bash
pip install -e ".[matrix-e2e]"
```

```bash
pip install -e ".[tutorbot]"
```

--------------------------------

### Start DeepTutor Chat

Source: https://github.com/hkuds/deeptutor/blob/main/README.md

Launches the interactive chat REPL for DeepTutor.

```bash
deeptutor chat
```

--------------------------------

### Install, Configure, and Use DeepTutor CLI

Source: https://github.com/hkuds/deeptutor/blob/main/site/src/content/docs/docs/cli/index.md

Basic commands to install, configure, and interact with the DeepTutor CLI for various tasks like chat, knowledge base management, and running bots.

```bash
# Install (one of the paths from Get Started)
pip install deeptutor

# Configure
deeptutor init

# Interactive chat
deeptutor chat

# Single-turn, agent-style
deeptutor run deep_solve "Find the derivative of sin(x²)" --tool reason --format json

# Manage knowledge bases
deeptutor kb create physics --doc chapter1.pdf
deeptutor kb search physics "What is angular momentum?"

# Run a TutorBot
deeptutor bot create my-bot --persona "Socratic math tutor"

# Inspect three-layer memory
deeptutor memory show L3
```

--------------------------------

### Manage DeepTutor TutorBot Instances

Source: https://github.com/hkuds/deeptutor/blob/main/SKILL.md

Commands for listing, creating, starting, and stopping TutorBot instances.

```bash
deeptutor bot list                             # List all TutorBot instances
deeptutor bot create <id> --name "My Tutor"    # Create and start a new bot
deeptutor bot start <id>                       # Start a bot
deeptutor bot stop <id>                        # Stop a bot
```

--------------------------------

### Start TutorBot Bot

Source: https://github.com/hkuds/deeptutor/blob/main/site/src/content/docs/docs/tutorbot/dingtalk.md

Initiate the TutorBot with a specific tutor name. This command starts the bot and connects it to configured channels, including DingTalk in stream mode.

```bash
deeptutor bot start my-math-tutor
```

--------------------------------

### Install Optional DeepTutor Extras

Source: https://github.com/hkuds/deeptutor/blob/main/README.md

Install additional dependency groups for specific features like testing tools (`dev`), TutorBot engine (`tutorbot`), Matrix chat integration (`matrix`, `matrix-e2e`), or math animations (`math-animator`).

```bash
pip install -e ".[dev]"             # tests/lint tools
```

```bash
pip install -e ".[tutorbot]"        # TutorBot engine + channel SDKs
```

```bash
pip install -e ".[matrix]"          # Matrix channel without E2EE/libolm
```

```bash
pip install -e ".[matrix-e2e]"      # Matrix E2EE; requires libolm
```

```bash
pip install -e ".[math-animator]"   # Manim addon; requires LaTeX/ffmpeg/system libs
```

--------------------------------

### Caddy Reverse Proxy Configuration

Source: https://github.com/hkuds/deeptutor/blob/main/site/src/content/docs/docs/get-started/multi-user.md

Example Caddyfile for routing API and main traffic to DeepTutor instances. Ensure this configuration matches your deployment setup.

```caddyfile
deeptutor.example.com {
    reverse_proxy /api/* localhost:8001
    reverse_proxy localhost:3782
}
```

--------------------------------

### Initialize and Search RAGService

Source: https://github.com/hkuds/deeptutor/blob/main/assets/releases/ver0-4-0.md

Demonstrates how to initialize the RAGService with a knowledge base and documents, and then perform a search query. Uses the RAG_PROVIDER environment variable for backend selection.

```python
from deeptutor.services.rag import RAGService

service = RAGService()  # Uses RAG_PROVIDER env var (default: raganything)
await service.initialize("my_kb", ["doc.pdf"])
result = await service.search("query", "my_kb")
```

--------------------------------

### Display Main CLI Help

Source: https://github.com/hkuds/deeptutor/blob/main/site/src/content/docs/docs/cli/index.md

Run this command to see all available top-level commands and their brief descriptions. This is useful for understanding the CLI's capabilities.

```text
$ deeptutor --help

 Usage: deeptutor [OPTIONS] COMMAND [ARGS]...  

 DeepTutor — agent-native, open-source personalized tutoring.  

╭─ Commands ───────────────────────────────────────────────────────────────────╮
│ init          Guided setup wizard.                                            │
│ start         Launch backend + frontend together.                             │
│ serve         Backend only.                                                   │
│ chat          Interactive REPL.                                               │
│ run           One-shot capability turn.                                       │
│ kb            Knowledge base management.                                      │
│ session       Session inspection.                                             │
│ notebook      Notebook records.                                               │
│ memory        Three-layer memory store.                                       │
│ bot           TutorBot lifecycle.                                             │
│ config        View runtime configuration.                                     │
│ plugin        Capability / tool registry.                                     │
│ provider      Provider auth flows.                                            │
│ book          Knowledge Books (Guided Learning).                              │
╰──────────────────────────────────────────────────────────────────────────────╯
```

--------------------------------

### Install DeepTutor CLI

Source: https://github.com/hkuds/deeptutor/blob/main/packaging/deeptutor-cli/README.md

Installs the DeepTutor CLI-only distribution using a virtual environment. Ensure the repository checkout remains after installation for editable installs.

```bash
python3 -m venv .venv-cli
source .venv-cli/bin/activate
python -m pip install --upgrade pip
python -m pip install -e ./packaging/deeptutor-cli
```

--------------------------------

### Install libolm for Matrix E2EE

Source: https://github.com/hkuds/deeptutor/blob/main/site/src/content/docs/docs/get-started/from-source.md

Install the libolm library on macOS or Debian/Ubuntu systems when encountering 'libolm not found' errors after installing the `matrix-e2e` extra. Reinstall the extra after installing the library.

```bash
brew install libolm                   # macOS
sudo apt install libolm-dev           # Debian / Ubuntu
pip install -e ".[matrix-e2e]" --force-reinstall
```

--------------------------------

### Skill Structure Example

Source: https://github.com/hkuds/deeptutor/blob/main/deeptutor/tutorbot/skills/skill-creator/SKILL.md

Illustrates the directory structure for a typical skill, including the required SKILL.md file and optional bundled resources.

```tree
skill-name/
├── SKILL.md (required)
│   ├── YAML frontmatter metadata (required)
│   │   ├── name: (required)
│   │   └── description: (required)
│   └── Markdown instructions (required)
└── Bundled Resources (optional)
    ├── scripts/          - Executable code (Python/Bash/etc.)
    ├── references/       - Documentation intended to be loaded into context as needed
    └── assets/           - Files used in output (templates, icons, fonts, etc.)
```

--------------------------------

### Initialize New Skill with init_skill.py

Source: https://github.com/hkuds/deeptutor/blob/main/deeptutor/tutorbot/skills/skill-creator/SKILL.md

Use this script to generate a new template skill directory. It automatically includes necessary files and structures, streamlining the skill creation process. Specify the skill name, output path, and optionally include resource directories or example files.

```bash
scripts/init_skill.py <skill-name> --path <output-directory> [--resources scripts,references,assets] [--examples]
```

```bash
scripts/init_skill.py my-skill --path ./workspace/skills
```

```bash
scripts/init_skill.py my-skill --path ./workspace/skills --resources scripts,references
```

```bash
scripts/init_skill.py my-skill --path ./workspace/skills --resources scripts --examples
```

--------------------------------

### Install DeepTutor using Conda

Source: https://github.com/hkuds/deeptutor/blob/main/site/src/content/docs/docs/get-started/from-source.md

Alternative installation using Conda for environment management. After creating and activating the Conda environment, proceed with pip and npm installations.

```bash
conda create -n deeptutor python=3.11
conda activate deeptutor
python -m pip install --upgrade pip
# ...then continue with `pip install -e .` and `npm ci`
```

--------------------------------

### Creating a Virtual Environment

Source: https://github.com/hkuds/deeptutor/blob/main/CONTRIBUTING.md

Set up a Python virtual environment to manage project dependencies.

```bash
python -m venv venv
source venv/bin/activate  # On Windows: venv\Scripts\activate
```

--------------------------------

### Create a new notebook

Source: https://github.com/hkuds/deeptutor/blob/main/deeptutor/tutorbot/skills/notebook/SKILL.md

Create a new notebook with a specified name and an optional description. The name is a required argument.

```bash
deeptutor notebook create <name> --description "Description text"
```

--------------------------------

### Clone DeepTutor Repository for CLI Installation

Source: https://github.com/hkuds/deeptutor/blob/main/README.md

Clones the DeepTutor GitHub repository to set up a local development environment for the command-line interface-only installation. This is the first step before creating a virtual environment and installing dependencies.

```bash
git clone https://github.com/HKUDS/DeepTutor.git
cd DeepTutor
```

--------------------------------

### Create a New Book via CLI

Source: https://github.com/hkuds/deeptutor/blob/main/assets/releases/ver1-2-0.md

Initiate the creation of a new book from the command line interface.

```bash
deeptutor book create
```

--------------------------------

### Launch DeepTutor REPL

Source: https://github.com/hkuds/deeptutor/blob/main/site/src/content/docs/docs/cli/chat-repl.md

Opens the interactive REPL. You can pre-attach KBs, enable tools, start in a specific capability, resume a prior session, or pass preferences via flags.

```bash
deeptutor chat
```

```bash
deeptutor chat --kb physics --tool rag --tool reason
```

```bash
deeptutor chat --capability deep_solve
```

```bash
deeptutor chat --session sess_abc123
```

```bash
deeptutor chat --language zh --kb papers --history-ref sess_old_xyz
```

--------------------------------

### Verify wecom-aibot-sdk Installation

Source: https://github.com/hkuds/deeptutor/blob/main/site/src/content/docs/docs/tutorbot/wecom.md

Verify that the wecom-aibot-sdk package has been successfully installed by running a simple Python command.

```bash
python -c "import wecom_aibot_sdk; print('ok')"
```

--------------------------------

### Interactive Chat REPL Example

Source: https://github.com/hkuds/deeptutor/blob/main/site/src/content/docs/docs/cli/index.md

Demonstrates entering the interactive chat REPL with a specified knowledge base. Shows the initial prompt and the format for user input.

```text
$ deeptutor chat --kb physics
┏━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━┓
┃ DeepTutor CLI                                                  ┃
┃ Type a message. /quit /tool /cap /kb /history /show /refs     ┃
┗━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━┛
[dim]session=(new) capability=chat tools=[] kb=[physics] history=[] notebook_refs=[] language=en config={}[/]
You> Explain the chain rule with a worked example
```

--------------------------------

### Install wecom-aibot-sdk

Source: https://github.com/hkuds/deeptutor/blob/main/site/src/content/docs/docs/tutorbot/wecom.md

Install the necessary Python package for WeCom integration. This is a prerequisite for using TutorBot with WeCom.

```bash
pip install wecom-aibot-sdk
```

--------------------------------

### Learning Path Generation from KB

Source: https://github.com/hkuds/deeptutor/blob/main/deeptutor/tutorbot/skills/deep-research/SKILL.md

Create a standard depth learning path for a topic using the knowledge base. Specify the knowledge base with the --kb flag.

```bash
deeptutor run deep_research "Machine learning fundamentals" --format json -l zh --config-json '{"mode":"learning_path","depth":"standard","sources":["kb"]}' --kb ml-textbook
```

--------------------------------

### Install DeepTutor CLI

Source: https://github.com/hkuds/deeptutor/blob/main/README.md

Commands to set up a Python virtual environment and install the DeepTutor CLI in editable mode.

```bash
python3 -m venv .venv-cli && source .venv-cli/bin/activate
python -m pip install --upgrade pip

python -m pip install -e ./packaging/deeptutor-cli
```

--------------------------------

### OpenCode Initialization and Prompt

Source: https://github.com/hkuds/deeptutor/blob/main/site/src/content/docs/docs/cli/agent-handoff.md

OpenCode follows a similar integration pattern. Initialize OpenCode, link the `SKILL.md` file from DeepTutor to your project, and then prompt OpenCode to interact with DeepTutor for tasks like planning study sessions.

```bash
opencode init
ln -s /path/to/DeepTutor/SKILL.md ./SKILL.md
opencode "Plan a study session on quantum mechanics using deeptutor"
```

--------------------------------

### Get Specific Book via API

Source: https://github.com/hkuds/deeptutor/blob/main/assets/releases/ver1-2-0.md

Fetch details for a specific book by its ID using this GET request.

```http
GET /{book_id}
```

--------------------------------

### Launch deeptutor backend and frontend

Source: https://github.com/hkuds/deeptutor/blob/main/site/src/content/docs/docs/cli/commands.md

The `deeptutor start` command launches both the backend and frontend services. It blocks execution until interrupted. `deeptutor serve` can be used for backend-only launches with options for host, port, and hot reloading.

```bash
# Launch both backend + frontend (blocking; Ctrl+C stops both)
deeptutor start
deeptutor start --home /path

# Backend only
deeptutor serve --host 0.0.0.0 --port 8001
deeptutor serve --reload                # Hot reload on file changes (dev only)
```

--------------------------------

### Create Knowledge Base

Source: https://github.com/hkuds/deeptutor/blob/main/README.md

Create a new knowledge base, optionally from documents or a directory.

```bash
deeptutor kb create <name>
```

--------------------------------

### Python: Dependency Installation with uv pip

Source: https://github.com/hkuds/deeptutor/blob/main/assets/releases/ver1-2-4.md

This Python code snippet demonstrates dependency installation using `uv pip`. It ensures packages are installed into the current Python interpreter, especially when running within a virtual environment managed by the tour script.

```python
# Example usage within scripts/start_tour.py
# ...
subprocess.run([
    sys.executable, "-m", "uv", "pip", "install",
    "--python", sys.executable, "-e", "."
])
# ...
```

--------------------------------

### Install libolm for E2EE

Source: https://github.com/hkuds/deeptutor/blob/main/site/src/content/docs/docs/tutorbot/matrix.md

Install the libolm development library on macOS or Debian/Ubuntu systems to enable end-to-end encryption for Matrix.

```bash
# macOS
brew install libolm

# Debian / Ubuntu
sudo apt install libolm-dev
```

--------------------------------

### Create a knowledge base

Source: https://github.com/hkuds/deeptutor/blob/main/deeptutor/tutorbot/skills/knowledge-base/SKILL.md

Create a new knowledge base. You can add a single document using `--doc` or a directory of documents using `--docs-dir` during creation. Creation from large PDFs may take time.

```bash
deeptutor kb create <kb_name> --doc /path/to/file.pdf
```

```bash
deeptutor kb create <kb_name> --docs-dir /path/to/directory/
```

--------------------------------

### Inline Math Rendering Example

Source: https://github.com/hkuds/deeptutor/blob/main/site/src/content/docs/docs/tutorbot/zulip.md

Demonstrates how to format inline mathematical expressions using '$' delimiters for rendering within Zulip.

```text
Inline: $x^2$
```

--------------------------------

### L1 Trace Event Example

Source: https://github.com/hkuds/deeptutor/blob/main/site/src/content/docs/docs/explore/memory.md

An example of a single event recorded in the L1 Workspace mirror, which is an append-only trace of user interactions.

```jsonl
{"id":"evt_001","timestamp":"2026-05-21T14:23:01Z","surface":"chat","kind":"turn","content":"User asked about the chain rule"}
{"id":"evt_002","timestamp":"2026-05-21T14:23:18Z","surface":"chat","kind":"tool_call","content":"rag_search"}
{"id":"evt_003","timestamp":"2026-05-21T14:24:38Z","surface":"chat","kind":"turn_complete","content":"Explained with worked example"}
```

--------------------------------

### Install libolm for Matrix E2EE

Source: https://github.com/hkuds/deeptutor/blob/main/site/src/content/docs/docs/get-started/troubleshooting.md

Install the libolm library, which is required for Matrix End-to-End Encryption. Instructions are provided for macOS and Debian/Ubuntu systems.

```bash
# macOS
brew install libolm

# Debian / Ubuntu
sudo apt install libolm-dev

# Reinstall the matrix-e2e extra
pip install -e ".[matrix-e2e]" --force-reinstall
```

--------------------------------

### Preview Production Build

Source: https://github.com/hkuds/deeptutor/blob/main/site/README.md

Locally previews the production build before deploying.

```bash
npm run preview
```