Generated by Code IQ · v1.0

deer-flow
Knowledge Tutorial

deer-flow is a comprehensive AI agent platform that orchestrates a Lead Agent and specialized Sub-Agents to handle complex, multi-step tasks. It utilizes a secure Sandboxed Environment for safe code execution, a modular Skills System for extending capabilities, and Long-Term Memory to persist user context, all managed through a unified Gateway API and visualized in a rich Frontend Workspace.

7
Chapters
-
Subsystems
∞
Rabbit Holes
▶ Start Reading ⎇ View on GitHub
System Architecture

How the pieces fit

deer-flow is organized as connected concepts and components. Start broad, then drill down chapter by chapter.

⚙️
Frontend Workspace & AI Elements
Frontend Workspace & AI Elements
👥
Lead Agent & Orchestration
Lead Agent & Orchestration
⚙️
Skills & Capabilities System
Skills & Capabilities System
👥
Sub-Agent Execution System
Sub-Agent Execution System
⚙️
Sandboxed Environment
Sandboxed Environment
⚙️
Long-Term Memory Updater
Long-Term Memory Updater
⚙️
Gateway API
Gateway API
deer-flow — bash
➜open tutorial
◆ Scanning numbered chapters
◆ Building navigation and Mermaid diagrams
◆ Generating chapter and subsystem pages
✓ 7 chapter pages built
✓ Theme toggle enabled
➜
Repository Overview

Intro and Architecture Diagram

deer-flow is a comprehensive AI agent platform that orchestrates a Lead Agent and specialized Sub-Agents to handle complex, multi-step tasks. It utilizes a secure Sandboxed Environment for safe code execution, a modular Skills System for extending capabilities, and Long-Term Memory to persist user context, all managed through a unified Gateway API and visualized in a rich Frontend Workspace.

Source Repository: https://github.com/bytedance/deer-flow

flowchart TD A0["Lead Agent & Orchestration"] A1["Sub-Agent Execution System"] A2["Skills & Capabilities System"] A3["Sandboxed Environment"] A4["Long-Term Memory Updater"] A5["Gateway API"] A6["Frontend Workspace & AI Elements"] A0 -->|"Delegates complex tasks"| A1 A0 -->|"Executes code safely in"| A3 A0 -->|"Updates user context"| A4 A2 -->|"Provides executable tools"| A0 A1 -->|"Inherits execution context"| A3 A6 -->|"Streams conversation state"| A0 A6 -->|"Fetches resources and config"| A5 A5 -->|"Exposes configuration of"| A2
Tutorial Chapters

All 7 chapters

Follow sequentially or jump to any topic. Start with Frontend Workspace & AI Elements.

Ch.01 CORE
Frontend Workspace & AI Elements
Welcome to deer-flow! We are about to build an AI system that doesn't just "chat"—it works.
↗
Ch.02 AGENTS
Lead Agent & Orchestration
In Chapter 1: Frontend Workspace & AI Elements, we built the visual dashboard—the "Cockpit" for our application. But a cockpit is useless w…
↗
Ch.03 CORE
Skills & Capabilities System
In Chapter 2: Lead Agent & Orchestration, we built the "Brain" of our system. We created a Lead Agent capable of thinking, planning, and ma…
↗
Ch.04 AGENTS
Sub-Agent Execution System
In Chapter 3: Skills & Capabilities System, we gave our Lead Agent "hands" (Skills) to interact with the world. It can now run SQL queries…
↗
Ch.05 CORE
Sandboxed Environment
In Chapter 4: Sub-Agent Execution System, we built a team of Sub-Agents capable of writing code and executing complex tasks in the backgrou…
↗
Ch.06 CORE
Long-Term Memory Updater
In Chapter 5: Sandboxed Environment, we built a secure laboratory where our Agent can run code without destroying your computer. Our Agent…
↗
Ch.07 CORE
Gateway API
Welcome to the final chapter of the deer-flow tutorial!
↗
About This Project

Generated by Code IQ

This tutorial was automatically generated by Code IQ and rendered with the shared tutorial site builder. It can be produced for any repository tutorial folder that follows the numbered markdown chapter layout.

View Code IQ ↗
python build_site.py '/home/runner/work/Code-IQ/Code-IQ/output/deer-flow'

// → 7 chapters
// → source: bytedance/deer-flow