qwen-agent-tutorial

layout	default
title	Qwen-Agent Tutorial
nav_order	136
has_children	true
format_version	v2

Qwen-Agent Tutorial: Tool-Enabled Agent Framework with MCP, RAG, and Multi-Modal Workflows

Learn how to use QwenLM/Qwen-Agent to build production-capable agents with function calling, MCP integration, memory/RAG patterns, and benchmark-aware planning workflows.

Why This Track Matters

Qwen-Agent combines practical framework primitives with broad application patterns (tool calling, MCP, code interpreter, and RAG), making it a strong foundation for advanced agent applications.

This track focuses on:

• launching a first Qwen-Agent workflow quickly
• understanding core framework modules and extension points
• integrating MCP and tool-calling patterns safely
• applying benchmark and operational practices for production use

Current Snapshot (auto-updated)

• repository: QwenLM/Qwen-Agent
• stars: about 15.7k
• latest release: v0.0.26 (published 2025-05-29)

Mental Model

flowchart LR
    A[User Request] --> B[Agent orchestration]
    B --> C[LLM and reasoning flow]
    C --> D[Tools MCP RAG code execution]
    D --> E[Memory and context updates]
    E --> F[Structured outputs and apps]

Loading

Chapter Guide

Chapter	Key Question	Outcome
01 - Getting Started	How do I install and run Qwen-Agent quickly?	Working baseline
02 - Framework Architecture and Core Modules	How are agents, models, tools, and context structured?	Strong architecture model
03 - Model Service and Runtime Strategy	How do I choose DashScope vs self-hosted runtime paths?	Better deployment decisions
04 - Tool Calling and MCP Integration	How do I integrate external capabilities safely?	Reliable integration baseline
05 - Memory, RAG, and Long-Context Workflows	How do I support document-heavy and recall-heavy tasks?	Better retrieval strategy
06 - Application Patterns and Safety Boundaries	How do BrowserQwen and code interpreter patterns apply?	App-level design clarity
07 - Benchmarking and DeepPlanning Evaluation	How do I evaluate long-horizon planning quality?	Evaluation discipline
08 - Contribution Workflow and Production Governance	How do teams operate and extend Qwen-Agent responsibly?	Governance runbook

What You Will Learn

• how to build and run Qwen-Agent applications with tool integration
• how to choose model-serving and parser strategies across runtimes
• how to apply MCP/RAG patterns safely and effectively
• how to evaluate and govern Qwen-Agent workflows in production-like settings

Source References

• Qwen-Agent Repository
• Qwen-Agent README
• Qwen-Agent Docs
• Qwen-Agent Guide
• DeepPlanning Benchmark Page

Related Tutorials

• Mini-SWE-Agent Tutorial
• SWE-agent Tutorial
• MCP Servers Tutorial
• LangGraph Tutorial

---

Start with Chapter 1: Getting Started.

Navigation & Backlinks

• Start Here: Chapter 1: Getting Started
• Back to Main Catalog
• Browse A-Z Tutorial Directory
• Search by Intent
• Explore Category Hubs

Full Chapter Map

1. Chapter 1: Getting Started
2. Chapter 2: Framework Architecture and Core Modules
3. Chapter 3: Model Service and Runtime Strategy
4. Chapter 4: Tool Calling and MCP Integration
5. Chapter 5: Memory, RAG, and Long-Context Workflows
6. Chapter 6: Application Patterns and Safety Boundaries
7. Chapter 7: Benchmarking and DeepPlanning Evaluation
8. Chapter 8: Contribution Workflow and Production Governance

Generated by AI Codebase Knowledge Builder