Content
# Tool List
> ✅ **Systematic Open Source Teaching Project**, guiding you to build a fully functional AI Agent from scratch using Python, covering Prompt, LLM, LangChain, RAG, LangGraph, MCP, and deployment.
[](https://github.com/Annyfee/agent-craft/actions/workflows/ci.yml)
## 📘 Project Overview
If you're learning AI agent development but struggling with "understanding concepts but not knowing how to implement" or "being able to call APIs but not understanding the principles" -
**Agent Craft is the learning path designed for you.**
We start from the basics of LLM calls and guide you step-by-step to build a complete Agent capability stack:
- Let models call external tools (Function Calling)
- Access private knowledge bases for Q&A (RAG)
- Implement stateful, debuggable decision-making processes with LangGraph
- Integrate memory, tools, and retrieval to create a truly usable intelligent agent
All content follows two principles:
- 💻 **Runnable code**: each module is independent, with clear comments, and can be reproduced locally with one click
- 📖 **Understandable principles**: accompanying CSDN blog posts explain design ideas and key mechanisms
> 💡 **We don't reinvent the wheel, but we go beyond just calling frameworks** -
> Instead, we explore how Agents think, make decisions, and take actions using mainstream tools like LangChain and LangGraph.
## 🧭 Module Overview (15 Modules)
> 💡 Each module corresponds to an independent directory (including code, instructions, and examples) and can be run and learned independently.
> 🔥 Updated to 13 Streamlit Quick Start, continuously updated!
| Chapter | Module | Blog | Core Keywords | Difficulty |
|:-----------:|:---------------------------------------------------------------------------------------------------------|:--------------------------------------------------------------------:|:-------------------------------------------------------------|:-----:|
| 🏗️ **Basics** | [01 Agent Introduction & Environment Setup](https://github.com/Annyfee/agent-craft/tree/main/m01_agent_introduction) | [🏠](https://blog.csdn.net/2401_87328929/article/details/153729555) | OpenAI API | ⭐ |
| | [02 LLM Fundamentals](https://github.com/Annyfee/agent-craft/tree/main/m02_llm_fundamentals) | [🏠](https://blog.csdn.net/2401_87328929/article/details/153735431) | LLM API Call · prompt · Context Memory | ⭐ |
| | [03 Function Calling & Tool Calling](https://github.com/Annyfee/agent-craft/tree/main/m03_function_calling_tools) | [🏠](https://blog.csdn.net/2401_87
Connection Info
You Might Also Like
everything-claude-code
Complete Claude Code configuration collection - agents, skills, hooks,...
markitdown
MarkItDown-MCP is a lightweight server for converting URIs to Markdown.
servers
Model Context Protocol Servers
servers
Model Context Protocol Servers
Time
A Model Context Protocol server for time and timezone conversions.
Filesystem
Node.js MCP Server for filesystem operations with dynamic access control.