AI Agents From Zero
🚀 2026 最系统的 AI Agent 速成指南｜智能体实战教程 · 完整学习路径 + 实战项目 + 面试题库 · 对标大模型应用开发工程师岗位 · 覆盖LangChain / LangGraph / Coze / Dify / MCP / skills / LLM / RAG / 提示词 · 企业级部署与微调 · 从0到企业级落地 + 从学习到上线项目 + 面试准备一体化
What is AI Agents From Zero?
AI Agents From Zero is a Model Context Protocol (MCP) server that allows AI assistants like Claude, Cursor, and VS Code to 🚀 2026 最系统的 ai agent 速成指南｜智能体实战教程 · 完整学习路径 + 实战项目 + 面试题库 · 对标大模型应用开发工程师岗位 · 覆盖langchain / langgraph / coze / dify / mcp / skills / llm / rag / 提示词 · 企业级部署与微调 · 从0到企业级落地 + 从学习到上线项目 + 面试准备一体化
🚀 2026 最系统的 AI Agent 速成指南｜智能体实战教程 · 完整学习路径 + 实战项目 + 面试题库 · 对标大模型应用开发工程师岗位 · 覆盖LangChain / LangGraph / Coze / Dify / MCP / skills / LLM / RAG / 提示词 · 企业级部署与微调 · 从0到企业级落地 + 从学习到上线项目 + 面试准备一体化
This server falls under the Coding Agents category on MCPgee, the world's largest MCP server directory with 33,000+ servers.
Features
- 🚀 2026 最系统的 AI Agent 速成指南｜智能体实战教程 · 完整学习路径 + 实战项目 + 面试题库 · 对
Use Cases
Maintainer
Works with
Installation
Manual Installation
npx ai-agents-from-zeroConfiguration
Configuration Details
claude_desktop_config.json
Performance
Response Metrics
Resource Usage
How to Set Up and Use AI Agents From Zero
AI Agents From Zero is a comprehensive, open-source educational repository and companion MCP server providing a structured learning path for building production AI agents with Python. It covers the full stack from LangChain and LangGraph fundamentals through advanced topics like RAG, tool calling, MCP integration, multi-agent systems, and enterprise deployment on platforms including Alibaba Cloud and Tencent Cloud. Developers, students, and engineers preparing for AI application development roles use this resource to progress from hello-world LLM calls to complete runnable projects like an NL2SQL query system and a multi-agent research pipeline, supported by an interview question bank aligned with industry job descriptions.
Prerequisites
- Python 3.10 or higher
- Git for cloning the repository
- API keys for at least one LLM provider: Qwen (Alibaba Cloud), DeepSeek, OpenAI, or Anthropic
- An MCP client such as Claude Desktop or Cursor if using the MCP integration modules
- Docker (optional, for enterprise deployment examples)
Clone the repository
Clone the ai-agents-from-zero repository to your local machine to access all example code, projects, and learning materials.
git clone https://github.com/didilili/ai-agents-from-zero.git
cd ai-agents-from-zeroCreate a Python virtual environment
Set up an isolated Python 3.10 environment to avoid dependency conflicts with other projects.
python3.10 -m venv .venv
source .venv/bin/activate # macOS/Linux
# .venv\Scripts\activate # WindowsInstall dependencies
Install all required Python packages from the requirements file.
pip install -r requirements.txtConfigure your API keys
Copy the example environment file and add your LLM provider API keys. The examples support Qwen, DeepSeek, OpenAI, and others.
cp .env-example .env
# Edit .env and add your keys:
# QWEN_API_KEY=your-qwen-key
# DEEPSEEK_API_KEY=your-deepseek-key
# OPENAI_API_KEY=your-openai-keyRun your first example
Start with the LangChain hello-world example to verify your environment and API keys are working correctly.
python "案例与源码-2-LangChain框架/01-helloworld/StandardDesc.py"Explore the complete projects
Once the basics work, explore the two complete runnable projects: the NL2SQL query system (which converts natural language questions to SQL) and the multi-agent research system for automated topic research.
AI Agents From Zero Examples
Client configuration
Claude Desktop MCP configuration for using the AI Agents From Zero MCP integration modules.
{
"mcpServers": {
"ai-agents-from-zero": {
"command": "npx",
"args": ["ai-agents-from-zero"],
"env": {
"OPENAI_API_KEY": "sk-your-openai-key",
"DEEPSEEK_API_KEY": "your-deepseek-key"
}
}
}
}Prompts to try
Example prompts and learning exercises from the repository's curriculum.
- "Explain how LangChain's LCEL (LangChain Expression Language) differs from the legacy chain API."
- "Show me how to build a RAG pipeline with LangGraph that retrieves from a Chroma vector store."
- "Walk me through implementing tool calling in LangChain so an agent can search the web."
- "How do I set up a multi-agent system in LangGraph where a supervisor delegates to specialist agents?"
- "What MCP tools can I build in Python that integrate with Claude Desktop?"Troubleshooting AI Agents From Zero
ModuleNotFoundError for LangChain or LangGraph after pip install
Ensure you are inside the activated virtual environment ('source .venv/bin/activate' on macOS/Linux). The requirements.txt pins specific versions; if you see conflicts, try 'pip install -r requirements.txt --force-reinstall'.
API key errors when running examples
Verify your .env file is in the project root directory and that you copied from .env-example correctly. Each provider uses a different variable name — check the example script's imports to see which key it reads. Some examples target Qwen (QWEN_API_KEY) rather than OpenAI.
Chinese file paths cause errors on Windows
The repository contains Chinese characters in directory and file names. On Windows, run 'chcp 65001' in your terminal to switch to UTF-8 encoding before running Python scripts, or use WSL2 which handles UTF-8 paths natively.
Frequently Asked Questions about AI Agents From Zero
What is AI Agents From Zero?
AI Agents From Zero is a Model Context Protocol (MCP) server that 🚀 2026 最系统的 ai agent 速成指南｜智能体实战教程 · 完整学习路径 + 实战项目 + 面试题库 · 对标大模型应用开发工程师岗位 · 覆盖langchain / langgraph / coze / dify / mcp / skills / llm / rag / 提示词 · 企业级部署与微调 · 从0到企业级落地 + 从学习到上线项目 + 面试准备一体化 It connects AI assistants to external tools and data sources through a standardized interface.
How do I install AI Agents From Zero?
Follow the installation instructions on the AI Agents From Zero GitHub repository. Clone the repo, install dependencies, and add the server config to your AI client.
Which AI clients work with AI Agents From Zero?
AI Agents From Zero works with all major MCP-compatible AI clients including Claude Desktop, Claude Code, Cursor, VS Code (GitHub Copilot), Windsurf, and Cline.
Is AI Agents From Zero free to use?
Yes, AI Agents From Zero is open source and available under the MIT license. You can use it freely in both personal and commercial projects.
AI Agents From Zero Alternatives — Similar Coding Agents Servers
Looking for alternatives to AI Agents From Zero? Here are other popular coding agents servers you can use with Claude, Cursor, and VS Code.
Dify
★ 142.2kProduction-ready platform for agentic workflow development.
Ruflo
★ 54.0k🌊 The leading agent orchestration platform for Claude. Deploy intelligent multi-agent swarms, coordinate autonomous workflows, and build conversational AI systems. Features enterprise-grade architecture, self-learning swarm intelligence, RAG integrat
Goose
★ 45.7kan open source, extensible AI agent that goes beyond code suggestions - install, execute, edit, and test with any LLM
Antigravity Awesome Skills
★ 38.3kInstallable GitHub library of 1,400+ agentic skills for Claude Code, Cursor, Codex CLI, Gemini CLI, Antigravity, and more. Includes installer CLI, bundles, workflows, and official/community skill collections.
AgentScope
★ 25.5kBuild and run agents you can see, understand and trust.
Serena
★ 24.5kA coding agent toolkit that provides IDE-like semantic code retrieval and editing tools, enabling LLMs to efficiently navigate and modify codebases using symbol-level operations instead of basic file reading and string replacements.
Browse More Coding Agents MCP Servers
Explore all coding agents servers available in the MCPgee directory. Each server includes setup guides for Claude, Cursor, and VS Code.
Set Up AI Agents From Zero in Your Editor
Choose your AI client for step-by-step setup instructions.
Quick Config Preview
Add this to your claude_desktop_config.json or .cursor/mcp.json
Ready to use AI Agents From Zero?
Browse our complete directory of 33,000+ MCP servers, read setup guides for your editor, and start building with the Model Context Protocol.