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 / Di
What is 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
Overview of ai-agents-from-zero
What it is
ai-agents-from-zero is an open-source tutorial repository that provides a systematic learning path for AI Agent development, from zero to enterprise-level deployment. It covers LangChain, LangGraph, Coze, Dify, MCP, LLM, RAG, prompt engineering, and more. The repository includes a complete curriculum, runnable source code, practical projects, and an interview question bank. It is designed to align with the job requirements of AI Agent / large model application development engineers. The project is continuously updated and aims to be a comprehensive, long-term resource.
Key features
- Systematic and open-source: the first open-source AI Agent tutorial that covers tutorials, source code, practical projects, and interview questions.
- Full-stack coverage: from large models and prompts to low-code platforms (Coze/Dify) and code frameworks (LangChain/LangGraph), enterprise RAG/Agent, fine-tuning, and engineering practices.
- Python-focused: the main line uses Python + LangChain + LangGraph, directly targeting the most common engineering route for AI Agent development.
- Beginner-friendly yet deep: arranged from shallow to deep, explaining core concepts first, then moving to source code, frameworks, deployment, and project design.
- Enterprise-level projects: includes projects like NL2SQL + LangGraph (e-commerce query), DeepAgents (deep research), and others, covering intent parsing, multi-source knowledge, human handoff, monitoring, and cost control.
- Runnable cases: each case is provided with runnable code, environment setup, and troubleshooting tips.
- Interview preparation: an independent interview question bank organized by ability domains, including real interview questions from large companies.
Use cases
- Individuals who want to systematically learn AI Agent development from scratch.
- Developers transitioning from frontend/backend/product roles to AI application development.
- Job seekers preparing for AI application engineer, AI Agent engineer, or AI product technical lead positions.
- Teams looking for a structured curriculum and practical projects for internal training.
Getting started
See the repository README for installation and quick-start instructions.
License and pricing
MIT license. Open source.
Based on the project's public README and repository metadata.