#3939th of 88 in Learning and cookbooks
ai-agents-from-zero
Chinese tutorial with runnable code for building LLM agents in LangChain and LangGraph
- Stars
- 5.9k
- License
- MIT
- Last commit
- Nov 2026
- Language
- Python
419 on 21 Apr 20265,948 on 10 Nov 2026
From GitHub's daily star counts.
Checked on GitHub.
Overview
A Chinese-language course repository covering LLM basics, Coze and Dify low-code platforms, LangChain, LangGraph, MCP, A2A, RAG, and LoRA/QLoRA fine-tuning. It ships runnable Python examples plus two end-to-end projects (NL2SQL with LangGraph, and a DeepAgents research system) and an interview question bank. Examples call cloud APIs such as Qwen and DeepSeek, or local Ollama models.
Who it is for: Chinese-reading developers moving into LLM app and agent engineering
Strengths
- Covers LangChain, LangGraph, MCP, A2A, RAG and fine-tuning in one ordered curriculum
- Two full projects with separate source repos: NL2SQL (Qdrant, Elasticsearch) and DeepAgents research
- Examples run from the repo root with a requirements.txt and .env-example
- Includes an interview question bank and an online reading site
Weaknesses
- Main text is in Chinese; English version exists only under translations/en
- Most examples need paid or free-tier cloud API keys unless Ollama is used
- Course material is partly adapted from a commercial training course, per the README
- README is heavy on promotion and sponsor content; some listed projects have no linked source
What it needs
- GPU optional
- Needs Python 3.10-3.13, Qwen/DeepSeek API keys or Ollama, Docker, MySQL, Qdrant, Elasticsearch
- Models: Qwen, DeepSeek, Ollama local models, vLLM, Xinference
Quick answers
Is ai-agents-from-zero open source?
Yes. Its code is on GitHub under the MIT license.
Does ai-agents-from-zero need a GPU?
No. It runs on a CPU and can use a GPU when you have one.
Also in Learning and cookbooks
See all 88| Rank | Project | Score |
|---|---|---|
| 1 | ai-engineering-from-scratchHands-on AI engineering curriculum with 542 lessons across 20 phases | 91 out of 100 |
| 2 | generative-ai-for-beginners21-lesson course on building generative AI apps in Python and TypeScript | 83 out of 100 |
| 3 | rag_techniquesCollection of 42 runnable notebooks implementing RAG techniques | 81 out of 100 |
| #4 | cs249r_bookOpen textbook and course materials for machine learning systems engineering | 81 out of 100 |
| #5 | ai-for-beginners24-lesson AI curriculum with notebooks in PyTorch and TensorFlow | 80 out of 100 |