# didilili/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

Repository: https://github.com/didilili/ai-agents-from-zero
Canonical: https://ross.abutalabs.com/products/ai-agents-from-zero
Homepage: https://didilili.github.io/ai-agents-from-zero/
Language: Python
License: MIT
License Family: permissive
Topics: agent, aigc, coze, dify, langchain, llm, mcp, rag, tutorial, gpt, agent-framework, ai-agent, langgraph, skills, agentic-ai, cursor, deepagents
Last push: 2026-06-23T16:29:23+00:00

## Health v2 (maintenance only)
Score: 55/100 (v2, computed 2026-09-02T17:46:02.011165+00:00)
- activity 89, release rhythm 35, longevity 15
- inputs: {"age_days": 216, "days_push": 71, "days_rel": null, "gap_med": null, "n_releases_24m": 0}
- flags: no_releases
- formula: round(0.45*activity + 0.35*rhythm + 0.20*longevity); archived -> min(score, 10)

## Adoption (not part of the score)
Stars 4094, forks 579 (observed 2026-08-28T04:08:34.660357+00:00)

## What it is
A comprehensive open-source Chinese-language tutorial and learning roadmap for building AI agents and LLM applications, covering LangChain, LangGraph, Coze, Dify, MCP, RAG, prompting, fine-tuning, and enterprise deployment. It includes runnable source code, two complete hands-on projects, and an interview question bank aligned with AI application engineer job requirements.

## Use cases
- learn to build AI agents from scratch
- study LangChain and LangGraph with runnable examples
- prepare for LLM application developer interviews
- build a RAG chatbot over e-commerce data
- learn multi-agent deep research systems
- understand MCP and agent skills
- find a structured alternative to paid AI bootcamps

## When to choose
- you want a free, systematic, continuously updated AI agent curriculum
- you prefer the Python ecosystem over Java-based stacks
- you need end-to-end coverage from basics to enterprise deployment
- you want project source code plus interview prep in one place

## When to avoid
- you need production-grade software rather than educational material
- you only read English, since the content is in Chinese
- you want a Java or Spring AI focused curriculum
- you need official framework documentation instead of a guided course

## Facets
- artifact type: learning-resource
- maturity: active
- function: agent-framework, rag, prompt-engineering, llm-inference, mcp, developer-tools
- domain: artificial-intelligence, large-language-models, tutorials
- platform: python, cross-platform
- tags: ai-agents, langchain, langgraph, coze, dify, interview-preparation, chinese-language, hands-on-projects, roadmap, retrieval-augmented-generation, natural-language-processing

## Member repositories
- didilili/ai-agents-from-zero (main) score 55

## Provenance
- Observed fields: from GitHub, fetched 2026-08-28T04:08:34.660357+00:00.
- Health v2: computed from the inputs above; adoption is never an input.
- Inferred fields (summary, facets, guidance): AI-extracted, prompt v1, taxonomy v1, on 2026-08-29T18:23:19.930405+00:00, confidence not recorded.
  - readme: https://github.com/didilili/ai-agents-from-zero (fetched 2026-08-28T04:08:34.660357+00:00, sha 688d334788c6)
  - homepage: https://didilili.github.io/ai-agents-from-zero/ (fetched 2026-08-29T09:14:56.798482+00:00, sha 37f0777c8511)
- Data as of 2026-08-30T08:39:29.467469+00:00.