Skip to content

github.com / WenyuChiou / awesome-agentic-ai-zh

The AI Agent learning map

From "what is an LLM and how are tokens counted" all the way to building your own multi-agent systems.

Start learning Full roadmap

繁體中文简体中文English
8stages
240+projects
23exercises
3languages

Pick a learning track

  • Track A — CLI power user

    Push CLI agents like Claude Code to their limit: workflows, productionization.

    Start at A1

  • Track B — Agent builder

    From tool calls all the way to multi-agent systems and your own MCP server.

    Start at Stage 3

Eight stages, step by step

  • Stage 1 — LLM basics

    Tokens, context, choosing a model.

    Open

  • Stage 2 — Prompt engineering

    Say what you want so the model delivers reliably.

    Open

  • Stage 3 — Tool use

    Give the LLM tools; write your first agent.

    Open

  • Stage 4 — Agent frameworks

    LangGraph, AutoGen, Agents SDK — which to pick.

    Open

  • Stage 5 — Claude Code ecosystem

    CLI agents, MCP, Skills, subagents.

    Open

  • Stage 6 — Memory & RAG

    Let an agent remember and retrieve.

    Open

  • Stage 7 — Multi-agent

    Harness, multi-agent collaboration, production.

    Open

  • Stage 8 — Agent interfaces

    Computer Use, Browser Use, Sandbox.

    Open

Trilingual, with hands-on exercises in every stage. For the full intro and table of contents → project overview.