datawhalechina/agent-learning-hub

★ 399Audience · developerComplexity · 1/5Setup · easy

Mindmap

mindmap
  root((Agent Learning Hub))
    Inputs
      Reader level
      Goals
    Outputs
      Stage checklists
      Project ladder
      Curated links
    Use Cases
      Self study agents
      Pick a study path
      Compare frameworks
    Stages
      Stage 0 concepts
      Stage 1 agent loop
      Stage 2 RAG and tools
      Stage 3 deep study
      Multi agent and MCP

mindmap root((Agent Learning Hub)) Inputs Reader level Goals Outputs Stage checklists Project ladder Curated links Use Cases Self study agents Pick a study path Compare frameworks Stages Stage 0 concepts Stage 1 agent loop Stage 2 RAG and tools Stage 3 deep study Multi agent and MCP

Click or tap to explore — scroll the page freely

Things people build with this

USE CASE 1

Pick a staged study path for moving from LLM API calls to building real agents

USE CASE 2

Use the Project Ladder to choose a concrete agent project to ship

USE CASE 3

Find recommended deep dives on Claude Code, LangGraph, MCP and other agent systems

Tech stack

Markdown

Getting it running

Difficulty · easy Time to first run · 5min

It is a reading roadmap not runnable code, and parts of the README are in Chinese.

In plain English

This repository is called Agent Learning Hub. It is not a piece of software in the usual sense. The whole project is one long README, written in a mix of English and Chinese, that lays out a curated learning roadmap for people who want to build AI agents instead of just reading random links about them. It is maintained by a Datawhale community member named Chen Sizhou. The README opens with a guide for different kinds of readers. Beginners are told to follow a Learning Todo List in order, ticking items as they go. People who already know how to call large language model APIs are pointed at Stage 2 or Stage 3, which cover the agent loop, tool calling, evaluation, and engineering. People who want to ship projects are sent to a Project Ladder. People who only want references are sent to a Curated Resources section. The roadmap itself is divided into stages. Stage 0 explains what an agent is and how it differs from a chatbot or a fixed workflow. Stage 1 walks through building a minimal agent loop with one model, structured JSON output, and a few tool functions. Stage 2 covers retrieval-augmented generation, memory, and turning search, databases, files, browsers, and code execution into tools. Stage 3 asks the reader to study one modern agent system in depth, with Claude Code, OpenClaw, Hermes, LangGraph, and others suggested. Later stages cover multi-agent coordination, skills and protocols like MCP and A2A, browser and computer-use agents, and evaluation, observability, and safety. The author also gives an opinion on what is worth studying right now. The README puts coding agents, agent harness engineering, personal local-first agents, the Skills and MCP family of protocols, and evaluation at the top. It explicitly recommends against spending most of your time on older role-play multi-agent frameworks. Each stage lists concrete checkboxes, recommended reading from official documentation, and example open-source projects. The output of the whole repository is meant to be a personal learning checklist rather than runnable code.

Copy-paste prompts

Prompt 1

Turn the Agent Learning Hub Stage 1 checklist into a two week study plan with daily tasks

Prompt 2

Pick three projects from the Agent Learning Hub Project Ladder that fit a Python developer with no RAG experience

Prompt 3

Summarize what the Agent Learning Hub author recommends against studying right now and why

Prompt 4

Extract every external link in Agent Learning Hub and group them by stage and topic

Open on GitHub → Explain another repo

← datawhalechina on gitmyhub — every repo by this author, as a profile.

Verify against the repo before relying on details.