# datawhalechina/Agent-Learning-Hub

AI Agent 学习路线与资料库收集

Repository: https://github.com/datawhalechina/Agent-Learning-Hub
Canonical: https://ross.abutalabs.com/products/agent-learning-hub
Homepage: https://datawhalechina.github.io/Agent-Learning-Hub/
Language: HTML
License: MIT
License Family: permissive
Last push: 2026-07-19T12:59:49+00:00

## Health v2 (maintenance only)
Score: 56/100 (v2, computed 2026-09-02T17:46:02.011165+00:00)
- activity 93, release rhythm 35, longevity 7
- inputs: {"age_days": 108, "days_push": 45, "days_rel": null, "gap_med": null, "n_releases_24m": 0}
- flags: no_releases, young
- formula: round(0.45*activity + 0.35*rhythm + 0.20*longevity); archived -> min(score, 10)

## Adoption (not part of the score)
Stars 7105, forks 743 (observed 2026-08-28T04:09:55.927275+00:00)

## What it is
A curated AI Agent learning roadmap and resource collection maintained by Datawhale, organized as an actionable todo list with stages from basic agent loops to evaluation and safety. It aggregates official docs, papers, blog posts, and open-source projects into a structured path for building reliable agents.

## Use cases
- learn how to build AI agents from scratch
- find a structured roadmap for LLM agent development
- understand agent loops and tool calling
- study agent evaluation and safety practices
- find curated papers and projects about AI agents
- decide when to use an agent versus a workflow

## When to choose
- you want a step-by-step curriculum for learning AI agent engineering
- you need curated, opinionated resources instead of random link dumps
- you are a beginner or an LLM developer filling gaps in tool use, RAG, memory, or evals

## When to avoid
- you need runnable agent code or a framework rather than a guide
- you want a comprehensive textbook-style reference with exercises and grading
- you only want role-play multi-agent framework tutorials, which the repo explicitly deprioritizes

## Facets
- artifact type: learning-resource
- maturity: active
- function: agent-framework, llm-inference, rag, prompt-engineering, mcp, developer-tools
- domain: artificial-intelligence, large-language-models, tutorials, awesome-lists
- platform: -
- tags: learning-roadmap, curated-resources, ai-agents, study-guide, datawhale, chinese, web-server

## Member repositories
- datawhalechina/Agent-Learning-Hub (main) score 56

## Provenance
- Observed fields: from GitHub, fetched 2026-08-28T04:09:55.927275+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 2026-08-29T17:40:08.387444+00:00, confidence not recorded.
  - readme: https://github.com/datawhalechina/Agent-Learning-Hub (fetched 2026-08-28T04:09:55.927275+00:00, sha 3b5821cceba3)
  - homepage: https://datawhalechina.github.io/Agent-Learning-Hub/ (fetched 2026-08-29T08:35:43.289647+00:00, sha 3813d21c4d7b)
- Data as of 2026-08-30T08:39:29.467469+00:00.