# datawhalechina/deepagents-in-action

📚 《Deep Agents 实战》—— LangChain 官方大使出品，基于 LangChain / LangGraph 生态，从零构建生产级 AI Agent 的完整指南

Repository: https://github.com/datawhalechina/deepagents-in-action
Canonical: https://ross.abutalabs.com/products/deepagents-in-action
Homepage: https://datawhalechina.github.io/deepagents-in-action/
Language: Astro
License Family: other
Topics: agentic-ai, ai-agents, astro, chinese, context-engineering, course, langchain, langgraph, tutorial, deepagents, sandbox
Last push: 2026-08-26T02:12:02+00:00

## Health v2 (maintenance only)
Score: 58/100 (v2, computed 2026-09-03T02:20:16.233290+00:00)
- activity 99, release rhythm 35, longevity 8
- inputs: {"age_days": 120, "days_push": 8, "days_rel": null, "gap_med": null, "n_releases_24m": 0}
- flags: no_releases, young, no_license
- formula: round(0.45*activity + 0.35*rhythm + 0.20*longevity); archived -> min(score, 10)

## Adoption (not part of the score)
Stars 1790, forks 180 (observed 2026-08-28T04:05:36.939956+00:00)

## What it is
An open-source Chinese-language course ('Deep Agents 实战') that teaches building production-grade AI agents with the LangChain/LangGraph Deep Agents SDK. It includes 16 chapters with lectures, videos, and hands-on labs covering planning, subagents, memory, human-in-the-loop, sandboxing, MCP, and streaming.

## Use cases
- learn to build production AI agents with LangGraph
- understand context engineering for agents
- build multi-agent systems with subagents
- add long-term memory to an AI agent
- run agent code safely in a sandbox
- extend agents with MCP tools
- debug LangChain apps with LangSmith traces

## When to choose
- you want a structured, chapter-by-chapter guide to the Deep Agents SDK
- you prefer Chinese-language tutorials with video and labs
- you are moving from agent frameworks to production agent harnesses

## When to avoid
- you need a ready-to-use agent application rather than a course
- you need English-only material
- you want content under a permissive code license (content is CC BY-NC-SA)

## Facets
- artifact type: learning-resource
- maturity: active
- function: agent-framework, developer-tools, mcp, rag
- domain: artificial-intelligence, large-language-models, tutorials, developer-tools
- platform: python, cross-platform
- tags: deepagents, langchain, langgraph, context-engineering, chinese, course, tutorial, agentic-ai, sandbox, astro, ai-agents

## Member repositories
- datawhalechina/deepagents-in-action (main) score 58

## Provenance
- Observed fields: from GitHub, fetched 2026-08-28T04:05:36.939956+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 2026-08-30T03:23:16.786388+00:00, confidence not recorded.
  - readme: https://github.com/datawhalechina/deepagents-in-action (fetched 2026-08-28T04:05:36.939956+00:00, sha 43808235d960)
  - homepage: https://datawhalechina.github.io/deepagents-in-action/ (fetched 2026-08-29T11:02:17.058106+00:00, sha fd747297fea3)
- Data as of 2026-08-30T08:39:29.467469+00:00.