Create

Sign in to ReadmeX

or

How we handle your data: Privacy Policy

ReadmeX

Your AI reading companion

What would you like to catch up on?

Pick a briefing, or ask your own question.

Your community and people briefings stay personal to you.

Story

Author unveils a more complex second LangGraph full-stack project

AI summary

The project author presented a second LangGraph full-stack project built around one main graph and two subgraphs. According to the author, it adds supervisor-based coordination, context summarization, short- and long-term memory, user-confirmed web search, three MCP integrations, and bar-chart rendering of BYD January–October 2026 sales data.

In-depth insight

The update demonstrates how LangGraph can coordinate multiple subgraphs, memory features, human-confirmed search, and MCP-connected data workflows in one full-stack agent project.

222.png

这是第二个项目相对第一个项目更复杂,

  • 一个主图和两个子图
  • 有上下文压缩功能 summarize 节点,会话过长时压缩上下文,阶段性触发压缩
  • 有短期记忆和长期记忆
  • 主图模型节点 supervisor 负责统筹指挥
  • 需要搜索前要经过用户确认,确认后走 researcher 子节点
  • data 子节点是 mcp 独立节点 目前接三个mcp 项目 (动态生成网页的,数据管理项目查询的,查星座运势的)
image.png

查 自己的项目 mcp 数据

image.png

联网搜索前需要用户确认

image.png

按要求搜索比亚迪2026年1 - 10 月销量数据并用柱状图显示

本人git地址

#LangGraph#MCP#BYD

Original · 1 min readRead the original
Group chat

No comments yet. Start the conversation.