AGENT SKILL

langchain_langgraph

Historic standalone skill

License 许可
MIT
最近更新
2026-10-09
Stars
★ 2
Forks
1

01 前言 Front Matter

name
langchain_langgraph
keywords
[ "langchain_langgraph", "ingested" ]
description
Historic standalone skill
mcp_compatible
true

03 SKILL.md 正文

LangChain & LangGraph

LangChain Overview

LangChain is a high-level framework for building agents and LLM-powered applications. It provides interoperable components to connect models to data sources and external systems.

Core Features

  • Real-time data augmentation: Connect LLMs to diverse data sources.
  • Model interoperability: Swap models in and out easily.
  • Deep Agents: Higher-level package built on LangChain for agents capable of planning and subagent usage.

LangGraph Overview

LangGraph is a low-level orchestration framework for building, managing, and deploying long-running, stateful agents. It is the underlying infrastructure that powers robust LLM workflows.

Core Features

  • Durable execution: Agents persist through failures and resume from where they left off.
  • Human-in-the-loop: Incorporate human oversight and interrupt/modify state.
  • Comprehensive memory: Short-term working memory and long-term persistent memory across sessions.
  • Graph abstraction: Uses graphs (inspired by Pregel/NetworkX) to orchestrate complex stateful execution.

Source: github.com/langchain-ai/langchain & github.com/langchain-ai/langgraph

04 同仓库更多 Skills