LangGraph is the open-source framework for building stateful, orchestrated agent workflows. LangSmith Deployment is the managed service for running those agents at scale in production. LangGraph is an extension of LangChain that introduces a graph-based approach to AI workflows. Instead of chaining steps in one direction, LangGraph lets you define nodes and edges like a flowchart. Each agent can have its own prompt, LLM, tools, and other custom code to best collaborate with the other agents. That means there are two main considerations when thinking about different multi-agent workflows: What are the multiple independent agents? How are those agents connected? This thinking lends itself incredibly well to a graph representation, such as that provided by langgraph . In this approach, each agent is a node in the graph, and their connections are represented as an edge ... LangGraph Framework Documentation Relevant source files Purpose and Scope This document describes the LangGraph framework documentation content within the LangChain ecosystem docs. LangGraph is documented as a low-level orchestration framework and runtime for building stateful, long-running agents. The documentation covers core graph abstractions (StateGraph, nodes, edges), persistence mechanisms, human-in-the-loop patterns, streaming capabilities, and common workflow patterns. For high ...
