🦜🕸️LangGraph.js

⚡ Building language agents as graphs ⚡

[!NOTE] Looking for the Python version? See the Python repo and the Python docs.

Overview

LangGraph is a library for building stateful, multi-actor applications with LLMs, used to create agent and multi-agent workflows. Check out an introductory tutorial here.

LangGraph is inspired by Pregel and Apache Beam. The public interface draws inspiration from NetworkX. LangGraph is built by LangChain Inc, the creators of LangChain, but can be used without LangChain.

Why use LangGraph?

LangGraph powers production-grade agents, trusted by Linkedin, Uber, Klarna, GitLab, and many more. LangGraph provides fine-grained control over both the flow and state of your agent applications. It implements a central persistence layer, enabling features that are common to most agent architectures:

• Memory: LangGraph persists arbitrary aspects of your application's state, supporting memory of conversations and other updates within and across user interactions;
• Human-in-the-loop: Because state is checkpointed, execution can be interrupted and resumed, allowing for decisions, validation, and corrections at key stages via human input.

Standardizing these components allows individuals and teams to focus on the behavior of their agent, instead of its supporting infrastructure.

Through LangGraph Platform, LangGraph also provides tooling for the development, deployment, debugging, and monitoring of your applications.

LangGraph integrates seamlessly with LangChain and LangSmith (but does not require them).

To learn more about LangGraph, check out our first LangChain Academy course, Introduction to LangGraph, available for free here.

LangGraph Platform

LangGraph Platform is infrastructure for deploying LangGraph agents. It is a commercial solution for deploying agentic applications to production, built on the open-source LangGraph framework. The LangGraph Platform consists of several components that work together to support the development, deployment, debugging, and monitoring of LangGraph applications: LangGraph Server (APIs), LangGraph SDKs (clients for the APIs), LangGraph CLI (command line tool for building the server), and LangGraph Studio (UI/debugger).

See deployment options here (includes a free tier).

Here are some common issues that arise in complex deployments, which LangGraph Platform addresses:

• Streaming support: LangGraph Server provides multiple streaming modes optimized for various application needs
• Background runs: Runs agents asynchronously in the background
• Support for long running agents: Infrastructure that can handle long running processes
• Double texting: Handle the case where you get two messages from the user before the agent can respond
• Handle burstiness: Task queue for ensuring requests are handled consistently without loss, even under heavy loads

Installation

npm install @langchain/langgraph @langchain/core

Example

Let's build a tool-calling ReAct-style agent that uses a search tool!

npm install @langchain/anthropic zod

export ANTHROPIC_API_KEY=sk-...

Optionally, we can set up LangSmith for best-in-class observability.

export LANGSMITH_TRACING=true
export LANGSMITH_API_KEY=lsv2_sk_...

The simplest way to create a tool-calling agent in LangGraph is to use createReactAgent:

import { createReactAgent } from "@langchain/langgraph/prebuilt";
import { MemorySaver } from "@langchain/langgraph";
import { ChatAnthropic } from "@langchain/anthropic";
import { tool } from "@langchain/core/tools";

import { z } from "zod";

// Define the tools for the agent to use
const search = tool(async ({ query }) => {
  // This is a placeholder, but don't tell the LLM that...
  if (query.toLowerCase().includes("sf") || query.toLowerCase().includes("san francisco")) {
    return "It's 60 degrees and foggy."
  }
  return "It's 90 degrees and sunny."
}, {
  name: "search",
  description: "Call to surf the web.",
  schema: z.object({
    query: z.string().describe("The query to use in your search."),
  }),
});

const tools = [search];
const model =  new ChatAnthropic({
  model: "claude-3-5-sonnet-latest"
});

// Initialize memory to persist state between graph runs
const checkpointer = new MemorySaver();

const app = createReactAgent({
  llm: model,
  tools,
  checkpointSaver: checkpointer,
});

// Use the agent
const result = await app.invoke(
  {
    messages: [{
      role: "user",
      content: "what is the weather in sf"
    }]
  },
  { configurable: { thread_id: 42 } }
);
console.log(result.messages.at(-1)?.content);

"Based on the search results, it's currently 60 degrees Fahrenheit and foggy in San Francisco, which is quite typical weather for the city."

Now when we pass the same "thread_id", the conversation context is retained via the saved state (i.e. stored list of messages)

const followup = await app.invoke(
  {
    messages: [{
      role: "user",
      content: "what about ny"
    }]
  },
  { configurable: { thread_id: 42 } }
);

console.log(followup.messages.at(-1)?.content);

"According to the search results, it's currently 90 degrees Fahrenheit and sunny in New York City. That's quite a warm day for New York!"

[!TIP] LangGraph is a low-level framework that allows you to implement any custom agent architectures. Click on the low-level implementation below to see how to implement a tool-calling agent from scratch.

import { AIMessage, BaseMessage, HumanMessage } from "@langchain/core/messages";
import { tool } from "@langchain/core/tools";
import { z } from "zod";
import { ChatAnthropic } from "@langchain/anthropic";
import { StateGraph } from "@langchain/langgraph";
import { MemorySaver, Annotation, messagesStateReducer } from "@langchain/langgraph";
import { ToolNode } from "@langchain/langgraph/prebuilt";

// Define the graph state
// See here for more info: https://langchain-ai.github.io/langgraphjs/how-tos/define-state/
const StateAnnotation = Annotation.Root({
  messages: Annotation<BaseMessage[]>({
    // `messagesStateReducer` function defines how `messages` state key should be updated
    // (in this case it appends new messages to the list and overwrites messages with the same ID)
    reducer: messagesStateReducer,
  }),
});

// Define the tools for the agent to use
const weatherTool = tool(async ({ query }) => {
  // This is a placeholder for the actual implementation
  if (query.toLowerCase().includes("sf") || query.toLowerCase().includes("san francisco")) {
    return "It's 60 degrees and foggy."
  }
  return "It's 90 degrees and sunny."
}, {
  name: "weather",
  description:
    "Call to get the current weather for a location.",
  schema: z.object({
    query: z.string().describe("The query to use in your search."),
  }),
});

const tools = [weatherTool];
const toolNode = new ToolNode(tools);

const model = new ChatAnthropic({
  model: "claude-3-5-sonnet-20240620",
  temperature: 0,
}).bindTools(tools);

// Define the function that determines whether to continue or not
// We can extract the state typing via `StateAnnotation.State`
function shouldContinue(state: typeof StateAnnotation.State) {
  const messages = state.messages;
  const lastMessage = messages[messages.length - 1] as AIMessage;

  // If the LLM makes a tool call, then we route to the "tools" node
  if (lastMessage.tool_calls?.length) {
    return "tools";
  }
  // Otherwise, we stop (reply to the user)
  return "__end__";
}

// Define the function that calls the model
async function callModel(state: typeof StateAnnotation.State) {
  const messages = state.messages;
  const response = await model.invoke(messages);

  // We return a list, because this will get added to the existing list
  return { messages: [response] };
}

// Define a new graph
const workflow = new StateGraph(StateAnnotation)
  .addNode("agent", callModel)
  .addNode("tools", toolNode)
  .addEdge("__start__", "agent")
  .addConditionalEdges("agent", shouldContinue)
  .addEdge("tools", "agent");

// Initialize memory to persist state between graph runs
const checkpointer = new MemorySaver();

// Finally, we compile it!
// This compiles it into a LangChain Runnable.
// Note that we're (optionally) passing the memory when compiling the graph
const app = workflow.compile({ checkpointer });

// Use the Runnable
const finalState = await app.invoke(
  { messages: [new HumanMessage("what is the weather in sf")] },
  { configurable: { thread_id: "42" } }
);

console.log(finalState.messages[finalState.messages.length - 1].content);

Step-by-step Breakdown:

There are two main nodes we need:

First, we need to set the entry point for graph execution - agent node.

Then we define one normal and one conditional edge. Conditional edge means that the destination depends on the contents of the graph's state. In our case, the destination is not known until the agent (LLM) decides.

Documentation

• Tutorials: Learn to build with LangGraph through guided examples.
• How-to Guides: Accomplish specific things within LangGraph, from streaming, to adding memory & persistence, to common design patterns (branching, subgraphs, etc.), these are the place to go if you want to copy and run a specific code snippet.
• Conceptual Guides: In-depth explanations of the key concepts and principles behind LangGraph, such as nodes, edges, state and more.
• API Reference: Review important classes and methods, simple examples of how to use the graph and checkpointing APIs, higher-level prebuilt components and more.
• LangGraph Platform: LangGraph Platform is a commercial solution for deploying agentic applications in production, built on the open-source LangGraph framework.

Resources

• Built with LangGraph: Hear how industry leaders use LangGraph to ship powerful, production-ready AI applications.

Contributing

For more information on how to contribute, see here.