LangChain Instrumentation

Quick setup? Instead of following these steps manually, copy a prompt into your coding agent and it will set this up for you automatically.

LangWatch integrates with Langchain to provide detailed observability into your chains, agents, LLM calls, and tool usage.

Installation

npm i langwatch @langchain/openai @langchain/core

pnpm add langwatch @langchain/openai @langchain/core

yarn add langwatch @langchain/openai @langchain/core

bun add langwatch @langchain/openai @langchain/core

Usage

The LangWatch API key is configured by default via the LANGWATCH_API_KEY environment variable.

Use LangWatchCallbackHandler to capture Langchain events as spans within your trace.

import { setupObservability } from "langwatch/observability/node";
import { LangWatchCallbackHandler } from "langwatch/observability/instrumentation/langchain";
import { ChatOpenAI } from "@langchain/openai";
import { HumanMessage } from "@langchain/core/messages";

setupObservability({ serviceName: "<project_name>" });

async function main(message: string): Promise<string> {
  const chatModel = new ChatOpenAI({ model: "gpt-6-luna" }).withConfig({
    callbacks: [new LangWatchCallbackHandler()],
  });

  const result = await chatModel.invoke([new HumanMessage(message)]);
  return result.content as string;
}

console.log(await main("Hey, tell me a joke"));

The LangWatchCallbackHandler captures Langchain events and converts them into detailed LangWatch spans. Pass the callback handler to your Langchain components via the callbacks option in withConfig().

Check it worked

Run the example. The SDK flushes pending spans when the process exits. Then open your project in LangWatch: a new trace appears in the traces list within a few seconds. Open it to see the LangChain steps and the LLM call. If no trace appears, check that LANGWATCH_API_KEY is set in the environment the process runs in.

Capturing RAG - Learn how to capture RAG data from LangChain retrievers and tools
Capturing Metadata and Attributes - Add custom metadata and attributes to your traces and spans
Capturing Evaluations & Guardrails - Log evaluations and implement guardrails in your LangChain applications

Last modified on October 29, 2026

Overview

Tools

LangChain Instrumentation

Installation

Usage

Check it worked

​Installation

​Usage

​Check it worked

​Related

Installation

Usage

Check it worked

Related