Langfuse in n8n: Community Nodes for Prompts and Tracing

n8n has no built-in Langfuse node: n8n’s integrations documentation lists none. Langfuse is an open-source LLM engineering platform for tracing, metrics, evaluations and prompt management, and n8n users reach it through community nodes: one official package from the Langfuse team for prompts, and several packages that trace n8n’s AI agents and language models to Langfuse. This guide compares them, using the description and README each author publishes on npm and our own download data.

What do you need?

Langfuse community nodes

Our Langfuse hub lists 18 packages that pass our quality rule, with 22,146 npm downloads a week between them. The most downloaded, with the description each author gives on npm (weekly npm downloads as of 27 October 2026):

@langfuse/n8n-nodes-langfuse (official)

Published by Langfuse, with its repository in the langfuse GitHub organization. Its README lists one operation, Get Prompt: you enter a prompt’s name and a label (default production) and the node fetches that version from Langfuse Prompt Management, for example as the system prompt of an AI agent. The credential takes your Langfuse hostname, public key and secret key, from Langfuse Cloud or a self-hosted Langfuse. Its README also says it is a verified community node that n8n Cloud users can find by searching for Langfuse.

AI agents with tracing

These packages replace n8n’s AI Agent node with one that sends traces to Langfuse:

• n8n-nodes-agent-langfuse: picks a production prompt from Langfuse in the node, fills its {{variables}} as fields, can use the model and temperature from the prompt config, links each generation to the prompt version and traces every run with tool calls. Its README lists n8n 2.0.0 or newer and Langfuse 3.0 or newer (version 0.3.3 for n8n 1.x).
• n8n-nodes-ai-agent-langfuse: from Wistron DXLab; traces reasoning steps, tool calls and outputs and adds sessionId, userId and JSON metadata to each trace.
• n8n-nodes-langfuse-ai-agent: runs an agent with a prompt stored in Langfuse, with a required chat model and structured output parser, and traces it.

Model nodes with tracing

n8n-nodes-openai-langfuse, also from Wistron DXLab, is a chat model node for OpenAI-compatible models that traces every request and response to Langfuse. Its README now points to n8n-nodes-ai-agent-langfuse as the upgraded version. @open-condo/n8n-nodes-llm-openai-langfuse describes the same idea for OpenAI models.

Check each node page here for the latest release and, where it has one, its GitHub repository for open issues before you build on a package.

How to choose

• Prompts managed in Langfuse, used in any workflow: the official @langfuse/n8n-nodes-langfuse.
• Traces of your AI agents in Langfuse: one of the agent packages; compare their README requirements with your n8n and Langfuse versions.
• Anything else in the Langfuse API: the HTTP Request node with Langfuse’s API documentation.

To install a package on a self-hosted instance, an owner or admin enters its npm name in Settings > Community Nodes; full steps are in How to Install n8n Community Nodes. On n8n Cloud only verified community nodes can be installed, see Verified vs Unverified n8n Community Nodes. Related: OpenAI in n8n.

FAQ

Does n8n have a Langfuse node?

Not a built-in one. The official Langfuse node, @langfuse/n8n-nodes-langfuse, is a community node published by Langfuse.

Can I use Langfuse on n8n Cloud?

The official package’s README says it is a verified community node, available on n8n Cloud by searching for Langfuse. Unverified packages need a self-hosted instance.

How do I trace an n8n AI agent in Langfuse?

With a community agent node that sends traces, such as n8n-nodes-agent-langfuse or n8n-nodes-ai-agent-langfuse. The official package fetches prompts; its README lists no tracing operation.

What is the most used Langfuse community node?

@langfuse/n8n-nodes-langfuse, with 20,235 weekly npm downloads on 27 October 2026.