Back to directory

n8n-nodes-ai-agent-langfuse

This is a community node for the n8n workflow automation platform that sends Langfuse tracing and observability data for tool-calling AI agent workflows, including reasoning steps, tool calls and structured output.

n8n-nodes-ai-agent-langfuse

The node integrates with LangChain's AgentExecutor and ToolCallingAgent inside n8n, automatically sending each agent run's reasoning, tool calls and output to a configured Langfuse instance, whether that is Langfuse Cloud or a self-hosted deployment. Custom metadata such as a session ID, user ID or arbitrary structured JSON can be attached to each trace for later filtering.

It is installed like any other n8n community node, either from the n8n UI's community nodes settings, through a preconfigured Docker setup included in the repository, or by installing the npm package directly into an existing n8n installation.

It is published on npm and written in TypeScript.

More in AI evals

See all 269
  • Provenance gate

    github.com

    A deterministic authorization gateway that sits between an AI agent and its tools, tracing where each parameter of a side-effect call came from, and blocking the call or asking a human when the source does not check out.

  • JevBench

    benchmarkheaven.com

    A reproducible benchmark from Benchmark Heaven that ranks Jev-class typed decision models on intelligence, calibration, speed, and cost, with a published harness, scoring rules, and results.

  • A co-evolutionary adversarial red-teaming tool for AI agents that uses quality-diversity evolutionary search to autonomously breed edge-case scenarios, testing whether an agent with tool access can be made to hallucinate, deadlock or leak funds.