Skip to content
BENIBIX Learn

Langfuse

Development🧬 AI EngineeringLLM App Operations

Also known as Langfuse Cloud, Langfuse Tracing

A free tool that records each step of an LLM app. You can run it yourself.

Think of it like

It is like a home camera you own. The tapes stay in your house.

Example

Jack's company keeps all data in its own country. His team runs Langfuse on their own servers, so traces with customer text never leave.

Why it matters

Teams that cannot send data to an outside service can still trace their app. Open code also means you are not stuck with one vendor.

Definition

Langfuse is an open-source platform for tracing and improving LLM apps. You can use its cloud or run it on your own servers. Each trace holds the model calls and the steps around them, like searches and API calls. It also stores prompt versions, runs evaluations and shows cost and speed on a dashboard. It is built on OpenTelemetry, a shared standard for tracing.

Example code

bash
LANGFUSE_SECRET_KEY="sk-lf-..."
LANGFUSE_PUBLIC_KEY="pk-lf-..."
LANGFUSE_BASE_URL="https://cloud.langfuse.com"
Two keys and an address connect your app. A copy you run yourself uses your own address.
Langfuse records a run like this, and you can keep it on your own servers.

Common mistake

Logging prompts full of private data and forgetting who can read them. Traces hold the real text, so hide what should not be kept.

Key takeaways

  1. 1
    Open source. Run it yourself or in its cloud.
  2. 2
    Traces and prompts. One place for both.
  3. 3
    OpenTelemetry. Uses the shared tracing standard.

Compare