Skip to content
BENIBIX Learn

LangSmith vs Langfuse

People think LangSmith and Langfuse are one tool, because the names sound alike and both trace and test LLM apps. LangSmith comes from LangChain, the team behind the LangChain framework. Langfuse is a separate project with open code, free to run on your own servers. Both record each step of a run, keep prompts and score answers.

Development🧬 AI Engineering

LangSmith

A tool from LangChain that records, tests and watches LLM apps.

LangSmith is a platform from LangChain for tracing, testing and watching LLM apps. Each run of your app becomes a trace, with every model call and tool step inside. You turn it on with two settings: LANGSMITH_TRACING set to true, and your key. It works with many frameworks, not only LangChain. It also has tests, dashboards and alerts, in the cloud or on your own servers.

Example
Emma's agent gives a wrong refund amount. In LangSmith she opens that run's trace and sees that a tool returned last year's price.
Why it matters
An LLM app can fail in many quiet ways. A trace shows the exact step that went wrong, so you do not have to guess.
Full entry
Development🧬 AI Engineering

Langfuse

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

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
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.
Full entry

In one line

LangSmith
A tool from LangChain that records, tests and watches LLM apps.
Langfuse
A free tool that records each step of an LLM app. You can run it yourself.