← Back to all projects

Langfuse

Tracing, prompt management and evaluation for LLM applications

OfficialMIT
Stars
36.8k
Forks
4.1k
Open issues
1.1k
Last commit
30 Oct 2026

What is Langfuse?

Records what an agent actually did — every call, tool invocation and cost — and turns those traces into evaluation datasets. The managed service runs the same codebase you can self-host with Docker Compose, so migrating in either direction stays cheap. Some enterprise features sit outside the MIT core; check which tier you need before committing.

What can you do with Langfuse?

  • Instrument an app function by function — Importing from langfuse.openai import openai captures each OpenAI call with its model parameters, and every function you wrap in @observe() is recorded as its own nested step — the README's main() and story() pair — so retrieval and agent code appears in the trace only once it is decorated too.
  • Version prompts outside your code — Prompt Management holds prompts centrally with version control, and caching on both server and client means fetching the current version adds no latency to your application.
  • Turn traces into test sets — Datasets build benchmarks for pre-deployment testing, scored with LLM-as-a-judge, code evaluators, manual labelling or collected user feedback.
  • Retry failures in the playground — From a bad result in a trace you can jump straight into the LLM Playground and re-run it against a different prompt or model configuration.
  • Self-host on your own infrastructure — docker compose up for a local instance, a Helm chart as the preferred production path on Kubernetes, and Terraform templates for AWS, Azure and GCP.

Before you choose Langfuse

  • Treat the cost figures as an estimate until you have checked them against your provider's own billing. For one provider the token count is read wrongly and the cost comes out roughly nine times too high.Reported in#8020

Star history

15 Aug to 30 Oct · +3.6k

33.1k36.8k

Frequently asked questions

Is Langfuse free for commercial use?

Langfuse is released under the MIT licence — OSI-approved open source, which permits commercial use.

How can Langfuse be deployed?

Langfuse is available as Self-hosted / Managed cloud.