langfuse

🪢 Open source AI engineering platform: AI Gateway, agent observability, evals, and prompt/skill management, built on OpenTelemetry. One open platform for every

What is langfuse?

🪢 Open source AI engineering platform: AI Gateway, agent observability, evals, and prompt/skill management, built on OpenTelemetry. One open platform for every AI call and every agent. Self-host or use Langfuse Cloud.

Overview of langfuse

What it is

Langfuse is an open source LLM engineering platform. According to its README, it helps teams collaboratively develop, monitor, evaluate, and debug AI applications. It can be self-hosted in minutes and is built with the ClickHouse open source database. The README states that since January 2026 Langfuse is part of ClickHouse.

Key features

  • LLM application observability: instrument an app and ingest traces to track LLM calls and related logic such as retrieval, embedding, or agent actions, and inspect logs and user sessions.
  • Prompt management: centrally manage, version control, and collaboratively iterate on prompts, with caching on the server and client side so prompt iteration does not add latency.
  • Evaluations: LLM-as-a-judge, code evaluators, user feedback collection, manual labeling, and custom evaluation pipelines via APIs/SDKs.
  • Datasets: test sets and benchmarks supporting continuous improvement, pre-deployment testing, structured experiments, and integration with frameworks such as LangChain and LlamaIndex.
  • LLM Playground: test and iterate on prompts and model configurations, and jump to the playground from a bad result seen in tracing.
  • API and SDKs: OpenAPI spec, Postman collection, and typed SDKs for Python and JS/TS.

Use cases

  • Tracing and debugging LLM calls, retrieval, embeddings, and agent actions.
  • Versioning and iterating on prompts without adding application latency.
  • Running evaluations and benchmarks on datasets before deployment.
  • Testing prompts and model configurations in the playground.
  • Building bespoke LLMOps workflows on top of the API.

Getting started

Self-host locally with Docker Compose:bash# Get a copy of the latest Langfuse repositorygit clone --depth=1 https://github.com/langfuse/langfuse.gitcd langfuse# Run the langfuse docker composedocker compose upThe README also lists deployment on a single VM with Docker Compose, on Kubernetes via Helm (described as the preferred production deployment), Terraform templates for AWS, Azure, and GCP, and the managed Langfuse Cloud.

License and pricing

Metadata lists the pricing type as open source, while the license field is NOASSERTION, so the specific license is not stated here. The README describes a managed Langfuse Cloud deployment with a free tier and no credit card required, and self-hosting on your own infrastructure.

Based on the project's public README and repository metadata.

Add this badge to your README

Featured on YunoDB Badge styles & help

Maintain this project? Show that it is featured on YunoDB.

Markdown[![Featured on YunoDB](https://yunodb.com/badge/langfuselangfuse.svg)](https://yunodb.com/tools/langfuselangfuse?utm_source=github&utm_medium=badge)
HTML<a href="https://yunodb.com/tools/langfuselangfuse?utm_source=github&utm_medium=badge"><img src="https://yunodb.com/badge/langfuselangfuse.svg" alt="Featured on YunoDB" height="20"></a>