Langfuse: Open Source Machine Learning Infrastructure

Langfuse

“Open source LLM engineering platform for AI-powered applications”

star history · 6d tracked

+220

stars★ 35K forks⑂ 3.8K licensecustom written inTypeScript categoryAI & Machine Learning typeMachine Learning Infrastructure last push3 hours ago

🪢 Open source AI engineering platform: LLM evals, observability, metrics, prompt management, playground, datasets. Integrates with OpenTelemetry, LangChain, OpenAI SDK, LiteLLM, and more. 🍊YC W23

maintainer? embed the star badge

get the markdown →

What is Langfuse?

What it is

Langfuse is an open source LLM engineering platform for building, monitoring, and improving AI-powered applications. It lives in the LLMops ecosystem and provides tooling for the full development lifecycle—from prompt iteration and evaluation to observability and dataset management. Built with TypeScript and powered by ClickHouse, it enables teams to track LLM calls, user sessions, and internal logic like retrieval or agent actions in a unified interface.

The platform solves the problem of fragmented tooling in LLM development. Without it, teams juggle separate systems for tracing, evals, prompt versioning, and dataset management, leading to slow iteration, inconsistent evals, and poor visibility into production failures. Langfuse unifies these workflows into one coherent system, reducing operational overhead and accelerating feedback loops.

Key capabilities

Traces LLM calls, embeddings, retrieval, and agent actions with full context and timing
Manages prompts with version control, caching, and collaborative review
Supports LLM-as-a-judge, code-based, and custom evaluation pipelines via API or UI
Stores and runs datasets for benchmarking, pre-deployment testing, and experiment tracking
Provides a playground for rapid prompt/model iteration with direct links from trace inspection
Exposes a comprehensive REST API with typed SDKs for Python and JavaScript/TypeScript
Integrates with OpenTelemetry, LangChain, LlamaIndex, LiteLLM, and AutoGen

Who uses it and how

ML engineering teams instrument their apps with Langfuse SDKs to trace production LLM calls and debug failures
Prompt engineers use the playground and versioning tools to iterate on system prompts and system messages
QA and MLOps teams run repeated dataset evaluations to measure performance changes before deployments
Platform teams build internal LLMOps dashboards using Langfuse’s API and ClickHouse backend
Startups and enterprises self-host Langfuse to maintain data control while gaining LLM observability

Getting started

Langfuse Cloud offers a managed option with a generous free tier. Self-hosting uses Docker Compose (docker compose up), Kubernetes (Helm), or infrastructure-as-code (Terraform for AWS/Azure/GCP). The repo includes langfuse/langfuse as the Docker image name.

When to use it — and when not to

Use Langfuse when you need integrated tracing, evals, and prompt management for LLM apps and want to self-host or use a managed service with open core. It replaces fragmented paid tools but requires ClickHouse and PostgreSQL for self-hosting, plus SMTP for emails. Avoid it if you only need basic logging—its strength is full-stack LLM observability and evaluation, not simple telemetry.

project readme (upstream, from github) — read inline

Langfuse Cloud · Self Host · Demo

Docs · Report Bug · Feature Request · Changelog · Roadmap ·

Langfuse is an open source LLM engineering platform. It helps teams collaboratively develop, monitor, evaluate, and debug AI applications. Langfuse can be self-hosted in minutes and is battle-tested. Proudly made with ClickHouse open source database.

🧑‍💻 We're hiring

Langfuse is growing fast (we doubled the team in the last 6 months) - since January 2026 we're part of ClickHouse, we're hiring engineering hybrid across the EU. We hire engineers who love open source and great developer experiences. See open roles →

✨ Core Features

LLM Application Observability: Instrument your app and start ingesting traces to Langfuse, thereby tracking LLM calls and other relevant logic in your app such as retrieval, embedding, or agent actions. Inspect and debug complex logs and user sessions. Try the interactive demo to see this in action.
Prompt Management helps you centrally manage, version control, and collaboratively iterate on your prompts. Thanks to strong caching on server and client side, you can iterate on prompts without adding latency to your application.
Evaluations are key to the LLM application development workflow, and Langfuse adapts to your needs. It supports LLM-as-a-judge, Code evaluators, user feedback collection, manual labeling, and custom evaluation pipelines via APIs/SDKs.
Datasets enable test sets and benchmarks for evaluating your LLM application. They support continuous improvement, pre-deployment testing, structured experiments, flexible evaluation, and seamless integration with frameworks like LangChain and LlamaIndex.
LLM Playground is a tool for testing and iterating on your prompts and model configurations, shortening the feedback loop and accelerating development. When you see a bad result in tracing, you can directly jump to the playground to iterate on it.
Comprehensive API: Langfuse is frequently used to power bespoke LLMOps workflows while using the building blocks provided by Langfuse via the API. OpenAPI spec, Postman collection, and typed SDKs for Python, JS/TS are available.

📦 Deploy Langfuse

Langfuse Cloud

Managed deployment by the Langfuse team, generous free-tier, no credit card required.

Self-Host Langfuse

Run Langfuse on your own infrastructure:

Local (docker compose): Run Langfuse on your own machine in 5 minutes using Docker Compose.

# Get a copy of the latest Langfuse repository
git clone --depth=1 https://github.com/langfuse/langfuse.git
cd langfuse

# Run the langfuse docker compose
docker compose up

VM: Run Langfuse on a single Virtual Machine using Docker Compose.
Kubernetes (Helm): Run Langfuse on a Kubernetes cluster using Helm. This is the preferred production deployment.
Terraform Templates: AWS, Azure, GCP

See self-hosting documentation to learn more about architecture and configuration options.

[!TIP] Self-hosting Langfuse? Subscribe to the self-hosting update list to get an email about important features and new releases for open source Langfuse — self-hosting updates only, no marketing.

🔌 Integrations

Main Integrations:

Integration	Supports	Description
SDK	Python, JS/TS	Manual instrumentation using the SDKs f

Frequently asked questions

Is Langfuse free to use?

Langfuse is open source. There is no licence fee and no seat count — you can self-host it or, where the project offers one, pay a vendor for a managed version instead.

What does Langfuse do?

Open source LLM engineering platform for AI-powered applications

What is Langfuse written in?

Langfuse is primarily written in TypeScript. Its source is publicly available at https://github.com/langfuse/langfuse, and it has 34,729 GitHub stars.