Langfuse — Self-Hosted, Open-Source

LLM engineering platform for model tracing, prompt management, and application evaluation. Langfuse helps teams collaboratively debug, analyze, and iterate on their LLM applications such as chatbots or AI agents.

License: MIT. Built with: TypeScript, JavaScript, Shell, Dockerfile, CSS, PLpgSQL. Website: https://langfuse.com. Source: https://github.com/langfuse/langfuse.

Features

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, user feedback collection, manual labeling, and custom evaluation pipelines via APIs/SDKs.
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.

Installation

# Get a copy of the latest Langfuse repository git clone https://github.com/langfuse/langfuse.git cd langfuse # Run the langfuse docker compose docker compose up

Why self-host Langfuse

Self-hosting gives you three things SaaS can’t: data ownership (the files live on disks you control), cost predictability (a one-time setup vs. recurring per-seat fees that grow with your household or team), and longevity (open-source means the app keeps working even if the maintainers move on, since you can pin a working version). The trade-off is that you take on the operational work of running a server, applying updates, and handling backups.

What hardware do you need

Most self-hosted apps run comfortably on modest hardware — a Raspberry Pi 4, a mini PC, a NAS with Docker support, or a small VPS is usually enough for personal or family use. CPU and RAM requirements scale with how many simultaneous users or how much data you push through Langfuse. Storage requirements depend on the kind of data you keep; check the README for guidance on data retention.

Where to go from here

Last verified: 2026-04-21