Langfuse LLM Observability Platform and SDK

Use Langfuse to capture prompts, traces, generations, evaluations, and cost telemetry for LLM applications and agent workflows. This skill turns Langfuse from a generic observability brand into a concrete implementation pattern for tracing and analyzing model behavior.

Installation

Use the upstream install or setup path that matches your environment:

• git clone https://github.com/langfuse/langfuse.git
• docker compose up
• pip install langfuse openai

Requirements and caveats from upstream:

• <a href="https://hub.docker.com/u/langfuse" target="_blank">
• <img alt="Docker Pulls" src="https://img.shields.io/docker/pulls/langfuse/langfuse?labelColor=%20%23FDB062&logo=Docker&labelColor=%20%23528bff"></a>
• <a href="https://pypi.python.org/pypi/langfuse"><img src="https://img.shields.io/pypi/dm/langfuse?logo=python&logoColor=white&label=pypi%20langfuse&color=blue" alt="langfuse Python package on PyPi"></a>

Basic usage or getting-started notes:

• 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...

• Run Langfuse on your own infrastructure:

• Kubernetes (Helm): Run Langfuse on a Kubernetes cluster using Helm. This is the preferred production deployment.

• Source: https://github.com/langfuse/langfuse

• Extracted from upstream docs: https://raw.githubusercontent.com/langfuse/langfuse/HEAD/README.md

Source

• Agent Skill Exchange