analytics

Langfuse

Name: Langfuse
Author: langfuse

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

28,544 stars2,953 forksTypeScriptUpdated 6/5/2026100% free · open source

What it does

Langfuse is an open-source platform for large language model (LLM) engineering, providing observability, metrics, and management tools for LLM development and deployment.

Install / run

git clone https://github.com/langfuse/langfuse.git && cd langfuse && npm install

When to use it

•When you need to monitor and optimize the performance of your LLMs
•When you want to manage and version your prompts and datasets for LLMs
•When you need to integrate your LLMs with other tools and platforms like OpenTelemetry, Langchain, or OpenAI SDK

Quick start

1Run 'npm run dev' to start the Langfuse development server
2Configure your LLM and dataset settings in the 'config.ts' file
3Use the 'langfuse playground' to test and refine your prompts and LLM configurations
4Explore the 'langfuse metrics' dashboard to monitor your LLM's performance and optimize its settings
5Integrate Langfuse with your preferred LLM library, such as Langchain or OpenAI SDK, by following the documentation in the 'integrations' folder

Ready-to-paste prompt

Run 'npm run eval -- --model <your-llm-model> --prompt <your-prompt-text>' to evaluate your LLM's performance on a specific prompt

Heads up: Make sure you have a compatible version of Node.js (14 or higher) and TypeScript installed, as Langfuse is built with TypeScript and relies on Node.js for its development server and build process

Saves to your device