langfuse/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

View on GitHub

What it does

Langfuse is an open-source platform that helps teams build, track, and improve AI-powered applications by giving them visibility into how their AI is performing in real time. It lets product and engineering teams monitor AI behavior, test prompts (the instructions given to AI models), and measure quality — all in one place.

Why it matters for PMs

As AI features become central to products, teams need a way to ensure their AI is actually working well and improving over time — Langfuse fills that gap the way analytics tools like Mixpanel did for user behavior. With 22,000+ stars and backing from Y Combinator, it signals strong market demand for 'AI observability' tooling, making it a space worth watching for anyone building or investing in AI products.

Early Signal Score18

Early stage — limited signal data

Stars
22.0k
Forks
2.2k
Contributors
122
Language
TypeScript

Score updated Feb 18, 2026

Get the weekly digest

What just moved on gitfind.ai — delivered every Tuesday. No noise, just signal.