Langfuse

Observability & Evals

Open-source LLM observability and prompt management.

What it’s for

Langfuse records every trace of your LLM application — prompts, latencies, costs, scores — so you can debug and improve what you shipped. It also versions prompts and runs dataset-based evaluations, covering the loop from development to production.

How to use it

Self-host with Docker or Kubernetes, or start on the cloud free tier. Instrument via OpenTelemetry or the SDKs; there are deep integrations with LangChain, LlamaIndex, the OpenAI SDK and LiteLLM.

Pricing

Core is open source (MIT). The cloud has a generous free tier, then usage-based plans.

Website ↗ GitHub ↗