Reche Inc
Reche Inc
ENChange languagePortuguêsBook a diagnosisChat on WhatsApp
Back to blog
AI Tools

Langfuse: observability and evaluation for LLM applications

Langfuse is an open-source platform to observe, evaluate and debug LLM apps: tracing, cost, latency, prompt management and datasets. An alternative to LangSmith.

Published on June 19, 20265 min readView on GitHub

When an AI application fails in production, without observability you are in the dark. Langfuse is the open-source platform that lights it up: it traces every model and agent call, with cost, latency and tokens, plus evaluation and prompt management. It is the open alternative to LangSmith.

What is Langfuse?

Langfuse offers nested tracing of LLM and agent calls, prompt management with versioning, a playground and dataset/experiment tooling for evaluation. It has Python and JS SDKs and OpenTelemetry integration, and is self-hostable.

Key features

  • Tracing of LLM and agent calls with cost, latency and tokens
  • Prompt management with versioning and a playground
  • Evaluation via LLM-as-judge, feedback and custom metrics
  • Python/JS SDKs and OpenTelemetry integration, self-hostable
  • Extremely active, with hundreds of releases

How Reche uses it

Observability from the first sprint is a RecheOS principle. Reche instruments the products it builds with tools like Langfuse, so AI in production is monitorable and improvable, not a black box.

Want to implement this in your product?

Reche's initial diagnosis defines scope, timeline, and budget. Credited to the project if you move forward.