Skip to content
Back to directory

Langfuse

Open-source LLM engineering platform. Tracing, evals, prompt management and cost tracking for LLM apps.

Visit Langfuse (opens in a new tab)

Langfuse records traces of your LLM application: every model call, retrieval step and tool call, with latency, token usage and cost attached.

Why it’s useful

  • Debug RAG: see exactly which chunks were retrieved for a query and what the model did with them.
  • Track spend: actual token usage per trace. Compare it against estimates from the RAG Chunk & Token Calculator.
  • Prompt management and evals built in. Open source (MIT) and self-hostable.

Free tools that pair with Langfuse

More in AI Tooling

Back to directory