An open-source LLM engineering platform for tracing what an application's prompts and agent steps actually did in production, plus tools for prompt management and running evaluations against test datasets.
Visit tool This is mine — claim it
Listing URL: https://langfuse.com
Show your listing is live — the card backlinks here and picks up the verified badge automatically once you claim it.
<iframe src="https://wingmanprotocol.com/embed/card/langfuse" width="340" height="170" style="border:0;border-radius:10px" loading="lazy" title="Langfuse — live on WingMan Protocol"></iframe>
Or the one-line script:
<script src="https://wingmanprotocol.com/embed/card.js" data-slug="langfuse" async></script>
Or a README badge:
[](https://wingmanprotocol.com/directory/langfuse?utm_source=badge)
An ML and LLM observability platform that monitors models and AI applications in production for drift, embedding-space issues and output quality; Phoenix is its
An evaluation platform for AI applications: run a prompt or pipeline change against a test dataset, score the outputs, and track whether quality improved or reg
An ML experiment-tracking platform (logging training runs, metrics and models) that has added Opik, a dedicated tool for tracing and evaluating LLM applications
An evaluation and observability platform for LLM applications that scores production and pre-release outputs for hallucination and quality issues, aimed at catc
An AI evaluation and safety platform that automatically scores an LLM's outputs against test cases for correctness, safety and hallucination, aimed at testing a
A long-standing ML experiment-tracking platform - logging runs, metrics and model versions - that has extended into LLM app tracing and evaluation (Weave) along