Langfuse
Traces, prompts, and evaluations for LLM applications — the closest thing to a decision trail an agent currently produces.
The governance lens
What it gives you toward an auditable agent decision trail, and where it stops: it records the call chain, not the model state that produced it.
There is no shortage of writing about Langfuse. This register asks the question the general coverage does not: what does it contribute to governing an autonomous system that touches capital, and where does that contribution stop?
Status and disclosure
Listed — not yet reviewed. Structured facts and a governance lens, with no score attached. A full profile requires hands-on use, and we do not score what we have not run.
No commercial relationship. Langfuse is listed on editorial merit and has no input into this description.