
Langfuse
8.1#1 in ai agent observability toolsFrom $29 a monthFree planWebAPILinuxSelf-hosted
Visit
| Fact | Langfuse | PromptVersions |
|---|---|---|
| Evaluations | Evaluation supports LLM-as-a-Judge, heuristic or code evaluators, human review, annotation queues, and scoring of production data or experiments. | Users can define metrics and test cases, then batch-evaluate a version or run evaluations automatically on every save. |
Langfuse suits teams building AI agent applications that need tracing, prompt management, and evaluation tools. It also supports teams that want to self-host the core on their own infrastructure.
You want what its maker publishes above — check its page for the details.