OpenLLMetry
LLM traces as standard OpenTelemetry spans — so they land in the observability stack you already pay for.
The practical problem with most LLM observability is that it creates a second observability silo: traces live in a new tool that your existing dashboards, alerts, and on-call rotation do not know about. OpenLLMetry avoids that by emitting ordinary OpenTelemetry spans from LLM and vector database calls, which any OTel backend can ingest. If your organisation already runs a tracing backend, this is usually the cheapest way to get LLM visibility without a platform decision.
Best for: Organisations with an existing OpenTelemetry stack who do not want a second observability silo