OpenLLMetry

If your application is already instrumented with OpenLLMetry (Traceloop’s SDK), point its exporter at Rius and your existing traces flow in; no re-instrumentation needed.

Point the exporter here


from traceloop.sdk import Traceloop
 
Traceloop.init(
    app_name="my-agent",
    api_endpoint="https://ingest.eu.console.rius-glassflow.com",
    headers={"Authorization": "Bearer <your API key>"},
)

OpenLLMetry exports OTLP/HTTP protobuf by default, which is exactly what the endpoint expects. The same values can come from OpenLLMetry’s environment variables if you prefer configuration over code.

What gets captured

Everything OpenLLMetry emits is stored and inspectable: traces arrive, spans nest, prompt and completion content is visible in trace inspection.

Analytics coverage depends on the attribute convention, and OpenLLMetry has used several across versions: recent releases emit OTel GenAI (gen_ai.*) attributes, which get full analytics (model, tokens, server-side cost); older releases emit legacy gen_ai.prompt.* / gen_ai.completion.* and traceloop.entity.* keys, which are stored but not yet analytics-mapped. Check what your version sends against the supported-conventions matrix, and prefer a current OpenLLMetry release for the gen_ai.* path.

Verify in one minute: run one traced LLM call, open the trace in the console, and check the span shows a model name and token counts. If the span is there but those fields are empty, your OpenLLMetry version is emitting a legacy convention.

Next steps

Span attribute reference: which OpenLLMetry attribute families map to analytics today.
OpenTelemetry Collector: fan out to Rius next to your existing backend while you evaluate.