Skip to main content
Agno agents are instrumented by the OpenInference Agno instrumentor, which captures agent runs, model calls, and tool calls as OTLP spans. The instrumentor reads token usage directly from Agno’s model responses, so model, tokens, and cost all populate without a separate provider instrumentor. Point the exporter at AgentMark and the traces arrive normalized. Agno is a Python framework.

​
Setup

1

Install the instrumentor and the OTLP exporter

pip install openinference-instrumentation-agno \
  opentelemetry-sdk opentelemetry-exporter-otlp-proto-http
2

Point the exporter at AgentMark and instrument Agno

Use your AgentMark API key and app id from project settings.
from openinference.instrumentation.agno import AgnoInstrumentor
from opentelemetry.sdk.trace import TracerProvider
from opentelemetry.sdk.trace.export import BatchSpanProcessor
from opentelemetry.exporter.otlp.proto.http.trace_exporter import OTLPSpanExporter

provider = TracerProvider()
provider.add_span_processor(
    BatchSpanProcessor(
        OTLPSpanExporter(
            endpoint="https://api.agentmark.co/v1/traces",
            headers={
                "Authorization": "<YOUR_API_KEY>",  # raw key, no "Bearer" prefix
                "X-Agentmark-App-Id": "<YOUR_APP_ID>",
            },
        )
    )
)

AgnoInstrumentor().instrument(tracer_provider=provider)
3

Run your agent

Run your Agno agent as usual. Each agent run, model call, and tool call arrives in AgentMark as a span, grouped into a trace. See Traces and logs.

​
What AgentMark captures

Agno spans use the OpenInference attribute conventions — model, token usage, input and output messages, tool calls, settings, and span kind are all mapped onto AgentMark’s normalized trace fields, and token counts feed cost tracking. See OpenInference for the full attribute mapping.

​
Next steps

OpenInference

How AgentMark reads OpenInference attributes

Traces and logs

Explore traces once they arrive

​
Have questions?

Reach out any time: