Skip to main content
  1. Sign up — Create an account at platform.respan.ai
  2. Create an API key — Generate one on the API keys page
  3. Add credits or a provider key — Add credits on the Credits page or connect your own provider key on the Integrations page

​
What is Agno?

Agno is a Python framework for building AI agents with built-in OpenInference instrumentation. Use the Respan Agno exporter to capture Agno spans (via OpenInference + OpenTelemetry) and send them to Respan tracing.
Make sure you have an OpenTelemetry TracerProvider with a SpanProcessor configured before running your agent (otherwise spans will not be exported).
How Respan Agno integration works

​
Setup

1

Install packages

pip install agno openinference-instrumentation-agno respan-exporter-agno
2

Set environment variables

.env
RESPAN_API_KEY=your-respan-api-key
RESPAN_BASE_URL=https://api.respan.ai/api

# If calling OpenAI directly (without Respan gateway):
OPENAI_API_KEY=your-openai-api-key
3

Instrument and run an agent

import os
from agno.agent import Agent
from agno.models.openai import OpenAIChat
from openinference.instrumentation.agno import AgnoInstrumentor
from opentelemetry import trace as trace_api
from opentelemetry.sdk import trace as trace_sdk
from opentelemetry.sdk.trace.export import SimpleSpanProcessor
from opentelemetry.sdk.trace.export.in_memory_span_exporter import InMemorySpanExporter
from respan_exporter_agno import RespanAgnoInstrumentor

def main():
    respan_api_key = os.getenv("RESPAN_API_KEY")
    base_url = os.getenv("RESPAN_BASE_URL", "https://api.respan.ai/api")

    # Set up TracerProvider
    tracer_provider = trace_api.get_tracer_provider()
    if not isinstance(tracer_provider, trace_sdk.TracerProvider):
        tracer_provider = trace_sdk.TracerProvider()
        trace_api.set_tracer_provider(tracer_provider)
    tracer_provider.add_span_processor(SimpleSpanProcessor(InMemorySpanExporter()))

    # Export Agno spans to Respan
    RespanAgnoInstrumentor().instrument(
        api_key=respan_api_key,
        base_url=base_url,
        passthrough=False,
    )

    # Create Agno spans (OpenInference)
    AgnoInstrumentor().instrument()

    agent = Agent(
        name="Respan Agno Quickstart Agent",
        model=OpenAIChat(
            id=os.getenv("OPENAI_MODEL", "gpt-4o-mini"),
            api_key=respan_api_key,
            base_url=base_url,
        ),
    )

    agent.run("hello from Respan Agno exporter quickstart")
    tracer_provider.force_flush()

if __name__ == "__main__":
    main()
4

View your trace

Open the Traces page in the Respan dashboard.
Agno quickstart tracing in Respan

​
Observability

With this integration, Respan auto-captures:
  • Agent runs — each agent execution as a span
  • LLM calls — model, input/output messages, token usage
  • Errors — failed runs and error details
View traces on the Traces page.