Agno | Respan Docs

Agno is a Python framework for building AI agents with built-in reasoning, tool use, and OpenInference instrumentation. Respan gives you full observability over every agent run, model call, and tool invocation — and gateway routing through the OpenAI-compatible Respan endpoint.

Set up Respan

Create an account at platform.respan.ai and grab an API key. For gateway, also add credits or a provider key.

Run npx @respan/cli setup to set up with your coding agent.

Example projects

Python examples

Tracing

Gateway

Setup

Install packages

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

Set environment variables

$ export OPENAI_API_KEY="YOUR_OPENAI_API_KEY"
$ export RESPAN_API_KEY="YOUR_RESPAN_API_KEY"

OPENAI_API_KEY is used for LLM requests. RESPAN_API_KEY is used to export traces to Respan.

Initialize and run

1 import os
2 from agno.agent import Agent
3 from agno.models.openai import OpenAIChat
4 from respan_exporter_agno import RespanAgnoInstrumentor
5 
6 RespanAgnoInstrumentor.instrument(api_key=os.environ["RESPAN_API_KEY"])
7 
8 agent = Agent(
9     model=OpenAIChat(id="gpt-4.1-nano"),
10     instructions="You are a helpful assistant.",
11 )
12 agent.print_response("Tell me a joke about AI")

View your trace

Open the Traces page to see your agent run with model spans, tool calls, and reasoning steps.

Configuration

Parameter	Type	Default	Description
`api_key`	`str`	`RESPAN_API_KEY` env var	Respan API key.
`endpoint`	`str \| None`	`None`	Custom ingest endpoint URL.
`base_url`	`str \| None`	`None`	API base URL.
`environment`	`str \| None`	`None`	Environment label.
`customer_identifier`	`str \| None`	`None`	Default customer identifier.

See the Agno Exporter SDK reference for the full API.