Skip to main content
This example shows how to enable tracing for an agent. Once tracing is enabled, all agent runs, model calls, and tool executions are automatically captured and stored in your database.
1

Create a Python file

touch basic_agent_tracing.py
2

Add the following code to your Python file

basic_agent_tracing.py
from agno.agent import Agent
from agno.db.sqlite import SqliteDb
from agno.models.openai import OpenAIChat
from agno.tools.hackernews import HackerNewsTools
from agno.tracing import setup_tracing

# Set up database for traces
db = SqliteDb(db_file="tmp/traces.db")

# Enable tracing (call once at startup)
setup_tracing(db=db)

# Create agent - automatically traced!
agent = Agent(
    name="HackerNews Agent",
    model=OpenAIChat(id="gpt-5-mini"),
    tools=[HackerNewsTools()],
    instructions="You are a hacker news agent. Answer questions concisely.",
    markdown=True,
    db=db,
)

# Run the agent - traces are captured automatically
agent.print_response("What's trending on HackerNews?")

# Query traces from the database
traces, count = db.get_traces(agent_id=agent.id, limit=10)
print(f"\nFound {count} traces for agent '{agent.name}'")
for trace in traces:
    print(f"  - {trace.name}: {trace.duration_ms}ms ({trace.status})")
3

Create a virtual environment

Open the Terminal and create a python virtual environment.
python3 -m venv .venv
source .venv/bin/activate
4

Install libraries

pip install -U openai agno opentelemetry-api opentelemetry-sdk openinference-instrumentation-agno
5

Export your OpenAI API key

export OPENAI_API_KEY="your_openai_api_key_here"
6

Run the agent

python basic_agent_tracing.py

​
Developer Resources

  • View the Cookbook for a full example that visualizes the trace tree in CLI.