This guide demonstrates how to use TrueFoundry OtelCollector along with the Traceloop SDK to instrument google ADK agent code. In this example, the Google agent is a research agent which researches the latest trends to conduct detailed market research with keen attention to detail. For example, it can generate “A comprehensive report on AI and machine learning.”
1

Create Tracing Project, API Key and copy tracing code

Follow the instructions in Getting Started to create a tracing project, generate API key and copy the tracing code.
2

Install Dependencies

First, you need to install the following
pip install traceloop-sdk google-adk litellm dotenv
3

Add Tracing code to Google ADK agents

For CrewAI agents, we need to add the Traceloop.init() call to the application. The Traceloop SDK will automatically trace all agent activities.
CrewAI Code
import asyncio
import random
import os
from dotenv import load_dotenv

from traceloop.sdk import Traceloop
from traceloop.sdk.decorators import tool

from google.adk import Agent, Runner
from google.adk.sessions import InMemorySessionService
from google.genai import types
from google.adk.models.lite_llm import LiteLlm

load_dotenv()

TFY_API_KEY = os.environ.get("TFY_API_KEY")
Traceloop.init(
    api_endpoint="https://internal.devtest.truefoundry.tech/api/otel",
    app_name="your tracing application name",
    headers = {
        "Authorization": f"Bearer {TFY_API_KEY}",
        "TFY-Tracing-Project": "tracing-project:truefoundry/Tracing-test/google-adk",
    }
)


 # # --- Constants ---
MODEL_GPT_4O = "openai/gpt-4.1"
APP_NAME = "trending_topic_app"
USER_ID = "user_1"
SESSION_ID = "session_001"


@tool(name="get_random_topic")
def get_random_topic() -> str:
    """Get a random topic from a list of AI-related subjects for research."""
    words = [
        "AI", "Machine Learning", "Data Science", "Deep Learning",
        "Computer Vision", "Natural Language Processing", "Robotics",
        "Blockchain", "Quantum Computing", "Gen AI", "LLMs", "RAG",
        "LLM Agents", "LLM Tool Calling", "LLM Planning", "LLM Self-Reflection"
    ]
    return random.choice(words)

agent = Agent(
    name="trending_topic_agent",
    model=LiteLlm(
        model=MODEL_GPT_4O,
    ),
    description="Expert in AI with keen attention to detail.",
    instruction=(
        "You are an AI assistant that analyzes trends in AI. "
        "When the user asks for a trending topic, use the `get_random_topic` tool "
        "to pick a topic, then provide a brief summary of recent developments in that area."
    ),
    tools=[get_random_topic],
)
 
session_service = InMemorySessionService()
  
# create the session once
async def setup():
    await session_service.create_session(
        app_name=APP_NAME, user_id=USER_ID, session_id=SESSION_ID
    )

asyncio.run(setup())
 
runner = Runner(agent=agent, app_name=APP_NAME, session_service=session_service)
 
user_msg = types.Content(role="user", parts=[types.Part(text="What is the latest trend in AI?")])

for event in runner.run(user_id=USER_ID, session_id=SESSION_ID, new_message=user_msg):
    if event.is_final_response():
        print(event.content.parts[0].text)
4

Run your application and view logged trace