Langwatch

This example shows how to instrument your agno agent and send traces to LangWatch.

Code

cookbook/integrations/observability/langwatch_op.py

import langwatch
from agno.agent import Agent
from agno.models.openai import OpenAIChat
from agno.tools.duckduckgo import DuckDuckGoTools
from openinference.instrumentation.agno import AgnoInstrumentor

# Initialize LangWatch and instrument Agno
langwatch.setup(instrumentors=[AgnoInstrumentor()])

# Create and configure your Agno agent
agent = Agent(
    name="Stock Price Agent",
    model=OpenAIChat(id="gpt-5-mini"),
    tools=[DuckDuckGoTools()],
    instructions="You are an internet search agent. Find and provide accurate information on any topic.",
    debug_mode=True,
)

agent.print_response("What are the latest developments in artificial intelligence?")

Usage

1. Create a virtual environment

   Open the Terminal and create a python virtual environment.

   Mac

   python3 -m venv .venv
   source .venv/bin/activate
   
2. Set your API key

   - Sign up for an account at https://app.langwatch.ai/.
   - Set your LangWatch API key as an environment variables:
   ```bash
   export LANGWATCH_API_KEY=<your-key>
   

   </Step>
   
   <Step title="Install libraries">
   ```bash
   pip install -U agno openai ddgs langwatch openinference-instrumentation-agno
   
3. Run Agent

   Mac

   python cookbook/integrations/observability/langwatch_op.py