LangWatch Integration

Register the OpenInference AgnoInstrumentor through langwatch.setup() so a YFinance stock-price agent reports spans to LangWatch.

Demonstrates instrumenting an Agno agent and sending traces to LangWatch.

langwatch_op.py

"""
LangWatch Integration
=====================

Demonstrates instrumenting an Agno agent and sending traces to LangWatch.
"""

import langwatch
from agno.agent import Agent
from agno.models.openai import OpenAIChat
from agno.tools.yfinance import YFinanceTools
from openinference.instrumentation.agno import AgnoInstrumentor

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


# ---------------------------------------------------------------------------
# Create Agent
# ---------------------------------------------------------------------------
agent = Agent(
    name="Stock Price Agent",
    model=OpenAIChat(id="gpt-5.2"),
    tools=[YFinanceTools()],
    instructions="You are a stock price agent. Answer questions in the style of a stock analyst.",
    debug_mode=True,
)


# ---------------------------------------------------------------------------
# Run Example
# ---------------------------------------------------------------------------
if __name__ == "__main__":
    agent.print_response("What is the current price of Tesla?")

Run the Example

1. Set up your virtual environment

   Mac

   uv venv --python 3.12
   source .venv/bin/activate
   

   uv venv --python 3.12
   .venv\Scripts\activate
   
2. Install dependencies

   uv pip install -U agno langwatch openai openinference-instrumentation-agno yfinance
   
3. Export your API keys

   Mac/Linux

   export LANGWATCH_API_KEY="your_langwatch_api_key_here"
   export OPENAI_API_KEY="your_openai_api_key_here"
   

   $Env:LANGWATCH_API_KEY="your_langwatch_api_key_here"
   $Env:OPENAI_API_KEY="your_openai_api_key_here"
   
4. Run the example

   Save the code above as langwatch_op.py, then run:

   python langwatch_op.py
   

Full source: cookbook/observability/langwatch_op.py