How to beginner · 3 min read

AgentOps key features

Q: AgentOps key features

The agentops Python SDK provides automatic tracking of AI agent interactions, session management for observability, and seamless integration with OpenAI clients. It enables developers to monitor and analyze LLM calls with minimal code changes.

Quick answer

The agentops Python SDK provides automatic tracking of AI agent interactions, session management for observability, and seamless integration with OpenAI clients. It enables developers to monitor and analyze LLM calls with minimal code changes.

PREREQUISITES

Python 3.8+
AgentOps API key
OpenAI API key
pip install agentops openai>=1.0

Setup

Install the agentops Python package and set your API keys as environment variables. This enables automatic instrumentation of OpenAI API calls for observability.

Install packages: pip install agentops openai
Set environment variables: AGENTOPS_API_KEY and OPENAI_API_KEY

bash

pip install agentops openai

output

Collecting agentops
Collecting openai
Successfully installed agentops-1.0.0 openai-1.0.0

Step by step

Initialize agentops with your API key to enable automatic tracking. Use the OpenAI OpenAI client as usual. Start and end sessions manually to group calls and add tags.

python

import os
from openai import OpenAI
import agentops

# Initialize AgentOps with API key from environment
agentops.init(api_key=os.environ["AGENTOPS_API_KEY"])

# Create OpenAI client
client = OpenAI(api_key=os.environ["OPENAI_API_KEY"])

# Start a session with tags
session = agentops.start_session(tags=["example-agent"])

# Make a chat completion call
response = client.chat.completions.create(
    model="gpt-4o-mini",
    messages=[{"role": "user", "content": "Hello, AgentOps!"}]
)
print("Response:", response.choices[0].message.content)

# End the session
agentops.end_session("Success")

output

Response: Hello, AgentOps!

Common variations

You can use agentops with asynchronous OpenAI calls by initializing agentops the same way. The SDK automatically instruments OpenAI calls for tracing. You can also rely on automatic session tracking without manual start/end calls.

For other LLM providers, agentops supports auto-instrumentation if compatible or manual tracking via custom wrappers.

python

import asyncio
import os
from openai import OpenAI
import agentops

agentops.init(api_key=os.environ["AGENTOPS_API_KEY"])
client = OpenAI(api_key=os.environ["OPENAI_API_KEY"])

async def main():
    response = await client.chat.completions.create(
        model="gpt-4o-mini",
        messages=[{"role": "user", "content": "Async call with AgentOps"}]
    )
    print("Async response:", response.choices[0].message.content)

asyncio.run(main())

output

Async response: Async call with AgentOps

Troubleshooting

If you see no tracking data in the AgentOps dashboard, verify your AGENTOPS_API_KEY is set correctly and agentops.init() is called before any OpenAI client usage.
For missing session tags, ensure you call agentops.start_session() with tags before making API calls.
If OpenAI calls fail, check your OPENAI_API_KEY and network connectivity.

✅

Key Takeaways

agentops auto-instruments OpenAI API calls for seamless AI agent observability.
Use agentops.start_session() and agentops.end_session() to group and tag LLM interactions.
The SDK supports both synchronous and asynchronous OpenAI client usage with minimal code changes.

Verified 2026-04 · gpt-4o-mini

Verify ↗