Skip to content

Python SDK for AI agent monitoring, LLM cost tracking, benchmarking, and more. Integrates with most LLMs and agent frameworks including CrewAI, Agno, OpenAI Agents SDK, Langchain, Autogen, AG2, and CamelAI

4.2 KB
Raw Blame
---
title: AG2
description: "Track and analyze your AG2 agents with AgentOps"
---

[AG2](https://ag2.ai/) (formerly AutoGen) is a framework for building multi-agent conversational AI systems. AgentOps provides seamless, automatic instrumentation for AG2 — just call `agentops.init()` and all agent interactions are tracked.

## Installation

<CodeGroup>
  ```bash pip
  pip install agentops pyautogen
  ```
  ```bash poetry
  poetry add agentops pyautogen
  ```
  ```bash uv
  uv pip install agentops pyautogen
  ```
</CodeGroup>

## Setting Up API Keys

Before using AG2 with AgentOps, you need to set up your API keys. You can obtain:
- **OPENAI_API_KEY**: From the [OpenAI Platform](https://platform.openai.com/api-keys)
- **AGENTOPS_API_KEY**: From your [AgentOps Dashboard](https://app.agentops.ai/)

Then to set them up, you can either export them as environment variables or set them in a `.env` file.

<CodeGroup>
    ```bash Export to CLI
    export OPENAI_API_KEY="your_openai_api_key_here"
    export AGENTOPS_API_KEY="your_agentops_api_key_here"
    ```
    ```txt Set in .env file
    OPENAI_API_KEY="your_openai_api_key_here"
    AGENTOPS_API_KEY="your_agentops_api_key_here"
    ```
</CodeGroup>

Then load the environment variables in your Python code:

```python
from dotenv import load_dotenv
import os

# Load environment variables from .env file
load_dotenv()

# Set up environment variables with fallback values
os.environ["OPENAI_API_KEY"] = os.getenv("OPENAI_API_KEY")
os.environ["AGENTOPS_API_KEY"] = os.getenv("AGENTOPS_API_KEY")
```

## Usage

Initialize AgentOps at the beginning of your application to automatically track all AG2 agent interactions:

<CodeGroup> 
```python Single Agent Conversation
import agentops
import autogen
import os

# Initialize AgentOps
agentops.init()

# Configure your AG2 agents
config_list = [
    {
        "model": "gpt-4",
        "api_key": os.getenv("OPENAI_API_KEY"),
    }
]

llm_config = {
    "config_list": config_list,
    "timeout": 60,
}

# Create a single agent
assistant = autogen.AssistantAgent(
    name="assistant",
    llm_config=llm_config,
    system_message="You are a helpful AI assistant."
)

user_proxy = autogen.UserProxyAgent(
    name="user_proxy",
    human_input_mode="TERMINATE",
    max_consecutive_auto_reply=10,
    is_termination_msg=lambda x: x.get("content", "").rstrip().endswith("TERMINATE"),
    code_execution_config={"last_n_messages": 3, "work_dir": "coding"},
)

# Initiate a conversation
user_proxy.initiate_chat(
    assistant,
    message="How can I implement a basic web scraper in Python?"
)
```
</CodeGroup>

## Examples

<CardGroup cols={2}>
  <Card title="AG2 Async Agent Chat" icon="notebook" href="/v2/examples/ag2">
   AG2 Async Agent Chat with Automated Responses
  </Card>
  <Card title="Async Human Input" icon="notebook" href="https://github.com/AgentOps-AI/agentops/blob/main/examples/ag2/ag2_async_agent.ipynb" newTab={true}>
    Demonstrates asynchronous human input with AG2 agents.
  </Card>
  <Card title="Wikipedia Search Tool" icon="notebook" href="https://github.com/AgentOps-AI/agentops/blob/main/examples/ag2/tools_wikipedia_search.ipynb" newTab={true}>
    Example of AG2 agents using a Wikipedia search tool.
  </Card>
  <Card title="Multi-Agent Group Chat" icon="notebook" href="https://github.com/AgentOps-AI/agentops/blob/main/examples/ag2/groupchat.py" newTab={true}>
    Orchestrate a team of specialized agents (researcher, coder, critic) with full AgentOps tracing.
  </Card>
</CardGroup>

## Resources

<CardGroup cols={2}>
  <Card title="AG2 - AgentOps Ecosystem Docs" icon="book" href="https://docs.ag2.ai/latest/docs/ecosystem/agentops/" newTab={true}>
    Official AG2 documentation on integrating with AgentOps.
  </Card>
  <Card title="AG2 OpenTelemetry Tracing" icon="blog" href="https://docs.ag2.ai/latest/docs/blog/2026/02/08/AG2-OpenTelemetry-Tracing/" newTab={true}>
    Full observability for multi-agent systems with AG2's built-in tracing.
  </Card>
</CardGroup>

<script type="module" src="/scripts/github_stars.js"></script>
<script type="module" src="/scripts/scroll-img-fadein-animation.js"></script>
<script type="module" src="/scripts/button_heartbeat_animation.js"></script>
<script type="css" src="/styles/styles.css"></script>