CAMEL-AI is the first large language model (LLM) multi-agent framework and an open-source community dedicated to finding the scaling law of agents. Checkout their comprehensive documentation here.

Adding AgentOps to CAMEL agents

1

Install the AgentOps SDK

pip install agentops
2

Install CAMEL-AI with all dependencies

pip install "camel-ai[all]==0.2.11"
3

Add AgentOps code to your code

Make sure to call agentops.init before calling any openai, cohere, crew, etc models.

import agentops
agentops.init(<INSERT YOUR API KEY HERE>)

# your code here

agentops.end_session("Success") # Success|Fail|Indeterminate

Set your API key as an .env variable for easy access.

AGENTOPS_API_KEY=<YOUR API KEY>

Read more about environment variables in Advanced Configuration

4

Run your agent

Execute your program and visit app.agentops.ai/drilldown to observe your CAMEL Agent! πŸ•΅οΈ

After your run, AgentOps prints a clickable url to console linking directly to your session in the Dashboard

Clickable link to session

Full Examples

Single Agent Example with Tools

Here’s a simple example of tracking a single CAMEL agent with tools using AgentOps:

import agentops
import os
from camel.agents import ChatAgent
from camel.messages import BaseMessage
from camel.models import ModelFactory
from camel.types import ModelPlatformType, ModelType

# Initialize AgentOps
agentops.init(os.getenv("AGENTOPS_API_KEY"))

# Import toolkits after AgentOps init for tracking
from camel.toolkits import SearchToolkit

# Set up the agent with search tools
sys_msg = BaseMessage.make_assistant_message(
    role_name='Tools calling operator',
    content='You are a helpful assistant'
)

# Configure tools and model
tools = [*SearchToolkit().get_tools()]
model = ModelFactory.create(
    model_platform=ModelPlatformType.OPENAI,
    model_type=ModelType.GPT_4O_MINI,
)

# Create the agent
camel_agent = ChatAgent(
    system_message=sys_msg,
    model=model,
    tools=tools,
)

# Run the agent
user_msg = 'What is CAMEL-AI.org?'
response = camel_agent.step(user_msg)
print(response)

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

Multi-Agent Example

Check out the example notebook here to see how to track multi-agent setups.