> ## Documentation Index
> Fetch the complete documentation index at: https://agno-v2.mintlify.site/llms.txt
> Use this file to discover all available pages before exploring further.

# CrewAI Instantiation Performance Evaluation

> Measure CrewAI Agent instantiation over 1000 iterations with PerformanceEval, using a gpt-4o llm and a decorated weather tool.

Demonstrates agent instantiation benchmarking with CrewAI.

```python crewai_instantiation.py theme={null}
"""
CrewAI Instantiation Performance Evaluation
===========================================

Demonstrates agent instantiation benchmarking with CrewAI.
"""

from typing import Literal

from agno.eval.performance import PerformanceEval
from crewai.agent import Agent
from crewai.tools import tool


# ---------------------------------------------------------------------------
# Create Benchmark Tool
# ---------------------------------------------------------------------------
@tool("Tool Name")
def get_weather(city: Literal["nyc", "sf"]):
    """Use this to get weather information."""
    if city == "nyc":
        return "It might be cloudy in nyc"
    elif city == "sf":
        return "It's always sunny in sf"
    else:
        raise AssertionError("Unknown city")


tools = [get_weather]


# ---------------------------------------------------------------------------
# Create Benchmark Function
# ---------------------------------------------------------------------------
def instantiate_agent():
    return Agent(
        llm="gpt-5.6-luna",
        role="Test Agent",
        goal="Be concise, reply with one sentence.",
        tools=tools,
        backstory="Test",
    )


# ---------------------------------------------------------------------------
# Create Evaluation
# ---------------------------------------------------------------------------
crew_instantiation = PerformanceEval(func=instantiate_agent, num_iterations=1000)

# ---------------------------------------------------------------------------
# Run Evaluation
# ---------------------------------------------------------------------------
if __name__ == "__main__":
    crew_instantiation.run(print_results=True, print_summary=True)
```

## Run the Example

<Snippet file="create-venv-step.mdx" />

**1. Install dependencies**

```bash theme={null}
uv pip install -U agno crewai memory-profiler
```

**2. Run the example**

Save the code above as `crewai_instantiation.py`, then run:

```bash theme={null}
python crewai_instantiation.py
```

Full source: [cookbook/09\_evals/performance/comparison/crewai\_instantiation.py](https://github.com/agno-agi/agno/blob/v3.0.4/cookbook/09_evals/performance/comparison/crewai_instantiation.py)


This documentation is built and hosted on [Mintlify](https://mintlify.com), a developer documentation platform.