# Agent Instantiation Performance Evaluation (/examples/evals/performance/instantiate-agent)



Demonstrates measuring agent instantiation performance.

This evaluation performs 2,010 callable invocations: 10 warm-ups, 1,000 runtime measurements, and 1,000 memory measurements. It measures construction, not model inference.

`PerformanceEval` runs the callable separately for each enabled metric: warm-ups first, then runtime measurements, then memory measurements. `num_iterations` applies to each metric, and the default is 10 additional warm-up calls. Model retries, tools, delegation, and memory extraction can add provider requests beyond the callable count.

Memory measurements use Python’s `tracemalloc`; they do not measure process RSS, GPU memory, database-server memory, or remote model memory. Record dependency versions, database state, and model settings when comparing results.

```python title="instantiate_agent.py"
"""
Agent Instantiation Performance Evaluation
==========================================

Demonstrates measuring agent instantiation performance.
"""

from agno.agent import Agent
from agno.eval.performance import PerformanceEval


# ---------------------------------------------------------------------------
# Create Benchmark Function
# ---------------------------------------------------------------------------
def instantiate_agent():
    return Agent(system_message="Be concise, reply with one sentence.")


# ---------------------------------------------------------------------------
# Create Evaluation
# ---------------------------------------------------------------------------
instantiation_perf = PerformanceEval(
    name="Instantiation Performance", func=instantiate_agent, num_iterations=1000
)

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

## Run the Example [#run-the-example]

<Steps>
    <Step title="Set up your virtual environment">
      <CodeBlockTabs defaultValue="Mac">
        <CodeBlockTabsList>
          <CodeBlockTabsTrigger value="Mac">
            Mac
          </CodeBlockTabsTrigger>

          <CodeBlockTabsTrigger value="Windows">
            Windows
          </CodeBlockTabsTrigger>
        </CodeBlockTabsList>

        <CodeBlockTab value="Mac">
          ```bash
          uv venv --python 3.12
          source .venv/bin/activate
          ```
        </CodeBlockTab>

        <CodeBlockTab value="Windows">
          ```bash
          uv venv --python 3.12
          .venv\Scripts\activate
          ```
        </CodeBlockTab>
      </CodeBlockTabs>
    </Step>

  <Step title="Install dependencies">
    ```bash
    uv pip install -U agno
    ```
  </Step>

  <Step title="Run the example">
    Save the code above as `instantiate_agent.py`, then run:

    ```bash
    python instantiate_agent.py
    ```
  </Step>
</Steps>

Full source: [cookbook/09\_evals/performance/instantiate\_agent.py](https://github.com/agno-agi/agno/blob/8f36eaf2d18e91afa7b327eec66a3cd3685dcb87/cookbook/09_evals/performance/instantiate_agent.py)