Agent Instantiation Performance Evaluation

Measure runtime and memory of 1000 bare Agno Agent constructions with only a system message.

Demonstrates measuring agent instantiation performance.

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

1. Set up your virtual environment

   Mac

   uv venv --python 3.12
   source .venv/bin/activate
   
2. Install dependencies

   uv pip install -U agno memory-profiler
   
3. Run the example

   Save the code above as instantiate_agent.py, then run:

   python instantiate_agent.py
   

Full source: cookbook/09_evals/performance/instantiate_agent.py