Disable warnings about experimental skills and memory features

[wigging]

I'm using Python 3.14 and agent-framework-openai 1.8.2 and I get the following warnings

/Users/homer/Desktop/agents-example/.venv/lib/python3.14/site-packages/agent_framework/_skills.py:121:
ExperimentalWarning: [SKILLS] SkillResource is experimental and may change or be removed in future versions without notice.

/Users/homer/Desktop/agents-example/.venv/lib/python3.14/site-packages/agent_framework/_harness/_memory.py:651:
ExperimentalWarning: [HARNESS] MemoryStore is experimental and may change or be removed in future versions without notice.

when I run an agent like in the following code

import asyncio

from agent_framework import Agent
from agent_framework.openai import OpenAIChatClient
from dotenv import load_dotenv

async def main():
    """Run this example."""
    load_dotenv()

    client = OpenAIChatClient(model="gpt-5.5")
    agent = Agent(client=client, instructions="You are a funny agent.")
    result = await agent.run("What is the capital of France?")

    print(f"\nAgent:\n{result}")

if __name__ == "__main__":
    asyncio.run(main())

Is there a way to disable the warnings shown above when I use Agent Framework in a Python project?

[eavanvalkenburg]

thanks @wigging I need to have a look to see when the harness and skills are triggering the warning, but in general, you can do this:

import warnings
warnings.filterwarnings("ignore", message=r"\[SKILLS\].*", category=FutureWarning)

[wigging]

HARNESS needs to be in the message too.

warnings.filterwarnings(
    "ignore", message=r"\[(SKILLS|HARNESS)\].*", category=FutureWarning
)

[wigging]

Hopefully you can update Agent Framework to not emit these warnings so they don't have to be explicitly ignored.

[eavanvalkenburg]

yeah, working on that