Skip to main content
Tool result caching is designed to avoid unnecessary recomputation by storing the results of function calls on disk. This is useful during development and testing to speed up the development process, avoid rate limiting, and reduce costs. This is supported for all Agno Toolkits

​
Example

Pass cache_results=True to the Toolkit constructor to enable caching for that Toolkit.
cache_tool_calls.py
import asyncio

from agno.agent import Agent
from agno.models.openai import OpenAIChat
from agno.tools.duckduckgo import DuckDuckGoTools

agent = Agent(
    model=OpenAIChat(id="gpt-4o-mini"),
    tools=[DuckDuckGoTools(search=True, news=True)],
    show_tool_calls=True,
)

asyncio.run(
    agent.aprint_response(
        "What is the latest news about technology and search for recent AI developments?",
        markdown=True,
    )
)