Skip to main content

​
Virtual Environment Setup

setup.sh
python3 -m venv .venv
source .venv/bin/activate
pip install "xpander-sdk[agno]"

​
Environment Setup

The .env file is created when you download your agent code:
xpander init
This downloads your agent code from the platform with the .env file pre-configured with your keys.
custom_tools_example.py
from dotenv import load_dotenv
load_dotenv()

from xpander_sdk import Backend, register_tool
from agno.agent import Agent

@register_tool 
def weather_check(location: str) -> str:
    """Check weather for a location"""
    return f"Weather in {location}: Sunny, 25°C"

backend = Backend()
agno_agent = Agent(**backend.get_args())

agno_agent.print_response(message="What's the weather in Tel Aviv?")

​
How to Run

custom_tools_example.py
python custom_tools_example.py
This example shows automatic tool discovery where the agent recognizes it needs weather information, calls the custom weather_check tool seamlessly during conversation, and uses the tool’s response to provide a complete answer. Tools are registered with type hints and docstrings that help the AI understand their purpose and usage.

​
Production Deployment

For creating and deploying agents to production, see the Setup and Deployment Guide.
⌘I