Python SDK

Documentation for the Agentuity Python SDK

The Agentuity Python SDK provides a powerful framework for building AI agents in Python. It offers a comprehensive set of tools for creating, deploying, and managing agents with features like key-value storage, vector storage, and OpenTelemetry integration.

Installation

When you create a project with Agentuity, you will automatically have access to the Agentuity Python SDK.

agentuity new

The SDK currently works with Python and the project will automatically install the correct dependencies.

Prerequisites

Before using the Agentuity Python SDK, ensure you have the following prerequisites installed:

  • Python: Version 3.10 or higher is required

Installing Python

You can download and install Python from the official website. Make sure to install version 3.10 or higher.

Installing UV

UV is an optional but recommended package manager for Python. You can install it using the following command:

curl -LsSf https://astral.sh/uv/install.sh | sh

For more information, visit the UV installation documentation.

Development

You can start your project by running the following command:

agentuity dev

This will start your project in development mode and open a new browser window connecting your Agent to the Agentuity Console in Live Mode.

You can also start your project in development mode without connecting to the Agentuity Console by running the following command:

uv run server.py

If you would like to manually test your Agents locally, you can do so by running the following command:

curl -v http://localhost:3500/run/agent_ID --json '{"input": "Hello, world!"}'

Make sure you replace agent_ID with the ID of your Agent.

Next Steps

  • Core Concepts - Learn about the fundamental concepts of the Agentuity Python SDK
  • LLM - Learn about the LLM integrations available in the Agentuity Python SDK
  • Frameworks - Learn about using frameworks with the Agentuity Python SDK
  • API Reference - Explore the detailed API documentation

On this page