agentica-sdk

Develop Python AI agents with the Agentica SDK using decorators and spawn().

8|1|Updated Jan 4, 2026
One-click install
npx skills add https://github.com/scooter-lacroix/Maestro --skill agentica-sdk
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: agentica-sdk
Source: https://github.com/scooter-lacroix/Maestro/tree/main/maestro/skills/agentica-sdk
Command: npx skills add https://github.com/scooter-lacroix/Maestro --skill agentica-sdk

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

This Skill simplifies the creation and management of AI agents in Python, enabling developers to build sophisticated multi-agent systems with features like state persistence, tool integration, and advanced model selection.

Core Features & Use Cases

  • Agentic Functions: Define agents using the @agentic decorator for simple function-like agents.
  • Spawned Agents: Create more complex agents with spawn() for greater control over premise, scope, and model.
  • Persistence: Enable agents to remember conversation history and state across calls.
  • Tool Integration: Easily pass tools and functions into agent scopes for them to use.
  • Model Selection: Choose from a variety of LLM providers and models.
  • Use Case: Develop a customer support agent that can access a knowledge base, remember past interactions, and escalate complex issues to a human agent.

Quick Start

Use the agentica-sdk skill to create a simple agent that adds two numbers.

Frequently Asked Questions about agentica-sdk

High-intent search queries and answers about installing and using this skill.

FAQPage Schema
How do I build a Python multi-agent system?

To build a Python multi-agent system, you can use the Agentica SDK to define agents with the @agentic decorator for simple functions or spawn() for complex agents needing custom premises and model selection.

How do I add memory and state persistence to Python AI agents?

Adding memory and state persistence to Python AI agents is supported natively by Agentica SDK, enabling agents to remember conversation history and maintain state across multiple calls automatically.

Does Agentica SDK support tool integration and MCP integration?

Yes, Agentica SDK supports tool integration and MCP integration, allowing you to pass tools and functions into agent scopes and connect to external tool servers for extended capabilities.

What is the best way to scope tools for different LLM agents?

The best way to scope tools for different LLM agents is using Agentica SDK's flexible tool scoping features, which allow fine-grained control over which tools specific agents can access during execution.

Can I enforce typed outputs from Python AI agents?

Yes, you can enforce typed outputs from Python AI agents using Agentica SDK, which provides native support for typed outputs to ensure agents return structured and predictable data formats.

How do I instantiate multiple AI agents in Python?

Instantiating multiple AI agents in Python is done using the Agentica SDK's spawn() function, which provides granular control over each agent's premise, scope, model selection, and token limits.