Chapter 1: Getting Started

April 13, 2026 ยท View on GitHub

Welcome to Chapter 1: Getting Started. In this part of Agno Tutorial: Multi-Agent Systems That Learn Over Time, you will build an intuitive mental model first, then move into concrete implementation details and practical production tradeoffs.

This chapter gets your first Agno agent running with persistent storage and learning enabled.

Learning Goals

  • create and run a first Agno agent
  • enable storage-backed memory behavior
  • validate learning mode and session continuity
  • confirm model connectivity

Minimal Example

from agno.agent import Agent
from agno.db.sqlite import SqliteDb
from agno.models.openai import OpenAIResponses

agent = Agent(
    model=OpenAIResponses(id="gpt-5.2"),
    db=SqliteDb(db_file="tmp/agents.db"),
    learning=True,
)

First Validation Checklist

  1. initial response succeeds
  2. follow-up recalls prior context
  3. persisted state survives process restart
  4. logs show expected execution path

Source References

Summary

You now have an Agno baseline with persistent memory and learning enabled.

Next: Chapter 2: Framework Architecture

Source Code Walkthrough

libs/agno/agno/agent/agent.py

The core Agent class in libs/agno/agno/agent/agent.py is the primary entry point for Chapter 1. Creating your first agent means instantiating this class with a model and optional tools. The constructor parameters map directly to the concepts introduced in the getting started chapter: model, tools, instructions, markdown, and debug_mode.