CrewAI

CrewAI is an open-source Python framework for orchestrating autonomous AI agents and building production-ready multi-agent workflows, built around two layered abstractions:

  1. A crew, which is a team of role-based agents that collaborate to complete a shared objective
  2. A flow, which manages application state, event-driven execution, and control logic across one or more crews.

Each agent in a crew is defined by a role, a goal, and a backstory, and can be equipped with built-in or custom tools for web search, file operations, and external API calls.

CrewAI includes a unified memory system, a single Memory class that consolidates what were previously separate short-term, long-term, entity, and external memory types, and it supports multiple LLM providers including OpenAI, Anthropic, and locally hosted models. It allows agents and tasks to be declared in YAML or configured through Python APIs.

Official website: crewai.com

PydanticAI: Typed LLM Agents With Structured Outputs

Tutorial

Pydantic AI: Build Type-Safe LLM Agents in Python

Learn how to use Pydantic AI to build type-safe LLM agents in Python with structured outputs, function calling, and dependency injection patterns.

intermediate ai

For additional information on related topics, take a look at the following resources:

By Leodanis Pozo Ramos • Updated July 13, 2026
AI Coding Tools Share Feedback