PydanticAI
ai.pydantic.dev
Agent framework from the Pydantic team with a strong emphasis on type safety and structured outputs. Uses Pydantic models for tool inputs and outputs, making agent behavior more predictable. Supports dependency injection, streamed responses, and testing.
More in Agent Core & Orchestration
Lightweight, high-performance agent framework formerly known as Phidata. Agents are pure Python classes with built-in memory, knowledge, tools, and reasoning. Supports multimodal agents and ships with a monitoring UI out of the box.
Multi-agent framework built on LlamaIndex for building production agentic pipelines. Implements a message-queue architecture with service discovery and a control plane for coordinating agents. Enables both local development and cloud deployment.
Durable execution platform for long-running, fault-tolerant workflows. Agents built on Temporal survive process crashes, network failures, and server restarts — state is automatically persisted and replayed, making it production-grade infrastructure for complex multi-step agents.
Minimal Go library for building message-passing agent systems with clean abstractions. Designed for developers who want full control over agent logic without opinionated orchestration overhead — ideal for embedding into existing Go services.
Role-playing multi-agent framework where agents take on specialized roles (researcher, writer, engineer) and collaborate toward a shared goal. Supports both sequential and hierarchical process flows with human-in-the-loop checkpoints.
Low-code interface to build, debug and evaluate multi-agent workflows powered by AutoGen. Provides a drag-and-drop UI for designing agent teams and testing their conversations. Ships with sample agents for coding, research, and data analysis.