OpenAI Swarm
github.com
Lightweight experimental multi-agent orchestration framework from OpenAI. Uses handoffs and routines as core primitives, making it easy to build networks of specialized agents. Stateless by design — great for learning agent patterns.
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.