lobehub/lobehub
LobeHub is a platform that enables multi-agent collaboration and human-agent co-evolution by treating AI agents as units of work, providing tools to build, manage, and collaborate with AI agent teams seamlessly.
Awesome MCP › Agent Orchestration Platforms
openai/swarm
Swarm is an educational framework developed by the OpenAI Solutions team that explores ergonomic and lightweight multi-agent orchestration. It is designed to facilitate coordination and execution among multiple agents in a scalable, controllable, and testable manner. The framework introduces two core abstractions: Agents and handoffs. An Agent is defined by its instructions and tools, and it can hand off conversations to other Agents, enabling complex interactions and workflows. Swarm operates statelessly, powered by the Chat Completions API, and runs primarily on the client side without storing state between calls. Swarm is intended as an educational resource for developers interested in multi-agent orchestration patterns that are lightweight and customizable. It is particularly useful for scenarios involving numerous independent capabilities and instructions that are challenging to consolidate into a single prompt. The framework supports function calling, context variables, and streaming responses, allowing developers to build rich, real-world multi-agent systems. Swarm is not related to the Assistants API, which provides fully-hosted threads and memory management; instead, it offers a more hands-on approach to understanding agent coordination. The project includes various examples demonstrating fundamental concepts such as setup, function calling, handoffs, and context variables, as well as more complex use cases like customer service bots, personal shopping agents, and triage systems. Swarm's client.run() method manages the interaction loop, handling agent completions, tool executions, agent switching, and context updates until the conversation concludes. Although Swarm is experimental and has been replaced by the production-ready OpenAI Agents SDK, it remains a valuable educational tool for learning multi-agent orchestration techniques. Keywords: multi-agent orchestration, agent coordination, lightweight framework, educational, OpenAI, Chat Completions API, function calling, context variables, handoffs, stateless, client-side, scalable, customizable, multi-agent systems, agent handoff, streaming responses, experimental, OpenAI Agents SDK, examples, customer service bot, personal shopper, triage agent.
https://github.com/openai/swarm
Also in Agent Orchestration Platforms
tinyhumansai/openhuman
OpenHuman is a local-first personal AI assistant with persistent Markdown memory, multi-agent workflow orchestration, and research tools, connecting to 100+ OAuth integrations and thousands of MCP servers.
assafelovic/gpt-researcher
GPT Researcher is an autonomous AI agent that conducts deep local and web research on any topic, generating detailed, unbiased reports with citations and supporting integration with the Model Context Protocol (MCP) for enhanced data sourcing.
deepset-ai/haystack
Haystack is an open-source AI orchestration framework for building production-ready LLM applications in Python, enabling modular pipelines and agent workflows with explicit control over retrieval, ...
activepieces/activepieces
Activepieces is an open-source AI automation platform providing an extensible MCP toolkit and over 280 MCP servers for AI agents, designed for both technical and non-technical users.
superset-sh/superset
Superset is a desktop application designed to orchestrate and manage multiple CLI-based AI coding agents in parallel, using isolated Git worktrees for efficient, context-separated development.
VoltAgent/voltagent
VoltAgent is an open-source TypeScript framework for building and orchestrating autonomous AI agents with support for the Model Context Protocol (MCP) to enable standardized tool interactions and scalable multi-agent systems.
MervinPraison/PraisonAI
PraisonAI is a production-ready Multi AI Agents framework that provides a low-code solution for building and managing multi-agent LLM systems with a focus on simplicity, customization, and human-agent collaboration.