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
Azure-Samples/azure-ai-travel-agents
Azure AI Travel Agents is an enterprise-grade application designed to enhance travel agency operations by leveraging multiple AI agents orchestrated through the Model Context Protocol (MCP). This project demonstrates the integration of various AI agents, each specialized in different tasks such as understanding customer queries, recommending travel destinations, planning detailed itineraries, executing custom code, performing model inference, and conducting live web searches. The agents communicate and collaborate seamlessly using MCP servers implemented in diverse technologies including Python, Node.js, Java, and .NET, showcasing the protocol's flexibility and interoperability. The architecture is modular and scalable, with all components containerized using Docker and deployed serverlessly on Azure Container Apps. This setup ensures easy management, scalability, and cloud-native operation. The application uses LlamaIndex.TS to orchestrate the AI agents, enabling efficient handling of customer interactions and travel planning workflows. Additionally, the system incorporates a custom large language model (LLM) running on Azure Container Apps' serverless GPU infrastructure for high-performance inference, utilizing ONNX and vLLM technologies. The project also features an Aspire Dashboard integrated with OpenTelemetry for monitoring the performance and behavior of the AI agents, providing valuable insights for maintenance and optimization. The inclusion of an llms.txt file helps guide LLMs during inference, enhancing the system's adaptability and intelligence. Users can preview the application locally using Docker Model Runner, although running the large Phi4 14B model requires significant computational resources. For those without sufficient local resources, the application can be run using Azure AI Foundry. The project is well-documented with setup scripts, architecture diagrams, and community support links, making it accessible for developers interested in building scalable AI-driven travel solutions using MCP.
https://github.com/Azure-Samples/azure-ai-travel-agents
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.
openai/swarm
Swarm is an educational framework by OpenAI for lightweight, scalable multi-agent orchestration using agents and handoffs, designed to explore and teach multi-agent coordination techniques.
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.