concierge

Concierge AI implements the Model Context Protocol (MCP) to provide a robust framework for building reliable AI applications. It helps orchestrate AI agent workflows through progressive tool disclosure, enforced ordering, and server-side state management.

concierge sits in the RAG / Knowledge Base category, so it is usually better judged by workflow fit, deployment style, and team needs than by isolated features alone. Based on the available metadata, it leans most clearly toward Progressive Tool Disclosure. A representative use case is Building reliable AI agent applications with predictable behavior. The listed license is NOASSERTION. GitHub stars are currently 528. Relevant tags include AI Agents, Model Context Protocol.