# AI Travel Agents

A modular reference application in which several AI agents, orchestrated by LangChain.js, LlamaIndex.TS and Microsoft Agent Framework, handle travel-agency customer queries, destination recommendations and itinerary planning through MCP servers.

The application extracts customer preferences, suggests destinations, and builds a detailed itinerary through separate agents, plus an echo-ping agent used as an MCP server example. Each capability the agents use is provided by an MCP server, and the servers are implemented independently in Python, Node.js, Java and .NET.

Three orchestration options run as standalone services and demonstrate different stacks: LangChain.js and LlamaIndex.TS in TypeScript and Node.js, and Microsoft Agent Framework in Python; each coordinates interaction between the agents and MCP clients. All components are containerized with Docker for deployment to Azure Container Apps, and an Aspire Dashboard monitors performance and behavior through OpenTelemetry.

Website: https://azure-samples.github.io/azure-ai-travel-agents/