azure-ai-travel-agents

Travel-agency multi-agent sample using MCP servers in four languages

Stars: 483
License: MIT
Last commit: Sep 2026
Language: TypeScript

Overview

Reference app where agents extract customer preferences, recommend destinations and plan itineraries, calling tools exposed as MCP servers written in Python, Node.js, Java and .NET. Three interchangeable orchestrators are provided: LangChain.js, LlamaIndex.TS and Microsoft Agent Framework (Python). It runs locally with Docker Model Runner and Phi4 14B, or deploys to Azure Container Apps with `azd up`.

Who it is for: Engineers learning MCP-based multi-agent design on Azure

Strengths

Three orchestrators (LangChain.js, LlamaIndex.TS, Microsoft Agent Framework) over the same MCP tools
MCP server examples in Python, Node.js, Java and .NET
OpenTelemetry tracing viewable in Aspire Dashboard
One-command Azure deploy with `azd up`; MIT license

Weaknesses

Sample app, not a reusable framework; the domain is fixed to travel
Local preview needs Phi4 14B (about 7.8 GB download, 16 GB RAM minimum)
Local GPU acceleration only on Apple Silicon and NVIDIA GPUs on Windows
Deployment path is tied to Azure; no release published

What it needs

TypeScript, Phi4 14B (Docker Model Runner), Azure OpenAI, Microsoft Foundry
Needs Docker, Docker Model Runner, Node.js 22+, Azure Container Apps, Azure OpenAI or Microsoft Foundry

Also in Agent backends

See all 18

Also in Agent backends
Rank	Project	Score
1	eve-software-factory-templateeve pipeline that turns GitHub or Linear issues into reviewed draft PRs1.2k stars, MIT	65 out of 100
2	marketing-team-eve-templateeve lead agent delegating to five marketing specialists with approval gates450 stars, MIT	59 out of 100
3	personal-agent-templateeve and Nuxt personal agent with Slack, GitHub, Linear and per-user memory477 stars, MIT	57 out of 100
#4	adk-recipesRunnable Agent Development Kit recipes, from single patterns to deployable agents10.4k stars, Apache-2.0	53 out of 100
#5	ai-townGenerative-agents town simulation on Convex with Ollama by default Live demo ↗ (opens in a new tab)10.6k stars, MIT	52 out of 100

How to choose

Choose the framework you want to live with; templates are thin and the framework is the real dependency.
Check where state lives (Durable Objects, Postgres, a managed platform) and whether that fits your hosting.
Favor templates that ship tests or an eval hook so agent changes can be checked.

For maintainers

Show this rank in your README. It updates twice a day.

[![Archestack](https://archestack.github.io/badge/azure-samples/azure-ai-travel-agents.svg)](https://archestack.github.io/best-of-vibe-coding/projects/azure-ai-travel-agents/)

How badges work

Spot a wrong fact?

Reviews are written from each project's README and checked facts. Report it on GitHub ↗ (opens in a new tab)