Azure/agent-landing-zone

Enterprise-grade landing zone for AI agent applications on Azure. Deploy the secure infrastructure, the agent app, or both — built on Microsoft Foundry and Microsoft Agent Framework, with Zero-Trust networking, observability and IaC.

What it solves

Agent Landing Zone provides a secure, enterprise-ready foundation for deploying AI agent applications on Microsoft Azure. It addresses the challenge of setting up complex cloud infrastructure that adheres to strict security and networking requirements, such as Zero-Trust principles, while supporting the deployment of AI-based orchestrators and user interfaces.

How it works

This project uses Infrastructure-as-Code (IaC) to provision a pre-configured environment on Azure. It is designed to be deployed using the Azure Developer CLI (azd). The architecture includes modular components for the application UI, an orchestrator for managing agent logic, and optional ingestion pipelines for data, all integrated within a secure Azure networking environment.

Who it’s for

This is for enterprise developers and cloud architects who need to deploy AI agent applications into production environments on Azure while ensuring compliance, security, and scalability.

Highlights

  • Implements a Zero-Trust network architecture for secure AI deployments.
  • Uses Infrastructure-as-Code (IaC) for consistent and repeatable environment provisioning.
  • Supports flexible deployment options, including full-stack, infrastructure-only, or custom application integration.
  • Built-in compatibility with the Azure Developer CLI (azd) for streamlined deployment workflows.

Related

  • Project
    java-up-up/nexus-agent

    An enterprise-grade AI agent platform that implements a complete loop from document governance and hybrid RAG retrieval to ReAct-based agentic reasoning and MCP tool integration.

  • Project
    Azure-Samples/openai

    A collection of practical code samples and templates for building agentic workflows and AI solutions using Azure AI Foundry and Azure OpenAI Service.

  • Dispatch
    Hugging Face Models on Foundry Managed Compute

    Microsoft Foundry now integrates a curated, weekly-refreshed catalog of Hugging Face open-weight models that can be deployed in one click onto Foundry Managed Compute for enterprise-grade operationalization.

  • Project
    GoogleCloudPlatform/cymbal-air-toolbox-demo

    A reference implementation for building agentic applications that use RAG and a middleware toolbox to securely query and interact with cloud databases.

  • Project
    openairymax/agentrt

    AgentRT is an AI Agent runtime platform that provides a unified orchestration layer for multi-agent cognitive cycles, memory, and security isolation.