foxminchan/BookWorm

The practical implementation of Aspire using Microservices, AI-Agents

What it solves

BookWorm is a cloud-native application designed to demonstrate the integration of AI agents within a complex microservices architecture. It provides a reference implementation for building scalable, enterprise-grade applications that combine Domain-Driven Design (DDD) and multi-agent AI orchestration.

How it works

The project uses .NET Aspire for cloud-native orchestration and Azure OpenAI for LLMs and embeddings. It implements a multi-agent workflow using a dedicated Agent Framework, enabling agents to communicate with each other via the A2A Protocol and interact with users through the AG-UI Protocol. To standardize AI tooling, it utilizes the Model Context Protocol (MCP).

Who it’s for

Developers and architects interested in implementing AI agents into microservices, specifically those using the .NET ecosystem, Azure, and cloud-native patterns like CQRS and Saga patterns.

Highlights

  • Multi-Agent Orchestration: Uses a specialized framework to coordinate multiple AI agents.
  • AI-to-UI Integration: Enables agents to generate rich, interactive user interfaces using A2UI.
  • Standardized Tooling: Implements the Model Context Protocol (MCP) for consistent AI tool access.
  • Enterprise Architecture: Combines Vertical Slice Architecture, gRPC for service communication, and Keycloak for authentication.
  • Cloud-Native Stack: Built with .NET Aspire, Next.js, and deployed via Azure Container Apps.

Related

  • Project
    Azure-Samples/azure-ai-travel-agents

    A modular reference application that uses multiple AI agents and the Model Context Protocol (MCP) to automate travel tasks like destination recommendation and itinerary planning.

  • Project
    Azure-Samples/AI-Gateway

    An enterprise-grade AI Gateway framework powered by Azure API Management that provides centralized security, cost control, and observability for managing AI models, tools, and agents.

  • Project
    VRSEN/agency-swarm

    A framework for building multi-agent AI applications that organizes agents into collaborative swarms based on real-world organizational structures.

  • Project
    microsoft/mcp

    A collection of Model Context Protocol (MCP) servers and core tooling that standardizes how AI agents and LLMs connect to Microsoft services and external data sources.

  • Project
    0xjeffro/astroclaw

    A cloud-native AI agent framework that decomposes monolithic agents into serverless components for better scalability, security, and cost-efficiency on AWS.