agent-framework-agui-csharp

Build AG-UI protocol clients and servers with the Microsoft Agent Framework .NET SDK.

34|17|Updated May 27, 2026
One-click install
npx skills add https://github.com/microsoft/Learn-Microsoft-Agent-Framework-with-Foundry-ZavaShop-Supply-Chain-Workshop --skill agent-framework-agui-csharp
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: agent-framework-agui-csharp
Source: https://github.com/microsoft/Learn-Microsoft-Agent-Framework-with-Foundry-ZavaShop-Supply-Chain-Workshop/tree/main/.github/skills/agent-framework-agui-csharp
Command: npx skills add https://github.com/microsoft/Learn-Microsoft-Agent-Framework-with-Foundry-ZavaShop-Supply-Chain-Workshop --skill agent-framework-agui-csharp

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill requires Microsoft.Agents.AI.AGUI.AspNetCore, Microsoft.Agents.AI.OpenAI, Azure.AI.OpenAI, Azure.Identity, and includes scripts (resource) and references (resource) and assets (resource) components.

What problem does it solve?

This Skill allows you to create AG-UI protocol clients and servers using the Microsoft Agent Framework .NET SDK, enabling you to expose AIAgent over HTTP with server-sent events, build remote agent clients, support frontend tool rendering, and more.

Core Features & Use Cases

  • AG-UI Protocol Client/Server Implementation: Build both clients and servers for the AG-UI protocol, facilitating communication between frontends and agent servers.
  • HTTP with Server-Sent Events: Expose AIAgent over HTTP with server-sent events for real-time data communication.
  • Frontend Tool Rendering: Support frontend tool rendering and agentic generative UI.
  • Predictive State Updates: Implement predictive state updates for efficient UI updates.
  • Shared State: Manage shared state between agents and clients for collaborative tasks.
  • Human-in-the-Loop UX: Enable human-in-the-loop user experiences.
  • Use Case: Develop a chatbot that can interact with a user through a UI, receiving inputs and sending responses in real-time.

Quick Start

Run the provided server code with the following command: dotnet run --urls "http://localhost:5100".

Frequently Asked Questions about agent-framework-agui-csharp

High-intent search queries and answers about installing and using this skill.

FAQPage Schema
How do I expose an AI agent over HTTP using server-sent events in .NET?

You can expose an AI agent over HTTP with server-sent events by building an AG-UI protocol server using the Microsoft Agent Framework .NET SDK. This enables real-time streaming communication between frontends and your agent server.

Can I build a remote agent client to communicate with an AG-UI protocol server?

Yes, you can build a remote agent client using AGUIChatClient within the Microsoft Agent Framework .NET SDK. This allows your frontend applications to consume real-time responses and interact directly with remote agent servers.

How do I implement shared state and human-in-the-loop UX for agentic generative UI?

Implement shared state and human-in-the-loop UX using MapAGUI and session storage within the Microsoft Agent Framework .NET SDK. This supports collaborative tasks, predictive state updates, and interactive frontend tool rendering.

Does the Microsoft Agent Framework support streaming agent responses via the AG-UI protocol?

Yes, the framework supports streaming agent responses via the AG-UI protocol using the AgentResponseUpdate streaming contract. This enables real-time data communication over HTTP with server-sent events for your .NET applications.

What .NET dependencies are required to build AG-UI protocol clients and servers?

Building AG-UI protocol clients and servers requires dependencies including Microsoft.Agents.AI.AGUI.AspNetCore, Microsoft.Agents.AI.OpenAI, Azure.AI.OpenAI, and Azure.Identity to handle authentication and AI model integration.

How do I run an AG-UI protocol server locally for testing?

Run your AG-UI protocol server locally using the command `dotnet run --urls "http://localhost:5100"`. This starts your .NET application and exposes the agent endpoint for frontend client testing.