agent-framework

name	agent-framework
description	Use when building AI agents with Microsoft.SemanticKernel or Microsoft.Extensions.AI.Agent frameworks. Covers agent creation, tool/plugin registration, multi-agent orchestration, chat completion agents, and OpenAI Assistants integration. USE FOR: building AI agents with tools and plugins, multi-agent chat workflows, Semantic Kernel agent orchestration, OpenAI Assistants API integration, agent-based automation pipelines DO NOT USE FOR: simple chat completions without agent patterns (use microsoft-extensions-ai), inter-service agent communication over A2A protocol (use a2a), ML model training (use mlnet), raw ONNX inference (use onnx)
license	MIT
metadata	{"displayName":"Agent Framework","author":"Tyler-R-Kendrick","version":"1.0.0"}
compatibility	claude, copilot, cursor
references	[{"title":"Semantic Kernel Documentation","url":"https://learn.microsoft.com/semantic-kernel"},{"title":"Semantic Kernel GitHub Repository","url":"https://github.com/microsoft/semantic-kernel"},{"title":"Microsoft.SemanticKernel NuGet Package","url":"https://www.nuget.org/packages/Microsoft.SemanticKernel"}]

Agent Framework

Overview

The Microsoft Semantic Kernel Agent Framework provides a structured way to build AI agents that can use tools, maintain conversation history, and collaborate in multi-agent workflows. It supports ChatCompletionAgent for LLM-backed agents, OpenAIAssistantAgent for the Assistants API, and AgentGroupChat for orchestrating conversations between multiple agents with configurable termination and selection strategies.

NuGet Packages

dotnet add package Microsoft.SemanticKernel
dotnet add package Microsoft.SemanticKernel.Agents.Core
dotnet add package Microsoft.SemanticKernel.Agents.OpenAI
dotnet add package Microsoft.SemanticKernel.Connectors.OpenAI

ChatCompletionAgent

The simplest agent type wraps an IChatCompletionService with instructions and optional plugins.

using Microsoft.SemanticKernel;
using Microsoft.SemanticKernel.Agents;
using Microsoft.SemanticKernel.ChatCompletion;

var builder = Kernel.CreateBuilder();
builder.AddOpenAIChatCompletion("gpt-4o", Environment.GetEnvironmentVariable("OPENAI_API_KEY")!);
var kernel = builder.Build();

var agent = new ChatCompletionAgent
{
    Name = "CodeReviewer",
    Instructions = """
        You are a senior .NET developer who reviews code for correctness,
        performance, and adherence to best practices. Provide specific,
        actionable feedback with code examples.
        """,
    Kernel = kernel
};

var history = new ChatHistory();
history.AddUserMessage("Review this code: public int Add(int a, int b) => a + b;");

await foreach (var message in agent.InvokeAsync(history))
{
    Console.WriteLine(message.Content);
}

Agents with Plugins (Tools)

Plugins give agents the ability to call functions, access data, and interact with external systems.

using Microsoft.SemanticKernel;
using Microsoft.SemanticKernel.Agents;
using System.ComponentModel;

  
{
    []
    
    {
        
         city.ToLower() 
        {
             => ,
             => ,
             => ,
            _ => 
        };
    }

    []
     = )
    {
         ;
    }
}

 builder = Kernel.CreateBuilder();
builder.AddOpenAIChatCompletion(, apiKey);
builder.Plugins.AddFromType<WeatherPlugin>();
 kernel = builder.Build();

 agent =  ChatCompletionAgent
{
    Name = ,
    Instructions = ,
    Kernel = kernel,
    Arguments =  KernelArguments(
         OpenAIPromptExecutionSettings { ToolCallBehavior = ToolCallBehavior.AutoInvokeKernelFunctions })
};