> ## Documentation Index
> Fetch the complete documentation index at: https://mintlify.com/microsoft/autogen/llms.txt
> Use this file to discover all available pages before exploring further.
# Installation
> Install AutoGen for .NET via NuGet
## Package Overview
AutoGen for .NET provides multiple NuGet packages to suit different needs. You can install the all-in-one package or choose specific packages based on your requirements.
All packages require **.NET 6.0** or later.
## Quick Install
For most users, install the all-in-one package:
```bash theme={null}
dotnet add package AutoGen
```
This package includes:
* `AutoGen.Core` - Core abstractions and types
* `AutoGen.OpenAI` - OpenAI integration
* `AutoGen.LMStudio` - LM Studio support
* `AutoGen.SemanticKernel` - Semantic Kernel integration
* `AutoGen.SourceGenerator` - Type-safe function generation
## Package Versions
Install the latest stable version from NuGet:
[](https://badge.fury.io/nu/AutoGen.Core)
```bash theme={null}
dotnet add package AutoGen
```
For the latest features and bug fixes, use nightly builds:
**Add the nightly feed to your `NuGet.config`:**
```xml NuGet.config theme={null}
```
**Or add via command line:**
```bash theme={null}
dotnet nuget add source https://pkgs.dev.azure.com/AGPublish/AGPublic/_packaging/AutoGen-Nightly/nuget/v3/index.json --name AutoGen-Nightly
```
**For dotnet-interactive support:**
```bash theme={null}
dotnet nuget add source https://pkgs.dev.azure.com/dnceng/public/_packaging/dotnet-tools/nuget/v3/index.json --name dotnet-tools
```
**Install the nightly package:**
```bash theme={null}
dotnet add package AutoGen --version VERSION
```
## Individual Packages
Install only the packages you need for a minimal footprint:
Core abstractions for agents, messages, and group chat. Use this if you want to avoid dependencies on specific LLM providers.
```bash theme={null}
dotnet add package AutoGen.Core
```
**Includes:**
* Agent abstractions (`IAgent`, `IStreamingAgent`)
* Message types (`TextMessage`, `ImageMessage`, etc.)
* Group chat and orchestration
* Middleware infrastructure
OpenAI model integration including GPT-4, GPT-3.5, and Azure OpenAI.
```bash theme={null}
dotnet add package AutoGen.OpenAI
```
**Features:**
* `OpenAIChatAgent` for OpenAI models
* Streaming support
* Function calling
* Vision capabilities
Claude model integration from Anthropic.
```bash theme={null}
dotnet add package AutoGen.Anthropic
```
**Features:**
* `AnthropicClientAgent` for Claude models
* Prompt caching support
* Tool/function calling
Azure AI Inference integration for models deployed on Azure.
```bash theme={null}
dotnet add package AutoGen.AzureAIInference
```
**Features:**
* `ChatCompletionsClientAgent` for Azure AI models
* Support for GitHub Models, Azure AI Studio
* Compatible with various model providers
Integration with Microsoft Semantic Kernel.
```bash theme={null}
dotnet add package AutoGen.SemanticKernel
```
**Features:**
* `SemanticKernelAgent` wrapper
* Access to Semantic Kernel plugins
* Unified agent interface
Source generator for type-safe function definitions.
```bash theme={null}
dotnet add package AutoGen.SourceGenerator
```
**Features:**
* `[Function]` attribute for methods
* Automatic schema generation from XML docs
* Compile-time type safety
* Zero runtime reflection
Code execution support using dotnet-interactive.
```bash theme={null}
dotnet add package AutoGen.DotnetInteractive
```
**Supports:**
* C# code execution
* F# code execution
* PowerShell scripts
* Python scripts (with Python kernel)
Mistral AI model integration.
```bash theme={null}
dotnet add package AutoGen.Mistral
```
Google Gemini model integration.
```bash theme={null}
dotnet add package AutoGen.Gemini
```
Local model support via Ollama.
```bash theme={null}
dotnet add package AutoGen.Ollama
```
LM Studio local model support.
```bash theme={null}
dotnet add package AutoGen.LMStudio
```
## Choosing the Right Package
Install `AutoGen` if you want to get started quickly with common providers like OpenAI and don't mind the additional dependencies.
```bash theme={null}
dotnet add package AutoGen
```
Install `AutoGen.Core` if you:
* Want minimal dependencies
* Plan to implement custom agents
* Only need the abstraction layer
```bash theme={null}
dotnet add package AutoGen.Core
```
Install specific provider packages based on your LLM:
```bash OpenAI theme={null}
dotnet add package AutoGen.Core
dotnet add package AutoGen.OpenAI
```
```bash Anthropic theme={null}
dotnet add package AutoGen.Core
dotnet add package AutoGen.Anthropic
```
```bash Azure AI theme={null}
dotnet add package AutoGen.Core
dotnet add package AutoGen.AzureAIInference
```
Enhance your application with optional packages:
```bash theme={null}
# For type-safe functions
dotnet add package AutoGen.SourceGenerator
# For code execution
dotnet add package AutoGen.DotnetInteractive
# For Semantic Kernel integration
dotnet add package AutoGen.SemanticKernel
```
## Verification
Verify your installation by checking the installed packages:
```bash theme={null}
dotnet list package
```
You should see the AutoGen packages listed with their version numbers.
## Example Project File
Here's a complete `.csproj` example with common packages:
```xml YourProject.csproj theme={null}
Exe
net8.0
enable
```
Replace version numbers with the latest available versions from NuGet.
## Next Steps
Build your first AutoGen application
Learn about agents and messaging