👁 Image
tryAGI.Anthropic 3.8.3

Anthropic

👁 Nuget package
👁 dotnet
👁 License: MIT
👁 Discord

Disclaimer: This package is not affiliated with, endorsed by, or sponsored by Anthropic. Anthropic and Claude are trademarks of Anthropic, PBC.

Features 🔥

• Fully generated C# SDK based on official OpenAPI specification using AutoSDK
• Automatic releases of new preview versions if there was an update to the OpenAPI specification
• Source generator to define tools natively through C# interfaces
• All modern .NET features - nullability, trimming, NativeAOT, etc.
• Support .Net Framework/.Net Standard 2.0
• Supporting Microsoft.Extensions.AI
• Supports all endpoints of the API, including batch requests, count tokens, and prompt caching.

Usage

using Anthropic;

using var client = new AnthropicClient(apiKey);

var messageParams = new CreateMessageParams()
{ 
 Model = new Model(ModelVariant6.Claude35SonnetLatest),
 Messages = [
 new InputMessage(InputMessageRole.User, "What's the weather like today?"),
 new InputMessage(InputMessageRole.Assistant, "Sure! Could you please provide me with your location?"),
 new InputMessage(InputMessageRole.User, "Dubai, UAE")
 ],
 MaxTokens = 250
};
var response = await client.Messages.MessagesPostAsync(messageParams);

Tools

using CSharpToJsonSchema;

public enum Unit
{
 Celsius,
 Fahrenheit,
}

public class Weather
{
 public string Location { get; set; } = string.Empty;
 public double Temperature { get; set; }
 public Unit Unit { get; set; }
 public string Description { get; set; } = string.Empty;
}

[GenerateJsonSchema]
public interface IWeatherFunctions
{
 [Description("Get the current weather in a given location")]
 public Weather GetCurrentWeather(
 [Description("The city and state, e.g. San Francisco, CA")] string location,
 Unit unit = Unit.Celsius);
 
 [Description("Get the current weather in a given location")]
 public Task<Weather> GetCurrentWeatherAsync(
 [Description("The city and state, e.g. San Francisco, CA")] string location,
 Unit unit = Unit.Celsius,
 CancellationToken cancellationToken = default);
}

public class WeatherService : IWeatherFunctions
{
 public Weather GetCurrentWeather(string location, Unit unit = Unit.Celsius)
 {
 return new Weather
 {
 Location = location,
 Temperature = 22.0,
 Unit = unit,
 Description = "Sunny",
 };
 }
 
 public Task<Weather> GetCurrentWeatherAsync(string location, Unit unit = Unit.Celsius, CancellationToken cancellationToken = default)
 {
 return Task.FromResult(new Weather
 {
 Location = location,
 Temperature = 22.0,
 Unit = unit,
 Description = "Sunny",
 });
 }
}

using Anthropic;

using var client = new AnthropicClient(apiKey);

var service = new WeatherService();
var tools = service.AsTools();

var messageParams = new CreateMessageParams()
{ 
 Model = new Model(ModelVariant6.Claude35SonnetLatest),
 Messages = [new InputMessage(InputMessageRole.User, "What is the current temperature in Dubai, UAE in Celsius?")],
 MaxTokens = 4096,
 System = "You are a helpful weather assistant.",
 ToolChoice = new ToolChoice(new ToolChoiceAuto()),
 Tools = tools
};
var response = await client.Messages.MessagesPostAsync(messageParams);

messageParams.Messages.Add(response.AsInputMessage());

foreach (var toolUse in response.Content.Value2!
 .Where(x => x.IsToolUse)
 .Select(x => x.ToolUse))
{
 var json = await service.CallAsync(
 functionName: toolUse!.Name,
 argumentsAsJson: toolUse.Input.AsJson());
 messageParams.Messages.Add(json.AsToolCall(toolUse));
}

response = await client.Messages.MessagesPostAsync(messageParams);

Microsoft.Extensions.AI

The SDK implements IChatClient for seamless integration with the .NET AI ecosystem:

using Anthropic;
using Microsoft.Extensions.AI;

IChatClient chatClient = new AnthropicClient(apiKey);

var response = await chatClient.GetResponseAsync(
 [new ChatMessage(ChatRole.User, "Hello!")],
 new ChatOptions { ModelId = "claude-sonnet-4-20250514" });

Console.WriteLine(response.Text);

Chat Client Five Random Lines

using var client = GetAuthenticatedChatClient();

var response = await client.GetResponseAsync(
 messages: [new ChatMessage(ChatRole.User, "Generate 5 random words.")],
 new ChatOptions
 {
 ModelId = DefaultModel,
 ResponseFormat = ChatResponseFormatForType<StringArraySchema>(),
 Tools = new List<AITool>(),
 });

Console.WriteLine(response.ToString());

Chat Client Five Random Words Streaming

using var client = GetAuthenticatedChatClient();

var enumerable = client.GetStreamingResponseAsync(
 messages: [new ChatMessage(ChatRole.User, "Generate 5 random words.")],
 new ChatOptions
 {
 ModelId = DefaultModel,
 });

var deltas = new List<string>();
await foreach (var response in enumerable)
{
 Console.Write(response.ToString());

 deltas.Add(response.ToString());
}

Chat Client Five Random Words

using var client = GetAuthenticatedChatClient();

var response = await client.GetResponseAsync(
 messages: [new ChatMessage(ChatRole.User, "Generate 5 random words.")],
 new ChatOptions
 {
 ModelId = DefaultModel,
 });

Console.WriteLine(response.ToString());

Complete History

using var client = new AnthropicClient(apiKey);

var response = await client.MessagesPostAsync(
 model: DefaultModel,
 messages: [
 "What's the weather like today?",
 "Sure! Could you please provide me with your location?".AsAssistantMessage(),
 "Dubai, UAE",
 ],
 maxTokens: 300,
 temperature: 0);

Console.WriteLine(response.AsSimpleText());

Five Random Words

using var client = new AnthropicClient(apiKey);

var response = await client.MessagesPostAsync(
 model: DefaultModel,
 messages: ["Generate 5 random words."],
 maxTokens: 300,
 temperature: 0);

Console.WriteLine(response.AsSimpleText());

Streaming

using var client = new AnthropicClient(apiKey);

var enumerable = client.CreateMessageAsStreamAsync(new CreateMessageParams
{
 Model = DefaultModel,
 Messages = ["Once upon a time"],
 MaxTokens = 250,
});

var deltas = new List<string>();
await foreach (var response in enumerable)
{
 Console.Write(response.ContentBlockDelta?.Delta.TextDelta?.Text);

 deltas.Add(response.ContentBlockDelta?.Delta.TextDelta?.Text ?? string.Empty);
}

Support

Priority place for bugs: https://github.com/tryAGI/Anthropic/issues
Priority place for ideas and general questions: https://github.com/tryAGI/Anthropic/discussions
Discord: https://discord.gg/Ca2xhfBf3v

Acknowledgments

This project is supported by JetBrains through the Open Source Support Program.