EmberLlm 0.1.0

dotnet add package EmberLlm --version 0.1.0
                    
NuGet\Install-Package EmberLlm -Version 0.1.0
                    
This command is intended to be used within the Package Manager Console in Visual Studio, as it uses the NuGet module's version of Install-Package.
<PackageReference Include="EmberLlm" Version="0.1.0" />
                    
For projects that support PackageReference, copy this XML node into the project file to reference the package.
<PackageVersion Include="EmberLlm" Version="0.1.0" />
                    
Directory.Packages.props
<PackageReference Include="EmberLlm" />
                    
Project file
For projects that support Central Package Management (CPM), copy this XML node into the solution Directory.Packages.props file to version the package.
paket add EmberLlm --version 0.1.0
                    
#r "nuget: EmberLlm, 0.1.0"
                    
#r directive can be used in F# Interactive and Polyglot Notebooks. Copy this into the interactive tool or source code of the script to reference the package.
#:package EmberLlm@0.1.0
                    
#:package directive can be used in C# file-based apps starting in .NET 10 preview 4. Copy this into a .cs file before any lines of code to reference the package.
#addin nuget:?package=EmberLlm&version=0.1.0
                    
Install as a Cake Addin
#tool nuget:?package=EmberLlm&version=0.1.0
                    
Install as a Cake Tool

EmberLlm

A .NET client for local LLM servers (LM Studio, Ollama, llama.cpp, vLLM), built on Microsoft.Extensions.AI.

Until 1.0, minor versions (0.2, 0.3) may include breaking changes.

  • Finds running servers. EmberLlmDiscovery.FindAsync() probes the default ports of LM Studio, Ollama, llama.cpp and vLLM and identifies the backend.
  • Is an IChatClient. Works anywhere Microsoft.Extensions.AI is used, including its middleware.
  • Returns typed results. GetAsync<T>() builds on Microsoft.Extensions.AI's GetResponseAsync<T>, adding cleanup of <think> blocks and code fences, strict parsing and corrective retries.
  • Keeps reasoning separate. Thinking models' reasoning arrives as TextReasoningContent, not mixed into the answer.
  • Never fails silently. Every option you set is sent or rejected before the request goes out.
  • Suits local hardware. No model name required, a 10-minute default timeout with no silent re-sends, and clear errors when the server isn't running.

Quick start

using EmberLlm;

using var llm = new EmberLlmClient("http://127.0.0.1:1234");

string answer = await llm.CompleteAsync("Explain Span<T> in two sentences.");
Console.WriteLine(answer);

await foreach (string token in llm.StreamAsync("Write a haiku about garbage collection."))
    Console.Write(token);

// Typed results
CodeReview review = await llm.GetAsync<CodeReview>("Review this method: int Div(int a, int b) => a / b;");

public record CodeReview(string Summary, string[] Issues, int Severity);

With dependency injection:

services.AddEmberLlm(o => o.BaseUrl = "http://127.0.0.1:1234");
// then inject IChatClient or EmberLlmClient

Learn more

MIT licensed.

Product Compatible and additional computed target framework versions.
.NET net10.0 is compatible.  net10.0-android was computed.  net10.0-browser was computed.  net10.0-ios was computed.  net10.0-maccatalyst was computed.  net10.0-macos was computed.  net10.0-tvos was computed.  net10.0-windows was computed. 
Compatible target framework(s)
Included target framework(s) (in package)
Learn more about Target Frameworks and .NET Standard.

NuGet packages

This package is not used by any NuGet packages.

GitHub repositories

This package is not used by any popular GitHub repositories.

Version Downloads Last Updated
0.1.0 94 10/17/2026
0.1.0-beta.1 54 10/16/2026