WeaveLLM.Core 0.2.1-alpha

This is a prerelease version of WeaveLLM.Core.

dotnet add package WeaveLLM.Core --version 0.2.1-alpha

NuGet\Install-Package WeaveLLM.Core -Version 0.2.1-alpha

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="WeaveLLM.Core" Version="0.2.1-alpha" />

For projects that support PackageReference, copy this XML node into the project file to reference the package.

<PackageVersion Include="WeaveLLM.Core" Version="0.2.1-alpha" />
                    

                            Directory.Packages.props

<PackageReference Include="WeaveLLM.Core" />
                    

                            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 WeaveLLM.Core --version 0.2.1-alpha

The NuGet Team does not provide support for this client. Please contact its maintainers for support.

#r "nuget: WeaveLLM.Core, 0.2.1-alpha"

#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 WeaveLLM.Core@0.2.1-alpha

#: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=WeaveLLM.Core&version=0.2.1-alpha&prerelease
                    

                            Install as a Cake Addin

#tool nuget:?package=WeaveLLM.Core&version=0.2.1-alpha&prerelease
                    

                            Install as a Cake Tool

The NuGet Team does not provide support for this client. Please contact its maintainers for support.

LangChain is slow and leaky — WeaveLLM is a native .NET 8 AI orchestration framework that treats errors as values, wires into ASP.NET Core DI out of the box, and composes like middleware.

Quick Example

var builder = WebApplication.CreateBuilder(args);

builder.Services
    .AddWeaveLLM()
    .AddOpenAI(apiKey: builder.Configuration["OpenAI:ApiKey"]!, modelId: "gpt-4o");

var app = builder.Build();

app.MapPost("/chat", async (string message, IChatModel model) =>
{
    var result = await model.ChatAsync([Message.User(message)]);
    return result.IsSuccess ? Results.Ok(result.Value!.Content) : Results.Problem(result.Error!.Message);
});

app.Run();

Why WeaveLLM

Railway-oriented results — every call returns ChainResult<T>; no swallowed exceptions, composable error paths
ASP.NET-style middleware pipeline — stack retry, caching, rate limiting, PII scrubbing, and cost tracking as layers
Single fluent registration — AddWeaveLLM() wires providers, memory, agents, health checks, and telemetry in one call
Native .NET 8 — built on IServiceCollection, IAsyncEnumerable, and the BCL; no Python bridges, no wrapper tax
OpenTelemetry first-class — traces, token cost metrics, and PII scrubbing ship in WeaveLLM.Observability

Supported Providers

Provider	Package	Notes
OpenAI	`WeaveLLM.Providers`	GPT-4o, GPT-4-turbo, GPT-3.5
Anthropic	`WeaveLLM.Providers`	Claude 3.x / 4.x series
Ollama	`WeaveLLM.Providers`	Local models via Ollama REST API
HuggingFace	`WeaveLLM.Providers`	Inference API (text-generation)

Installation

dotnet add package WeaveLLM.Core
dotnet add package WeaveLLM.Providers
dotnet add package WeaveLLM.Memory
dotnet add package WeaveLLM.Observability
dotnet add package WeaveLLM.Extensions.DependencyInjection

Testing

Use WeaveLLM.Testing to unit-test code that depends on IChatModel without any real API calls:

dotnet add package WeaveLLM.Testing

var fake = new FakeStreamingChatModel
{
    Tokens = ["Hello", ", ", "world", "!"],
    BlockingResponse = "Hello, world!"
};

var result = await fake.ChatAsync([Message.User("Hi")]);
result.Value!.Content // → "Hello, world!"

Product	Compatible and additional computed target framework versions.
.NET	net8.0 is compatible. net8.0-android was computed. net8.0-browser was computed. net8.0-ios was computed. net8.0-maccatalyst was computed. net8.0-macos was computed. net8.0-tvos was computed. net8.0-windows was computed. net9.0 was computed. net9.0-android was computed. net9.0-browser was computed. net9.0-ios was computed. net9.0-maccatalyst was computed. net9.0-macos was computed. net9.0-tvos was computed. net9.0-windows was computed. net10.0 was computed. 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.

NuGet packages (5)

Showing the top 5 NuGet packages that depend on WeaveLLM.Core:

Package	Downloads
WeaveLLM.Providers OpenAI, Anthropic, Azure OpenAI, and Ollama providers for WeaveLLM	181
WeaveLLM.Extensions.DependencyInjection ASP.NET Core and IServiceCollection integration for WeaveLLM	172
WeaveLLM.Observability OpenTelemetry tracing, metrics, and LLM evaluation for WeaveLLM	140
WeaveLLM.Testing Pre-built test doubles and fakes for unit-testing WeaveLLM integrations — no real API calls required.	106
WeaveLLM.Memory Memory and vector store implementations for WeaveLLM — in-memory, PostgreSQL/pgvector, and Qdrant stores.	71

GitHub repositories

This package is not used by any popular GitHub repositories.

Version	Downloads	Last Updated
0.2.1-alpha	88	5/8/2026
0.2.0-alpha	62	5/7/2026
0.1.0-alpha	68	4/26/2026