LM-Kit Documentation

One engine, two deployment forms: LM-Kit One, the server you deploy, and LM-Kit.NET, the runtime you embed. Each with guides and a complete API reference.

LM-Kit One

The Private AI Application Server: models, documents, search, and agents served behind OpenAI, Anthropic, Ollama, and MCP compatible APIs, on infrastructure you operate. Product overview.

Guides Install, secure, operate, and build: authored walkthroughs for every capability, from first run to production. REST API reference Every endpoint, parameter, and schema of the REST API, generated from the server itself.

LM-Kit.NET

The Embedded Private AI Runtime for .NET: models, agents, RAG, search, document intelligence, vision, and speech, in process inside your application. Get it on NuGet.

Guides Concepts, tutorials, and sample walkthroughs for building with the SDK in C# and .NET. API reference The complete namespace, class, and member reference of the LM-Kit.NET assembly. Samples on GitHub Runnable demo applications covering every capability pillar, from console apps to MAUI. Models on Hugging Face The curated model catalog: quantized, tested, and ready to load by model ID.