No code rewrites
Code that consumes IChatClient or IChatCompletionService works as-is. Swap the registration; inference now runs on the box.
Solutions · Integrations
Drop into the .NET AI ecosystem.
LM-Kit meets your stack where it is. Bridges implement the .NET AI abstractions, Microsoft.Extensions.AI and Semantic Kernel, so existing pipelines run on a local backend. Connectors persist embeddings in production vector databases. And a provider-agnostic embedding layer lets you bring managed models like Amazon Bedrock, or keep everything local. Same orchestration, same storage; you choose where inference runs.
Bridges, connectors, and providers.
Each ships as a separate NuGet package. Add the ones that match the abstractions, vector stores, and embedding providers your codebase already speaks.
Microsoft
Microsoft.Extensions.AI bridge
Implements IChatClient and IEmbeddingGenerator<string, Embedding<float>>. Streaming, function calling, function-invocation middleware all work. Drop into any pipeline already built on the abstraction.
Microsoft
Semantic Kernel bridge
Implements IChatCompletionService and a memory store backed by LM-Kit embeddings. Existing kernels, plugins, planners, prompt files, and memory connectors run on-device.
Amazon
Amazon Bedrock embeddings
Implements IEmbedder over Amazon Titan and Cohere Embed. Plug managed cloud embeddings into the same RagEngine pipeline as local models, or run both behind one contract.
Data
Vector database connectors
Persist RAG embeddings in Qdrant or PostgreSQL/pgvector. Both implement the same IVectorStore as the built-in memory path, so retrieval code does not change.
Investment preserved.
Teams that adopted Microsoft.Extensions.AI or Semantic Kernel built investments in plugins, planners, prompt-function libraries, memory connectors, and middleware. Switching to a local backend should not cost that investment. Bridges keep the surface, swap the backend.
Hybrid by default
Register multiple chat services. Route per request: local for sensitive data, cloud for bulk traffic. Same abstraction handles both.
Middleware preserved
Logging, caching, retry, function-invocation middleware written against the abstraction works unchanged. The bridge is just another implementation.
CI-friendly
Run end-to-end tests against the abstraction with the LM-Kit implementation. No external API quota, no flaky network in CI.
Library publishers
A NuGet that consumes IChatClient works with LM-Kit out of the box. The library author does not need to know about LM-Kit.
Future-compatible
Both abstractions evolve. The bridges track the surface. New methods on IChatClient land as new methods on the bridge.
Related capabilities.
Tools & function calling
When the abstraction is not enough for fine control, the native Tools API gives finer control over invocation, permissions, streaming.
Built-in vector database
The vector store under both bridges' memory paths. Same primitive other LM-Kit RAG paths use.
Document RAG
For full-document workflows beyond text snippets, the native RAG primitives add source attribution and adaptive ingestion.
Edge & offline deployment
Once your kernel runs on the bridge, shipping to edge environments is a packaging change.
Frequently asked questions.
Does LM-Kit.NET integrate with Semantic Kernel?
Yes. LM-Kit ships a Semantic Kernel bridge that implements IChatCompletionService and a memory store backed by LM-Kit embeddings. Existing kernels, plugins, planners, prompt files, and memory connectors run on-device.
Can I use LM-Kit.NET with Microsoft.Extensions.AI and IChatClient?
Yes. The Microsoft.Extensions.AI bridge implements IChatClient and IEmbeddingGenerator, so streaming, function calling, and function-invocation middleware all work. It drops into any pipeline already built on the abstraction.
What integrations does LM-Kit.NET provide?
LM-Kit provides bridges for Microsoft.Extensions.AI and Semantic Kernel, an Amazon Bedrock embedding provider, and vector database connectors for Qdrant and PostgreSQL/pgvector. Each ships as a separate NuGet package.
Do I have to rewrite my code to switch to a local backend with LM-Kit.NET?
No. Code that consumes IChatClient or IChatCompletionService works as-is; you swap the registration and inference then runs on the box. The bridges keep the surface and swap the backend, so plugins, planners, and middleware are preserved.
Can LM-Kit.NET run both cloud and local inference through the same abstraction?
Yes. You can register multiple chat services and route per request, for example local for sensitive data and cloud for bulk traffic. The Amazon Bedrock provider also plugs managed cloud embeddings into the same RagEngine pipeline as local models.
Build it. Read it. Try it.
Working console demos on GitHub, step-by-step how-to guides on the docs site, and the API reference for the classes used on this page.
Demo
Microsoft.Extensions.AI integration
Console demo: LM-Kit.NET as an IChatClient implementation.
Open on GitHub → DemoSemantic Kernel + memory
Console demo: LM-Kit-backed memory store for Semantic Kernel.
Open on GitHub → RepoAmazon Bedrock integration
Source for the LM-Kit.NET Bedrock embedding provider.
Open →