LM-Kit Blog

Insights for AI pioneers.

Announcements, engineering deep dives, and the decisions behind LM-Kit One and LM-Kit.NET: private AI across models, agents, RAG, search, and documents.

LM-Kit One Arrives September 15
Latest · Announcement

LM-Kit One Arrives September 15

Serving a model is the easy part. We built the rest of the private AI application stack, put it into production across our own group for a year, and on September 15 anyone can download that stack.

4 min read

Read article

Continue reading.

Agent Skills Explained: Turn Any Agent Into an On-Demand Specialist with SKILL.md Guide

Agent Skills Explained: Turn Any Agent Into an On-Demand Specialist with SKILL.md

A comprehensive guide to the open standard that turns AI agents into on-demand specialists

12 min read

LM-Kit.NET Goes Agentic: MCP, Tools, Orchestration, All On-Device Release

LM-Kit.NET Goes Agentic: MCP, Tools, Orchestration, All On-Device

Let's be direct: the AI industry told .NET developers they had two choices. Use cloud APIs and accept the trade-offs (latency, costs, data exposure, vendor

6 min read

Meet LM-Kit Tool Calling for: Local Agents Guide

Meet LM-Kit Tool Calling for: Local Agents

Deploy AI agents that call tools, chain workflows, and run entirely on-device. LM-Kit .NET SDK supports Mistral, LLaMA, Qwen with full privacy and no API charges.

10 min read

Introducing Speech-to-Text Support: in LM-Kit Release

Introducing Speech-to-Text Support: in LM-Kit

Discover LM-Kit.NET's new speech-to-text capabilities, enabling secure, fast, and accurate local audio processing with Whisper integration, perfect for .NET developers.

2 min read

Embedding Strategies in LM-Kit: Rapid Prototyping to Durable Storage Guide

Embedding Strategies in LM-Kit: Rapid Prototyping to Durable Storage

Compare in-memory, built-in, and external vector storage methods in LM-Kit. Learn when to use each and how to switch with a unified API.

6 min read

Introducing AgentMemory: Elevating Contextual Recall with Custom Filtering Release

Introducing AgentMemory: Elevating Contextual Recall with Custom Filtering

Discover AgentMemory from LM-Kit, a breakthrough in persistent, context-aware memory for chatbots. Learn how dynamic recall and custom filtering enhance multi-turn conversations for...

7 min read

LM-Kit Goes Multimodal: Introducing Vision Support and Our 2025 Roadmap Release

LM-Kit Goes Multimodal: Introducing Vision Support and Our 2025 Roadmap

LM-Kit now supports Vision Language Models (VLMs), enabling multimodal AI with text and image inputs. New .lmk format simplifies deployment.

5 min read

Introducing LM-Kit’s Keyword: Extraction API Release

Introducing LM-Kit’s Keyword: Extraction API

Discover LM-Kit’s on-device keyword extraction with tiny LLMs. Achieve fast, accurate insights at scale with minimal resources.

4 min read

Building a Function Calling Agent: with LM-Kit Guide

Building a Function Calling Agent: with LM-Kit

Function calling, also known as tool calling, has emerged as a transformative feature in the landscape of artificial intelligence (AI), enabling language

8 min read

Introducing LM-Kit’s New Multilingual Sentiment: Analysis Model Release

Introducing LM-Kit’s New Multilingual Sentiment: Analysis Model

Bringing Real-Time Sentiment Analysis to Any Device with Unparalleled Accuracy.

5 min read

Introducing Dynamic Sampling in LM-Kit.NET: Up to 75% Error Reduction and 2x Faster Processing for LLMs Engineering

Introducing Dynamic Sampling in LM-Kit.NET: Up to 75% Error Reduction and 2x Faster Processing for LLMs

We are thrilled to announce a significant enhancement in our latest release of LM-Kit.NET: the introduction of a new parameter  that allows you to activate or

7 min read

Hello World! Announcement

Hello World!

It’s been an exciting week for us here at LM-Kit. After months of hard work, passion, and innovation, we are beyond thrilled to introduce our company to the

4 min read