Announcements, engineering deep dives, and the decisions behind LM-Kit One and LM-Kit.NET: private AI across models, agents, RAG, search, and documents.
Most document AI fails before the model sees a word. LM-Kit Document Parsing turns PDFs, scans and photos into structure an LLM can trust, leads every self-hosted method on ParseBench, and runs entirely on your hardware.
Engineering
Every component in a private AI stack can be excellent while the system as a whole stays mediocre. Why we build LM-Kit as one engineering system, and measure it as one.
Perspective
Neither term has a formal definition. The questions behind them do: where the computation runs, and who can reach the data and what derives from it. How the vendors who use each term define it, with sources.
Announcement
LM-Kit One is generally available: the private AI application server for every developer and team putting private AI into their organization or the software they ship. Free to build and evaluate, nothing to activate.
Announcement
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.
Guide
A comprehensive guide to the open standard that turns AI agents into on-demand specialists
Release
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
Guide
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.
Release
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.
Guide
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.
Release
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...
Release
LM-Kit now supports Vision Language Models (VLMs), enabling multimodal AI with text and image inputs. New .lmk format simplifies deployment.
Release
Discover LM-Kit’s on-device keyword extraction with tiny LLMs. Achieve fast, accurate insights at scale with minimal resources.
Guide
Function calling, also known as tool calling, has emerged as a transformative feature in the landscape of artificial intelligence (AI), enabling language
Release
Bringing Real-Time Sentiment Analysis to Any Device with Unparalleled Accuracy.
Engineering
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
Announcement
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
