LM-Kit.NET is an enterprise-grade toolkit designed for seamlessly integrating generative AI into your .NET applications, fully supporting Windows, Linux, and macOS. Empower your C# and VB.NET projects with a flexible platform that simplifies the creation and orchestration of dynamic AI agents.
Leverage efficient Small Language Models for on‑device inference, reducing computational load, minimizing latency, and enhancing security by processing data locally. Experience the power of Retrieval‑Augmented Generation (RAG) to boost accuracy and relevance, while advanced AI agents simplify complex workflows and accelerate development.
Native SDKs ensure smooth integration and high performance across diverse platforms. With robust support for custom AI agent development and multi‑agent orchestration, LM‑Kit.NET streamlines prototyping, deployment, and scalability—enabling you to build smarter, faster, and more secure solutions trusted by professionals worldwide.
Learn more

AnalyticsCreator is a metadata-driven design application for data warehouse automation and data product engineering across the Microsoft data stack.
Its Governed Control Model connects business meaning, data structures, transformation rules, dependencies, lineage and technical implementation in one controlled project model. Data teams design the required architecture in AnalyticsCreator, then generate native Microsoft assets from that design.
Generated outputs can include SQL Server objects, SSIS packages, Azure Data Factory pipelines, supported Microsoft Fabric components, deployment artefacts and Power BI semantic models. AnalyticsCreator supports dimensional, 3NF and hybrid modelling approaches together with ingestion, transformations, delta loading, historisation, Slowly Changing Dimensions, snapshots and repeatable data-processing patterns.
Because generated outputs are native Microsoft technology, no AnalyticsCreator runtime is required in production. Organisations retain ownership of the resulting implementation and can integrate generated assets into Git, Azure DevOps and CI/CD workflows.
Lineage, documentation and dependency information remain connected to the design, helping teams understand change impact before regenerating affected assets.
Design Intelligence extends this governed project context into AI-assisted data engineering by providing authorised AI tools and agents with structured access to metadata, lineage, dependencies and design rules.
Typical use cases include enterprise data warehouse development, Microsoft Fabric adoption, SQL Server and SSIS modernisation, governed Power BI delivery and repeatable data product engineering.
Learn more
Pikkart AR SDK
Develop your Augmented Reality applications with a lightweight, user-friendly, rapid, stable, and cost-effective on-device detection and tracking SDK. Enjoy the benefits of unlimited image datasets through the Cloud Recognition Service, which is both fast and precise, allowing for easy scalability to accommodate extensive image collections. Leverage our image recognition SDK to craft exceptional augmented reality experiences utilizing native API, Unity 3D, or Xamarin platforms, regardless of how many images need recognition. Construct your application in an uncomplicated and scalable manner while utilizing your CMS for effective marker management. Enhance your project by incorporating geolocated augmented markers and integrating navigation services into your augmented reality features. Additionally, our SDK enables the creation of diverse augmented reality experiences from various prints of the same image, ensuring flexibility in your designs. Embrace the power of our technology to streamline your AR development process and deliver engaging experiences to your users.
Learn more
Virtual REX
Electromagnetic sensors are composed of two main components: a "front-end" that both generates and detects electromagnetic waves via a subsystem known as the Receiver/Exciter (REX), and a "back-end" responsible for signal and data processing, which is generally carried out through software. Each of these subsystems must be developed independently before they can be seamlessly integrated. The process of creating the complete sensor becomes increasingly complex and time-consuming due to unforeseen challenges that arise during integration testing. This complexity largely stems from the interdependencies between the subsystems that are not easily testable during their individual development phases. As a result, any necessary software updates, configuration adjustments, waveform modifications, and technology upgrades can incur significantly higher costs since they often require on-site verification with the actual front-end hardware. To mitigate these issues, the Virtual Receiver/Exciter (VREX) utilizes a simulated front-end, thus streamlining the testing and integration process. By employing a virtual model, developers can identify and address potential integration issues much earlier in the development cycle.
Learn more