Lightweight graph database with relational and vector support built using Sqlite, designed to power knowledge and artificial intelligence persistence and retrieval.

Qwen3 models family inference using ONNX Runtime

🏰 AI-powered Windows security monitoring with conversational AI chat for natural language threat hunting. Features human-in-the-loop actions, YARA malware detection, MITRE ATT&CK mapping, vector search & threat intelligence. React dashboard with real-time updates. 12K+ events/sec. .NET 8, Ollama/OpenAI, Qdrant.

⚡ Production-ready .NET Standard 2.1 RAG library with 🤖 multi-AI provider support, 🏢 enterprise vector storage, 📄 intelligent document processing, and 🗄️ multi-database query coordination. 🌍 Cross-platform compatible.

Multi-language BPE tokenizer implementation for Qwen3 models. Lightweight byte-pair encoding for C#/.NET

A Blazor Web App and Minimal API for performing RAG (Retrieval Augmented Generation) and vector search using the native VECTOR type in Azure SQL Database and Azure OpenAI.

Practical GenAI-Eshop application using Semantic Kernel, multi-agent orchestrations, Mcp tools, A2A Agents, Semantic Search, Aspire and more.

Side / Portfolio Project: A .NET Core backend API for a peer-to-peer job matching platform with Telegram bot integration. This application connects people offering services with those requesting services through intelligent matching and recommendations.

Face similarity search

An open-source vector database

Part of the LangChain.NET project. Has separate abstractions, does not contain dependencies on the main project and can be used independently

A lightweight, cross-platform .NET library for building RAG (Retrieval-Augmented Generation) pipelines with local embedding models and SQLite vector storage. Perfect for developers who need privacy-focused, offline-capable document search and AI-powered question answering without external API dependencies.

Aspire, Distrubted Apps, GenAI, Ollama, Vector DB, Minimal APIs, YARP - Api Gateway , Keycloak, Azure Container Apps

🍔 An AI restaurant agent demonstrating the RAG pattern using Semantic Kernel for orchestration and Qdrant for vector memory.

A full-stack movie ticket booking system with FastAPI backend , Windows Forms frontend and Integrate embeddings, vectordb.

Simple PoC of RAG in XAF Blazor

Lightweight, single-file vector database for experiments and small projects.

Local Vector Database coded in c# supports Cosine Similarity, Jaccard Dissimilarity as well as Euclidean , Manhattan, ChebyShev and Canberra distances

Feedback Loops in Generative AI

C# .NET NOSQL ( key value, object store embedded TextSearch SemanticSearch Vector layer ) ACID multi-paradigm database management system.