Open Chat Playground (OCP) is a web UI that is able to connect virtually any LLM from any platform.

Docker Desktop extension that deploys Open WebUI with Docker Model Runner integration in one click

This provides sample codes that uses Microsoft.Extensions.AI for locally running LLMs through Docker Model Runner, Foundry Local, Hugging Face and Ollama

Saraf AI is a fully local assistant built with Next.js and Docker. It connects seamlessly to LLMs via Docker Model Runner using Docker Compose.

Kiwix ZIM-to-vector RAG system for local, offline LLM knowledge retrieval

AI-Native Autoscaler for Docker Compose built with cagent + MCP + Model Runner.

A flexible, extensible AI agent backend built with NestJS—designed for running local, open-source LLMs (Llama, Gemma, Qwen, DeepSeek, etc.) via Docker Model Runner. Real-time streaming, Redis messaging, web search, and Postgres memory out of the box. No cloud APIs required!

A curated collection of Spring Boot projects demonstrating AI and LLM integrations, including examples of AI-powered applications, multi-provider LLM setups, and best practices for Spring AI, modular design, and integration testing.

Multi-agent AI blog generator using Microsoft Agent Framework

A streamlined chat application that leverages Docker Model Runner to serve Large Language Models (LLMs) through a modern Streamlit interface. This project demonstrates containerized LLM deployment with a user-friendly web interface.

A privacy-first, automated code review tool powered by local LLMs. Analyse Git diffs using Docker or Ollama models — no cloud and no data sharing required, just intelligent code reviews on your machine.

This project demonstrates how to configure Spring AI to interact with Ollama and Docker Model Runner

Demo of Docker Model Runner in both development and production environments.

Local AI Chat Agent using Microsoft Agent Framework integrated with Docker Model Runner (DMR) locally

Personal Knowledge Base (PKB) Links tool to organize, store and search effectively

📚 Build an offline multimodal RAG system that retrieves grounded answers from diverse document types with full citation support, all in one unified interface.