This repository is an organized collection of links and resources focused on local LLM deployment and usage. It covers inference platforms and engines, model providers, user interfaces, agent frameworks, Model Context Protocol tooling, RAG implementations, coding agents, evaluation and observability tools, hardware recommendations, and tutorials. The list spans general-purpose models, coding models, multimodal models, and specialized variants, serving as a reference guide for developers and enthusiasts looking to self-host and run language models on their own hardware.