Hosted on MSN

I added these MCP servers to my local LLM stack, and one of them replaces a $249 paid tool

If you've spent any time around local LLMs, you've almost certainly heard about MCP. The Model Context Protocol started life as a Claude-only thing in late 2024, and it has since turned into the de ...
note

Reading zvec at the implementation level: Design and minimal Python implementation of an in-process vector DB

I want to use vector search without setting up an external server. There are surprisingly many requirements like that. When you don't want to bring in Docker at the PoC stage, want to embed search ...
note

[May-June 2026] Local LLM Observation Log: Two Months of Specialized 4B Medical Models and the New Generation of Embeddings

This series is a fixed-point observation record of local LLMs for hospital pharmacists. Every month, I collect information from multiple AIs using the same research prompt, adding primary source ...
GitHub

Zero-Cost AI Web Scraper

🚀 Complete self-hosted AI web scraping stack with ZERO external API costs! This project combines powerful open-source tools to create a comprehensive web scraping and AI extraction system that runs ...
GitHub

retrieval-augmented-generation-rag

AI-Rag-ChatBot is a complete project example with RAGChat and Next.js 14, using Upstash Vector Database, Upstash Qstash, Upstash Redis, Dynamic Webpage Folder, Middleware, Typescript, Vercel AI SDK ...