Demystify AI agents by building them yourself. Local LLMs, no black boxes, real understanding of function calling, memory, and ReAct patterns.

Demystify RAG by building it from scratch. Local LLMs, no black boxes - real understanding of embeddings, vector search, retrieval, and context-augmented generation.

Run AI ✨ assistant locally! with simple API for Node.js 🚀

Build an AI communication analyzer from scratch to understand how AI products actually work. Learn prompt engineering, reasoning pipelines, and local LLM integration using Node.js - no frameworks, no abstractions, just fundamentals

Local Llama project, L³ is an electron app that runs llama 3 models locally

Build AI engineering skills from scratch with 260+ lessons, 20 phases, and hands-on tools for practical learning

Context engineering decides what a model sees. 14 self-contained examples that build the mental model one piece at a time, Node.js + local GGUF. Understand deeply, then use frameworks wisely. Hands-on context engineering - all local.

The friendly and powerful desktop AI chatbot supporting both local and cloud AI models

Turn SQL into authenticated HTTP APIs — with schema-aware Text-to-SQL, AI review & mock data, powered by local LLM (GGUF / Ollama). Supports MySQL / PostgreSQL / Oracle / SQL Server.

AHIVE Ecosystem: A full-stack Multi-Agent system featuring a Local LLM Core Engine, Tauri-based IDE, 3D Visualization Dashboard, and Electron Desktop App.该系统强调**本地化部署**（Local-First）和**可视化交互**，支持多智能体（Multi-Agent）协同工作，适用于个人开发者、AI 研究团队及企业级自动化场景。

A retro terminal AI companion that runs open language models entirely on your own machine — no cloud, no accounts, no telemetry.

A comprehensive Next.js application for running and exploring .gguf open-source LLM models locally.

🤖 Build an AI agent from scratch to analyze emotional impact in messages, enhancing your understanding of AI product development principles.

Ts RAG system. ingest documents, creates embeddings, stores in pgvector and query through cli or mcp server. fully local with node-llama-cpp

🤖 Run any GGUF language model locally with a Claude-inspired UI. Built-in HuggingFace downloader, real-time streaming, dark/light mode & code highlighting. Zero API keys. NVIDIA CUDA supported. Deploy free on HuggingFace Spaces.

Autonomous, privacy-first AI companion browser powered by Qwen 2.5 local LLM, Chrome DevTools Protocol & real-time HTTP automation API

AI-powered web development with local LLM inference using Electron and node-llama-cpp

Privait is a self-hosted personal AI system that combines LLMs, vector memory, and RAG to create a private, extensible AI workspace.

📚 Enhance LLMs with retrieval augmented generation, using external data for improved factual recall and grounding in context.