Open source. Open possibilities.

A curated collection of 90+ hands-on AI engineering tutorials and projects covering LLMs, RAG, agents, MCP, multimodal apps, fine-tuning and evaluation, organized by beginner, intermediate and advanced difficulty.

Lexos is an event-driven AI document processing engine combining a Go gateway, Python workers, Redis queues and self-hosted models for offline RAG, summarization and speech transcription.

ParadeDB is a Postgres extension that integrates full-text search, vector retrieval, and analytics into a single database.

LEANN is a lightweight vector database designed for personal RAG applications, reducing storage requirements by up to 97% through graph-based selective recomputation.

PixelRAG renders documents as screenshots and retrieves over images directly, preserving visual structure like tables and charts that text parsing loses. Includes a hosted 8.28M-page Wikipedia index, CLI tools, and Claude Code integration.

CocoIndex is an open-source incremental indexing framework designed to provide AI agents and LLM applications with continuously fresh context by reprocessing only changed data.

MemPalace is a local-first AI memory system that stores conversation history verbatim and retrieves it via semantic search, with pluggable backends, an MCP server, knowledge graph, and CLI hooks for coding agents.

QMD is a local, on-device search engine for markdown notes, docs, and meeting transcripts. It combines BM25 keyword search, vector semantic search, and LLM reranking, all running locally via node-llama-cpp. Supports CLI, SDK, MCP server, and agentic workflows with JSON output and metadata filtering.

Utility OS is a Next.js academic workspace for university students with Google Drive-synced notes, hybrid RAG AI search with grounded citations, a study planner, GPA calculator, SRS flashcards, Pomodoro timer, and a PWA client.

A first-principles handbook on context engineering for LLMs, covering foundations, RAG, memory systems, multi-agent orchestration, cognitive tools, and neural field theory with runnable examples, templates, and research-backed guidance.

Lemory is a local middleware that transforms markdown notes (e.g., Obsidian vaults) into a context database for AI agents. It supports keyless on-device hybrid search, Korean-specific processing, hierarchical token savings, and knowledge graph visualization, integrating with various AI tools via MCP.

TalaDB is an embedded vector and document database designed for on-device AI, providing a unified TypeScript API across Browser, Node.js, and React Native.

Redis is an open-source in-memory data structure server used as a cache, NoSQL database, message broker, search and vector query engine. The README covers key use cases, data types, client libraries, quick start, and source build instructions.

Open WebUI is a self-hosted, extensible AI platform that provides a user-friendly interface for local and cloud-based models, supporting Ollama and OpenAI-compatible APIs.

Python library for on-device AI data infrastructure, offering quantized image/text embedding providers, batch indexing for images, videos and documents, incremental clustering, semantic search and few-shot classification.

Web of Flaws is a structured, markdown-first catalog of web security vulnerabilities and secure code replacements designed for developers, security engineers, and AI coding agents.

Crawl4AI is an open-source LLM-friendly web crawler and scraper that converts web pages into clean, structured Markdown for RAG, agents, and data pipelines. Features async crawling, LLM extraction, Docker deployment, stealth mode, and a CLI.

HelixDB is an OLTP graph-vector database built in Rust on object storage, designed for knowledge graphs and AI memory.

RAGFlow is an open-source Retrieval-Augmented Generation (RAG) engine that combines RAG with Agent capabilities to provide a high-fidelity context layer for Large Language Models.

An unofficial MCP server that gives AI assistants seven read-only tools to search, list and read any Fumadocs documentation site, working against a deployed URL or a local docs repo via a single npx command.