[knowledge-rag] - Drop docs, search instantly from Claude Code — 12 MCP tools, 20 format parsers, hybrid search + reranking. Zero servers, zero API keys, 100% local.

SQL-like query language and CLI for Qdrant vector search engine

The highest-scoring AI memory system ever benchmarked that isn't reliant on LLM reranking. And it's free & burns less tokens.

A context-aware coding assistant that understands your entire codebase.

Chat with Lex! A RAG app, using HyDE with milvus DB for vector store, VLLM for LLM inference, and FastEmbed for Embeddings!

FastAPI backend for archive.ire.org

A polars plugin for embedding DataFrames

A fast and simple local API for generating text embeddings.

This project showcases how to use AWS Lambda Managed Instances with AI/ML capabilities for real-time customer analytics

🧠 Universal long-term memory for AI agents. GraphRAG-powered knowledge base with vector search + graph traversal. Privacy-first, local-only, MCP-compatible. Connect Claude, Copilot, or any AI assistant.

Hub repo for Claude Code related tools

Hub repo for Claude Code related tools (Japanese distributions)

In-memory vector store with FastEmbed integration for Python applications.

Graxon: First Open-Source Hybrid RAG to eliminate hallucinations through a persistent Knowledge Graph layer.

An AI-powered customer support system that automatically classifies tickets and provides intelligent responses using Retrieval-Augmented Generation

Lodestar — a 2026 agentic, RAG-grounded HBCU career-advice assistant (model-agnostic, hybrid RAG, MCP server). Evolved from IgniteAI, the first-place HP FOWA 2024 custom GPT (faithfully reproduced here).

Semantic search and Q&A Telegram bot for Google Drive, backed by Qdrant and an optional OpenAI-compatible LLM.

Local AI memory daemon — persistent memory for Claude Code, Cursor, Windsurf, Cline. Reference implementation of the Open Memory Protocol. Apache 2.0.

Chatbot modulaire Python avec LangChain (LCEL), Ollama, RAG sur PDF et interface Streamlit