Knowledge Rag

Knowledge Rag is a local Retrieval-Augmented Generation (RAG) system designed for use with Anthropic's Claude Code model. It features hybrid search, cross-encoder reranking, markdown-aware chunking, and includes 12 MCP tools. The tool is fully local, relying on pure ONNX in-process computation with no dependence on external servers, making it ideal for developers and organizations seeking secure, private, and customizable AI-powered document and code search and retrieval.