# Local RAG

A high-performance local RAG system based on Rust, integrated with Claude Desktop via the MCP protocol to achieve local processing, semantic search, and privacy protection of PDF documents.

Linggen is a locally-first RAG and MCP memory layer that provides cross-project shared memory, code repository navigation, and multi-tool connection capabilities for AI programming assistants. All data is processed locally by default.

The Knowledge RAG System is a local retrieval - augmented generation system that integrates with Claude Code through the MCP protocol. It supports hybrid search (semantics + keywords) for multiple document formats such as PDF and Markdown, and provides keyword routing functions, suitable for personal knowledge base management.

Libragen is a local RAG library construction tool used to connect AI assistants (such as Claude) with your actual documents and code libraries. It reduces AI hallucinations by creating a searchable knowledge base, supports building from local files or Git repositories, and is directly integrated into the AI workflow through the MCP protocol.

Haiku RAG is an intelligent retrieval - augmented generation system built on LanceDB, Pydantic AI, and Docling. It supports hybrid search, re - ranking, Q&A agents, multi - agent research processes, and provides local - first document processing and MCP server integration.

A locally run RAG - style Model Context Protocol (MCP) server for web search. It can provide the latest web information retrieval function for models such as Claude without using an API.

AmanMCP is a privacy-first, zero-configuration local code library retrieval-augmented generation (RAG) tool that integrates with Claude AI through the MCP protocol, providing hybrid search functionality. It runs entirely locally without the need for an internet connection.

ctx-sys is a locally prioritized hybrid retrieval-augmented generation (RAG) tool designed for AI programming assistants. It analyzes the codebase through a tree parser, combines semantic vector search, keyword retrieval, and graph relationship traversal to provide in-depth project understanding for AI assistants. All operations are performed locally to protect code privacy.

DeepRepo is a production-grade local RAG engine Python library that supports multiple AI providers, provides vector storage, MCP server integration, and a RESTful API, without the need for an external vector database or heavy framework.