Claude local semantic code search tool that uses the EmbeddingGemma model to achieve fully offline intelligent multi - language code search. Integrates with Claude Code through the MCP protocol, protects privacy, and does not require an API key.

This project is a document processing server based on the Model Context Protocol (MCP) standard. By building a vector database and an MCP interface, it enables AI assistants to access external document resources and break through the knowledge limitations of large language models. The project includes two major components: a document processing pipeline and an MCP server. It supports multiple embedding models and file formats and can be applied to scenarios such as querying the latest technical documents and understanding private code libraries.

A code semantic search MCP server based on PostgreSQL and Voyage embedding model, providing code snippet search, file list, and content retrieval functions

An MCP server project that provides a service for automatically selecting the OpenAI O3 or Google Gemini 2.5 Pro model based on the number of tokens, supports recursive embedding of file paths in prompts, and is suitable for code review and solving complex problems.

A semantic code search server based on the MCP protocol, supporting two embedding models, OpenAI and Ollama, capable of indexing local projects or Git repositories, and providing an enterprise - level private code search solution.

VectorCode is a code repository indexing tool designed to optimize the prompt construction of large programming language models (LLMs) by indexing and providing code repository information. It supports multiple embedding engines, provides command - line tools and Neovim plugins to help developers more efficiently use project context to improve the quality of model output.