hitmux/hitmux-context-engine

Semantic code search and context engine for AI coding agents.

What it solves

It provides AI agents with a way to find relevant information across local directories that goes beyond simple text searching (grep). It allows agents to perform semantic searches for code, documentation, notes, and configuration files to better understand the context of a project.

How it works

The engine indexes a local directory into a Milvus-compatible vector storage system (such as Local Milvus or Zilliz Cloud). It then exposes these indexes to MCP (Model Context Protocol) clients—like Claude Code, Cursor, and Windsurf—via a server. This allows the AI to use natural-language queries, filenames, or identifiers to retrieve the most relevant snippets of context from the indexed data.

Who it’s for

Developers using MCP-compatible AI coding assistants and agents who need their tools to have a deeper, semantic understanding of their local codebase and project documentation.

Highlights

  • Semantic Search: Supports natural-language queries instead of just keyword matching.
  • MCP Integration: Works with a wide range of clients including Claude Code, OpenAI Codex CLI, Cursor, and Windsurf.
  • Flexible Storage: Compatible with Local Milvus and Zilliz Cloud.
  • Scoped Search: Ability to narrow searches specifically to code-only or docs-only context.
  • Simplified Config: Uses .conf files for project configuration rather than complex per-client environment variables.

Related

  • Project
    SammySnake-d/fast-context-mcp

    An MCP server that provides AI-driven semantic code search for AI clients, using Windsurf's Devstral API to iteratively find relevant code snippets via local commands.

  • Project
    zilliztech/claude-context

    An MCP plugin that adds semantic code search to AI coding agents, allowing them to efficiently retrieve relevant snippets from large codebases using a vector database.

  • Project
    AminForou/mcp-gsc

    An MCP server that connects Google Search Console to AI assistants, enabling SEO analysis and site management through natural language conversations.

  • Project
    Context-Engine-AI/Context-Engine

    A semantic code search and symbol intelligence system that provides AI coding assistants with deep codebase context, memory, and navigation tools via MCP.

  • Project
    MicrosoftDocs/mcp

    A Model Context Protocol (MCP) server that gives AI assistants direct, real-time access to official Microsoft documentation and code samples to prevent hallucinations.