hitmux/hitmux-context-engine

Semantic code search and context engine for AI coding agents.

What it solves

AI agents often struggle to find specific information within large codebases or documentation sets using simple text search (grep). Hitmux Context Engine provides a semantic search layer that allows AI agents to find relevant code, notes, and configuration files using natural language queries, filenames, or identifiers.

How it works

The project indexes local directories into a Milvus-compatible vector storage system (such as Local Milvus or Zilliz Cloud). It then exposes these indexes as tools for Model Context Protocol (MCP) clients—including Claude Code, Cursor, and Windsurf—allowing the AI to perform semantic searches across the indexed content.

Who it’s for

Developers using MCP-compatible AI coding assistants and agents who need their AI to have a deeper, context-aware understanding of their local project files.

Highlights

  • MCP Integration: Native support for a wide range of MCP clients like Claude Code, OpenAI Codex CLI, and Windsurf.
  • Semantic Search: Supports natural-language queries, filename searches, and identifier-heavy searches.
  • Flexible Indexing: Ability to narrow search scopes to just code or just documentation.
  • Simplified Configuration: Uses simple .conf files for project settings instead of 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
    blazickjp/arxiv-mcp-server

    A local MCP server for agent literature work. The differentiator is original-LaTeX section reads, BibTeX from arXiv metadata, and topic watches. Papers stay on disk. The working loop is paper ID → outline → one section → citations. Search is optional.

  • Project
    AminForou/mcp-gsc

    An MCP server that connects Google Search Console to AI assistants, enabling natural language analysis of SEO data, indexing audits, and sitemap management.

  • Project
    Context-Engine-AI/Context-Engine

    Context Engine is a service that adds semantic code search, symbol graph navigation, and persistent memory to AI coding assistants via MCP tools and per-editor skill files, letting them understand and navigate codebases more accurately than grep-based approaches.