mq VS navajo

mq-db takes a different approach: it parses every Markdown element into a typed block, builds interval and secondary indexes, and exposes the result through SQL and a jq-inspired query language called mq.

Built on top of mq, a jq-like command-line tool for Markdown processing, mx parses your Markdown documents and executes the code blocks within specific sections.

The markdown-query package brings the functionality of the mq Markdown processor to Python. mq uses a jq-like syntax to filter, transform, and extract data from Markdown documents.

HTML Element Markdown Output Notes - # - ###### Header levels preserved Text blocks Paragraph spacing maintained , -, 1. List structure preserved Pipe tables Column alignment detected `code` Inline code formatting code blocks Code blocks with language detection > Quote block formatting [text](url) Links with titles preserved  Images with alt text Processing Pipeline The HTML to Markdown conversion follows this sequence: HTML Parsing: DOM tree construction from input HTML Structure Analysis: Identify semantic elements and nesting Markdown Generation: Convert elements to Markdown syntax Query Processing: Apply mq queries to resulting structure Output Formatting: Return filtered and formatted content Installation Install the mq CLI tool which includes the MCP server: # Using Cargo cargo install --git https://github.com/harehare/mq.git mq-cli # Using Homebrew brew install harehare/tap/mq # Direct binary download curl -L https://github.com/harehare/mq/releases/latest/download/mq-linux-x86_64 -o mq chmod +x mq Enter fullscreen mode Exit fullscreen mode Integration Benefits Structured Processing: jq-like queries enable precise content extraction Format Flexibility: Handles both HTML and Markdown inputs Discovery Features: Built-in function and selector documentation Resources mq Documentation MCP Specification mq Playground Claude Desktop MCP Guide Support 🐛 Report bugs 💡 Request features ⭐ Star the project if you find it useful!

# Install via Homebrew brew install harehare/tap/mqcr # Download pre-built binary directly curl -L https://github.com/harehare/mq/releases/latest/download/mqcr-linux-x86_64 -o mqcr chmod +x mqcr # Or build from source cargo install https://github.com/harehare/mq.git mq-crawler

# Convert all HTML to Markdown using mq-crawler $ mqcr https://mqlang.org # Extract specific elements from multiple HTML files $ mqcr -o docs https://mqlang.org

Uploading multiple Markdown files to NotebookLM one by one is tedious. mq solves this by merging and filtering files into a single, optimized input for better AI analysis.

The crate is named navajo after the code talkers of WW2. It isn't stable yet (still in version 0.0.x) and isn't wire compatible with tink as I took some liberties to change the way it processes online/streaming AEAD.

Working on getting navajo closer to a place where others can use it.