defuddle

Extract clean markdown from web pages, removing clutter and navigation to minimize token usage. Use Defuddle CLI to extract clean readable content from web pages. Prefer over WebFetch for standard web pages — it removes navigation, ads, and clutter, reducing token usage. If not installed: npm install -g defuddle Always use --md for markdown output: Save to file: Extract specific metadata: - Converts web page content to readable markdown using the --md flag, stripping ads, navigation, and boilerplate - Supports output to file with -o flag and extraction of specific metadata properties (title, description, domain) via -p - Offers multiple output formats: markdown, JSON with both HTML and markdown versions, or raw HTML - Preferred alternative to WebFetch for standard web pages, documentation, articles, and blog posts where token efficiency matters