QuartzUnit

RSS/Atom feed collection with 417 curated feeds. Python MCP server.

Token-efficient browser agent for local LLMs. Playwright + accessibility tree + MarkGrab.

URL to screenshot with metadata. Python MCP server. Claude Vision optimized.

Web page change tracking with structured diffs. markgrab + snapgrab integration.

Local semantic search — embedding-powered grep for files, zero external services.

Universal web content extraction — any URL to LLM-ready markdown. HTML, YouTube, PDF, DOCX.

Schema-driven document extraction with local OCR + LLM. Document in, Structured JSON out.