published by arknill

7 listings on this page, in order of arrival. Each one has its own page with README, repository facts and source links.

1. Browsegrab
   Token-efficient browser agent for local LLMs. Playwright + accessibility tree + MarkGrab.
2. Diffgrab
   Web page change tracking with structured diffs. markgrab + snapgrab integration.
3. Docpick ★ 1
   Schema-driven document extraction with local OCR + LLM. Document in, Structured JSON out.
4. Embgrep
   Local semantic search — embedding-powered grep for files, zero external services.
5. FeedKit
   RSS/Atom feed collection with 417 curated feeds. Python MCP server.
6. MarkGrab
   Universal web content extraction — any URL to LLM-ready markdown. HTML, YouTube, PDF, DOCX.
7. Snapgrab
   URL to screenshot with metadata. Python MCP server. Claude Vision optimized.