I m launching webclaw here because I kept hitting the same problem while building agents and RAG workflows: getting a page is easy, but getting clean context from that page is not.
Raw HTML usually brings too much noise: nav, footers, cookie banners, duplicated layout text, scripts, missing JS-rendered content, and inconsistent structure.
webclaw is my attempt at solving that layer: scrape/crawl/map websites and return clean markdown, JSON, structured extraction, summaries, diffs, and MCP/CLI-friendly output.
Webclaw turns websites into clean markdown, JSON, structured data, and LLM-ready content. Use it to scrape pages, crawl docs, extract fields, summarize, diff changes, and feed reliable web context into AI agents, RAG pipelines, CLI workflows, SDKs, and MCP clients. Designed for developers building with Claude Code, Cursor, LangChain, LlamaIndex, and custom agents.
Press āā§S from any app ā a floating post-it appears. Type your thought, press Escape, done. Under 3 seconds.
Notes are plain .md files on your Mac. No account. No cloud. No tracking. Ever.
On-device AI semantic search finds notes by meaning. Zero data leaves your machine.
Built with Rust & Tauri ā 8MB, launches in 0.3s. No Electron.
āā§M ā Folder selector
āā§P ā AI search
āā§1-9 ā Jump to folders
Free. Open source. MIT license. Your thoughts, your files.
