DocOCR – Convert document images to Markdown locally on macOS
Local Markdown OCR via CLI and HTTP, though macOS Live Text overlaps heavily.
A local proxy that converts websites and APIs to clean Markdown. Convert HTML pages, JSON APIs, and dynamic sites. Get token counts for LLM budgeting.
Markdown-for-Agents proxy for private/internal sites, but Jina.ai and Firecrawl cover most use cases.
AI/LLM engineers, platform teams managing internal APIs, developers feeding web content to AI agents
Cloudflare Markdown for Agents · Jina.ai Reader API · Firecrawl
I built this on my 35-minute BART ride to SF using my phone as the IDE (and a couple of hours of feature creep/testing). It's a combination MCP server + HTTP proxy that converts web content to markdown on-the-fly.
Key features:
* HTTP/HTTPS proxy with automatic HTML to markdown conversion * Token counting and caching to stay efficient * Content negotiation (only converts when Accept: text/markdown) * MCP server * JavaScript rendering for dynamic sites
Let me know what you think!
Local Markdown OCR via CLI and HTTP, though macOS Live Text overlaps heavily.
Built-in IPv6 NDP spoofing turns SOCKS chains into transparent proxies.
Content negotiation serves raw Markdown to agents, skipping the reconversion tax entirely.
Yet another Markdown server when markserv, docsify, and mkdocs already exist.
Embeds DOM selectors in markdown comments so scrapers don't need LLM on every run.
Zero-code proxy capture beats SDK-based eval tools like LangSmith and Arize.