Launched this week
Submit any URL, get clean Markdown back. JavaScript-rendered pages handled automatically. Navigation, footers, and cookie banners stripped. Output goes straight into an LLM context window or knowledge base with no post-processing. Anti-bot evasion built in: proxy rotation, browser fingerprinting, retries. CDN-hosted screenshot included. Same API handles PDFs, DOCX, PPTX, images, audio, and video. Free plan available.
Fabric
@johnny_makes Tried it a couple of times and got crazy good output. Great job!
Fabric
@seomaxtech Amazing, glad to hear that! Would love to hear more about your potential use case!
@johnny_makes Congrats! This looks great but I'm a little unsure of the use case for such a tool. I understand markdown is the preferred diet of LLMs so is this a more elegant form of scraping or are there more possibilities? If you can share some possible use cases that would be great. Thank you :)
Fabric
Hey @mark_townsend1 – good way to think of this is specialised scraping + processing, so a developer gets the scraped content in the highest quality in the target format for immediate use.
The alternative would be multiple separate steps (scrape, then turn that into Markdown), with some possible quality loss also as the scraper isn't gathering for a particular format from the outset.
Looks useful for AI agents. Did you think about providing an MCP server or a hook to use in claude/codex? It could replace the curl command.
Fabric
@mateuszkonik Thanks for the feedback, we're starting to explore this! Thinking about a skill and possibly also MCP, so agents can use these services on your behalf
Progress AI Observability
This seems super useful to me as a marketer, especially handling all different formats too. I will give it a check, upvoted!
Fabric
@martin_yochev1 Thanks Martin – do let us know how you get on, we love all feedback!