Launched this week
Snapdown
Turn anything on your Mac screen into clean Markdown
156 followers
Turn anything on your Mac screen into clean Markdown
156 followers
Snapdown turns any part of your Mac screen into structured Markdown, preserving headings, lists, tables, and text instead of flattening everything into plain OCR. Capture with one shortcut, paste anywhere, and keep every screenshot local on Apple silicon.
Snapdown
@bsuffern Hey Broden - good work! Tried it out and like it! Happily paid the license! Wishing you lots of success!!
Snapdown
@supamca Thank you very much for the support! I’m happy to hear that you like it.
@bsuffern
The structure-preserving part is the bit that matters. I deal with a lot of scanned compliance documents, certificates, permits, inspection reports and every OCR tool I've tried turns a table of expiry dates into a paragraph of numbers with no way to tell which date belongs to which row.
Two questions: does Aggregate Mode handle a table that spans a scroll, where you capture it in two passes? And does running locally on Apple silicon mean it works on a machine with no network at all, that's a real constraint in some of the sites my users operate in.
Upvoted. Nice to see something shipped for a boring problem
Snapdown
@fasathor Thank you for the support and for sharing that use case. That’s exactly where preserving the relationships between rows and values becomes important.
Currently, capturing a table in two passes with Aggregate Mode would produce two separate tables rather than stitching them together. A scrolling capture feature, where you select a region and scroll the document within it, could solve this and is something I’d like to explore in a future Snapdown update.
The Mac only needs an internet connection at the time of licence activation. Once activated, all OCR processing runs locally and Snapdown continues working without a network connection.
I hope that answers your questions. Thanks again for checking out Snapdown.
@bsuffern That answers both, thanks. Activation-only network is the right trade-off, and honest of you to say the two-pass stitching isn't there rather than fudging it.
Scrolling capture would make this properly useful for my case, a full-page inspection report never fits one screen. If you do build it, I'd happily be a test case with some genuinely ugly scanned documents.
Congrats on the launch.
Snapdown
@fasathor Thank you, I appreciate it. If I add scrolling capture in a future Snapdown update, I’ll reach out. Testing it with genuinely difficult scanned documents would be very helpful.
@bsuffern I’ve found structured OCR becomes risky when it silently invents table cells. Do you preserve block-level confidence or source coordinates, or mark uncertain Markdown sections as needing review? That would make it much safer for personal-data screenshots.
Snapdown
@anupam_chugh Thanks for the thoughtful feedback! That’s a great point. At the moment Snapdown doesn’t expose confidence scores or flag uncertain sections—the only warning it currently provides is for potential duplicate input. Block-level confidence, source coordinates, and optional review flags are definitely ideas I’d like to explore in future updates to make structured OCR more robust. On the privacy side, though, everything is processed entirely locally, so no screenshots or personal data ever leave your device.
The Mac-only caveat I’d want to know before recommending this to my team: when you capture from a browser window, does it pull the rendered text from the DOM or does it run the OCR pipeline on the screenshot? For Notion and Coda docs specifically, the difference shows up in whether nested blocks and toggles come out flat or preserve their structure.
Snapdown
@hazy0 Great question! Snapdown currently works purely from the screenshot—it doesn’t access the browser DOM or application data. That means it only processes what’s actually visible on screen. For things like Notion or Coda, collapsed toggles wouldn’t be captured because they’re not visible in the screenshot, while visible nested blocks are reconstructed from the visual layout by the OCR pipeline rather than the underlying document structure.
Yeah Broden! Markdown era is here and you're a doing an amazing job on it. Congrats on this impressive launch
Snapdown
@german_merlo1 Thank you very much for the support! I really appreciate the kind words.