Hi everyone! Looking for honest feedback on our multi-parser CLI tool

Hey everyone! Happy to finally say hello here!

I’ve spent most of my time working on document parsing, and one of the open-source projects I released earlier was OCRFlux. I’m now working on DocDot, a local PDF parser stack for macOS. The problem we kept coming back to was pretty simple: people want to keep documents local for privacy reasons, but local tools often force a tradeoff between speed and parsing quality.

We built DocDot around that tension, so people can run multiple parsers locally, compare them, and choose the one that fits the file instead of settling for a single compromise.

We bring several parsers into one workflow so you can install them in one place, switch between them based on the file, and compare outputs in our webUI. Right now that includes NanoDoc (developed by ourselves), PaddleOCR, GLM-OCR, LiteParse, and MinerU.

I keep coming back to the same question while we tighten the product: where does PDF parsing usually break down for you? If you’ve spent time dealing with PDFs, I’d really love to hear what you wish tools in this space did better!

I also share our launch page here. If you have thoughts on the assets, the way we explain it or what feels unclear, I’d really appreciate that too!!