Every Format

Built for Every Kind of Data.

Notes, links, files, videos, CSVs, Markdown, JSON, and more: one shortcut captures them all. Email import is on the way.

What you can save

  1. Drop any file type into the capture overlay (PDF, image, video, spreadsheet, archive) and Mindly stores it.
  2. Text-based files (PDF, Markdown, JSON, CSV) get content-aware processing: AI reads inside them for summaries and tags.
  3. Images get visual-content tags. Videos get thumbnails, metadata, and timeline markers.
  4. Everything you save, every type, is searchable, organized, and visible in the mind map.

What people actually save

Mixed research

PDFs of papers, CSVs of datasets, MP3s of interview recordings, and typed notes about each one, all in the same Space. Mindly reads inside the PDFs and transcribes the audio, so the entire library is searchable by content, not just by filename.

Design references and assets

Screenshots, hi-res images, and Figma exports sit alongside the notes you wrote while looking at them. Mindly applies visual tags (colour palette, layout style, subject matter) so finding the right reference is a search, not a scroll.

Code and data snippets

Drop a JSON config, a CSV export, or a Markdown spec into your library. AI parses the structure and tags by content. Months later you can find "that API response shape we used for v2" by description, not by where you saved the file.

Audio, video, and voice

Voice memos, podcast episodes, and video clips up to several gigabytes each. Mindly transcribes the audio, generates a summary, and stores the transcript searchable alongside the file. The video that mentioned the idea is findable by the idea, not the date.

What "supports every format" actually means

Text-based files: read inside the file

PDF, DOCX, Markdown, TXT, RTF, HTML, JSON, CSV, YAML, XML. Mindly extracts the text content, runs AI tagging and summarization on it, and makes the contents searchable. The file is not just a blob. It is a participant in your library.

Image files: visual tagging

PNG, JPG, GIF, WebP, HEIC, AVIF, SVG. Mindly applies visual tags using image-understanding models: subject matter, colour palette, layout type, text in the image (OCR). A screenshot of a Figma file gets tagged differently from a photo of a whiteboard.

Audio and video: transcribe and index

MP3, WAV, M4A, FLAC, MP4, MOV, WebM. Mindly transcribes the audio track, summarizes the content, and stores the transcript as searchable text alongside the file. Hour-long recordings become navigable.

Everything else: stored and tagged

ZIP archives, code files (JS, PY, TS, etc.), spreadsheets (XLSX), presentations (PPTX), and proprietary formats land in your library with filename and metadata tags. Even formats Mindly cannot read inside are organized by what you wrote about them.

Why it matters

Why "every format" is the real ask

Most note apps force you to choose what to save: text-only, or only what their parser understands, or only files under a certain size. The result is a fragmented memory. The paper is in Mendeley, the screenshot is in Dropbox, the voice memo is on iCloud, the spreadsheet is in Downloads, and the notes about all of them are in Notion. Six places for one idea is six places to check when you want to find the idea again, and nobody actually checks all six. Mindly closes the gap. Every file type lands in the same library. AI reads inside the ones it can parse, tags the ones it cannot, and surfaces all of them through a single search. The "where did I put that" problem disappears because there is only one "where". That is the real promise of a second brain: not just notes, but everything you saved, in one place that works.

File format questions, answered

What file formats can Mindly handle?

Notes (typed text), links (URLs with rich previews), images (PNG, JPG, GIF, WebP, HEIC, AVIF, SVG), documents (PDF, DOCX, RTF, Markdown, TXT, HTML), spreadsheets (CSV, XLSX), data files (JSON, YAML, XML), presentations (PPTX), audio (MP3, WAV, M4A, FLAC), video (MP4, MOV, WebM), code files, and ZIP archives. AI processing depth varies by type.

Can Mindly read inside PDFs, Word docs, and spreadsheets?

Yes. Text-based files get content-aware processing: Mindly extracts the text, runs AI tagging and summarization on it, and makes the contents searchable. A PDF you saved a year ago is findable by a phrase inside it, not just by filename.

Does Mindly support audio and video files?

Yes. Mindly transcribes the audio track of voice memos, podcasts, and video clips using cloud transcription. The transcript is stored alongside the file and is fully searchable. Hour-long recordings become navigable; a phrase you remember is enough to find it.

Are CSV, JSON, and Markdown files supported?

Yes. CSVs are parsed for column structure and content; JSON is parsed for key paths; Markdown is rendered with full formatting. All three are searchable inside, and Mindly applies content-based tags rather than just filename ones.

Are email and Notion exports supported yet?

Email and Notion are on the roadmap, not yet shipped. Google Drive integration is also planned. Today you can manually import individual files (a Notion export DOCX, an email saved as PDF) and Mindly will handle them like any other document.

How does Mindly preview files visually?

Images and PDFs render inline with thumbnails in the library and full preview on click. Audio and video files show a player. Documents show the first page or first paragraph as a snippet. Code and data files show syntax-highlighted content.

Guides from the blog

Bring your mess. Mindly sorts it.

Download Mindly and drop the next ten things you’d normally scatter across folders. See what comes out the other side.