Knowledge base, information manager, document organizer and more

DEVONthink Pro for Mac

DEVONthink Pro for Mac

  -  83 MB  -  Trial
DEVONthink Pro for Mac is your trusted supplementary brain. It's the one store for all your documents that also helps you keep them organized and presents you with just the right data you need for your work.

DEVONthink keeps all your information in one easy-to-backup database and presents it to you in a variety of ways optimized to your work style. Multiple views help you quickly navigate your data.

Let the app automatically file new documents for you based on how you filed similar documents. Later, the advanced search function retrieves the documents that you need for your task, while smart groups present related data together.

Quickly find similar documents using keywords extracted from the document and the unique "See also" function.

Collect, analyze, summarize, write: With the tool you have all you need in one app that actively supports your workflow. View all your data in one place, use an innovative approach to tags to quickly organize documents, and write in the enhanced rich text editor. Use manual or automatic Wiki-style links to effortlessly cross-reference your work.

Store your documents in the self-contained database or simply reference them by using the index feature. Clip data from other apps with just a keystroke, adding it to the GTD®-like inbox for later filing, or take notes with the Take Note panel or the Dashboard widget. Browser extensions, the Services menu, and the Sorter panel integrate DEVONthink for macOS with your workflow.

Sync your data directly on the local network, via WebDAV or Dropbox, or using just anything mountable, e.g. a USB stick or SD card. You decide what data is synced, when, and to which locations. Full AES 256 bit encryption keep everyone out who you don't want to let in. Your data belongs to you, not to your service provider or us.

Use separate databases for each project, and let automatic grouping create order from chaos. Add RSS feeds to your database to automatically import new articles, or download and archive full websites.

The concordance gives you a real-time analysis of your data.

Features and Highlights

Get organized, effortlessly
Keep your data organized, safe, and work with it the way you want.

Be more productive
Don't fight the info flood all yourself. DEVON think is smart and assists you.

Keep everything in sync
Use the same data on all your Macs. Work in a team. Fast, robust, and secure.

The Pro advantage
Use multiple databases, more file formats, and automate your workflow.

Made especially for you!
Researchers, students, educators, journalists, lawyers, power users...

How to Use
  • Open DEVONthink Pro from Applications folder
  • Create a new database or open an existing one
  • Import files or folders using drag and drop
  • Use smart groups to organize and filter data
  • Add tags, annotations, and comments to documents
  • Search documents using AI-enhanced search
  • Sync databases across devices via iCloud or WebDAV
  • Use the built-in web browser to capture web pages
  • Automate tasks using AppleScript or smart rules
  • Backup and archive your databases regularly
System Requirements

macOS 10.14 Mojave or later

Intel or Apple Silicon Mac

Minimum 4 GB RAM (8 GB recommended)

At least 1 GB of free disk space

Internet connection for sync and updates

PROS
  • Powerful AI-assisted search and organization
  • Flexible data import and export options
  • Supports a wide range of file types
  • Robust syncing with encryption support
  • Advanced automation via smart rules and scripts
CONS
  • Interface may feel overwhelming at first
  • High price compared to basic note apps
  • Mobile app requires separate purchase
  • Limited collaboration or team features
Note: 150 hours run-time trial version. Requires 64-bit processor.

Why is this app published on FileHorse? (More info)
  • DEVONthink 4.2.2 Screenshots

    The images below have been resized. Click on them to view the screenshots in full size.

    DEVONthink 4.2.2 Screenshot 1
  • DEVONthink 4.2.2 Screenshot 2
  • DEVONthink 4.2.2 Screenshot 3
  • DEVONthink 4.2.2 Screenshot 4
  • DEVONthink 4.2.2 Screenshot 5

What's new in this version:

New (Pro):
- Perform AI-driven research with multiple sources, e.g., arXiv, PubMed, even your databases, with the new `perform chat research` AppleScript command. Control where AI searches with the `sources` parameter and the number of results with `maximum results`.

Improved:
- The appearance of placeholder text in the interface, e.g., in some empty table views, is more consistent with the system settings
- We made some cosmetic improvements to the sidebar in the Help viewer
- You can now load external JavaScript for Automation (JXA) scripts with a `.js` extension in the Scripts menu, as well as use them for smart rules and batch processing
- Tags separated by commas or semicolons are better parsed and applied when set via scripting
- Updated application icon for older macOS releases and Sparkle

Improved (Pro):
- The automatically generated identifiers of custom metadata (see Data settings) now ignore characters reserved for our search syntax, e.g., `:`.
- Database searches via the Chat assistant, Chat - Query smart action, or the new AppleScript `perform chat research` command now filter irrelevant results.
- Revisions to the internal names of Anthropic's Claude models ensure future model updates won’t break existing scripts, templates, or smart rules. Also, the AI > Research Report and The Devonian Times templates now use Sonnet's revised name.
- Gemini Pro and Flash Lite are now at version 3.1 (Preview) via the native API and OpenRouter. Also, Gemini 3.1 Pro and 3.1 Flash handle reasoning better. Note that Gemini Flash Lite 3.1 (Preview) is more expensive than the former version 2.5.
- More reliable tool of chat assistant, the Chat - Query action of smart rules and batch processing, and the `get chat response for message` AppleScript command for evaluating mathematical expressions. In addition, the constant eps0 is now also supported.
- Ollama has improved support for the lfm2 model and GPT-OSS now reasons better.
- Ollama reasoning models (except GPT-OSS) enable thinking now only when using Settings > AI > Chat: Usage: Best (option is also available in the chat assistant). Otherwise it's disabled to speed up responses (e.g. up to twelve times faster in case of Qwen3.5).
- Nano Banana 2 replaces version 1 and now supports the Quality (HD or Standard) setting.
- The script assistant supports GPT 5.3 Codex via OpenRouter.
- We improved the AppleScript dictionary description of the `transcribe record… language` command.

Improved (Server):
- When revisiting the web sharing interface, a warning dialog will appear if you're not logged in.

Fixed:
- Repairing a database with orphaned OPML documents incorrectly converted them to RSS feeds or outlines. Fixed.
- The View > Hide/Show toolbar command wasn't disabled in the Help viewer. Fixed.
- Converting an empty rich text document to plain text or Markdown failed. Fixed.

Fixed (Pro):
- Importing OPML email attachments always converted them to RSS feeds or outlines and could create orphaned files. Fixed.

Removed (Pro):
- Removed the soon-to-be-retired Claude 3 Haiku. Bulk tasks, e.g., filtering search results, are now done with 4.5 Haiku. Note that the 4.5 model is more expensive
- Removed all Qwen3 235b models from OpenRouter, except the ones for coding. Use the latest Qwen 3.5 models instead