Home

Appendix

Quick links:   Version 4.1.1
Version 4.1 Europa
Version 4.0.2
Version 4.0 Copernicus
Application Icon   Version History

New  Improved  Fixed  Removed

Version 4.1.1

This release helps mitigate AI risks, especially when processing online content, to reduce the potential for malicious prompt behavior. We also updated the supported AI providers, adding support for Google's Nano Banana image engine and Anthropic's Claude 4.5 Sonnet.

DEVONthink now detects empty pages when clipping PDFs, ensuring more consistent and useful results, and we made the Safari and share extensions more reliable on macOS Tahoe. Mailboxes in the Import sidebar load faster and match Apple Mail's appearance and you can modify a document's searchable text via the chat or scripting. On the sync side, DEVONthink now automatically adjusts resource usage based on your machine's temperature and workload, and sync in general is more performant. Of course, we fixed bugs and glitches, too.

  • Pro — We added two new options to the AI > Chat settings: Allow download of web pages and Load remote images automatically to let DEVONthink download and examine web content while generating a response. We disabled these options by default, as they could be considered insecure.
  • Pro — We added separate Destination settings for image recognition and multimedia transcription.
  • Pro — DEVONthink now suports Anthropic's Claude 4.5 Sonnet model with pricing and possibilities identical to Claude 4 Sonnet. In addition, the Script Assistant uses now this model instead of Claude 4 Sonnet.
  • Pro — We added support for Google's Nano Banana text-to-image engine in all image creation functions, e.g., the Generate Image window. This model supports image editing, and, unusually, defines the size and style directly from the prompt. You must have a Gemini API key to access this model.
  • We improved the consistency of syntax colorizing for quotes in Markdown documents.
  • When converting EPUB documents, clipping web content, or using the download PDF document from AppleScript command to create PDF documents, DEVONthink now detects empty black and white pages and either filters them out or aborts the clipping.
  • When you select a local or global smart group or smart rule in the Navigate sidebar, DEVONthink now uses the targeted group as the destination for new items and grouping selected items.
  • We reduced resources used for versioning by 90%, especially during toolbar searches and while updating smart groups and rules.
  • DEVONthink now explicitly registers its extensions to ensure they're available in Safari and macOS' Share menu on macOS Tahoe or later.
  • You can now modify the plain text AppleScript property of transcribed files, e.g., images, PDF documents, audio and video files. You can also use the transcription synonym.
  • The external smart script Zettel-ID handles errors caused by Markdown documents that don't contain this ID.
  • We improved the handling of menu scripts execution.
  • Pro — Apple Mail mailboxes and their structures now load faster and more reliably in the Import > Emails sidebar.
  • Pro — Cross-linking items is now easier; just drag and drop an item onto the item link pop-up menu in the Info > Data inspector or sheet form views.
  • Pro — The Help assistant provides the current help page to the chat, enabling summarization, translation, and other AI-assisted tasks.
  • Pro — The Help and Chat assistants retain unsent prompts when reopening windows, inspectors, or popovers.
  • Pro — A revised system prompt for chats eliminates unnecessary AI remarks about anonymized links.
  • Pro — You can optionally save images created or edited via the Chat assistant to the database via prompt. DEVONthink adds the prompt to the Finder Comments of the image.
  • Pro — The Chat assistant lets you modify the searchable text of transcribed documents (e.g., images, PDFs, audio, and video files), allowing updates to translated or spell-checked versions.
  • Pro — The context window of the current AI model now determines the number of tags available for the Files > Tags > Import > Use only already existing tags of a database setting.
  • Pro — Database searches are faster across the board, from the Chat assistant to smart actions and scripting, with notable gains for local AI models.
  • Pro — Web and Wikipedia searches via the Chat assistant, AI smart actions, and AppleScript commands now also use the Ecosia and Yahoo search engines and better filter results from Bing and Brave.
  • Pro — All AI responses, whether from summarization, transformation, script commands, or the Chat assistant, now undergo sanitization to remove potentially insecure content. Tool call names are stripped from the input, web page downloads are restricted to non-document queries, and the Chat assistant disables downloads after accessing item contents, annotations, or comments.
  • Pro — DEVONthink more reliably handles broken links and item links, e.g, returned by OpenAI's gpt-oss model.
  • Pro — Google's Gemini models now automatically use the latest versions of their Flash Lite, Flash, and Pro models
  • Pro — The The Devonian Times and Research Overview templates now default to Claude 4.5 Sonnet when Claude is the selected AI provider.
  • Pro — All Perplexity Sonar models now support vision capabilities.
  • Pro — The Magistral Small and Medium models use version 1.2 now, adding vision support and expanding the context window to 128,000 tokens.
  • Pro — Tool calls with Mistral and local AI are simplified and improved.
  • Pro — Ollama (Remote) now supports API keys, e.g., for the new Ollama Cloud.
  • Pro — The OpenAI (Compatible) option now works with a broader range of providers and models, including those managed by universities and other institutions.
  • Pro — Qwen Code Plus is now available via OpenRouter in the Script Assistant.
  • Pro — The download image with prompt AppleScript command clearly reports an error if the provided image data is not an image.
  • Pro — We improved the as property descriptions for the chat response for message and add custom meta data commands.
  • Sync — The Reading List sidebar and custom metadata now sync more reliably via Bonjour.
  • Sync — DEVONthink now detects the battery and thermal state of the machine and automatically throttles CPU and I/O load during synchronization when necessary.
  • Thumbnailing many small documents could sometimes cause a crash. Fixed.
  • Converting rich text documents or emails to paginated PDF documents could intermittently freeze on macOS Tahoe. Fixed.
  • Invalid relative image and transclusion links in Markdown could break document previewing or conversion, or crash the application. Fixed.
  • Links entered in lists in Markdown documents didn't work properly in WYSIWYG mode. Fixed.
  • Markdown headings containing code didn't display with correct colors. Fixed.
  • Links pasted into Markdown lists did not use the correct color. Fixed.
  • Searches with proximity operators didn't always highlight hits in PDF documents. Fixed.
  • In macOS dark mode, text entered in new HTML documents didn't invert to white. Fixed.
  • Tools > Summarize Annotations and the summarize annotations of records AppleScript command sometimes returned annotations in the wrong order, such as those made by PSPDFKit. Fixed.
  • Web clipping via the Sorter when opened with the keyboard shortcut incorrectly included Safari's profile name. Fixed.
  • Images dropped or pasted into Markdown documents with the Files > Markdown > Import images to group setting enabled didn't apply the Files > Import > Recognition or Files > Tags > Import settings. Fixed.
  • Documents moved or duplicated between databases incorrectly added the extension to the internal name and document could be renamed with an empty name if General > Appearance > Show filename extensions was enabled. Fixed.
  • Duplicate notifications from the Extras sidebar occurred when multiple main windows were open. Fixed.
  • The AppleScript dictionary incorrectly defined and described the root of main windows. Fixed.
  • The internal name of files created via AppleScript incorrectly retained the extension. Fixed.
  • Pro — Loading the Model pop-up menu in the AI > Chat settings could sometimes cause a crash with local AI providers. Fixed.
  • Pro — Claude AI wasn't working anymore in the Help assistant. Fixed.
  • Pro — Retrying a chat in the Help assistant failed after reopening the panel. Fixed.
  • Pro — The Chat assistant and chat response popovers, such as Summarize, didn't render code blocks or multiple tildes correctly. Fixed.
  • Pro — The Reveal command in the item link pop-up menus of the Data inspector or sheet form view always opened a new window. Fixed.
  • Pro — AI responses in the Chat assistant, AI smart actions, or the get chat response for message AppleScript command could stall if required items became unavailable, such as when an item was deleted or its database closed. Fixed.
  • Pro — Image engines supporting image editing stopped working after creating two images. Fixed.
  • Pro — The OpenAI (Compatible) option in the AI > Chat > Provider settings incorrectly required /v1/ in the URL. Fixed.
  • Pro — In the German localization, the OCR > PDF Resolution setting couldn't be changed. Fixed.
  • Pro — In batch processing, the popovers in the Chat - Query and Chat - Continue if smart actions failed to initialize correctly after switching configurations. Fixed.
  • Sync — Bonjour synchronization could sometimes cause memory issues. Fixed.
  • Pro — We replaced no longer functioning models and outdated models from the OpenRouter options.

Version 4.1 Europa

Here it is, the first feature release for DEVONthink 4. Choose from a much wider range of server-based AI models via OpenRouter or by connecting to just any OpenAI-compatible provider. Integrate models from, e.g., Amazon, Meta, Microsoft, xAI, Baidu, Moonshot AI, Qwen, and more. In addition, DEVONthink Europa adds native support for Claude 4.1 Opus, Gemini 2.5 Flash Lite, OpenAI GPT-5, Google Imagen 4, and the latest models by Mistral. Connect to your institution's Ollama installation with a new configuration option.

To further automate your work, describe your task to the the AI-powered script assistant. It generates AppleScript and JavaScript for Automation (JXA) scripts and even corrects common scripting issues. Edit images, both generated or dropped in from other sources, with prompts using common AI image generation models. As generative AI is notoriously bad at maths, the Chat and other AI-assisted functions now support mathematical functions, and if you're working in academia, retrieval-augmented generation (RAG) gets direct access to the huge document collection on arXiv. In addition, DEVONthink Europa comes with a new Quick Look extension for previewing Spotlight results on macOS Sequoia and later, and more responsive editing of especially larger Markdown documents. It also updates and sorts lists and empties the trash significantly faster.

Note: This version is named after Europa, Jupiter's fourth-largest moon. It is a captivating world encased in an icy shell that hides a global subsurface ocean, one of the most promising locations for extraterrestrial life in our solar system. Discovered in 1610 by Galileo Galilei, its name, rooted in Greek mythology, reflects its enduring allure as a symbol of curiosity and the unknown.
  • A new script editor, opened via Data > New > Script lets you draft different DEVONthink scripts, e.g., for reminders or smart rules.
  • A new Quick Look plugin lets you preview documents in, e.g., Spotlight searches on macOS Sequoia and later. This only supports standard file formats: rich and plain text, PDF, HTML, XML, images, audio, and video.
  • A new search criterion Kind is PDF+Text serves as a shortened form of Kind is PDF/PS and Word Count > 0. Additionally, the toolbar search syntax is kind:pdf+text, its negated form kind:!pdf+text.
  • Added a placeholder to the alarm text field in the Info > Annotations & Reminders inspector.
  • The Zettel-ID external script for the Script with Input/Output smart rule action pull this information from Markdown metadata.
  • The AppleScript record class supports the new read-only properties language and markdown source.
  • Pro — Support for OpenRouter is available in the AI > Chat settings and the AppleScript suite. This provides access to some AI models that aren't natively supported. Currently accessible models are from: Amazon, Anthropic, Google, Meta, Microsoft, Mistral, OpenAI, Perplexity, xAI, Baidu, Deepseek, Moonshot AI, Qwen, zAI, noting we aren't providing access to beta, preview, experimental, outdated, or distilled models. The Help assistant, as well as the Research Overview and Mixture of Agents - Text/Markdown templates, also support OpenRouter.
  • Pro — Added support for OpenAI's GPT-5 models. Currently much less expensive than the 4.1 models, it does have a much smaller context window of 400,000 tokens but supports more output tokens and has been trained on more up to date information. Due to the lower costs, web searches are filtered with GTP-5 Nano.
  • Pro — Added support for Anthropic's Claude 4.1 Opus.
  • Pro — Added support for Mistral's Voxtral transcription to the AI > Transcription settings. Currently, this uses Voxtral Mini and is less expensive than OpenAI's speech-to-text models.
  • Pro — Added support for Google's Imagen 4 Ultra in the AI > Image Generation settings, the Generate Image window, and accessible via the download image for prompt AppleScript command. A Replicate.com account is required to use this model.
  • Pro — Added vision support to the Perplexity models Sonar, Sonar Pro, and Sonar Reasoning.
  • Pro — Added Ollama (Remote) the Chat > AI > Provider settings and renamed "Ollama" to Ollama (Local). This allows you to access Ollama running on a network, e.g., at a company or university. The remote provider is also supported in AppleScript, e.g. by the get chat response for message command.
  • Pro — Added a script assistant, available in the Script Editor window, smart actions Apply Script and Script with Input/Output, or reminder scripts. Describe the action you need and a code-compatible AI model will provide a draft script to get things started.
  • Pro — Save all images in a chat with the Save All Images context menu of the Chat assistant, available if the current chat contains more than one image.
  • Pro — The Generate Image window can now modify a generated image or one dropped or pasted into the window. Also, images generated via the Chat assistant can be modified. And as the Chat popover is persistent between launches, you can modify an image in it at a later time. Currently, this function is only available with certain models: Flux Schnell, Pro, Pro Ultra, Stable Diffusion Large or Turbo, and GPT-Image-1.
  • Pro — The Generate Image window now displays a history of created images.
  • Pro — Given the poor calculations produced by LLMs, a new tool lets the Chat assistamt, smart actions, and AppleScript commands evaluate mathematical expressions.
  • Pro — Added the new The Devonian Times template, summarizing today's news via AI.
  • Pro — Added the arXiv site as a search option the the AI > Chat settings.
  • Pro — Added a Language menu to the AI > Summarization settings.
  • Pro — Added a new built-in smart rule, Apply Chat Suggestions. This applies seven common AI suggestions to matched documents, e.g., tagging, summarization, etc., utilizing placeholders and one AI request. This rule can be duplicated and modified to suit your needs.
  • Pro — The Chat assistant, smart actions like Chat - Query, and the download chat response for message AppleScript command can download links in various formats (HTML, Markdown, text, snapshot). The format is automatically chosen, either by the AI or depending on the user's prompt. Currently, this only works with commercial models.
  • Pro — The new AppleScript property current chat model returns the default model.
  • Pro — The new get chat capabilities for engine… model AppleScript command retrieves the capabilities of a specific AI model.
  • Pro — The get chat response for message AppleScript command now has a usage parameter to improve results or control the costs of using external AI.
  • "Audit-proof" databases have been renamed to Revision-proof.
  • Editing very long Markdown documents is more performant. DEVONthink detects links in Markdown documents at least 25 times faster when syntax coloring and WYSIWYG is enabled.
  • Markdown WikiLinking now supports [[link|-]] to use the title of a linked item. This can be useful when using short aliases for linking.
  • Prism.js renders Objective-C code marked with the alternate objc or language-objc as well as the default language-objectivec.
  • DEVONthink indexes web-based documents and converts them to plain text better.
  • The Go > To Document and Edit > Insert > Item Link popovers now search after a short delay to avoid interfering with typing.
  • Updating or sorting by name or kind in item lists is up to ten times faster, including in popovers such as Go > To Document.
  • Editing annotations in the Info > Annotations & Reminders inspector now supports versioning.
  • The Data > Move > Put Back command as well as its context menu counterpart display the destination when only one item is selected.
  • For quicker sorting, the Ascending and Descending commands are now at the top of the View > Sort menu and the sort popup menu in the Information bar of main windows.
  • The Add and Preview buttons in the Sorter now display their shortcut keys when you hold the Command key.
  • In the Sorter's Voice Note and Video Note tabs, the camera and microphone menu is disabled if DEVONthink is disabled in macOS' Privacy & Security > Camera settings.
  • Emptying the Trash is up to five times faster when versioning is not enabled.
  • DEVONthink's built-in folder action scripts now run smart rules using the perform smart rule AppleScript command with the On Import and On OCR event triggers, as appropriate.
  • Querying tags via AppleScript is now supported, e.g., tags contains "support" or where its tags contains {"2025","documentation"}.
  • Records now support the sheet-related AppleScript commands get cell at row/column, set cell at row/column, add row cells, and delete row at position.
  • The AppleScript database property "audit proof" is now revision proof. However, audit proof has been added as a synonym to ensure backwards-compatibility.
  • Pro — Summarizing documents to annotations, e.g., via Edit > Summarize via Chat or Tools > Summarize Documents via Chat, first saves a version when versioning is enabled.
  • Pro — The Research Overview template now supports local AI engines and models having tool call support and a context window of at least 32,000 tokens.
  • Pro — The notification of a chat-summarized RSS article is simpler when only one article is involved.
  • Pro — The search assistant now accepts local AI models with a context window of at least 8,000 tokens.
  • Pro — In the Import > Image Capture sidebar, the Group menu now has a search field for quickly locating groups. Also, the destination settings are saved after each scan and restored when reconnecting to the scanner.
  • Pro — The From date in the Import > Emails sidebar now defaults to the last used To date.
  • Pro — The Chat assistant better handles detecting selected documents, especially when using the Chat popover.
  • Pro — AI-directed features using web, Wikipedia, and PubMed searches are more efficient, filtering out excess or links already processed by concurrent searches. This affects e.g., the Chat assistant, smart actions, and AppleScript commands, and could speed up responses and minimize token usage.
  • Pro — The Chat assistant's progress indicator more clearly shows chat activity, e.g., searching or downloading resources.
  • Pro — The Chat assistant doesn't scroll a received chat response out of sight anymore.
  • Pro — Prompt fields across the application, e.g., in the Chat assistant, the Generate Image window, and the Help assistant, now support using ⇧↩ in addition to ⌥↩ for inserting a line break.
  • Pro — The model menu in the Chat assistant features a search field if more than 25 items are available.
  • Pro — Search request made to Google, Bing, and Brave via chat functions, e.g., the Chat - Query action or prompts in the Chat assistant are more reliable. DEVONthink also handles Mistral's rate limits better.
  • Pro — Bulk processing items via chat, e.g., tagging or summarizing, uses better error handling.
  • Pro — Chat tools calls for local AI models have a reduced temperature for more reliable results and can now download web pages as needed. In addition, the Chat assistant handles errors better.
  • Pro — Irrelevant PubMed and arXiv search results are now filtered in all AI functions, e.g., in the Chat - Query smart action, maintaining the context of the current conversation. For commercial providers, the least expensive model is used for filtering. Additionally, once enough results have been received from these site and Wikipedia, other pending evaluations are cancelled, saving both tokens and time.
  • Pro — Chat suggestions in smart actions, e.g., suggested tags, are more reliably retrieved.
  • Pro — The download image for prompt AppleScript command now reports an error if the specified model doesn't support image editing. When using the Flux engine, the Flux Kontext models are used as they are built for image editing, not just generation.
  • Pro — Updated Gemini 2.5 Flash to the final version.
  • Pro — Both filtering web search results and the Help assistant use now Gemini 2.5 Flash Lite.
  • Pro — Updated Google Image 4 to final version and is used in the Mixture-of-Agents - Images template.
  • Pro — Both AI > Mixture-of-Agents templates no longer use Perplexity due to an increase in irrelevant responses.
  • Pro — Updated Mistral Medium to version 3.1. Mistral Large 3 has better vision support. And "Mistral AI" has been renamed to Mistral in the AI settings and Chat assistant.
  • Pro — The default context window set by DEVONthink for Ollama is now 16,000 tokens.
  • Pro — The "GPT4All" provider has been renamed to OpenAI (Compatible) and can be used connect to any compatible remote services. It also now supports an API key, affecting the AI settings, menus and related AppleScript commands.
  • Pro — Improved compatibility of chat-based smart actions with LM Studio's MLX models, e.g., Gemman 3n.
  • Server — Improved HTTP handling, should also address a rare crash.
  • Markdown lists didn't render properly when indented with one space. Fixed.
  • Thumbnailing Markdown documents could cause a rare crash. Fixed.
  • Scrolling Markdown documents was affected after pasting copied text, changing margins, or syntax highlighting. Fixed.
  • Remote images in Markdown documents didn't render in WYSIWYG mode if the files didn't have a valid file extension. Fixed.
  • Markdown MathJax equations in Asian text didn't render properly. Fixed.
  • Indexed Google Drive documents couldn't be opened via the Data > Open With command. Fixed.
  • Links using Apple Notes' URL scheme couldn't be clicked in documents. Fixed.
  • For RSS and Atom feeds with multiple authors, only the first was used. Fixed.
  • An open Quick Look panel didn't update when changing the selection of the view/edit pane when General > Interface > Preview group content was enabled. Fixed.
  • In the item list in List view, the Tags column didn't display autocompletion results. Fixed.
  • The tooltip shown when hovering over items with truncated names didn't fully display the name if the item also had property icons. Fixed.
  • Groups with a custom icon and applied color displayed differently in different parts of the interface, e.g., the item list and context menu. Fixed.
  • In the Navigate sidebar, you could only drag and drop multiple favorites, smart groups, or smart rules by the icon, not the name. Fixed.
  • The First, Previous, Next, and Last commands in the Go menu couldn't be used in toolbar search results. Fixed.
  • The search field in the context menu and destination popups, e.g., in the Sorter, didn't sort the results by relevance. Fixed.
  • In a multi-monitor setup with vertically positioned screens, the Sorter was only partially visible as a docked tab. Fixed.
  • The item count in the Database Properties window incorrectly included saved versions. Fixed.
  • The internal versions group was incorrectly made visible in the Sorter. Fixed.
  • The Spotlight index for a database could incorrectly contain document versions. Fixed, though rebuilding the Spotlight index via Database Properties may be needed.
  • .strings files weren't indexed correctly, potentially affecting versioning of AppleScript modified files. Fixed.
  • The Scan Text smart rule action didn't ignore Markdown metadata if there was no other content in the document. Fixed.
  • If the DEVONthink helper background task crashed, other background tasks, e.g., running scripts, could be blocked for a period of time. Fixed.
  • Pro — Processing multiple documents via the Chat assistant could sometimes crash the app. Fixed.
  • Pro — Timestamps weren't properly restored when revisiting the Chat assistant. Fixed.
  • Pro — Replies in the Chat assistant could contain improperly escaped Markdown. Fixed.
  • Pro — The (AI) suffix on an AI-generated document names could be misplaced if the name already had a file extension. Fixed.
  • Pro — Claude 3 Haiku responses in the Help assistant often included invalid links. Fixed.
  • Pro — Switching to Mistral in the Help assistant and resending the last chat message failed. Fixed.
  • Pro — AI-generated web searches containing multiple site: operators didn't work correctly. Fixed.
  • Pro — Item links or WikiLinks to groups weren't supported in the AI > Graph inspector. Fixed.
  • Pro — The AI > Graph inspector could incorrectly display a connection line to a hidden (disabled) node. Fixed.
  • Pro — In the popup of URL fields in the Info > Data inspector and the form view of sheets, the Paste and Remove commands neither saved changes nor updated the layout. Fixed.
  • Pro — In the Import > Emails sidebar, nested iCloud mailboxes were duplicated at the account's top-level. Fixed.
  • Pro — Search queries using date-based custom metadata weren't always parsed correctly. Fixed.
  • Pro — Some item properties, e.g., the URL or UUID, couldn't be retrieved by AI in the Chat assistant, smart actions, or the get chat response for AppleScript command. Fixed.
  • Pro — The prompt for Scripts > Chat > Geolocate Image was incorrect. Fixed.
  • Pro — The get chat response for message… as HTML AppleScript command could return incorrectly mapped links. Fixed.
  • Pro — Gemini 2.5 Pro didn't work with the get chat response for prompt AppleScript command when thinking was disabled. Fixed.
  • Server — The icons in the Server > Users settings didn't look correctly in dark mode. Fixed.

Version 4.0.2

This maintenance release introduces support for Google Imagen 4 (Preview), along with several improvements and fixes. We enhanced handling of relative links in Markdown documents to allow spaces, and we corrected an issue with list indentation. We also improved document language detection, which can influence Chat-suggested properties like tags. The Favorites section, e.g., in the Move To context menu now correctly lists all favorited groups. Colored groups also show their designated colors in more locations, such as the Path bar. For AI features, we expanded the prompt field in the Chat and Help assistants to accommodate longer prompts. We extended the timeout period for image generation, and queries will retry up to two times when necessary. As always, we focused on increasing the application's stability and reliability.

  • Image links in Markdown documents now support relative URLs containing spaces without requiring percent-escaping.
  • Custom colored groups now display in color in more places in the interface, e.g., the Path bar.
  • DEVONthink better detects the language of documents, whether you import, index, or create them within the application. This can also improve results of chat-based features of the higher editions, e.g., tag suggestions or summarization.
  • Pro — The prompt field in the Chat and Help assistants can now use up to one-third of the pane's height.
  • Pro — The Chat assistant, chat-driven smart actions, and the get chat response for message AppleScript command now perform two retries, as needed. Additionally, the Chat assistant now shows a message when retrying queries.
  • Pro — Image generation requests run longer before they timeout.
  • Pro — Using engine GPT-Image-1 with the AppleScript command download image for prompt now supports the image parameter.
  • Pro — Using Pico AI Server now supports vision for Gemma 3. We also reduced extraneous logging.
  • Server — In the web interface, only groups with sub-groups display a disclosure triangle.
  • Line items in Markdown lists indented with 4 or more spaces didn't render correctly. Fixed.
  • Images and PDF documents dragged from the Finder into DEVONthink between two Macs connected via Universal Control would be renamed on import. Fixed.
  • Copying section links in EPUB documents via the Table of Contents inspector didn't include anchors. Fixed.
  • After inserting or deleting pages in a PDF document, the title of main and document windows, and the subtitle of document windows didn't reflect the changed page count. Fixed.
  • Toolbar searches using the size: search prefix would fail if they contained spaces, e.g., size> 5 MB. Fixed.
  • Switching away from the AI > Tags inspector to another part of the interface would unnecessarily sound the system beep. Fixed.
  • The Favorites section in the Move To, Duplicate To, and Replicate To context menus and Destination popups, e.g., in the Sorter, only displayed the first favorited group. Fixed.
  • .applescript files couldn't be used as external smart rule scripts due to an AppleScript error. Fixed.
  • Sync — Databases with names containing, e.g., "GoogleDrive", "Google Drive", or "OneDrive" couldn't be created or imported from sync locations. Fixed.
  • Pro — Nested IMAP mailboxes incorrectly appeared in the top-level mailbox in the Import > Emails sidebar. Fixed.
  • Pro — The Label menus in the Info > Generic inspector, Info filter pane, and the context menu of the Navigate sidebar incorrectly contained the Chat Suggestion command. Fixed.
  • Server — PDF documents didn't load in the web interface in Safari. Fixed.
  • Server — In the web interface, EPUB documents couldn't be navigated via the table of contents. Fixed.
  • Server — Sorting the item list on the Size column sorted incorrectly and the Modified column sorted in the reverse direction, ascending or descending. Fixed.
  • Server — The item list and view/edit pane didn't scroll at the same rate. Fixed.

Version 4.0 Copernicus

Our fourth major release — DEVONthink 4.0 Copernicus — brings a host of powerful new features and improvements. DEVONthink now supports external AI providers, both commercial and local AI, as a complement to its own internal engine and implemented with privacy and data safety in mind. You can also write search queries in natural language, let the AI summarize or transform text, and extract text from images or handwritten notes. Use speech-to-text to transcribe and save the speech from media files. You can even create images using AI, directly within DEVONthink.

Store important legal or financial documents in audit-proof databases and as PDF/A. Text in PDFs without text layer and in images is searchable without OCR, and versioning lets you return to previous versions of a document. Edit a document's table of contents, adjust spacings, and fine-tune the WYSIWYG display for Markdown. Organize your favorites, smart groups, and smart rules into groups. We also added new inspectors, most notably a graph that visualizes document relationships. The rewritten web interface of the Server edition is built on a modern foundation, more powerful yet easier to use.

For automators of any skill level, there are new and improved smart actions, including some utilizing AI, as well as many new AppleScript commands. Batch processing now lets you save and reuse configurations.

Note: DEVONthink now requires macOS 13 Ventura or later.

Note: We're dedicating this version to the Copernicus lunar crater and its namesake, the Polish astronomer Nicolaus Copernicus (1473-1543), who revolutionized our understanding of the universe. Contrary to the prevailing view that the Earth was the center of everything, he proposed that the Sun revolved around the Earth. This crater, with its rays extending across the lunar surface, is as notable as the groundbreaking ideas of the man it honors.
  • Document versioning lets you preserve certain states of documents you're editing. Examine or restore saved versions from the new Versions inspector.
  • Audit-proof databases, a new type of databases, prohibit modifying documents placed into them, often necessary for legal or financial documents.
  • Create archival PDFs in PDF/A-2 format via: Data > Convert > to Flattened PDF (with Annotations burnt in), Convert (& Continue) smart actions, and the convert record AppleScript command.
  • Create new PDF bookmarks with the Add to Table of Contents command in the context menu of the view/edit pane, Content > Thumbnails inspector, and the Data > Add To menu.
  • The new batch processing window allows you to create your own library of reusable configurations.
  • Browse the built-in help in the new Help viewer with built-in navigation and search. With the higher editions, you have access to an assistant for chatting with AI about all things DEVONthink, even in languages other than English.
  • Toolbar searches have a new Related Words option, considering also words contextually similar to your entered search terms.
  • A new Tags inspector shows current, related, and suggested tags for the selected document. It also displays a graph of relationships for a selected tag.
  • The Destination and Location popup menus in the Sorter or View > Import section controls, as well as the context submenus for Move To, Duplicate T, and Replicate To, now have a search field at the top for more efficiently locating groups. Additionally, the location of potential matches is shown in macOS 14.4 Sonoma and later.
  • Add reminders to selected items with the Remind Me command available in the Data and contextual menus.
  • Data > Move To > Put Back returns moved, classified, or trashed items back to their previous location. This command is also available via the context menu.
  • Apply tags automatically with the new menu command Data > Tags > Assign Existing Tags. It uses DEVONthink's internal AI to look for tags on similar documents or find tags within the name and text and apply them automatically.
  • Typewriter-like scrolling keeps the currently edited line in the center of the document window. Enable or disable this feature via the Format menu or in the Editing > Format settings.
  • Change the scope bar options of toolbar searches with key commands. Press ⌃⌥1 through 4 while a search is active.
  • Choose whether you want to show the documents contained in a selected group in the view/edit pane with the General > Interface > Preview group content setting.
  • The General > Appearance settings allow assigning colors for duplicate and replicated items.
  • The Editing > Format settings let you control margin, line spacing, and maximum line widths.
  • We added Update name of WikiLinks in square brackets automatically to the WikiLinks settings.
  • Disable automatically loading bookmarks with the Files > Preview > Automatically load bookmarks setting. This might help avoiding issues with problematic bookmarks.
  • We added the option Files > Import > Use content creation & modification dates to use dates from a document's content instead of filesystem dates.
  • Disable or enable sending anonymized usage data via the General > General > Usage: Send anonymized analytics data setting. See our company's Privacy page for more information on the data that may be sent.
  • The menu command Help > Hidden Preferences lets you more easily access rarely used settings.
  • We added many new smart actions, e.g., Script with Input/Output for processing and passing data, Set Script Input that holds data to be passed to the action, and a batch processing action, User Input that allows you to enter information each time the automation runs.
  • We also added new placeholders, e.g., User Input holding the text you entered with the batch processing action of the same name, Script Output with the return value from the Script with Input/Output smart action, and Original Name using the originally imported name of a document.
  • And we added many external scripts for use with the Script with Input/Output smart action, e.g., Text - Lowercase/Uppercase and Daily Quote, that execute and pass the result to the next actions.
  • Add text to an existing document, by inserting, appending, or replacing the existing content, with the powerful update text AppleScript command.
  • Install some popular script libraries from Late Night Software, e.g., Dialog Toolkit Plus, via the DEVONthink > Install Add-Ons panel.
  • Pro — DEVONthink can access external AI engines — both commercial and local models — in a complementary but powerful role to its internal AI. Currently supported commercial services are the latest models of: ChatGPT, Claude, Gemini, Mistral AI, and Perplexity. Supported local AI applications are GPT4All, LM Studio, and Ollama. Depending on the capabilities of each model, DEVONthink supports these AI functions: vision, tool calls, reasoning, and deep research.
  • Pro — A new Chat assistant lets you interact with external AI engines in a variety of ways, from document examination to impromptu inquiries. You access it in a new Chat inspector and Chat popover. Copy or save your chats as a document for later reference, if needed.
  • Pro — We added a new suite of AI-driven templates in the Data > New from Template > AI submenu. These cover a variety of use cases, like deep research, image creation, story writing, and transcribing media and other documents into meeting notes.
  • Pro — Using Apple's Vision framework, DEVONthink will index certain PDFs on import, e.g., those with no text layer, an incomplete one, or with unintelligible content. This makes PDFs searchable without doing OCR explicitly. You can disable this behavior with the Files > Import > Transcribe PDF documents setting.
  • Pro — Via AI, DEVONthink can recognize text in images, including some handwriting, and speech converted to text in media documents. The results can be stored as searchable text, Finder comments, or in an annotation document.
  • Pro — The Data > New > Generate Image command lets you create images via your chosen text-to-image AI engine without leaving the application.
  • Pro — A new Search Assistant popover lets you write search queries in natural language and convert them to DEVONthink's search language via AI.
  • Pro — The annotation commands in the Annotations > Reminders popup menu give you the option to insert AI-generated summaries. For images and media files that have recognized text saved as Searchable Text, you can insert the transcription.
  • Pro — The menu command Edit > Summarize via Chat opens the Summarize popover for a selected document.
  • Pro — Summarize selected documents via AI using Tools > Summarize Documents via Chat. Output to a chosen format, e.g., rich text or a Finder comment.
  • Pro — The new Data > Recognize submenu gives you AI commands recognizing text and notes or barcodes in an image or transcribing speech-to-text.
  • Pro — New commands in the Data menu's Rating, Label, and Tags submenus let you use AI to change the metadata on selected files.
  • Pro — The new Graph inspector displays a variety of relationships for a selected document, e.g, WikiLinks, item links, mentions, etc.
  • Pro — Produce auditing records listing the import, renaming, and deletion history of the contents of an audit-proof database via new commands in the File > Export and Tools menus.
  • Pro — We added functions for importing email attachments, including Tools > Import Email Attachments, Files > Emails > Import attachments in the settings, and the import attachments of record AppleScript command.
  • Pro — The new AI settings pane lets you control various AI functions: Chat for setting up your default AI engine, Summarization to setup how summarization is done, Image Generation, and Transcription.
  • Pro — We added a Chat Font Size option in the General > Appearance settings to change the font size in AI-related actions, e.g., in the Chat assistant or the Summarize and Transform popover.
  • Pro — We added a Recognition section to the Files > Import settings, containing options for processing incoming documents with AI, e.g., to transcribe media files or PDFs.
  • Pro — The new setting Files > Tags > Import: Add Chat suggestion to documents lets you use AI to examine a document and add tags to it. You can limit the suggestions to already existing tags.
  • Pro — Import messages or mailboxes from Apple Mail or Microsoft Outlook with key commands that you set up in the Files > Emails settings.
  • Pro — The new batch processing window offers several built-in configurations using AI in a variety of ways, e.g., classifying documents or renaming a document based on its content.
  • Pro — Use AI-driven smart actions, e.g., Chat - Query for general AI queries, and the conditional Chat - Continue if action that only continues running with a positive response.
  • Pro — Run OCR and use the created document for subsequent actions using the OCR & Continue smart action.
  • Pro — We added new Chat Suggestions placeholders that DEVONthink resolves using AI, e.g., Price, Company, or Summary.
  • Pro — Several new AppleScript commands let you use external AI, e.g., get chat response for message, download image for prompt, and transcribe record. These commands also include many deep parameters, e.g., model, temperature, and thinking, to create very detailed AI interactions.
  • Pro — The new Chat category of the Scripts menu provides you with some useful example scripts.
  • Markdown documents now support live scrolling in Side-by-Side view and the rendering updates as you edit. Also, WYSIWYG editing now displays image links as images and hides raw URL data in the Markdown source.
  • Quickly create crosslinks between documents by typing >> and choosing from suggested matches.
  • Square bracket WikiLinks now support alternate names and section anchors, e.g., [[Technical Note 15040|Email Issues#remedies]].
  • Toolbar search results now support using the View > Show/Hide Details command to let you toggle displaying the matched item's location.
  • Toolbar searches are now more forgiving with some syntax, internally correcting it as needed.
  • You now can group your custom items in the Navigate sidebar, e.g., your favorites, smart rules, etc.
  • We relabeled some inspectors: "See Also & Classify" is now See Also, "Custom" is now Data.
  • The Info inspectors now include the Annotations & Reminders inspector.
  • Reminders now launch DEVONthink one minute before an alarm is set so you no longer need to keep it running all the time. Also, the alarms now include Send Email with Item Link and a new Send Email with Attachment, allowing you to email the document directly.
  • You can edit the outline in the Content > Table of Contents inspector. For text-based documents, e.g., rich text, moving sections in the inspector moves the document contents as well.
  • When you use the Data > New > With Clipboard command, it more intelligently creates a format appropriate to the type of data on the clipboard, e.g., a Markdown document when it detects Markdown content.
  • We reorganized the Settings panes to keep similar functions and concepts together. This reorganization has produced some new panes, e.g., the Files > Tags settings, as well as many updates to others, like setting label colors in the General > Labels view.
  • You can assign colors to groups via the Generic inspector or Info popover.
  • You can modify file dates and more types of custom metadata, e.g., currency, via smart rules and batch processing, including using AI suggested values.
  • When the Verify & Repair Database command finds errors, they are now shown in a more informative window. When relaunching after a crash or force quit, DEVONthink will attempt to resolve errors it can.
  • We have modernized and improved the AppleScript support. It comes with better JXA support, a new dictionary with code examples, new commands, properties, and parameters, and optimizations greatly improving the performance of filtering clauses, e.g., whose and where.
  • We've also made many subtle cosmetic changes to DEVONthink including updating many icons, like property icons, special group icons like Contacts, and updated toolbar icons.
  • Pro — Email handling now uses AppleScript and shows more accurate mailbox structures which also load more quickly in the Import > Emails sidebar. It also shows unread email counts per-mailbox, similar to Apple Mail.
  • Pro — The rewritten File > Import > References from Bookends command uses Bookend's improved AppleScript support and pulls in more information.
  • Server — We replaced the web interface with a rewritten, much more modern version, new login page, support for displaying more file formats, handling more data, and more robust interaction with DEVONthink.
  • Server — In the Server > Users settings, logged in users have an indicator next to their username. You can also set a Session Expiration to automatically log out idle users.
  • Sync — The approximate size of an encrypted database is now included in the sync data and used as the default size when importing the database on another Mac.

License Agreement →