🚀 New

• Added Groq LLAMA 4 models: Maverick 17B and Scout 17B.
• Introduced xAI Grok 3 models: Grok 3, Grok 3 Fast, Grok 3 Mini, and Grok 3 Mini Fast.
• Added OpenAI GPT-4.1, o3, and o4 Mini models.

🔧 Fixed

• Resolved issue preventing connection to the TogetherAI API.
• Fixed crashes when resetting conversations or deleting the newest message.
• Corrected incorrect model names returned from xAI Grok.

🚀 New

• Added support for the new Google Gemini 2.5 Pro Exp model.

✨ Improved

• Removed deprecated models from the Perplexity and Groq.
• Optimized internal image assets, reducing application size.
• Implemented general performance improvements throughout the app.

🔧 Fixed

• Resolved an error that prevented users from creating new Perplexity and Groq services.
• Corrected a problem that stopped users from archiving conversations.
• Addressed a license check issue that sometimes occurred during new conversation creation.
• Fixed a window management issue where clicking the app icon on the dock after closing could incorrectly open two windows.

🚀 New

• Added o3-Mini, o1, GPT-4.5-Preview for OpenAI.
• Added Claude 3.7 Sonnet and removed deprecated Claude models.
• Added Saba model for MistralAI.
• Added the DeepSeek Reasoner R1 model.
• Added Google Gemini models: Flash 2.0 Stable, Flash 2.0 Lite Stable, Flash 2.0 Thinking, and Gemini Pro 2.0.
• Introduced new Groq models: DeepSeek R1, Llama 3.3, and Qwen 2.5.
• Added Grok 2 and Grok 2 Vision models for xAI.
• Added new Cohere models: Command A and Command R7B.
• Added expanded Sonar lineup: Sonar Deep Research, Sonar Reasoning Pro, Sonar Reasoning, Sonar Pro, Sonar, R1 and removed deprecated Perplexity models.

🔧 Fixed

• Fixed a memory leak issue.
• Improved overall app performance.
• Resolved an issue causing crashes when undoing multiple times in the prompt editor.

🚀 New

• Added GPT-4o 20241120 for OpenAI.
• Added Sonar Huge Online (405B) for Perplexity services.
• Added Ministral (3B, 8B), Pixtral (Large, 12B) for MistralAI services.
• Added Gemini Flash 1.5 8B (Latest, Stable), Gemini Pro 1.5 Stable (Gemini Pro 1.5 002), Gemini Flash 1.5 Stable (Gemini Flash 1.5 002) for Google Gemini services.
• Added LLaMA 3.1 70B Specdec, LLaMA 3.2 Preview (1B, 3B), LLaMA 3.2 Vision Preview (11B, 90B) for Groq services.
• Added Gemini Pro 1.5 002, Gemini Flash 1.5 002, Claude 3.5 Sonnet v2, Claude 3.5 Haiku for Google Vertex AI service.
• Added Claude 3.5 Sonnet v2, Claude 3.5 Haiku for Anthropic Claude services.
• Added xAI support with Grok and Grok Vision models.

🔧 Fixed

• Resolved the problem when adding new Anthropic Claude and Google Vertex AI endpoints.

🚀 New

• Introduced new OpenAI models: o1-preview and o1-mini. Please notice that these models are exclusive to Tier 5 users who have spent over $1,000 and 30+ days since first successful payment.
• Added new models, including LLaMA Guard 3 and LLaVA 1.5 to Groq service. Users can now upload images and ask questions with the LLaVA 1.5 model on Groq.
• Added support for Cerebras models, further expanding our AI capabilities.

🔧 Fixed

• Resolved an issue preventing the addition of new Google AI endpoints.

🚀 New

• Added GPT-4o Long model for OpenAI.
• Added LLaMA 3.1 support for Groq and OctoAI services.
• Added LLaMA 3.1 (Llama 3.1 API Service) support for Google Vertex AI service.
• Updated models and removed deprecated models for Perplexity service.
• Added the ability to archive and unarchive multiple conversations and folders.
• Introduced a new keyboard shortcut, Command + Shift + C, to copy the last response of a conversation.
• A trash bin has been added, where deleted conversations and folders will be stored before being permanently deleted after 30 days.

✨ Improved

• Enhanced response handling for OctoAI.
• Set default max tokens to 4096 for Anthropic Claude models.

🔧 Fixed

• Auto spell checking now works correctly in the prompt editor.
• Resolved the problem where the prompt editor's height was not resetting after sending with quick action buttons.

🚀 New

• Added support for GPT-4o Mini for OpenAI, includes vision capabilities.
• Added support for Mistral NeMo & Mistral Codestral Mamba.

🔧 Fixed

• Fixed an issue where only the first character of the prompt was submitted when pressing the send button or quick action buttons.

🚀 New

• Added support for GPT-4o on OpenAI Azure, includes vision capabilities.

✨ Improved

• Enhanced overall scrolling experience for better user interaction.

🔧 Fixed

• Resolved an issue where the prompt editor failed to display prompt templates when selected from the built-in prompt library.

🚀 New

• Added Gemini 1.5 Flash model and Gemini 1.5 Pro with 2M context length.
• Introduced Anthropic Claude 3.5 Sonnet and Mistral Codestral models.

✨ Improved

• Removed the delete button from the top-left corner to prevent accidental deletion of all conversations.

🔧 Fixed

• Fixed performance issue when typing very long prompts.
• Fixed issue max_tokens is too large when use Anthropic Claude 3 models.
• Fixed issue where the prompt text was not cleared after being sent to the AI provider.
• Resolved issue with adding Vertex AI at the us-east5 region. Now, when adding the Vertex us-east5 endpoint, use claude-3-opus@20240229 as the input model.
• Fixed issue where the system and user roles were not alternating correctly with Perplexity models when the first message was from the assistant and context mode was set to the last 5 messages.

🚀 New

• Added support for OpenAI's new flagship GPT-4o model with vision and text capabilities.
• Introduced DeepSeek models.
• Added new models while removing deprecated ones for Perplexity.
• Implemented Speech to Text feature with support from both OpenAI and Apple native capability for prompt input.
• Added support for Text to Speech, allowing users to choose between OpenAI and Apple's native capability for reading AI responses out loud.
• Added actions for file upload, allowing audio files to be uploaded for transcription, summarization, translation, and key point extraction.
• Added support for copying and pasting files (image, audio, document) into prompt editor.

✨ Improved

• Updated app Settings UI.

🔧 Fixed

• Resolved occasional scroll issue causing jumping.
• Resolved issue of receiving infinite responses from Ollama llama2 model.
• Addressed problem with stream response not functioning well with Perplexity models.
• Fixed issue where the message view was being overlapped when the prompt editor grew in size.

🚀 New

• Added support for Llama 3 models on Anyscale.
• Added functionality to enter the model name during the validation of the Vertex AI endpoint.

✨ Improved

• Enhanced the scrolling effect for smoother navigation.
• Updated the user interface for the message editing view.

🚀 New

• Added support for Llama 3 models on Groq and Perplexity.
• Introduced support for LaTeX formatting.

✨ Improved

• Optimized overall application performance, including improved scrolling, better handling of long messages, and simplified multi-paragraph selection for copying.
• Disabled network proxy when using local inference sources such as Ollama, LMStudio, MLX.
• Transitioned explanatory messages to popover form in specific settings fields.
• Enhanced user interface for the main message view.

🔧 Fixed

• Resolved problems preventing some users from utilizing Claude 3 models on Vertex AI.

🚀 New

• Added custom model field for Ollama when creating new endpoint.

✨ Improved

• Updated model name for Cohere Command R+.
• Included service logos next to each answer from AI.
• Enhanced document upload capabilities, specifically for Excel and CSV file formats.
• More detailed error messages now shown for Vertex Claude 3 models.

🔧 Fixed

• Resolved a bug causing crashes during document uploads.
• Addressed a crash that occurred during the cleanup of conversations for certain users.

🚀 New

• Introduced GPT-4-Turbo model from OpenAI.
• Integrated the Gemini 1.5 Pro model for Vertex AI users.

✨ Improved

• Enhanced search functionality now allows for content search across all conversations.
• Updated the MindMac icon in the message view to reflect the icon selected in app settings.

🚀 New

• Introduced Command R & Command R+ models for Cohere.
• Added support for Brave Search for Internet Browsing.
• Integrated support for KeyMateAI Google Browse Assistant API.

🔧 Fixed

• Removed unnecessary quick text shortcuts for accessing prompt template list and occupation list.

🚀 New

• Added native support for llama.cpp.
• Introduced Gemini 1.5 Pro and Gemini Ultra models.
• Integrated Anthropic Claude 3 models into Vertex AI.

✨ Improved

• Implemented cost display for Claude 3 models in stream mode.

🔧 Fixed

• Resolved errors occurring when using Claude 3 models.

🚀 New

• Added Claude 3 Haiku model.
• Added support for image upload for Claude 3 models.
• Implemented support for Anyscale models.
• Introduced support for Kagi Search, enabling Internet browsing directly from the platform.
• Added support for MLX. Users can now easily connect to a MindMac by starting an MLX server or PicoMLXServer.

✨ Improved

• Improved citation in file upload feature.
• Improved performance when receiving response in stream mode.
• The model dropdown list has been updated to hide embedding models for a cleaner interface.
• Modified the default keyboard shortcut to activate "Bring MindMac to front" from Control + Space to Shift + Control + Space.

🔧 Fixed

• Enabled plain HTTP connection for local network.
• The platform now remembers the editing prompt when users switch between conversations.

🚀 New

• Introduced document upload feature: We're excited to announce the addition of a document upload feature, currently in beta. This allows you to upload files and inquire about their content. It seamlessly supports PDF, plaintext, and some code file formats. Preliminary testing with Microsoft Office files (Word, PowerPoint, Excel) has shown promise, and we encourage you to provide feedback on this functionality.
• Introduced new Anthropic Claude models: Claude 3 Opus & Claude 3 Sonnet.
• Rolled out new Perplexity models, including Sonar Small Chat, Sonar Small Online, Sonar Medium Chat, Sonar Medium Online, and Codellama 70B Instruct.
• Added new Large model from MistralAI, along with updates to existing models.
• Added native support for Groq service.

✨ Improved

• Discontinued support for outdated Anthropic Claude and Perplexity models.

🔧 Fixed

• Addressed a keyboard shortcut issue where Command + Shift + Enter inadvertently activated Inline mode, despite Shift + Enter being the designated shortcut.
• Resolved an issue causing poor rendering quality in Internet Browsing results with some OpenAI models, improving the visual experience.
• Fixed issue with alternating messages when using Perplexity models.

🚀 New

• Introduced network proxy setting, allowing configuration of HTTP or SOCKS5 proxy for routing MindMac traffic.
• Added a new option to enable or disable auto-correction.

✨ Improved

• Updated the menubar icon for better width conformity.

🔧 Fixed

• Addressed a problem where the right sidebar showed blank fields in macOS Ventura 13.
• Fixed a crash triggered by adjusting the width of the left sidebar in macOS Ventura 13.
• Corrected an issue where the conversation title was not fully visible in certain situations.
• Resolved a crash that occurred when an API endpoint was deleted and a new one was added immediately afterward.
• Solved a problem where GPT4All returned an empty response.

🔧 Fixed

• Resolved crashing problem when attempting to delete user messages or conversations while receiving streaming response.
• Fixed crashing problem during the cleanup process of conversations when launch the app.
• Addressed an issue where certain specific cases were causing blank fields to appear on the right sidebar.
• Fixed a problem where the message view would scroll up and down immediately after completing a streaming response.
• Corrected an issue where the summary line would display the incorrect context mode when switching between conversation and global profile.

🚀 New

• Enhanced overall app performance to provide a smoother user experience, including improved scrolling, faster search functionality, and seamless conversation switching.
• Added new OpenAI models: gpt-4-0125-preview, gpt-4-turbo-preview, and gpt-3.5-turbo-0125.
• Added a new Perplexity model: mixtral-8x7b-instruct.
• Introduced a quick action Diagram feature, enabling users to generate diagrams swiftly.
• Modified the left sidebar to remember the last state it was in when reopening the app, ensuring a seamless user experience.
• Introduced an add button to the left sidebar, which appears when it is narrow, allowing users to create new conversations or folders conveniently.
• Enabled image vision support for the Ollama LLaVA model, allowing users to upload images and ask something about them using local model via Ollama.

✨ Improved

• Disabled the unread notification feature by default to prevent unnecessary notifications.

🔧 Fixed

• Resolved the issue causing crashes when moving files into folders.

🔧 Fixed

• Fixed a bug that caused the app to crash for certain users when initializing data during the initial launch.
• Resolved an issue where incorrect prompt templates and occupations were displayed when switching between default data and user-input data.

🚀 New

• Added context setting in the profile.
• Introduced quick action buttons when starting to type on the prompt editor.
• Implemented an option to show or hide buttons on the toolbar.
• Added the functionality to remember the app when opening message content in an external app.
• Replaced the extra bar on top of the message view with a new status bar at the bottom of the app.

✨ Improved

• Enabled stream mode by default.
• Enhanced the user interface for the button list when hovering over a message.
• Set the conversation profile as the default with the same settings as the global profile when creating a new conversation.

🔧 Fixed

• Resolved a crash issue that occurred when deleting conversations from the sidebar.
• Fixed an issue that displayed the wrong model when switching between API endpoints in the conversation profile.

✨ Improved

• Eliminate the need to provide an API key when adding a new Ollama endpoint.
• Remove Ollama model from the list if it is not running upon refreshing the model list.

🔧 Fixed

• Fixed a crash issue that occurred when adding new endpoint in several specific cases.

🚀 New

• Introduced support for Together AI.
• Added an option to toggle the unread notification feature.
• Included select all and deselect all buttons in the model management view.

✨ Improved

• Updated OpenAI latest models.
• Updated Mistral AI logic to align with API changes.
• Made the width of the right sidebar persistent even after restarting the application.

🔧 Fixed

• Fixed a crash issue that occurred when adding Ollama as the first API endpoint.
• Resolved a crash issue that occurred when attempting to open prompts and occupation template lists when the keyboard shortcut was not functioning.

🔧 Fixed

• Resolved a crash issue that occurred when adding new Ollama endpoint.
• Fixed a bug causing a crash when using Inline mode on several Mac models.

🔧 Fixed

• Resolved a crash issue that occurred when adding new Ollama endpoint.

🚀 New

• Added full support for Ollama. Now you can use Ollama without LiteLLM.

🚀 New

• Introduced the Internet Browsing feature, allowing users to access the latest data from the web. This feature is available in both the main chat and Inline mode.
• Added support for OctoAI.
• Included additional new models for Anthropic Claude.
• Implemented the ability to archive conversations. Users can now archive conversations and unarchive them at a later time.
• Added a feature to change the app icon, giving users the ability to personalize the appearance of the app.
• Included an option to hide or show the total amount spent, providing flexibility in displaying financial information on the toolbar.
• Added an option to hide or show the user's prompt templates and occupation templates.

✨ Improved

• Removed the favorite icon from the toolbar and added it to each row on the sidebar for easier access.

🔧 Fixed

• Resolved a crash issue that occurred when regenerating a title from a sidebar row.
• Fixed a crash issue that occurred when attempting to delete an in-use endpoint for global profile.

🚀 New

• Added button to clear all chats and folders quickly.
• Implemented feature to refresh OpenRouter model list.

✨ Improved

• Improved performance when opening the model list of a specific API endpoint.

🚀 New

• Introduced support for Mistral AI models.
• Added support for Google Cloud Vertex AI Gemini models.
• Implemented a keyboard shortcut to submit prompts when "Enter to Send" is turned off.

✨ Improved

• Improved the parameter configuration and logic for Google AI Gemini models.
• Set a default API endpoint when adding new models.

✨ Improved

• Handled multiturn requests better for Google PaLM 2 Gemini models.

🔧 Fixed

• Resolved crashing issue when switching to GPT-4-Vision model in certain scenarios.
• Resolved crashing issue occurring during the first app launch on specific devices.

🚀 New

• Support Google PaLM 2 with Gemini Pro and Gemini Vision Pro models added.
• Added support for Google Vertex AI models. Vertex Gemini Pro and Vertex Gemini Vision Pro are coming in next days.
• Cohere models now supported.
• Added feature to edit messages.
• Added feature to fork messages to new conversation

✨ Improved

• Updated keyboard shortcuts for toolbar buttons.

🔧 Fixed

• Fixed issue calling wrong API for Azure OpenAI models.
• Fixed issue showing both main window and settings window when pressing Show Window button on menu bar.

🚀 New

• Introducing support for GPT-4 Vision, allowing users to upload images and ask questions.
• Added support for the DallE3 model for Azure OpenAI.
• Implemented a feature to multi-select and delete conversations.

✨ Improved

• Updated Perplexity models.
• Enhanced the appearance of links in Markdown mode.

🔧 Fixed

• Resolved a bug where Inline mode remained active after disabling and rebooting the application.

🚀 New

• Added support for all Perplexity models.
• Implemented a new feature that allows users to export entire conversation to PDF, Markdown, and ShareGPT.
• Added full support for LiteLLM API for utilizing Stream mode with Ollama.

🚀 New

• Now supporting DALL·E 2 and DALL·E 3 models for image generation, with detailed output preferences including quantity, quality, size, and style. Users can also enable auto save to store images permanently, or open generated images quickly in popular photo editors such as Adobe Photoshop or CleanShot X.
• Introducing the option to collapse long messages for improved readability.

🔧 Fixed

• Resolved lag issue when pasting long text and typing in the prompt editor.

🚀 New

• Integrated new OpenAI & OpenRouter models including gpt-3.5-turbo-1106 and gpt-4-1106-preview.
• Introduced option to toggle MindMac icon in the menu bar for customizable display.
• Added option to show window from the menu bar if the option to hide the icon from the dock was selected.

✨ Improved

• Utilized SettingsLink to display app settings in macOS 14 Sonoma for improved accessibility.

🚀 New

• Added feature that allows users to add a custom model for OpenRouter or a fine-tuned model based on gpt-3.5-turbo.
• Added a toggle button in the toolbar to switch between markdown mode and text mode.
• Added a button to switch between markdown mode and text mode for each message by hovering on the message.

✨ Improved

• Improved error handling by displaying clear error messages with detailed information when adding new API endpoints or new models fails.
• Sorted items in the output preferences picker in ascending order.

🔧 Fixed

• Fixed an issue where the response sometimes contained weird text chunks when the temperature was set near "More Creative".
• Fixed an issue where the prompt list would show slowly when typing "/p" in inline mode.

✨ Improved

• Enhanced the overall performance of the application.

🔧 Fixed

• Resolved the issue where the copy button was unresponsive when hovering over a message on macOS 14 Sonoma.

🚀 New

• Introduce a new feature that allows users to customize the output preferences for both the global and conversation profiles. This includes the ability to choose the language, tone, style, and format for the responses.

✨ Improved

• Decrease the minimum width of the sidebar to improve the overall layout.
• Reduced the margin of the input field for prompts to optimize space usage.
• Updated the color of the filter and sort buttons for improved visibility and aesthetics.
• Updated the color of folder and conversation icons for better consistency and visual appeal.
• Allow users to scroll upwards while receiving responses in stream mode to easily view previous messages. Please notice that macOS 14 Sonoma offers a more enhanced visual experience for scrolling animations compared to its predecessor, macOS 13 Ventura.

🔧 Fixed

• Resolved the issue where the text caret would jump to the end when pressing Shift + Enter in the middle of a prompt text, specifically when using the "Enter to Send" feature.
• Fixed issue where prompt template was not inserted correctly in certain cases. The problem occurred when applying a prompt template once and then removing it using the Cmd + A command. Subsequent attempts to apply the same prompt template were not being recognized.

✨ Improved

• Enhanced the positioning of the code block copy button.

🔧 Fixed

• Resolved the problem where code blocks occasionally display "undefined" for certain languages.

✨ Improved

• Improved the text color of the "Apply" button in the Prompt list, Occupation list, and Context mode list to enhance visibility and user experience.

🔧 Fixed

• Fixed the issue causing the application to crash when deleting a conversation using the keyboard shortcut.
• Resolved the problem with the context popover not remaining open when the context mode was set to either the last or first three messages.

🚀 New

• Added profile feature that allows users to set API parameters globally or by conversation: API provider, model, temperature, topP, topK (for Anthropic Claude), presense penalty, frequency penalty, max tokens.

🔧 Fixed

• Resolved the issue of invisible text when editing the Occupations Template and Prompt Template.
• Fixed the bug where input autofocus was missing when adding a new conversation.

✨ Improved

• Enhanced scrolling effect when receiving stream response.
• Set default conversation sorting to be by creation date in descending order.

🔧 Fixed

• Resolved issue where questions were being added to the wrong conversation when asked in a newly created conversation.

🚀 New

• Introduced a new sidebar for improved conversation organization.
• Added support for previous versions of OpenAI models: gpt-3.5-turbo-0301, gpt-4-0314, gpt-4-32k-0314.
• Implemented the ability to modify the font size of code blocks.

✨ Improved

• Enhanced overall performance of the application, resolving lag and unresponsiveness problems.

🔧 Fixed

• Modified the accessibility permission prompt to only appear during the initial launch of the app.

🔧 Fixed

• Fixed a critical crash problem that occurred when sending prompts in version 1.5.1 after upgrading from version 1.4.2 or earlier.

🔧 Fixed

• Fixed a critical crash problem that occurred when sending prompts in version 1.5.1 after upgrading from version 1.4.2 or earlier.

🚀 New

• Added model management feature, allowing users to choose which models should appear in the toolbar.
• Added support for fine-tuned models for OpenAI and Azure OpenAI.
• Fully supported local LLMs through LM Studio or LocalAI.
• Added a setting option to show/hide the icon in the Dock. This can be found in Settings → Configuration → Others.
• Added a setting option to show a confirmation dialog when deleting a message. This can be found in Settings → Configuration → Others.
• Added a setting option to automatically copy the response to the clipboard. This can be found in Settings → Configuration → Others.
• Added more options for GPT trigger command, prompt trigger command, and Inline setting trigger command.

🔧 Fixed

• Corrected the incorrect model code name for certain models in OpenRouter.

✨ Improved

• Updated code to switch to a different API endpoint if the current one is removed from Settings → Account → API Endpoint & Proxy

🔧 Fixed

• Fixed bug that prevented the correct model from being selected after adding a new API endpoint

🚀 New

• Added support for OpenRouter service. Users can now add OpenRouter as an API endpoint and utilize its 10 models

✨ Improved

• Enhanced user experience by remembering the last opened window size and position
• Made the entire prompt editor tappable for easy focus
• Trimmed whitespace and newline characters when activating a license by copying the license code
• Improved UI by bringing back the Delete Conversation button, which was removed in version 1.4.2

🔧 Fixed

• Resolve the problem causing the app to crash upon initial launch

🔧 Fixed

• Fix issue that unable to generate conversation title when stream mode is turned on

🚀 New

• Support Anthropic Claude models: Claude Instant and Claude 2
• Support multiple API endpoints and able to switch between them while chatting. Find more at Settings → Account → API Endpoint & Proxy
• Add unread notification with indicator in sidebar to monitor unread messages
• Add hotkeys Option + ↑ (⌥ ↑), Option + ↓ ( ⌥ ↓) to navigate question history while prompt editor active
• Add message information. Just hover on message and press information button

✨ Improved

• Now you don't need to restart MindMac after modifying keyboard shortcuts
• UI improvements: rearrange the toolbar buttons to improve visual appearance
• UI improvements: add Stop hotkey text in Inline loading indicator
• UI improvements: update API adding form and license activation form

🔧 Fixed

• Fix issue hotkey Shift + Enter (⇧ ↵) cannot be used in other apps while MindMac is in background and Inline mode is off
• Fix issue app crash when press on submit prompt hotkey while using Inline mode