This update fixes renaming chats on macOS 27, chat search, image generation and chat titles.

Improved

• When an AI Workflow can't paste its result because you switched to another app, the result is now on the clipboard instead of being lost.
• After this update, BoltAI rebuilds its search index once, so search finds text in all your messages. This usually takes a moment.

Fixed

• Fixed renaming a chat or editing a message failing on macOS 27.
• Fixed search missing text in some messages, and finding nothing when the search contained punctuation. [ref]
• Fixed OpenAI image generation failing for every request, including with Setapp. [ref]
• Fixed image generation with Google and xAI.
• Fixed chat titles not being generated for Apple Foundation Models, xAI, Perplexity and other providers, and custom title prompts having no effect. [ref]
• Fixed the Instant Chat Bar input not always getting focus when opened with its shortcut. [ref]
• Fixed Cloud Sync failing on every run when a file attached on this Mac had gone missing before it was uploaded.
• Fixed Settings pausing when opening General, and blank sidebar icons in Settings on older macOS versions.

This update fixes a crash on first launch and improves citations.

Improved

• Citation numbers in Perplexity and Grok replies now link to their sources.
• Improved crash reporting.

Fixed

• Fixed a crash when opening BoltAI for the first time on some macOS 15 versions.
• Fixed inline code being hard to read in dark mode.
• Fixed the chat link description in Chat Info.

This update fixes a few issues in chats and with API key encryption.

Improved

• BoltAI now shows a reminder to encrypt your API keys.
• Switching to another provider's model in the middle of a chat now shows a short note, since answers can get worse.
• API keys you import are now encrypted right away if you use a master password.

Fixed

• Fixed Settings > Security not offering to encrypt API keys for custom providers, Claude Code, Codex CLI and Gemini CLI.
• Fixed settings changed right after a sync not reaching your other devices.
• Fixed the chat going blank after sending a message in a short window, or after a reply failed.
• Fixed the find bar not appearing when opened a second time on macOS 26.
• Fixed the Tools setting of one chat being applied to another when switching chats.

This update turns on chat tabs for everyone, adds custom project icons, makes BoltAI open faster, and fixes several issues with agents and their tools.

New

• Chat tabs are now on by default: open different chats in tabs within one window. To go back to one chat per window, turn off "Enable native chat tabs" in Settings > Developer and restart BoltAI.
• Custom project icons: give a project an emoji or one of over a thousand symbols, in one of nine colors. Choose it in Project Settings > General, from the project page, or when you create a project. The icon shows in the sidebar and the project header. [ref]
• Max reasoning is now available on custom and OpenAI-compatible providers. BoltAI tells you once that your provider may not support it.

Improved

• BoltAI shows its main window sooner at launch.
• Long model names no longer overflow the model button in the composer. It shows the short name; hover to see the full one.
• In a new chat, Tools now follow the agent you pick, and clearing the agent puts your default tools back.

Fixed

• Fixed several problems when picking an agent: the agent could fall back to Default Agent until picked a second time, be dropped from a new tab on the first message, or switch on tools it does not have.
• Fixed a new chat tab that could not be closed, with the message "This tab is still working or has an unsaved response".
• Fixed a project's prompt mode sometimes not syncing to your other devices.
• Fixed importing a BoltAI backup dropping a project's default agent, prompt mode and loop settings.

This update adds auto-continue for long responses, makes cloud sync more reliable on an idle Mac, and fixes several chat, MCP and tool issues.

New

• Auto-continue long responses: when a model stops because it reached its output limit, BoltAI now asks it to continue and joins the result into the same message, up to three times. It is on by default; turn it off in Settings > General.
• On macOS 27, the composer has a floating glass appearance.
• The About window has a Copy Support Info button that copies your app and system details, to paste when you contact support.

Improved

• Thinking now stays collapsed while a model reasons, so the answer stays in view. To expand it automatically again, turn on "Automatically expand thinking" in Settings > Appearance. [ref]
• An idle Mac now picks up changes made on your other devices without needing a relaunch or Sync Now.
• Chats with very long plain-text paragraphs, such as pasted logs, open much faster.
• Restoring a chat from Trash now checks with the cloud first, and tells you if the chat was already permanently deleted there.
• Chat titles are more accurate when your first message refers to a file or image.
• Crash reporting no longer starts before you make your privacy choice during onboarding. Settings now says when a change takes effect.
• Printing or exporting a chat to PDF no longer includes buttons and other chat controls.

Fixed

• Fixed automatic cloud sync not running after launch on Macs that still had Local Account data, and the sync interval setting being ignored.
• Fixed new chats starting with an agent's tools turned off, and Instant Chat or switching agents overriding your Tools Off choice. [ref]
• Fixed chats staying in Trash past the date shown.
• Fixed MCP servers being sent repeated sign-in requests after an authorization failure.
• Fixed Claude models on OpenRouter failing to continue after running several tools at once.
• Fixed WebP images failing with LM Studio.
• Fixed AI services imported from a backup file with an unrecognized provider not working; they are now imported as OpenAI-compatible services.
• Fixed menus and popovers appearing in the wrong place under the toolbar on macOS 27.

This update fixes a launch crash on macOS 13 and 14, along with several other crashes and fixes.

Improved

• Kimi K3 can now use Low and High reasoning, not only Max, to keep costs down.
• The reasoning menu next to the model picker now offers Extra High and Max for supported Claude models.

Fixed

• Fixed BoltAI crashing at launch on macOS 13 and 14.
• Fixed the About window opening by itself at launch on macOS 13 and 14.
• Fixed "Hide Dock icon when last window closes" not working reliably on macOS 13 and 14.
• Fixed AI Workflows that insert or copy their result directly failing with "The model returned an empty response" when using Codex CLI. [ref]
• Project folders in the sidebar show their orange color again on macOS 14 and 15.
• Fixed a crash that could occur when stopping a response while it was streaming.
• Fixed a rare crash in background sync.

This update fixes chat and AI Workflow issues introduced in 2.17.

Improved

• Unavailable MCP tools remain visible in chat, default, agent, and project plugin settings, where you can remove their saved selections.
• Deleting an MCP server also removes its tool selections from saved defaults, agents, projects, and chats. Synced selections are updated on your other devices too. If you add the server again, select its tools again.

Fixed

• Fixed chats failing to send when an enabled MCP server could not load, including deleted servers still saved in chat defaults. Other available tools remain enabled.
• AI Workflows can continue when a selected MCP tool is unavailable or its server is still starting.
• Chats can continue when an attached text document cannot be read, using saved extracted text when available.
• Fixed certain AI Workflow requests failing with custom API base URLs, and corrected provider-specific request handling.
• Fixed results or errors from an earlier AI Workflow appearing in a later run.
• Fixed completion handling for No Preview workflows, including consecutive runs while BoltAI is in the background.

BoltAI now feels more at home on your Mac. The rebuilt chat window brings a native toolbar and sidebar, scrolling that blends into the window, and faster chat switching. Arrange the toolbar around your work, or try experimental tabs when you want several chats open at once.

New

• A more native chat window: The toolbar, sidebar search, and window layout now fit macOS more closely. On macOS 26, chat content scrolls beneath the toolbar and the inspector blends with its header.
• Experimental chat tabs: Press Command-T for a new tab, or right-click a chat and choose Open in New Tab. Each tab keeps its own place, and you can reopen closed tabs or restore previous tabs. To try tabs, go to Settings > Developer > Feature Flags, turn on Enable native chat tabs (experimental), then restart BoltAI. Tabs are off by default.
• Customize the native toolbar with the actions you use most, including Share and one-click PDF export.
• Review and remove duplicate starter prompts, agents, and workflows from your library. BoltAI shows what would be removed before you confirm.

Improved

• BoltAI holds onto less data from chats you are no longer viewing, helping long sessions stay lighter on memory, especially with document attachments.
• Supported Claude models have a larger default response allowance, giving them more room to think and finish an answer. Your custom limits still apply.
• AI Workflows explain capture and permission failures more clearly, provide a way to enable Accessibility, and let you review an incomplete result when a run cannot finish.
• Model pickers keep cached models visible while an updated list loads.
• BoltAI no longer offers to install starter prompts, agents, or workflows you already have.

Fixed

• Saved custom OpenRouter endpoints are now used when loading models and sending requests.
• Custom agents keep their selected plugins, and interrupted settings saves no longer display a cancellation error. [ref]
• Claude now reports when its response allowance is exhausted without an answer, including in empty chats. [ref]
• Answers that fail to save remain visible when switching chats. Refreshed history still reflects messages deleted or synced elsewhere.
• Fixed a case where regenerating an answer that failed to save could bring later messages back when you reopened the chat.
• Documents sent as text retain their saved extracted content if the original file is missing on this Mac.
• Dragged images use the correct format, and attachment-loading failures show an error.
• Prompt editor headings and buttons remain visible in their sheets.
• Fixed a crash that could occur when stopping or restarting speech playback during audio parsing.

AI Workflow permission change: AI Workflows need Accessibility permission in this version. If your workflows do not run, turn on BoltAI in System Settings > Privacy & Security > Accessibility, then try again.

Clipboard limitation: During selection capture, BoltAI currently restores only plain text up to 1 MB from the previous clipboard contents. A copied image, file, or rich formatting may not be restored.

This release brings more capable projects, faster AI workflows, and smoother everyday performance, along with a wide range of bug fixes.

New

• Projects now support linked files and folders on your Mac. Your AI can search, read, and edit them as you work. This feature is in beta. [ref] [ref]
• Choose a default agent for each project, so new chats start with that agent’s instructions, model, and plugins. [ref]
• BoltAI can automatically read AGENTS.md, AGENT.md, and CLAUDE.md from your linked project folders, saving you from copying instructions into each project.
• “Reveal in Sidebar” takes you from a search result to the chat’s location, so you can continue browsing your chats without the search filter. [ref]
• You can now connect your OpenRouter account via OAuth instead of manually entering an API key.
• GPT-6 Astra is now available through Codex CLI. Grok gains Extra High reasoning, and supported Claude models have more reasoning levels to choose from. [ref]
• Amazon Bedrock now caches prompts automatically to reduce the cost of reusing the same instructions and context, with a choice of cache duration.
• Approve edits to linked files directly in chat, either once or for the project. If you’re in another app, BoltAI can notify you when it needs your approval.

Improved

• Redesigned project settings to make them easier to navigate. You can now drag files and folders into the new-project window to link them.
• Improved startup speed, chat switching, and the display of code in responses.
• You can now disable providers you don’t use, including Setapp, to keep the model picker easier to browse. [ref]
• Improved AI workflow performance.

Fixed

• Fixed crashes related to clipboard handling in AI workflows.
• Fixed slow sidebar searches in large chat libraries.
• Fixed code highlighting losing its colors while a response was being generated.
• Claude now shows an error when it returns an empty response, rather than leaving you without a reply or explanation. [ref]
• Interrupted Claude responses are now marked as incomplete instead of looking like a finished answer. [ref]
• PDF attachments that can’t be read now show an error instead of being silently left out of your request.
• Fixed errors when continuing a Claude chat after it read a web page. [ref]
• Fixed plugin-related errors when your chat settings limit how much conversation history is included. [ref]
• Switching providers no longer sends plugins that the new provider doesn’t support.
• Fixed Mistral responses failing as they finished generating.
• Fixed duplicate responses and empty response controls caused by overlapping requests. [ref]
• Fixed follow-up messages being lost when sent just after pressing Stop. [ref]
• BoltAI now explains when an agent stops because it has reached its step limit, including after a plugin fails.
• Fixed the main window staying hidden when you clicked BoltAI in the Dock or switched to it with Command-Tab. [ref]
• Opening Instant Chat or Workflow Palette no longer unexpectedly brings up the main window. [ref]
• Fixed HEIC photos dragged from Apple Photos being rejected by AI providers.
• Refreshing the model list no longer keeps showing an outdated locally cached list.
• Failed image generation now shows an error instead of leaving an empty response or a stuck progress indicator.
• Fixed requests timing out after 60 seconds despite a longer timeout in Settings.
• Fixed chats remaining selected in Trash after they were deleted or restored. [ref]

This release includes bug fixes and compatibility improvements.

Fixed

• Fixed the Projects section label being partially hidden in the sidebar on macOS 27.
• Fixed PDF exports that could contain the chat title but leave the message content blank.

Note: After updating, BoltAI may still appear as BoltAI 2 in the Dock, Spotlight, and app launchers. To update the name, quit BoltAI and rename BoltAI 2.app to BoltAI.app in your Applications folder. Your chats and settings will remain available.

This maintenance release improves chat reliability when Cloud Sync updates arrive during an AI response.

Fixed

• Fixed an issue where an AI response or its reasoning could disappear when Cloud Sync refreshed the current chat while the response was still being generated or saved.

Build 72 is a focused bug-fix and polish update for chat switching, the native sidebar, and Cloud Sync reliability. Switching between chats should feel smoother, with fewer blank states, less flicker, and more reliable recovery when a chat load needs to retry.

Build 72 Changes

Improved

• Improved chat switching so recent messages appear with less unnecessary loading work.
• Improved the renderer so selected chats are less likely to flash an empty message list.

Fixed

• Fixed chat switches that could briefly show an empty message state before the selected chat finished rendering.
• Fixed duplicate message loads during native chat navigation, reducing redundant fetches and visual flicker.
• Fixed retry behavior after a failed chat load so the same chat can load correctly on the next navigation attempt.
• Fixed the native sidebar getting stuck on a bottom Loading... row after deleting a chat.
• Fixed a crash that could prevent automatic Cloud Sync from running reliably in the background.