Build 92
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.
Build 91
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.
Build 90
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. This update covers 2.17.0 through 2.17.2, including a fix for a launch crash on macOS 13 and 14.
On macOS 13 or 14 and BoltAI quits right after opening? Download 2.17.2 and install it manually. Here's how.
New
A more native chat window: the toolbar, sidebar search, and window layout fit macOS more closely. On macOS 26, chat content scrolls beneath the toolbar and the inspector blends with its header.
Customize the toolbar with the actions you use most, including Share and one-click PDF export.
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. To try them, go to Settings > Developer > Feature Flags, turn on "Enable native chat tabs (experimental)", then restart BoltAI.
Review and remove duplicate starter prompts, agents, and workflows from your library. BoltAI shows what will be removed before you confirm.
Improved
The reasoning menu next to the model picker now offers Extra High and Max for supported Claude models.
Kimi K3 can now use Low and High reasoning, not only Max, to keep costs down.
Supported Claude models have a larger default response allowance, giving them more room to think and finish an answer. Your custom limits still apply.
Long sessions use less memory, especially with document attachments.
AI Workflows explain capture and permission problems more clearly, help you turn on Accessibility, and let you review an incomplete result.
Unavailable MCP tools stay visible in chat, agent, and project settings, so you can remove them. Deleting an MCP server also removes its tool selections, including on your other devices.
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
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.
Project folders in the sidebar show their orange color again on macOS 14 and 15.
Fixed a crash when stopping a response while it streams, a rare crash in background sync, and a crash when stopping speech playback.
Fixed AI Workflows that insert or copy their result directly failing with "The model returned an empty response" when using Codex CLI. [ref]
Fixed chats failing to send when an MCP server could not load. AI Workflows also continue when a selected MCP tool is unavailable.
Fixed results or errors from an earlier AI Workflow appearing in a later run, and No Preview workflows not completing when run back to back.
Fixed certain AI Workflow requests failing with custom API base URLs.
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 show a cancellation error. [ref]
Claude now reports when its response allowance runs out before it answers. [ref]
Answers that fail to save stay visible when you switch chats, and regenerating one no longer brings back later messages.
Documents keep their extracted text if the original file is missing, and chats continue when an attached document can't be read.
Dragged images use the correct format, and attachment-loading failures show an error.
Prompt editor headings and buttons stay visible in their sheets.
Note: AI Workflows need Accessibility permission. If your workflows don't run, turn on BoltAI in System Settings > Privacy & Security > Accessibility, then try again.
Build 85
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]
Build 84
BoltAI 2.15.0 includes the reliability improvements from the 2.14.2–2.14.4 maintenance releases, together with a cleaner app name and fixes for PDF export and newer versions of macOS.
Improved
BoltAI downloaded from our website is now simply named BoltAI. New installations use BoltAI.app.
Improved AI provider errors so useful upstream details are shown when available instead of a generic failure.
Improved launch stability by loading the Workflow Palette only when it is first used.
Fixed
Fixed new projects selecting the wrong provider or losing the Base Agent model, generation settings, and loop limit.
Fixed Anthropic-powered chats occasionally failing after tool calls when using extended thinking through OpenRouter, AWS Bedrock, Anthropic, or Claude Code.
Fixed AI responses or reasoning disappearing when Cloud Sync refreshed the current chat while a response was still being generated or saved.
Fixed PDF exports that could contain the chat title but leave message content blank.
Fixed the Projects section label being partially hidden in the sidebar on macOS 27.
Existing installations: 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, then reopen it. Your chats and settings remain available.
Build 78
This release focuses on protecting your chats and provider credentials, improving Cloud Sync and backup recovery, and fixing reliability issues across Instant Chat, project defaults, streaming responses, provider models, and macOS conversation controls.
New
Added Sync Now to the File menu and sidebar settings menu, using the same safety checks as Cloud Sync settings.
Added a More menu to Instant Chat for quick access to conversation actions.
Improved
Improved sidebar search responsiveness and ensured hidden or deleted chats are excluded before results are ranked.
Improved provider credential syncing so related credential data is transferred together and updated credentials take effect without stale cached values.
Improved Backup & Restore warnings to distinguish unprotected credentials in the active account from those stored in inactive backup accounts.
Improved MiniMax model availability with current model discovery, reliable fallback models, and the correct MiniMax M3 identifier.
Fixed
Fixed API keys incorrectly prompting for a Master Password or appearing encrypted after relaunch, while keeping credential access scoped to the correct BoltAI account.
Fixed legacy folder deletions that could leave deleted chats searchable or allow chats and attachments to return after Cloud Sync.
Fixed deleted chats briefly flashing in the sidebar after using Delete Local Data and relaunching BoltAI.
Fixed Control-click not opening native context menus for chats and projects in the sidebar.
Fixed Save Temporary Chat and other Conversation commands being disabled or targeting the wrong chat in Instant Chat and companion windows.
Fixed Instant Chat prompts occasionally being sent more than once.
Fixed OpenRouter conversations losing reasoning details when continuing an existing chat.
Fixed Project Defaults appearing to save a provider or model while project cards and newly created chats continued using the previous selection.
Fixed Return while renaming a project also creating a new chat, and improved the alignment of Project Default controls.
Fixed incompatible Google Deep Research agents appearing as regular chat models and causing unsupported requests.
Fixed Last Sync appearing stale during normal use or reverting to Never synced after relaunch.
Fixed restored backups leaving Cloud Sync unable to reconnect. BoltAI now safely downloads current cloud data before offering the normal Local Account merge flow, while preserving restored local data if recovery cannot continue.
Fixed partial AI responses disappearing when generation reached an output limit, was stopped, disconnected, or ended with a provider error. Partial text and reasoning are preserved, terminal errors remain visible, and Continue is available when the provider reports an output limit.
Fixed Retry and Regenerate occasionally failing when an interrupted response had not finished saving.
Fixed empty completed responses from some providers surfacing an unrelated metadata error instead of the actual result.
Build 77
This update adds complete local backup and restore, new fullscreen companion chat options, support for the latest GPT and Claude models, and improved reliability across Cloud Sync, AI Workflows, MCP connectors, providers, and the macOS interface.
New
Added full local backup and restore for your BoltAI database and locally available attachments, with archive validation, safety backups, and guided Cloud Sync recovery. Learn how to back up and restore your BoltAI data.
Added GPT-5.6 Sol, Terra, and Luna for the Codex CLI provider, plus Max reasoning for supported GPT-5.6 models in the OpenAI and Codex CLI providers.
Added newer models for the Claude Code provider, including Claude Fable 5, with model-aware thinking controls.
Added options for New Chat and New Temporary Chat shortcuts to open in the current Space, including when another app is fullscreen.
Improved
Improved AI Workflows to preserve paragraphs, lists, and inline formatting when working with rich-text apps such as Notes, Obsidian, and Mail.
Improved MCP compatibility with automatic HTTP connector recovery, provider-compatible tool names, and complete tool input schemas including enums, defaults, and constraints.
Improved Custom provider model discovery for endpoints with explicit API versions and query parameters.
Improved Kimi K3 compatibility by applying its required inference settings and clearly explaining which model parameters cannot be customized.
Clarified Dock and menu-bar visibility settings when BoltAI must keep the Dock icon available for reopening the app.
Fixed
Fixed long or resumed Cloud Sync sessions that could miss remote changes, lose pending deletes, or fail when matching catalog items existed locally and in the cloud.
Fixed newer Claude requests that could include unsupported sampling or penalty parameters.
Fixed Perplexity streaming responses that could fail with a type-validation error.
Fixed Gemini conversations with tools failing to continue correctly, while preserving image context in follow-up messages.
Fixed edited provider credentials remaining stale until restart, and improved errors when a stored key cannot be read.
Fixed ShotSolve reusing content from an existing Instant Chat session instead of starting fresh.
Fixed Temporary Chat windows not honoring BoltAI's selected Light appearance.
Fixed unreadable text while renaming selected chats and restored Toggle Inspector for the focused chat.
Build 73
This update adds project duplication and polishes everyday workflows around permissions, shortcuts, licensing, and voice.
New
Added Duplicate Project to the sidebar so you can copy a project's setup, model configuration, instructions, tools, and project files without copying its chats.
Improved
Improved menu bar-only login launches so BoltAI keeps a recoverable main window until the menu bar item is ready.
Improved permission prompts for microphone, speech recognition, screen recording, and Accessibility so it is clearer which setting BoltAI is asking you to enable.
Improved the first-run shortcut defaults: new installs no longer reserve the Workflow Palette global shortcut by default, while existing users who relied on it keep their shortcut.
Improved Shortcut settings by showing the Instant Chat Bar shortcut alongside the other global shortcuts.
Improved voice defaults by using Apple text-to-speech as the default provider for new setups.
Fixed
Fixed license refreshes that could fail after local device identity was regenerated, such as after a Keychain reset or repair.
Fixed permission flows that could open System Settings with less helpful context after a denied or not-yet-decided permission state.
Fixed voice setup copy to better describe voice input rather than generic voice setup.
Fixed long action tooltips in chat messages so they fit better near the edge of the message row.
Fixed duplicated projects so attached project files are copied along with the project configuration.
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.
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.
