What's new in
Brainmox.

Mission Control records new task status changes more consistently in the timeline. Saved approval and autonomy settings apply consistently to subsequent work.

One-time reminders account for daylight-saving rules on the requested date, with clarification when a local time is ambiguous. Skipped runs also preserve the remaining count for limited-run schedules.

New assistant portraits use a consistent illustrated headshot style, making candidates easier to recognize as you browse and chat.

Voice questions in desktop and web chat can now receive spoken replies in your assistant's selected voice. The written answer remains available when speech cannot play or you move to another conversation.

Ask about tonight, this evening, or a specific time window. Your assistant can use a forecast for that local period, with clearer location and coverage information.

Work Summary and Activities now use the same local-day boundaries, so work around midnight appears under the right day in both views.

Rapidly opening spaces keeps your latest selection in view, and switching assistants loads the right conversation more reliably. Sending waits until that conversation's history is ready.

Dropbox searches and file renames work more reliably. Calendar availability checks now make incomplete results clearer.

Your assistant can update a specific existing record and check the field used to match records more carefully. It can also remove an obsolete field and its saved values after confirmation, or hide the field instead.

Files shared with a descriptive name retain their original extension, helping your computer open the download in the appropriate app.

With a full-access Gmail connection, your assistant can apply or remove labels across a group of messages, mark them read, or move them to Trash together.

Your assistant can arrange progress and completion updates for commands it starts in the background, then use those updates to continue the work in the originating chat.

The Knowledge panel refreshes in the background, so newly saved memories appear without closing and reopening it.

Interrupted work leaves a notice in the conversation, making its state easier to understand when you return.

Your assistant can see the names and details of attachments on Mission Control tasks, including attached links. File contents still need to be made available separately for the assistant to read.

Browser tasks handle more website file-upload controls. Calendar invitation replies update your attendance response while preserving the rest of the event.

Your assistant can retain and replay successful browser flows, adapt when page elements move, and verify form writes more carefully across repeated web tasks.

Board refreshes no longer interrupt card moves or discard edits in an open task. Returning to the tab also refreshes the board immediately.

Your assistant can organize workspace files with verified copy and move operations, preserving the original bytes. Finished-file links now open the desktop app's native download flow.

Brainmox remembers the assistant and space you were viewing, shows queued messages while work is running, and preserves completed replies if a later step is stopped or fails.

Link WhatsApp as a companion device through the guided setup. Use a dedicated account for normal conversations or keep an owner-linked connection limited to your self-chat.

Connect labeled Dropbox accounts with read-only or full access, and let your assistant use maps and weather information for grounded plans, routes, and recurring briefings.

Drop a supported voice memo or audio file into chat and your assistant can transcribe the workspace copy for notes, summaries, and follow-up work.

A new Gmail draft-only connection lets your assistant read mail and manage drafts while its available actions exclude sending. Drafted email, text, and phone actions are handed back for your review.

Enable launch at login from the desktop tray on macOS, Windows, or Linux. The option stays out of the way when a system service already manages startup.

Scroll upward to load older chat history, use Escape consistently to close dialogs, and receive clearer screen-reader announcements as messages arrive.

Your assistant can now create Word, Excel, PowerPoint, and EPUB files and make targeted edits to existing Word, Excel, and PowerPoint documents before delivering the result.

Your assistant can maintain dated obligations, counted goals, reminder lead times, and a combined agenda of upcoming items and scheduled work.

Open another space to review earlier work while your assistant is busy elsewhere. Active work continues uninterrupted, with sends and edits held until the assistant is ready.

Your assistant can keep structured records for contacts and businesses, add fields as your work evolves, link related records, and update matches instead of creating duplicates.

When your assistant creates a report, spreadsheet, or other file, it can place a download link directly in the conversation. Text and data attachments also arrive as real workspace files, preserving the original source.

Your assistant can keep track of multiple tabs more reliably and complete related browser steps efficiently. Stronger boundaries help separate untrusted page content from your instructions.

The desktop app returns to your last page after an unexpected restart and restores unsent Mission Control plan, comment, and link drafts. Support reports can also include app diagnostics when needed.

Unread counts now stay separate for each assistant, and desktop notifications identify which assistant responded.

This release includes additional safeguards and fixes for more dependable assistant work, scheduled tasks, and connected runtimes.

Ask your assistant to remove one incorrect or outdated memory while keeping the rest of its knowledge intact.

Add passwords, login details, and other secrets from Settings or while chatting. Your assistant can use them without exposing their values in conversation, and the vault shows a history of secret activity.

Give each assistant a custom label in Settings, then see it in the sidebar and chat header — especially useful when you manage several assistants.

The Activities panel now uses an expandable timeline with scheduled-work markers and richer daily stats, making it easier to review what your assistant has been doing.

Your assistant can now work with Google Tasks alongside Gmail, Calendar, Drive, Sheets, Docs, and Contacts — including creating, updating, completing, moving, and deleting tasks.

When it encounters a product issue, your assistant can now create a support request with the relevant details so the Brainmox team can help.

Your assistant can now generate short videos from a prompt and save the finished result to its workspace, with availability based on your plan.

The desktop app now provides familiar right-click actions for selected text, editable fields, images, and links, including copy, cut, paste, select-all, and open-link options where appropriate.

Interrupted scheduled runs can now recover after a restart, with a clear notice in chat when work resumes. Calendar events also support color, visibility, and busy-or-free settings.

Google Workspace support now goes beyond email and calendar — your assistant can work with your Google Drive files, Sheets, Docs, and Contacts.

Each assistant now builds a private library of skills from its work: it saves and refines its own how-to knowledge, and a nightly learning pass distills lessons from the day so it gets better at your recurring tasks over time.

Drop Word, Excel, PowerPoint, EPUB, or notebook files straight into chat — they're delivered to your assistant's workspace and converted so it can read them immediately.

When your assistant opens an image file — a screenshot, photo, or chart — it now actually sees the image rather than just noting the file, so it can describe, analyze, and act on visual content.

Connected Google accounts now show up directly as tools your assistant can use, refreshing live as you connect or disconnect accounts — no restart needed.

The chat header got a cleaner design with an agent menu, icon toolbar, a help menu with update badge, and an overflow menu for less-used actions.

The desktop app and dedicated-machine runtimes now update themselves with a verified one-click flow and automatic rollback if an update fails. The desktop app shows a friendly reconnect screen when you're offline, and you stay signed in across restarts.

Per-assistant preferences now sync with your account, so any device you sign in on has the same setup.

Each assistant now has a work-location setting, and you can move an existing assistant to another computer with a single copy-paste install command (Mac, Linux, or Windows) that verifies and activates everything for you.

Onboarding no longer asks for a license key — just sign in with Google, on desktop and web alike.

The desktop app and web app now share the same core interface and Mission Control experience. Native desktop file and runtime features still depend on the installed app.

All your assistants connect on load so you see live status at a glance, and replies stream to every open window at once — moving between web and desktop no longer drops your conversation.

Settings now shows your agent seats, existing customers can hire additional assistants anytime, and you can remove an assistant from the web app.

Your assistant's secure vault now stays unlocked while the assistant is actively working, so long-running tasks are no longer interrupted by a vault timeout.

Browser screenshots and media captured by your assistant while it works now appear directly in the app.

You can now hire a cloud-based assistant with zero installation — pick a candidate, hire, and start chatting right from the web app, with your spaces, work stats, and full conversation history.

A new cross-platform installer sets up your assistant's runtime on a dedicated machine, verifies the download, and can install it as a background service that starts automatically.

Pick where each assistant's tools run — on your own computer, on a dedicated machine, or in our cloud. The hiring wizard includes a runtime step, and a new Runtimes page lets you manage machines and assign assistants to them.

Your assistant now edits files more carefully: protected paths are off-limits, it notices when a file changed underneath it, and changes are applied safely so your files can't be left half-saved.

Emails your assistant sends and reads through Gmail now handle special characters correctly, so subjects and bodies with accents, emoji, or non-English text no longer show up garbled.

Your assistant can now reply within email threads with proper quoting and reply-all, add cc and bcc recipients, and outgoing mail is validated before sending.

The Mission Control board is now enabled for everyone, with board editing on by default. Scheduled tasks that were missed while your runtime was offline now run automatically when it comes back.

Give your assistant reusable skills — packaged instructions for recurring workflows — which it finds and loads on demand when a task calls for one.

In Telegram and Slack your assistant now reacts to show it received your message, is working, and is done — and you can type !stop to cancel what it's doing.

Image generation now supports flexible sizes and a quality setting, and generated images can be saved straight into your assistant's workspace.

Every night your assistant reviews the day's conversations, files the important parts into long-term memory, and merges duplicate or conflicting notes — so its knowledge of you stays organized and consistent.

Long-running answers and commands are no longer stopped by fixed timers — your assistant keeps going as long as it's making progress.

New per-assistant permission settings let you decide how much shell, file, and browser access your assistant gets, managed from a simple UI.

Memory search now combines keyword and meaning-based matching, favors recent information, and knows when a remembered fact has expired — so recall is more accurate and up to date.

Attach images in chat and your assistant will actually see them. It can also view images on web pages it reads, not just the text.

The dashboard now shows a download card that detects your platform automatically, and app updates apply themselves if you don't click Update.

Your assistant can now send files directly to you over Telegram and Slack, and rapid-fire messages are handled in order instead of colliding.

A new account dashboard lets you sign in with Google, follow a guided install, manage your seats, invite others, and transfer an assistant to another machine with a transfer code.

Desktop app updates are now smaller, faster, and more dependable across platforms.

Your assistant now works in Slack — mention it in channels or message it directly, share files and images, and get properly formatted replies that follow the thread.

Conversations are now organized into named, color-tagged Spaces with unread status. Switching spaces while an assistant is busy remains limited in the current interface.

Mission Control is now a full kanban board with drag-and-drop cards, filters, plan colors, attachments, AI task suggestions, and a final-approval review step before work is signed off.

Your assistant can autonomously pick up and complete tasks on a mission board, pacing itself around due dates, with a pause toggle per plan and a full activity timeline showing everything it did and delivered.

Link more than one Google account to your assistant, each with its own label and access level, instead of being limited to a single connection.

Send your assistant voice notes and photos on Telegram — it transcribes and understands them — and it can reply with spoken voice messages and images of its own, using the voice you've picked for it.

Your assistant can now write and run Python code in an isolated sandbox to crunch numbers, process files, and automate tasks.

New safeguards prompt your assistant to verify information before stating it as fact, for more rigorous and reliable answers.

Connecting your assistant to messaging channels is now a guided setup in the desktop app instead of something you ask the assistant to do.

Your assistant can now connect to your Google account to read and send email and manage your calendar, with a secure sign-in flow — including attachments, forwarding, and saving files to its workspace.

Cancel a running task cleanly or send new instructions while your assistant is mid-flight — it picks up your messages one at a time and adjusts course without losing its place.

A verification pass confirms tasks were actually completed before your assistant reports them done. Memory also got smarter about updating the right entry instead of creating duplicates.

Scheduled tasks now stream their output into your chat as they run, results land in the session that created them, and schedules respect your local timezone.

Drag any PDF into the chat and your assistant reads it — including scanned documents, thanks to built-in OCR.

Canadian tax calculation support covers federal and Ontario personal, corporate, payroll, GST/HST, credits, and registered accounts with source citations. Results still require review before filing or making a financial decision.

Report an issue directly from the app and get threaded replies back from the team, without leaving your conversation.

Upload multiple files at once to your assistant's knowledge base, then search and edit what it knows.

Your assistant can now connect to external MCP servers, unlocking third-party tools and services beyond what's built in.

Web search now supports specialized categories like news, so your assistant picks the right kind of source for the question.

New safeguards detect several repeated-call and no-progress patterns and apply selected call budgets and action caps. Coverage varies by tool and configuration.

Setup got much lighter, and unread message badges now show when your assistant has replied while you were elsewhere.

The desktop app lands with system tray access, native notifications, window state memory, and in-place updates for Mac, Windows, and Linux.

Push to talk in the app instead of typing. Messaging channels that support voice can also deliver spoken replies using the voice selected for your assistant.

Your assistant now persists conversation history and can use condensed context for long chats. The current client does not expose every stored-history search and pagination capability in the interface.

Web search got a performance overhaul — answers come back faster and searches fail less often.

Store credentials in the encrypted vault and let your assistant resolve them only for eligible tool execution without placing cleartext values in the conversation.

Tool activity now streams live into the chat, so you can see exactly what your assistant is doing — searches, page visits, and results — as it happens.

Your assistant browses the web more reliably, navigating sites the way a person would so fewer pages block it or break mid-task.

A new hiring wizard lets you pick your assistant from a set of generated candidates, each with a name, face, and identity. Your assistant keeps a work journal and syncs its profile to Telegram.

Chat with your assistant on Telegram, and ask it to run tasks on a schedule so work happens even when you're away.

The engine behind every Brainmox assistant came together: persistent conversations, safe sandboxed task execution, web search and browsing, image generation, PDF reading, scheduled reminders, a secure credential vault, and a knowledge system.