What’s new

Pick a template while you create an agent

The last step of the create-agent wizard now shows the full Explore roster under the composer, grouped by the same categories. Install one in place without a detour through the marketplace, or use the Import an Agent tile to bring your own.

TikTok Ads and Meta Ads in the MCP directory

Both ad platforms are now in the searchable MCP directory. TikTok comes in two shapes: the full catalogue of roughly 400 tools, or a core set of about 40 for a lighter agent. Meta still needs an OAuth client ID supplied by hand.

History for finished one-time tasks

The Triggers card counts completed one-time tasks and opens a sortable, paginated page of the sessions behind them. Those runs were hidden before. Live runs and session wakes stay out of the list, so it only shows work that finished.

Fixes and improvements

• The first message to a sleeping cloud agent goes through on the first try.
• Attachments upload as you drop them, with progress and retry on each chip.
• A stalled upload fails that file instead of hanging Send.
• New folders appear next to the button that made them.
• A dragged agent settles in place when dropped onto a collapsed folder.
• Code blocks in the markdown file preview have readable contrast.

Agent folders in the left nav

Group agents into one level of folders in the left nav. Drag them in, or use Move to Folder from the context menu on touch. Unfiled agents stay in Your Agents. Filing is per-user, so a shared agent never moves for anyone else.

See which agents are calling this one

Called from Other Agents lists every inbound call on its own history page, with per-caller switches for what runs automatically and what needs approval. Sessions opened by another agent name their caller, and stay out of your session list until one needs input.

Dashboards can start a session

A dashboard can now hand a prompt to its agent through dispatchSession, and the app shows a confirmation dialog with the prompt editable before anything runs. Sessions always belong to the dashboard's own agent, so a dashboard can't reach across to another one.

Fixes and improvements

• Cloud sessions pick up where they left off if the machine running them dies.
• Agents recover from a corrupted container image instead of failing to start.
• Dashboards open faster from a cold start, in the app and popped out.
• Returning to a dashboard tab wakes its agent if autosleep stopped it.
• A dashboard that fails to load offers a retry instead of a blank frame.
• Dashboard pop-outs have a draggable title bar with a refresh button.
• Screenshots and images from agent tools render inline in chat.
• Long sessions no longer creep up in memory as they run.
• Session costs in usage analytics account for cache and context tiers.
• On Agent Home and Notifications, titles slide into the top nav as you scroll.
• Composer placeholders suggest roles to fill, like recruiter or bookkeeper.

Browse agent templates in Explore

Explore is now a full-page template marketplace, with category browsing and a dedicated details page for each template. See example prompts, supported connections, and included files before installing. Browse Templates opens Explore from the composer. Templates marked Featured are built by the Gamut team.

Fixes and improvements

• Finished-session notifications include the agent's final answer.
• Dashboard names and actions now appear in the main app header.
• Marketplace templates install without an extra naming step.
• Your session's model, effort, and speed settings persist as you navigate.
• OpenRouter sessions work again with non-Anthropic models.
• Image-heavy sessions load messages faster and fetch images on demand.
• Chat continues following new messages when the window or content resizes.
• Settings → Account shows your current workspace first and lets you switch.
• Large exports use less memory while the archive is created.
• Slow file checks no longer stall the rest of the app.
• Agents consult product guides only when relevant to your task.
• After viewing a template, you return to the same place in Explore.
• Desktop download links for Mac and Windows work again.
• Browser preview tabs show ampersands and quotes correctly.
• The `/compact` command no longer reappears in your draft.

Agent templates can include starter prompts

Templates can now open a new agent with a ready-to-run task in the home composer. You can review or edit the prompt before sending, and templates with a starter prompt open in the composer instead of starting onboarding. If the prompt is too long, the template still installs without it.

Fixes and improvements

• Streaming replies stay in view until you scroll away.
• Long transcripts fetch less data and use less memory.
• Slack group DMs now support mention-only replies.
• Time markers separate pauses in long session transcripts.
• Recurring scheduled tasks and webhooks no longer stop after many runs.
• Long-running cross-agent tasks continue without duplicate runs.
• iOS widgets refresh after you start a session on that device.
• Subagent descriptions and progress now appear together on one line.
• Typed arrow sequences render correctly in the message composer.

Fixes and improvements

• Chat pages in older messages as you scroll.
• Streamed transcripts so large sessions no longer exhaust host memory.
• Hosted dashboards no longer come up blank under heavy asset loads.
• Chat, task, and webhook cards show the inherited model and effort.
• New sessions run at the inherited effort instead of High.
• Server-side upload size checks.
• The iMessage contact card uses the integration's Bot Name.

Built-in media generation

Agents generate images, video, and audio through the platform's own Replicate access, no separate account or API key needed. Output URLs expire quickly, so agents download anything worth keeping into the workspace. Available when the platform is your LLM provider, which meters and bills the calls.

Grok 4.6 in the model picker

Grok 4.6 is xAI's newest model and now the default for the grok family on both the platform and OpenRouter providers; 4.5 stays available as an explicit pin. It bills at $2 per million input tokens and $6 out, doubling past a 200k-token prompt.

Subagents and tasks share one activity rail

Subagents, background processes, and planned tasks now share one rail above the composer instead of three stacked sections. A band travels down the trunk and out along each live branch to show what is working, replacing the pulsing dot on every busy row. Silent under reduced motion.

Fixes and improvements

• Much faster first dashboard launch, with a visible preparation step.
• Open Cloud Agents keeps returning visitors signed in.
• Word-by-word reveal for streamed replies.
• Smoother transcript scrolling as text streams.
• Scrolling to the bottom re-pins the transcript.
• Unified error banner above the composer.
• Lighter heading weights so replies read as messages.
• Workflow approval buttons stay visible in Safari.
• Agent-created child agents are usable without a reload.

Usage analytics in Settings

Settings → Usage is now a dashboard: cost and token charts over a date range, broken down by model and agent, with summary metrics. Click a legend entry or a breakdown row to isolate one model or agent and see selected-versus-total figures.

Expired connections hold instead of failing

When an agent reaches for an account whose access has expired, the request parks and a reconnect prompt appears in chat; reconnecting resumes the original call. The agent home Connections card shows expired accounts and MCP servers. Ordinary messages still start immediately.

Meta's Muse Spark models

Meta's Muse Spark 1.1 and 1.2 are available on the platform provider: $1.25 in and $4.25 out per million tokens, a million-token context, image input, prompt caching. No hosted web tools. The contributor tier is cheaper, but Meta may use those prompts for product improvement.

Fixes and improvements

• Collapsing agent turns into a single row for better session scanability.
• Improved queued message handling and UI.
• Telegram remote chat stability improvements.
• Added default model selection to the onboarding flow.
• Better first agent prompt experience during onboarding.
• Installing a template now closes the setup wizard.
• Saved credentials fill the page shown in the browser viewer.
• Manual reveal and copy when a page hides its password field.
• Empty thinking cards no longer collect in long turns.
• Neighborhood focus when hovering the connections graph.
• New thought orb showing what the agent is doing.
• Restored the Gamut wordmark in the browser sidebar.

Your homepage prompt follows you through signup

A prompt typed into the homepage composer, and the model picked beside it, waits in the create-agent box when your workspace opens. Pick a template instead and its install dialog opens with the name filled in. New signups only; nothing runs until you press send.

Fixes and improvements

• Added the model picker to the create-agent composer.

Push notifications on your phone

Install Gamut to your home screen, switch on Push to this device in Settings → Notifications, and your phone gets a banner when a session finishes or stops to ask something. Tapping it opens the session. iOS 18.4 or later only.

Fixes and improvements

• More than halved the JavaScript needed to boot the web app.
• Full-UI precaching for instant navigation after first paint.
• Atomic asset swaps so open tabs survive a deploy.
• Faster agent lists and session starts via cached summaries.
• Opaque question, secret, and approval cards.
• Stable thinking-card identity across stream handoff.
• Incremental Chrome profile sync that preserves agent logins.
• Leaner production install and a much smaller server image.

Pair the iOS companion app

Settings → Mobile mints a single-use QR code or deep link that the iOS companion app redeems for a 90-day session. Paired devices are listed there and can be revoked individually. Pairing tokens expire after five minutes, and the tab appears only in auth mode.

Agents read the PDFs you attach

Attach a PDF, audio file, or video and the agent can read it — the container ships poppler-utils and ffmpeg, so page extraction, metadata probes, and frame grabs all work. Every format the file viewer renders is covered; OCR and Office documents are not.

Subagents on other providers' models

The parent agent can route a delegated task to any enabled model in your provider's catalog — a cheaper one for parallel exploration, a stronger one for a hard branch. Each family's latest model appears as its own subagent type; older versions do not.

Private GitHub skillsets

Skillsets in Settings can now carry a repository token, so private GitHub repositories work on hosted Gamut, which has no host credentials to inherit. The token is stored apart from skillset metadata and only ever returned masked. A fine-grained PAT with read-only Contents is enough.

Fixes and improvements

• Richer web search and fetch source cards.
• Markdown rendering inside thinking blocks.
• Embedded dashboards appear as soon as the server reports running.
• Translucent composer with a collapsible activity card.
• Smarter auto-follow of streaming output at the live edge.
• Slash commands resolve to the correct skill slug.
• Improved dictation contrast and mobile composer layout.
• Retryable answer submission instead of an endless spinner.
• MCP OAuth completes against cloud deployments from the desktop app.
• Settings → Users links to Platform on managed deployments.
• Faster cold wake for suspended cloud deployments.

Agent-to-agent permissions have their own page

Cross-agent policies open as their own page from the agent home Extras card, listing every agent as a Connected / Not connected toggle. Toggling on grants send immediately; toggling off can pin an explicit review, so you carve exceptions out of a global allow. Owners only.

Fixes and improvements

• Agent containers warm up as you type your first message.
• Provider tabs in the model picker now select a model.
• Better turn anchoring so replies stream into reserved space.
• Dashboard deep links, cookies, and HMR work under artifact mounts.
• Opt-in mounted upstream paths for dashboard servers.

The agent home is a widget board

Agent cards sit on a snap-to-grid board you rearrange in Arrange mode, each a live canvas that shifts color when a session needs input. Arrange lives in the Your Agents menu, and phone and desktop layouts save separately, so tidying one never disturbs the other.

Cloud agents from the desktop app

A Local / Cloud switch in the desktop toolbar points the app at your organization's deployment, so you can drive cloud agents without leaving the desktop. The tray, the Agents menu, and deep links follow the switch, which appears only when a cloud workspace is connected.

Sign in with your password manager

Agents can pull a credential from Apple Passwords through a host-side broker instead of stopping to ask you to type one. Suggestions stay metadata-only until use, and you approve each retrieval. Setup is under Settings → Password Managers, and needs the Chrome extension plus a six-digit pairing.

Browse from inside the agent container

Agents can open a page in the container's own Chromium instead of your configured host browser, reaching dashboards and dev servers on private container ports that a host browser cannot see. The choice sticks until the agent explicitly asks for the configured browser again.

Fixes and improvements

• Agents now arrive as a saved iMessage contact card.
• Tightened Allow once to authorize a single script run.
• Stricter session ownership checks in auth mode.
• Clickable links in agent request cards.
• Slack integration stability improvements.
• Improved MCP proxy handling of non-streaming servers.
• Smaller browser automation profiles with automatic cleanup.
• Faster dashboard availability after container start.
• Roughly halved cold-start pull time with smaller images.
• Consistent policy controls on the Connections page.
• Refined scrollbar styling on Windows.