Google Antigravity 2.29 adds cloud Remote Agents for Google AI Pro and Ultra subscribers
Google's Antigravity 2.29 adds Remote Agents that run in isolated cloud virtual machines for Google AI Pro and Ultra subscribers. The update also brings a Gemini Live-powered Voice Mode, a redesigned conversation page, and changes to Automations and the built-in browser.
Google is rolling out Remote Agents in Antigravity 2.29, letting paid Google AI Pro and Ultra subscribers run agent tasks in isolated cloud environments that keep working after the laptop is closed. The release, reported by 9to5Google on November 6, 2026, also adds a Voice Mode powered by Gemini Live and a redesigned conversation page.
Remote Agents
Antigravity is Google's agentic development platform for Mac, Windows, and Linux. Remote Agents are the largest change in version 2.29, according to 9to5Google. Users create a remote project in the cloud from either a GitHub repo or a Google Drive folder.
Google's Antigravity account on X says tasks run in independent cloud virtual machines. The company describes a workflow in which a user starts a task, steps away, unblocks permissions from a phone, and returns to passed tests and a clean pull request. Remote agents can be controlled from the existing antigravity.google.com/remote page on a phone. Google says it has been rolling out remote agents this week.
Availability is limited to paid Google AI Pro and Ultra subscribers. Pricing for the subscription tiers is not stated in the report.
Voice Mode
A new Voice Mode sits next to the existing microphone button and is powered by Gemini Live. Google says it lets users "talk to Antigravity and hand requests to the agent by voice." Several voice options are available, and playback speed can be set from 0.75x to 2x.
Redesign
The conversation page now places the prompt box at the bottom of the screen, with a greeting at the top similar to the Gemini app. Google Sans is now the default font, and Onyx is the default theme. Single-repo projects combine branch and Git worktree selection into one menu, and the agent picker now lives inside the model menu.
Other changes in 2.29
- Automations: The page now sorts automations into Scheduled, Always on, and Paused lists, with Next run and Last run times, plain-menu schedule pickers, in-page details, and a full-page creation form.
- Built-in browser downloads: Files save directly to the downloads folder without blocking prompts, progress appears in a toolbar downloads drawer, and a default download folder can be set under Settings > General.
- Built-in browser navigation: The address bar suggests matching pages from browsing history, and history can be cleared under Settings > General. The address bar has clearer connection security indicators, a thin loading progress bar runs along the top of the page, and an in-page prompt dialog appears when a site requests text input.
- Side panel: Users can open a web address or search Google from the New Tab page, drag links into the panel to open them in the built-in browser, and close tabs to the left from a tab's menu.
- Shortcuts: Keyboard shortcuts can be customized in Settings > Shortcuts and reset to defaults.
- Performance: Antigravity launches faster on cold start, and opening or closing the sidebar and side panel animates without layout jumps.
What this means
Remote Agents change where Antigravity tasks execute. Work runs in cloud virtual machines rather than on the user's local machine, so a task continues when the laptop is closed, and permission prompts can be handled from a phone. Tying access to Google AI Pro and Ultra means the feature is part of the paid subscription tiers. Voice Mode adds a spoken input path to the agent through Gemini Live, alongside the existing microphone. The Automations changes, with Scheduled, Always on, and Paused lists showing Next run and Last run times, make recurring agent jobs easier to track.
Related Articles
Meta adds real-time voice mode and expressive avatars to Muse AI agent in US app
Meta now lets users hold real-time voice conversations with their Muse AI agent, CEO Mark Zuckerberg announced. The voice mode and animated 'expressive' avatars are rolling out in the US for the app, with AI glasses support coming 'soon'.
Google shows Gemini Canvas turning a photo of a paper sketch into an interactive app
Google published a Gemini walkthrough on November 5, 2026, showing how a photograph of a paper sketch can become an interactive app in Canvas. The demonstration covers uploading the image, generating code, testing the result and refining it through conversation.
Google releases Gemini Omni 1.2 Flash video model: 15-second clips up to 4K with native audio
Google released Gemini Omni 1.2 Flash on November 5, 2026, a native multimodal video generation and editing model that succeeds Gemini Omni 1.1 Flash. It generates clips up to 15 seconds with native audio at resolutions from 360p to 4K. OpenRouter lists it at $1.50 input and $9 output per 1M with a 131K context window.
Google releases Gemini Omni 1.1 Flash, a generally available video model with 4K output and native audio
Google released Gemini Omni 1.1 Flash on Nov 4, 2026, a native multimodal video generation and editing model that is the generally available successor to Gemini Omni Flash Preview. It outputs clips from 360p drafts up to 4K with native audio, and is listed on OpenRouter at $1.50 input / $9 output per 1M tokens with a 131K context window.
Comments
Loading...