Antigravity v2.31.0 Adds Agent Swarms, Remote Work

// 12m agoPRODUCT UPDATE

Antigravity v2.31.0 Adds Agent Swarms, Remote Work

Google Antigravity’s v2.29.0–v2.31.0 releases add voice mode, remote cloud agents, native Jupyter viewing, knowledge-work layouts, and `/swarm` coordination. The latest update also introduces split-view plugins and browser download approvals.

// ANALYSIS

This is a meaningful expansion from AI coding workspace toward general-purpose agent platform, though workflow control matters more than the interface polish.

–`/swarm` gives multi-agent work an explicit coordination layer for long-running tasks.
–Remote agents let paid Pro and Ultra users move execution into Google’s cloud while retaining browser access.
–Importing MCP servers, skills, commands, subagents, and instructions from Claude Code, Codex, and Cursor lowers switching costs.
–Native notebooks and browser hardware access broaden Antigravity beyond traditional code editing.
–Product Hunt reviews praise planning and parallel agents but flag usage limits, weaker fallback models, and multi-file reliability concerns. [Product Hunt reviews](https://www.producthunt.com/products/google-antigravity/reviews)

// TAGS

google-antigravityai-codingcoding-agentagentmcpautomationcloud

DISCOVERED

12m ago

2026-11-10

PUBLISHED

1h ago

2026-11-10

RELEVANCE

9/ 10

AUTHOR

rodydavis

// KEEP READING

More AI developer news from the feed

EXPLORE FULL FEED

UPDATE38m ago

T3 Code 2.3 Adds Mobile Dictation

T3 Code 2.3 brings on-device dictation to iOS and Android, with optional transcription through paired computers or cloud models from OpenAI, Grok, and OpenRouter. The update also adds side chats, model mentions, Mermaid and math rendering, PDF improvements, and faster reconnects.

RESEARCH1h ago

Meta's AutoRefine Calibrates Code Judges

Meta’s AutoRefine paper presents a prompt-rewriting loop that uses noisy workflow outcomes—tests, merges, and abandons—to recalibrate LLM code judges, while abstaining when outcomes cannot be explained by the judge’s inputs. On held-out diffs from a deployed coding agent, agreement rose from Scott’s π 0.16 to 0.51. ([paper](https://arxiv.org/abs/2611.09291))

INFRA1h ago

Browser Use Cloud Clears CAPTCHA Bottleneck

Browser Use’s stealth cloud browser combines hardened Chromium, residential proxies, and automatic CAPTCHA solving for AI agents. The company reports 90.5% successful visits across 100 bot-protected sites in its own benchmark.