Esc

↑↓ move Enter openFull search with filters

Esta sección aún no está traducida. El contenido siguiente se muestra en inglés, tal como se publicó. Leer la versión en inglés.

Google · Enterprise platform

Gemini managed agents (Antigravity agent)

Best for: A hosted agent loop without running servers.

See noteEntry price
NoFree tier
YesMCP
NoOpen source

Compare with similar agents Open the Agent Finder

Checked 1 Nov 2026. A dash means not published on the sources we checked. Price source ai.google.dev (opens in a new tab)

Full sourced profile

MakerGoogle
CategoryEnterprise platform
Skill neededDeveloper
Underlying modelsGemini 3.8 Flash by default, configurable ai.google.dev (opens in a new tab)
Free tierNo ai.google.dev (opens in a new tab)
Plans and tiers–
Paid plans–
Runs onCloud ai.google.dev (opens in a new tab)
AutonomyCan run unattended ai.google.dev (opens in a new tab)
MCP supportYes ai.google.dev (opens in a new tab)
A2A support–
Open sourceNo ai.google.dev (opens in a new tab)
Integrations–
StatusPreview ai.google.dev (opens in a new tab)
Launched–
Best forA hosted agent loop without running servers
Limitations
  • Preview

Tools and MCP connectors that fit

Gemini managed agents (Antigravity agent) states MCP support ai.google.dev (opens in a new tab). It runs in the vendor cloud, so only remote servers are listed. This is not a test of each server.

Open the tool finder for Gemini managed agents (Antigravity agent)

Similar alternatives

Most shared jobs and the same category first, then the closest entry price. A similarity, not a ranking.

Compare Gemini managed agents (Antigravity agent) with Claude Managed Agents and Amazon Bedrock AgentCore

All 42 AI agents · AI models · How we check sources

Latest news from Google

All AI news

Google United States

Google DeepMind releases Gemini Robotics 2.5 for real-world robots

DeepMind says its new vision-language-action model, built with Gemini 4 Argon, was tested on more than 200 tasks, finishes tasks 20% to 30% faster than the previous version and packed automotive parts with a 96% success rate in proof-of-concept tests at Mercedes-Benz. It is rolling out through partners including Agile Robots, Apptronik and Boston Dynamics. The figures are DeepMind's own; more robot training and inference means more GPU demand in data centres.

Source: SiliconANGLE (opens in a new tab)

Google United States

One robots.txt line to opt a website out of AI training

Google says it will support a shared AI training control in robots.txt, alongside Microsoft, OpenAI and Anthropic. It is based on an IETF draft. Website owners get one switch instead of one per crawler.

Source: Google Search Central Blog (opens in a new tab)

Google United States

Google Cloud revenue more than doubles as Alphabet spends $51.4bn in a quarter

Alphabet put $51.4bn into capex in Q3, about 35% of its technical infrastructure spend going to data centres. Google Cloud revenue grew 103% to $30.7bn.

Source: Alphabet (SEC exhibit 99.1) (opens in a new tab)