惯性聚合 高效追踪和阅读你感兴趣的博客、新闻、科技资讯
阅读原文 在惯性聚合中打开

推荐订阅源

博客园 - 三生石上(FineUI控件)
博客园 - 叶小钗
博客园 - 聂微东
博客园 - 司徒正美
Hugging Face - Blog
Hugging Face - Blog
让小产品的独立变现更简单 - ezindie.com
让小产品的独立变现更简单 - ezindie.com
freeCodeCamp Programming Tutorials: Python, JavaScript, Git & More
Google DeepMind News
Google DeepMind News
Recent Announcements
Recent Announcements
IT之家
IT之家
J
Java Code Geeks
钛媒体:引领未来商业与生活新知
钛媒体:引领未来商业与生活新知
I
InfoQ
爱范儿
爱范儿
Vercel News
Vercel News
Apple Machine Learning Research
Apple Machine Learning Research
阮一峰的网络日志
阮一峰的网络日志
博客园 - Franky
U
Unit 42
酷 壳 – CoolShell
酷 壳 – CoolShell
腾讯CDC
F
Fortinet All Blogs
V
Visual Studio Blog
人人都是产品经理
人人都是产品经理

The Keyword

5 helpful tools from Google to keep your accounts safe This Teacher Appreciation Week, we’re celebrating educators who made a difference in our lives. Find out how AlphaEvolve has gone from research to solving real-life problems. Here’s how we're celebrating Asian American, Native Hawaiian and Pacific Islander Heritage Month 5 gardening tips you can try right in Search Google Flow Music and Believe bring next-gen tools to artists 5 new ways to explore the web with generative AI in Search AI is reshaping ad creative. Here’s how brands can get it right. Gemini API File Search is now multimodal: build efficient, verifiable RAG Approximate location sharing gives you more control over your location data in Chrome. Accelerating Gemma 4: faster inference with multi-token prediction drafters Here’s what’s new with Google Home. Celebrating educators’ creativity this Teacher Appreciation Week Turn your data into decisions: 3 things your business needs for growth in the AI era Here’s how we’re helping Belgium's farmers save water with AI. Putting educators at the center of AI learning The latest AI news we announced in April 2026 Here's how Google AI is powering small business growth Reduce friction and latency for long-running jobs with Webhooks in Gemini API Celebrating America’s 250th on Google Arts & Culture Supporting startups that are shaping the future of energy Your car with Google built-in is about to get smarter, thanks to Gemini Preferred Sources is now available in all languages. Adapt your Shopping campaigns to modern Search with AI Max. Meet travelers in the moments that matter with Search Campaigns for Travel. AI Max Turns 1 with new ways to steer performance and expansion to more advertisers How we’re protecting energy affordability in Oklahoma Alphabet is one of TIME’s 100 most influential companies of 2026. Q1 2026 earnings call: Remarks from our CEO A new way to create a digital wardrobe from your Google Photos
Introducing Managed Agents in the Gemini API
Ali Çevik · 2026-05-20 · via The Keyword

The Gemini API now supports managed agents. Run the Antigravity agent in a secure cloud sandbox, build custom agents with your own instructions, skills and data and define them as versionable files using AGENTS.md and SKILL.md.

Philipp Schmid

Philipp Schmid

Member of the Technical Staff, Google DeepMind

Your browser does not support the audio element.

Listen to article

This content is generated by Google AI. Generative AI is experimental

[[duration]] minutes

Today, we're launching Managed Agents in the Gemini API. With a single call, you can now spin up an agent that reasons, uses tools and executes code in an isolated, ephemeral Linux environment. This experience is powered by the new Antigravity agent, built on Gemini 3.5 Flash and available via the Interactions API and in Google AI Studio.

Building a production-grade agent meant managing complex infrastructure, scaffolding and managing isolated sandboxes to serve your customers as you prepare to scale. With Gemini Managed Agents, we’re abstracting away the complexity, so you can focus on your product experience and agent behavior.

Get access to Google's agent infrastructure

In December, we launched Deep Research as our first managed agent for complex research tasks. Now, we are opening up our agent harness and infrastructure so you can build your own custom managed agents.

A single API call to the Antigravity agent provisions a remote Linux environment where the agent can:

  • Reason, plan and call tools using the harness
  • Execute code and manage files in an isolated Linux sandbox
  • Browse the web to fetch and process live data

Each interaction creates or receives an environment, which you can use in follow-up calls to resume the session with all files and state intact.

Define your own agents

You can extend the Antigravity agent with your own instructions and skills. Instead of writing complex orchestration code, you can define everything in markdown files like AGENTS.md and SKILL.md and register them as a managed agent.

What developers are building

We’ve been working closely with a small set of developers both internally and externally to test the product and give us feedback. Here’s some of what they have to say:

Getting started

Managed Agents in the Gemini API is rolling out later today in preview in the Gemini API. You will also be able to get started instantly with our new custom templates in the Google AI Studio Playground. Check out our developer documentation on how to build, including a new Gemini API agent skill designed to help coding agents scaffold and manage your custom agents.

For enterprises, we’ve also added support for managed agents in Gemini API on the Gemini Enterprise Agent Platform in preview.

IOCollection_social

Get more stories from Google in your inbox.

Done. Just one step more.

Check your inbox to confirm your subscription.

You are already subscribed to our newsletter.

You can also subscribe with a

Related stories