Remote agents are now live in @Antigravity ☁️ Keep your agents working, even after you close your laptop. Offload tasks to isolated cloud environments that build, test, and prepare pull requests in the background while you're on the move. Watch @kevinhou22 break it down:

you can now build with google maps platform in AI Studio 🗺️📍 go from idea to app powered by @googlemaps in minutes! what’s new: - 1-click setup - create maps apps just by describing your idea, gemini does the rest - build with map tiles, places, weather, routing, 3D buildings, street view, and more try it out today:

Automating the @Unity asset pipeline with Gemini 4 Argon 🐬 Using Google @Antigravity, see how Gemini 4 Argon eliminates hours of tedious pipeline plumbing by turning a text prompt into a fully functional ocean exploration game. Check out how Argon can model and rig 3D assets in Blender, batch import them into Unity, and build artist-friendly custom editor tools to control procedural wave physics, custom shaders, and dynamic lighting.

Analyzing long-form video in the Gemini API just got more accurate and up to 66% cheaper. Agentic video understanding uses tool calls to fetch only the media slices your prompt calls for. Read the full developer guide ↓

🏁 Taking Gemini 4 Argon for a spin in Google @Antigravity. Learn how @genevieve__h transforms a desk photo into an interactive 3D racing game by using Argon to orchestrate subagents and leverage Nano Banana to generate assets for the build.

Build apps that can search through photos, videos, and audio just by describing what's in them. Here’s how everyday developers are pairing EmbeddingGemma 2 from @googlegemma with Google AI Edge to make it happen, completely on-device 🧵👇

introducing @NanoBanana 2.1 🍌 our latest image generation model outperforms our previous models across the board: - better visual design - mask-based editing - subject consistency - more natural-looking images try it out today in

We don’t just build the tools, we build with them. From interactive 3D worlds to real-time speech tools, our teams at Google have been putting the Gemini models to work. Take a look at a few of our favorite experiments and builds 🧵 ↓

Announcing Gemini 4 Argon, our new frontier model. Argon is built to sustain deep reasoning across complex, long-horizon workflows and delivers frontier performance in complex workflows across real-world software engineering, enterprise knowledge work like legal and finance, and cybersecurity defense. We’re also expanding the model’s output token limit to an industry-leading 1M tokens. Argon is currently rolling out to a set of trusted cyber defenders in the Fairwind Program, with broader availability as soon as possible.

Looking to level up your skills and connect with fellow builders? #DevFest# season is here 💫 Join local Google Developer Groups to learn from interactive workshops, share technical knowledge, and expand your network. Find an event near you and register today:

10,000 installs and counting! 📈 We created Modern Web Guidance to bring web platform expertise right into your agent workflows. Have you tried pairing these skills with Chrome DevTools for agents to audit performance and automatically fix code? Check it out and join 10K+ web developers who are coding smarter →

See how AI models can help you with multi-day engineering workflows with Android Bench 2.0. The updated benchmark evaluates long-horizon tasks like building apps and features from scratch, migrating cross-platform codebases to Android, and making complex architectural transitions, with continuous completion scoring that shows which tasks models perform well on. Check out what's new 👇

Open tooling builds stronger developer ecosystems. We teamed up with @speakeasydev to ship the new Google GenAI SDKs for our Interactions, Agents, and Webhooks APIs. Read why we believe SDK generation belongs in the open and explore Speakeasy's newly open-sourced OpenAPI generator suite:

Want to try Gemini 3.5 Transcribe, 3.8 Live, 3.8 Live Extended Thinking, and meet the folks who built them? 🎙️ Join us for Gemini Audio | At Night, an evening exploring the next frontier of voice-first AI. Connect with the product and research teams behind our latest Gemini Audio models, test live interactive demos, and network with fellow builders and founders. 📍 The Pearl, San Francisco 🗓️ Thursday, Sept 24 | 6:00 PM to 10:00 PM RSVP today:

Building voice AI with Gemini? Join us live on Discord with @thorwebdev from @GoogleDeepMind and @hermes_f from Agora. We’ll cover the latest real-time capabilities, natural turn-taking, interruptions, tool use, evals, and what it takes to ship dependable voice agents. 📅 Thursday, Sep 17 at 9 AM PT / 12 PM ET Link:

It's been a busy couple of weeks for the @antigravity team. Here's a few updates they've made ⬇️ > AlphaGenome Atlas Skills are launched to accelerate genomic discovery using AI agents. > /boost command for tackling complex developer tasks through a focused multi-agent reasoning workflow. > /teamwork-preview is improved and powering breakthroughs in mathematics, hardware simulation and open source optimization. > Interactive Generative UI Artifacts creation is now available, ranging from data visualizations to 3D explanatory simulations that can be rendered seamlessly inline and in your artifacts panel. > Updated Git Version Control System and Terminal, giving more flexibility to track changes to your repository and running tests, scripts, and commands directly in the embedded terminal.