# Antigravity Published articles for Antigravity. This is one page of public article previews, not the complete archive. Follow Next page to continue. Summaries are not the original full articles. ## \[Aug 2026\] AI Community -- Activity Highlights and Achievements DevFeed: [\[Aug 2026\] AI Community -- Activity Highlights and Achievements]() Original publisher: [Read original article]() Author: Nari Yoon Published: 2026-09-17T05:12:15Z Content type: article Language: en Sources: [Google Developer Experts - Medium]() Topics: [Google AI](), [Google](), [google-antigravity](), [Artificial Intelligence](), [MCP Server](), [computer-use](), [Fine-tuning]() Tags: [2026](), [agentic-ai](), [ai](), [ai-coding-agents](), [ai-studio](), [antigravity](), [api](), [automation](), [community](), [computer-use](), [gemini](), [google](), [google-ai](), [google-cloud](), [mcp](), [mcp-server](), [multi-agent](), [ocr](), [paper](), [pitfalls]() ### AI overview A monthly roundup of Google AI community activities and achievements, covering Antigravity prototyping and engineering, AI coding agents, MCP-based remote control, computer-use agent orchestration, earthquake research, and TPU fine-tuning and migration guidance. ### Source excerpt We love sharing the accomplishments of the Google AI communities over the month. We appreciate all the hard work and dedication of our community members. Without further ado, here are the key highlights by products! Agentic DevelopmentAntigravityPrototype App: OCR and Text Extraction by the author Prototyping and Bringing Ideas to Application Using Google AI Studio and Antigravity 2.0 by AI GDE Joan Santoso (Indonesia) shares a rapid prototyping workflow building an AI-powered Form Extractor using the Gemini API, featuring a lightweight OCR and text extraction workflow. Antigravity Engineering Series by GDE Amulya Bhatia (Germany) focuses on key features of Antigravity 2.0 across 10 articles covering topics such as multi-agent orchestration, safety architecture, and workflow automation, accompanied by source code examples. (image soruce) Remote Control for Google Antigravity: Drive Your AI Coding Agent From Telegram 🛰 by GDE Nicola Guglielmi (Italy) introduces an open-source MCP server that turns Telegram into a remote control surface for AI coding agents. Before the Quake: How Antigravity CLI's AI Agents & IoT Data Predict Earthquakes by GDE Kanshi Tanaike (Japan) introduces the paper establishing Unified LAIC-AGW Theory by integrating ultra-dense IoT weather data with seismic moment tensors. It demonstrates a pre-seismic early warning capability by capturing enthalpy anomalies and acoustic-gravity waves. ADKAI GDE Henry Ruiz (US) and AI GDE Margaret Maynard-Reid (US) AI GDE Henry Ruiz (US) and AI GDE Margaret Maynard-Reid (US) introduced UISurf: An Operator-Centric Multi-Agent Platform for Observable and Cross-Environment UI Automation at the Agentic AI Summit 2026. They highlighted how the model-agnostic framework leverages the Google Cloud and Gemini ecosystems, such as GEAP and ADK, to orchestrate and evaluate computer-use agents across web, desktop, and mobile environments. Frameworks and ResearchTPU Introduction to SFT on TPU with Tunix -- 10 pitfalls until 2 ## Pair Programming With Your AI Agent DevFeed: [Pair Programming With Your AI Agent]() Original publisher: [Read original article]() Author: blundell Published: 2026-09-06T21:50:09Z Content type: tutorial Language: en Sources: [Blundell]() Topics: [AI Agent](), [Local AI](), [Programming](), [Command-line interface]() Tags: [agent](), [ai](), [ai-agent](), [androiddev](), [antigravity](), [cli](), [gemini](), [geminicli](), [intermediate](), [intermediate-reference-ai-androiddev-gemini-geminicli-pairing](), [pair](), [pairing](), [programming](), [reference](), [terminal]() ### AI overview This tutorial presents sessions with a local AI agent as pair programming and maps four classic pairing styles--unstructured, Driver/Navigator, Strong-Style Pairing, and Ping Pong--to AI-assisted development. It uses Antigravity CLI for examples while noting that the approach is not specific to that tool. ### Source excerpt This post explains how to treat a session with a local AI agent as a pair programming session, and how the four classic pairing styles map onto working with one. I'll use Antigravity CLI for the concrete examples, though nothing here is specific to it. Swap in whichever agent sits in your terminal. The idea [...] The post Pair Programming With Your AI Agent first appeared on Blundell. ## Customizing Angular Aria Tabs Quickly with Google Antigravity CLI DevFeed: [Customizing Angular Aria Tabs Quickly with Google Antigravity CLI]() Original publisher: [Read original article]() Author: Angular Published: 2026-09-02T01:50:59Z Content type: tutorial Language: en Sources: [Angular]() Topics: [Angular](), [Accessibility](), [google-antigravity](), [CSS](), [User interface design]() Tags: [accessibility](), [angular](), [antigravity](), [css](), [material-design](), [ui]() ### AI overview This tutorial tests how far Angular Aria tabs can be customized while preserving accessibility. It uses Google Antigravity's coding agent and a /goal command to transform a basic tab interface into a neumorphic design, then addresses contrast problems identified by Lighthouse. After a correction, the application reaches a 100 accessibility score. ### Source excerpt The Angular team has called Angular Aria a set of customizable, fully accessible UI patterns. This is a strong claim, but in practice, how possible is it to heavily customize the components while maintaining accessibility features such as keyboard navigation and focus management? In this post, we're going to use Google Antigravity to put that claim to the test by updating a tab UI from generic styles to a neumorphism-based design. Motivation In the angular.dev documentation, the team has examples with a set of basic, Material Design-based, and retro styles meant to show developers what's possible with these new accessibility patterns. Here's the challenge: take the tabs basic styles example further by implementing the following neumorphism-inspired design. Here's a look at the UI before any changes: Angular Aria tabs component with basic styles applied The Lighthouse accessibility report shows a 100 score before making any changes: Accessibility score for the tabs based on the original styles Neumorphic designs are typically criticized for their poor accessibility. This experiment is designed to push the coding agent with complex CSS styles while stress-testing the customizability of Angular Aria tabs. Additionally, I'll ask the agent to update any accessibility issues that come up. Making the changes The styles for this UI are well organized, but require a lot of changes to achieve something like a neumorphic design. Instead of writing them by hand, Google Antigravity's coding agent can make the changes. Here's the prompt: /goal update the tabbed UI to be neumorphic style. The example UI is @example-ui.jpeg and the styles are in @src/app/app.css A few things to note here: This example used a reference image for inspiration (@example-ui.jpeg) to inform the designs. This example also uses the /goal command in Google Antigravity instructs the agent to work a task to completion without asking the user for immediate input. The Result Here's the resulting UI based on the ## Remote Control for Google Antigravity: Drive Your AI Coding Agent From Telegram DevFeed: [Remote Control for Google Antigravity: Drive Your AI Coding Agent From Telegram ]() Original publisher: [Read original article]() Author: Nicola Guglielmi Published: 2026-08-21T12:12:57Z Content type: tutorial Language: en Sources: [Google Developer Experts - Medium]() Topics: [google-antigravity](), [MCP Server](), [cursor](), [Claude Code](), [Terminal](), [Code]() Tags: [agent](), [ai](), [ai-agent](), [ai-coding](), [antigravity](), [coding](), [google-antigravity](), [mcp](), [mcp-server](), [telegram-bot](), [terminal](), [vibe-coding]() ### AI overview This tutorial introduces Telegravity, a single-binary MCP server that connects Telegram with AI coding agents such as Google Antigravity, Claude Code, and Cursor. It describes remote instructions, live status, conversation history, workspace selection, and an active mode for reacting to Telegram messages. ### Source excerpt Your agent runs for 20 minutes. You walk away from the laptop. What if your phone became your mission control? We are living a strange new moment in the software industry. We kick off an AI coding agent: Antigravity, Claude Code, Cursor, give it a task, and then... we sit there. Watching a terminal. Babysitting a process that might run for two minutes or for two hours. That always felt wrong to me. The whole promise of an autonomous agent is that it works while you live your life. But the moment you stand up to grab a coffee, you go blind: you can't see what it's doing, you can't nudge it, you can't say "wait, not that file" until you're back at the keyboard. So I built the missing piece I needed. I call the project Telegravity, the uplink between Telegram and my AI coding agent. In this article I want to show how it turns Antigravity into something you can drive remotely, from the same chat app you already check fifty times a day. Let's launch. 🚀 https://github.com/nicolaguglielmi/Telegravity The idea explained in one sentence Telegravity is a single-binary MCP server that exposes a tiny set of tools to your agent, pull instructions, post live status, stream conversation history, while the Telegram side gives you a polished dashboard, a conversation hub, and an Active Mode that wakes the agent the instant you type. That's it. One process. No cloud service in the middle, no extra account, no telemetry. Your bot token never leaves your machine. End to end, the whole conversation stays private. The magic is that it speaks the Model Context Protocol (MCP), so it doesn't care which agent you use. Antigravity is a first-class citizen, but the exact same setup works for Claude Code, Cursor, Cline, or anything else that speaks MCP. What you actually get Before the setup, here's the payoff, so you know what we're building toward: A live dashboard with an agent heartbeat: 💭 Thinking - ⚡ Executing - ✅ Done an unread inbox counter, the current workspace, and a chat-mode badge. A ## Android Skills: Philosophy, Selection Criteria, and Evaluation Methodology DevFeed: [Android Skills: Philosophy, Selection Criteria, and Evaluation Methodology]() Original publisher: [Read original article]() Author: Android Developers (noreply@blogger.com) Published: 2026-08-06T16:00:00Z Content type: opinion Language: en Sources: [Android Developers Blog]() Topics: [Android skills](), [Large Language Model](), [Android Studio](), [Command-line interface]() Tags: [agent](), [agents](), [ai-assisted-coding](), [android-skills](), [android-studio](), [antigravity](), [cli](), [docs](), [gemini]() ### AI overview Android Developer Relations explains how official Android Skills are selected, focusing on verifiable knowledge gaps in state-of-the-art models and fast-moving topics. The article also discusses context costs, evaluation requirements, model compatibility, and use of the Android Knowledge Base. ### Source excerpt Posted by Jose Alcérreca, Developer Relations Engineer, Android Developer Relations We released the official Android Skills in April, and the response surpassed all our expectations. In this blog post, I'll address some of the feedback we received, explaining the philosophy and methodology behind the project. Hopefully, this will also help you understand what happens behind the scenes when you install and use skills, allowing you to make better use of tokens and your own time. Why are there so few official skills? Currently, we only consider new skills when there's a verifiable knowledge gap in state-of-the-art (SOTA) models. Put simply: you don't need to teach the model what it already knows. (Though there are a few exceptions--read on!) We've released around 20 official skills so far, and they intentionally target highly specific, fast-moving areas that standard models aren't fully grounded on yet--things like AGP 9, Navigation 3, advanced Camera APIs, and Perfetto SQL. What about core, more general, skills? Every installed skill injects 100-200 tokens into the baseline context of every task you start. If that skill actually activates, that count can quickly jump into the thousands. In most cases, hoarding basic skills is both counterproductive and expensive. Before installing a skill for writing basic Kotlin or Compose, consider if your LLM of choice really needs it, or if it knows those topics well enough already. Evaluating skills Before their release, each skill is tested against a comprehensive set of evals that prove that the skill delivers clear value. These evals should pass when the skill is active, and fail otherwise. Evals are to skills what integration tests are to code. timeout_s: 1200 repository: url: [redacted - internal git repo] working_dir: wear_compose_m3_empty_app category_ids: - wear prompt: |- Add a horizontal pager to MainActivity.kt. Have three pages in the pager. Each page should contain the text "Page 1", "Page 2", and "Page 3" respectively ## LoopSmith: Closed-Loop AI Engineering for Self-Correcting Pipelines on Antigravity 2.0 DevFeed: [LoopSmith: Closed-Loop AI Engineering for Self-Correcting Pipelines on Antigravity 2.0]() Original publisher: [Read original article]() Author: Esther Irawati Setiawan Published: 2026-07-29T09:40:30Z Content type: tutorial Language: en Sources: [Google Developer Experts - Medium]() Topics: [AI Engineering](), [google-antigravity](), [Agent Harness](), [SDKs](), [Command-line interface](), [Code]() Tags: [agent-harness](), [agentic-ai](), [ai](), [ai-engineering](), [antigravity](), [cli](), [google-antigravity](), [pipelines](), [sdk](), [verification]() ### AI overview A guide to using Antigravity 2.0 to build closed-loop AI engineering workflows. It presents a state-machine pattern in which an agent writes, runs, and fixes code against a defined objective until the output is verified, while noting that the SDK is pre-v1.0 and its documented interfaces may change. ### Source excerpt LoopSmith: Closed-Loop AI Engineering -- Autonomous /goal Execution for Self-Correcting Pipelines on Antigravity 2.0Stop prompting the agent turn by turn. Hand it an objective, a bar to clear, and let the state machine write, run, and fix its own code until the output is verified.This guide targets Antigravity 2.0 -- the four-surface release (desktop app, agy CLI, google-antigravity SDK, and enterprise cloud) that shares one agent harness. The SDK is pre-v1.0; symbol names and CLI flags below reflect the documented API as of mid-2026. Treat the patterns as stable and re-check exact signatures against the current docs before you ship.Table of contents The problem with the on-demand agent The architectural shift: closed-loop engineering as a state machine Step 1 -- Initialize the project and the state machine (agy) Step 2 -- Define the objective and trigger /goal execution mode (SDK) Step 3 -- Implement the self-correcting loop Step 4 -- Verification and state finalization Conclusion 1. The problem with the on-demand agent Most "AI engineering" today is still conversational. You prompt; the model answers. You notice the answer is wrong; you prompt again. You paste a traceback; it apologizes and tries once more. The intelligence is real -- but you are the control loop. You are the thing that runs the code, reads the error, decides whether the output is good enough, and feeds the next instruction back in. Take the human out of that seat and the whole system stops. That's fine for a chat window. It falls apart the moment you want an agent to produce a deliverable -- a cleaned dataset, a reconciled financial report, a migration that actually compiles. Real analytical work is iterative and self-referential: you write a script, it crashes on a currency string, you fix the parse, it runs but the totals don't reconcile, you fix the aggregation, and only then is the output trustworthy. Every one of those arrows is a decision. An on-demand agent makes you supply all of them. There are ## \[May-Jun 2026\] AI Community -- Activity Highlights and Achievements DevFeed: [\[May-Jun 2026\] AI Community -- Activity Highlights and Achievements]() Original publisher: [Read original article]() Author: Nari Yoon Published: 2026-07-22T01:22:04Z Content type: article Language: en Sources: [Google Developer Experts - Medium]() Topics: [google-antigravity](), [Google](), [Google AI](), [AI Agent](), [Agent Skills](), [Model Context Protocol (MCP)](), [Windows Subsystem for Linux](), [Python](), [HTML](), [Command-line interface](), [CSV](), [SDKs]() Tags: [2026](), [ai](), [ai-agent](), [ai-agents](), [antigravity](), [cli](), [community](), [google](), [google-ai](), [here](), [html](), [mcp](), [python](), [sdk](), [skills](), [wsl]() ### AI overview This article highlights May-June 2026 activities and achievements from Google AI communities. It summarizes community projects, codelabs, experiments, and guides involving Google Antigravity, Gemini, the Antigravity SDK, AI agents, MCP servers, agent skills, CLI and IDE workflows, HTML dashboards, CSV data, and Windows Subsystem for Linux. ### Source excerpt We love sharing the accomplishments of the Google AI communities over the month. We appreciate all the hard work and dedication of our community members. Without further ado, here are the key highlights by products! Agentic DevelopmentAntigravity [Codelab] Building Trustable AI at 100 MPH by GDEs in the US: Hemanth HM, Vikram Tiwari, Lynn Langit, Sebastian Gomez, Rabimba Karanjai; Googler: Ajeet Mirwani; and the partner: Ocupop guides you in building a trustable AI prototype inspired by the field test from the Unstoppable GDE Cohort. The project summary, Bridging the Domain Gap: AI Race Coach built with Antigravity and Gemini and the members of the July cohort were featured on Google for Developers Blog✨. Skills over System Prompts: Building an Anki Tutor with the Antigravity SDK by AI GDE Ertuğrul Demir (Türkiye) demonstrates the value of a modular approach to AI agent design by creating custom Python tools and reusable skill packages for an Anki flashcard tutor using Antigravity SDK. (Image source) Startup on a Shoestring -- Building with a 50c Budget using Google Antigravity Cost & Token Monitors💸 by AI GDE Jigyasa Grover (US) conducted an SDK-powered cost engineering experiment to observe an AI agent prioritize, panic, and ship an MVP landing page under intense budget pressure. Google Antigravity CLI: Orchestrating Parallel AI Agents by AI GDE Aashi Dutt (India) explores how to create an interactive HTML dashboard from a raw CSV file with a single command and explains the benefits of the subagent architecture. (Image source) Configuring MCP Servers and Skills for Antigravity CLI and IDE by Cloud GDE Darren Lester (UK) provides a deep-dive guide on configuring MCP servers and agent skills for the new Antigravity CLI and IDE. He also shared Resolving WSL Friction with Google Antigravity: the Agy 2.0 and Agy IDE Edition discussing how to resolve friction between the Antigravity suite and the Windows Subsystem for Linux environment. Google Antigravity 2 & Gemini 3.5 ## Antigravity TagSpotter - Share data with Firebase DevFeed: [Antigravity TagSpotter - Share data with Firebase]() Original publisher: [Read original article]() Published: 2026-07-09T20:34:04Z Content type: tutorial Language: en Sources: [maiatoday]() Topics: [Firebase](), [Google](), [SDK](), [data](), [iOS]() Tags: [ai](), [ai-agents](), [antigravity](), [code](), [data](), [firebase](), [google](), [ios](), [kmp](), [sdk]() ### AI overview The article describes planning and implementing Firebase-based cloud storage for TagSpotter, including authentication, offline use, cross-device syncing, shared data packs, schema changes, migrations, and platform SDK constraints. It finds that defining requirements and edge cases required substantial planning before implementation. ### Source excerpt The challenge - Firebase with Google Plugins Now that I can see my graffiti spots on multiple platforms the obvious next step is I want to keep the data in the cloud so that I can capture spots when I'm out and about and then look at them and edit them on the laptop later. For this I need some kind of auth and data storage - like Firebase. Like before, can I do the implementation on a weekend. Easy enough? Well Antigravity 2.0 has firebase super powers in the form of Google shipped plugins but figuring out what I really want and what the edge cases are was not trivial. The prep grill-me grill-me grill-me For this exercise I was pretty confident antigravity could code up my solution. Just look at all these built in firebase skills. What I wasn't sure of was what I actually wanted. Let's get some ideas. I wanted users that didn't want to log in, not to be forced to do this. So there was the idea of an offline mode. Then when I do log in and I happen to change something on my phone and then on the desktop it should take the latest edit. I wanted it to update in the background but realistically only when I finish editing a spot. What happens when I delete a spot? How will it work when I import a pack? What happens when the photographer name is the same but the email differs? Can I have a way to save a pack of spots and just share a code to see it? What then, will I be able to change them? How does the db schema change? What migrations are needed? Will the old share packs work? How do I even set things up properly on firebase? What about desktop, there isn't an SDK for desktop? And so on and so on. I was clearly better at asking questions than building especially since I didn't know how to integrate the SDK on iOS. I spent about two evenings planning and changing my mind to come up with this plan It required multiple rounds of /grill-me and also asking antigravity for some suggestions on how things could work and picking the options I liked best. The plan had important s ## Vibe once, run anywhere with Antigravity and Flutter DevFeed: [Vibe once, run anywhere with Antigravity and Flutter]() Original publisher: [Read original article]() Author: Craig Labenz Published: 2026-06-29T16:01:02Z Content type: article Language: en Sources: [Flutter - Medium]() Topics: [Flutter](), [AI-assisted coding](), [cross-platform](), [Artificial Intelligence](), [Dart](), [Large Language Model]() Tags: [agentic](), [agentic-engineering](), [ai](), [antigravity](), [code](), [coding-agents](), [cross-platform](), [dart](), [flutter](), [flutter-app-development](), [game-development](), [google-antigravity]() ### AI overview This article describes how a team used Google's Antigravity and Flutter to build and launch DashLander, a moonlander-style game set on procedurally generated asteroids. It explains how coding agents handled assets, code, testing, marketing, and deployment, and why Flutter's cross-platform model and Dart's strong typing can support agentic development. ### Source excerpt co-authored with Rody Davis Coding agents and the way we use them has already dramatically evolved since their arrival just a handful of months ago. Initially, the focus was heavily on observation -- reviewing every single output line by line. But as models rapidly increased in capability, the industry shifted toward true agentic engineering. Today, developers, PMs, and designers are wearing multiple hats, focusing on lofty conceptual goals and letting agents tackle the individual components. To explore this new frontier, our team wanted to build an experience that showcased this exact workflow. We wanted to build a game, generate its assets, write the marketing page, and deploy the whole thing, all using Google's premiere AI-native platform: Antigravity. Antigravity brings the best of Google into one place, using a tight feedback loop of planning, acting, and verifying. It creates artifacts, writes code, runs tests, and even clicks buttons in your UI to ensure it actually completed the task correctly. The result of our agentic adventure is DashLander -- a moonlander-style game set on procedurally generated asteroids. Here is the story of how we built it. Why Flutter in the AI era? A lot of people might be thinking: If agents can write native code, why not just have them write Android, iOS, and web apps entirely separately? That is a valid question; and is what originally inspired the concept of Flutter as a "Vibe once, run anywhere" UI toolkit. Having a single source of truth is just as important for AI as it is for humans. By having an agent write a single, cross-platform app, teams can eliminate the subtle bugs that inevitably creep in between different languages or platform-specific paradigms. Furthermore, Dart's strong typing gives LLMs excellent feedback. Languages with looser typing systems require dramatically more analysis by the LLM to know whether a given piece of code is correct across all scenarios. Flutter and Dart, on the other hand, use their analysis ## Harness MCP Server Now Connects Google Antigravity IDE DevFeed: [Harness MCP Server Now Connects Google Antigravity IDE]() Original publisher: [Read original article]() Author: Rohan Gupta Chinmay Gaikwad Published: 2026-06-22T00:00:00Z Content type: release Language: en Sources: [Harness Blog]() Topics: [MCP Server](), [Model Context Protocol (MCP)](), [ide](), [Artificial Intelligence](), [Google]() Tags: [agents](), [ai](), [ai-agents](), [antigravity](), [google-antigravity](), [harness](), [ide](), [integration](), [mcp](), [mcp-server](), [personal-access-token]() ### AI overview Harness announces that its MCP Server connects directly to the Google Antigravity IDE, allowing AI agents to inspect pipelines, debug deployments, trigger approved runs, and use real-time delivery context. The article also describes setup with a Harness Personal Access Token and Antigravity's Customizations panel. ### Source excerpt Connect Harness MCP Server inside Google Antigravity to let AI agents inspect pipelines, debug deployments, trigger approved runs, and act on real-time delivery | Blog ## From Feature Branches to Agent Branches ft. Antigravity DevFeed: [From Feature Branches to Agent Branches ft. Antigravity]() Original publisher: [Read original article]() Author: Amit Merchant Published: 2026-06-20T00:00:00Z Content type: opinion Language: en Sources: [Amit Merchant]() Topics: [Git](), [Development](), [AI Development]() Tags: [ai](), [antigravity](), [coding](), [git](), [workflow]() ### AI overview The article explains how Antigravity's interface for Git worktrees changed the author's view of them from a convenience feature into a useful way to organize and isolate multiple development tasks. It describes using separate worktrees, or "agent branches," for individual features and tasks. ### Source excerpt When people talk about AI coding tools, the conversation usually revolves around models, prompts, context windows, and agent capabilities. That's usually what grabs the headlines. ## Antigravity TagSpotter - KotlinMultiPlatform evolve DevFeed: [Antigravity TagSpotter - KotlinMultiPlatform evolve]() Original publisher: [Read original article]() Published: 2026-06-14T19:10:33Z Content type: opinion Language: en Sources: [maiatoday]() Topics: [kotlinmultiplatform](), [multiplatform](), [Android](), [compose-multiplatform](), [Kotlin](), [iOS](), [Gradle](), [Web](), [Open Source]() Tags: [ai](), [ai-agents](), [android](), [antigravity](), [code](), [compose](), [compose-multiplatform](), [git](), [kmp](), [kotlin](), [kotlinmultiplatform](), [migration](), [tests]() ### AI overview The article documents an attempt to migrate the TagSpotter Android app toward Kotlin Multiplatform using Antigravity 2.0 and parallel agents. It describes preparation such as modularizing the codebase, adding tests, researching KMP migration, and planning support for iOS, Android, Desktop, and Web, while retaining Android-specific features such as the Wear app. ### Source excerpt The Challenge - bring on the subagents Can I make my TagSpotter Android app be multi-platform in a weekend using Antigravity 2.0 and a swarm of agents running in parallel? Can I do this even though I don't know how to use Xcode and I don't want to break my existing app. This was the question I had. TagSpotter is medium featured Android app I built two weeks ago. I use it to capture interesting and favourite spots in the city like unusual graffiti or yarn bombed sculptures. It has a fair few features including: Capture the places by camera with location Upload a photo AI lookup to find info on the internet from the photo, links, title, artist and suggested tags Export the spots in a zip file and import them again. This is how I share my favourite spots with friends. Make field notes by typing or speaking Share my favourites to Google maps for easy navigation Good category and location based filtering Wear app that can list started spots and navigate to a spot on the watch A good challenge because it isn't just a hello world app. The prep Because the clock would be ticking, I did a little bit of prep to make sure I had everything ready. Prep the codebase Clean up the app, no warnings, lint issues or unused imports Make sure the screens work in landscape, desktop mode will need this Split the app into feature based and pure kotlin modules. I know Compose multiplatform and pure kotlin modules can easily be re-used. Put some tests in place Checked everything works and make a tag in git incase Antigravity borked the project. Light research I collected a few salient links about KMP migration. A good blog post, some info on project structure and a link to the open source kmp libraries I might need. Nitty Gritty Friday evening, let's go. Make a plan I want to convert this app to a KMP app that supports iOS, Android, Desktop and Web. The other platforms do not have to support all features, e.g. the wear app. But Android still has to support this feature. I want to share as mu ## Google joins the Eclipse Foundation as a strategic member to accelerate AI-integrated developer tools DevFeed: [Google joins the Eclipse Foundation as a strategic member to accelerate AI-integrated developer tools]() Original publisher: [Read original article]() Author: Google Open Source (noreply@blogger.com) Published: 2026-06-10T18:30:00Z Content type: news Language: en Sources: [Google Open Source Blog]() Topics: [Google](), [Open Source](), [Artificial Intelligence](), [dev-tools](), [google-antigravity](), [Extension](), [Critical Infrastructure]() Tags: [ai](), [ai-integrated](), [antigravity](), [critical-infrastructure](), [developer-tools](), [eclipse-foundation](), [google](), [google-ospo](), [open-source](), [open-source-security]() ### AI overview Google joined the Eclipse Foundation as a Strategic Member in April 2026. It will sponsor Open VSX, participate in the foundation's governance, and support open infrastructure for AI-integrated developer platforms, along with open source security and regulatory compliance initiatives. ### Source excerpt by amanda casari & Mike Bufano, Google Open Source Collaboration with the Eclipse Foundation will support open infrastructure for AI-integrated developer platforms like Google Antigravity, while advancing broader open source security and regulatory compliance initiatives As of April 2026, Google has joined the Eclipse Foundation as a Strategic Member, reflecting the company's continued investment in open source technologies and modern developer infrastructure. As part of this collaboration, Google will additionally sponsor Open VSX and is among the first adopters of the recently announced Open VSX Managed Registry service. Open VSX is the open source, vendor-neutral extension registry for tools built on the VS Code™ extension API. It powers a rapidly growing ecosystem of AI-integrated IDEs, cloud development environments, and developer platforms, including Google Antigravity, AWS's Kiro, Cursor, and, Windsurf among many others. As a Strategic Member, Google will participate in the Eclipse Foundation's Board of Directors and Technical Advisory Council, helping guide the technical and strategic direction of one of the world's leading open source software foundations. "The industry is feeling the massive turning point as AI continues to change how developers write, deploy, and maintain software," said amanda casari of Google's Open Source Programs Office and new Eclipse Board member. "Joining The Eclipse Foundation as a Strategic Member ensures that the next generation of AI-integrated developer experiences--including platforms like Google Antigravity--are built in partnership with transparent, vendor-neutral foundations. Open registries, like Open VSX, are critical infrastructure which keep the global developer ecosystem open to everyone." Google and the Eclipse Foundation share a deep history, having collaborated across numerous initiatives since 2006. This Strategic Membership elevates the relationship and support critical to modern initiatives like Open VSX, Open Reg ## Google I/O 2026: The Sessions Worth Your Time DevFeed: [Google I/O 2026: The Sessions Worth Your Time]() Original publisher: [Read original article]() Author: blundell Published: 2026-06-02T17:22:00Z Content type: opinion Language: en Sources: [Blundell]() Topics: [Google](), [Artificial Intelligence](), [Android](), [Model Context Protocol](), [Jetpack](), [App]() Tags: [2026](), [agent](), [agentic](), [ai](), [android](), [androiddev](), [antigravity](), [generative-ui](), [google](), [google-i-o](), [google-io](), [intermediate](), [jetpack](), [mcp](), [reference](), [reference-androiddev-google-io]() ### AI overview An opinionated guide to the Google I/O 2026 sessions most relevant to developers. It highlights Gemini updates, agent transaction protocols, generative UI in Google Search, and Android App Functions, which are presented as being in preview and enabling assistants to call app capabilities. ### Source excerpt Like every year, I binge-watched I/O. And like every year I came out the other side with more links than time. A fire-hose of announcements, most of which you'll never touch, a handful of which will change how you work next week. Here I filter for you. Links to the sessions are inline so you [...] The post Google I/O 2026: The Sessions Worth Your Time first appeared on Blundell. ## Antigravity 2.0 vs Android Studio - making TagSpotter DevFeed: [Antigravity 2.0 vs Android Studio - making TagSpotter]() Original publisher: [Read original article]() Published: 2026-05-31T08:21:45Z Content type: opinion Language: en Sources: [maiatoday]() Topics: [Android Studio](), [ide](), [Command-line interface](), [Gradle](), [Emulator](), [Git](), [cpu]() Tags: [agent](), [ai](), [ai-agents](), [android](), [android-studio](), [antigravity](), [cli](), [code](), [command-line](), [cpu](), [debug](), [emulator](), [git](), [gradle](), [multi-agent]() ### AI overview An Android development article compares how Antigravity 2.0 and Android Studio fit into agent-assisted workflows. It describes Antigravity as suited to broad exploration, planning, parallel agent work, worktrees, and command-line builds or emulator runs, while Android Studio remains preferable for editing, debugging, previewing, and other IDE conveniences. The author also notes performance costs from multiple Android Studio instances and competing tools. ### Source excerpt How does Antigravity and Android Studio work together? What do I do where? There are as many workflows and preferences as there are Android engineers starting with light mode vs dark mode. This is not an attempt to provoke a holy war. What I have noticed is that in the days BA (Before Agents) I used to open Android Studio and do most things in there, edit, debug, preview, git and do CLI things. Now its not like that anymore. Click here if you want to skip the rant 😤 and just jump to Antigravity experiment Today in Android Studio I can run 1 agent or 2 if one is on a command line, max 3 if the third is just the Ask/chat tab. Or I can have a ton of terminals open with multiple agents juggling work trees. Or I can use one of the many multi agent solutions like Conductor, Superset or Antigravity 2.0 that are popping up like mushrooms. Then I could open multiple Android Studio versions in the worktrees I spun up with the agents. If I am in full agent mode and I just quickly want to edit something, I can do it in a small editor in the orchestrator tool but very soon I miss the creature comforts of Android Studio. But opening multiple instances of Android Studio is super slow (looking at you gradle sync and indexing). If my orchestrator environment is Antigravity 2.0 I can either jump back into Antigravity IDE or open the project in AndroidStudio. The problem Arrgh so many chat boxes everywhere with agents waiting to eat my tokens! So many tool combos all fighting for RAM and CPU cycles on my machine! I just want to add a setting to a file, I might as well edit it in vi. ok deep breath. I don't have a solution and I'm sure the internet has many suggestions so let me just figure out whre Antigravity 2.0 shines and what is better to do in Android Studio. Use Antigravity The mindset - broad, explore, plan, hands off, chatty, parallel work In Antigravity it is broader picture, start an app. Exploration and planning. Multiple agents doing things in worktrees. Agents are editing ## What's new from Firebase at Google I/O 2026 DevFeed: [What's new from Firebase at Google I/O 2026]() Original publisher: [Read original article]() Author: Seba Gnagnarella; Arthur Thompson; Kristen Richards Published: 2026-05-19T01:00:00Z Content type: news Language: en Sources: [Firebase Blog]() Topics: [Firebase](), [Agent Skills](), [Google](), [Mobile](), [Android Studio](), [Flutter](), [Model Context Protocol]() Tags: [2026](), [a-b-testing](), [agent-skills](), [ai-logic](), [ai-studio](), [android](), [android-studio](), [antigravity](), [app-check](), [application-design-center](), [authentication](), [cloud-logging](), [cloud-run](), [crashlytics](), [firebase](), [firestore](), [flutter](), [google](), [google-i-o](), [hybrid-inference](), [ios](), [mcp](), [mobile](), [news](), [remote-config](), [security]() ### AI overview Firebase announces updates from Google I/O 2026, including integrations with Google Antigravity and Android Studio, expanded Agent Skills for mobile development, and support for Firestore, Firebase Authentication, Crashlytics, and Remote Config. ### Source excerpt News, tutorials, and updates from the Firebase team. ## Building My Dream Developer Blog with Astro, Cloudflare, and AI DevFeed: [Building My Dream Developer Blog with Astro, Cloudflare, and AI]() Original publisher: [Read original article]() Author: Shreyas Patil Published: 2026-04-20T00:00:00Z Content type: article Language: en Sources: [Shreyas Patil's Blog]() Topics: [Astro](), [Cloudflare](), [AI Agent](), [Google]() Tags: [ai-agent](), [antigravity](), [astro](), [blogging](), [cloudflare](), [developer](), [engineering](), [gemini](), [git](), [google](), [markdown]() ### AI overview The author describes migrating more than 60 technical blogs from Hashnode to a custom Astro site hosted on Cloudflare Pages. The site uses Markdown files in Git, and the author used Google Antigravity as a pair-programming AI agent while building it. ### Source excerpt How I migrated my 60+ engineering blogs from Hashnode to a custom Astro setup on Cloudflare with the help of Google Antigravity AI. ## From prompt to production: Build full-stack apps faster with Google AI Studio and Firebase DevFeed: [From prompt to production: Build full-stack apps faster with Google AI Studio and Firebase]() Original publisher: [Read original article]() Author: Kara Yu; Sam Phillips Published: 2026-03-19T00:00:00Z Content type: release Language: en Sources: [Firebase Blog]() Topics: [Firebase](), [Google AI](), [Firestore](), [Google](), [Authentication](), [backends](), [Agent Harness]() Tags: [agent](), [agent-harness](), [ai](), [ai-studio](), [antigravity](), [authentication](), [backends](), [build](), [firebase](), [firebase-studio](), [firestore](), [google](), [security]() ### AI overview Firebase announces an integration with Google AI Studio that can provision Firebase projects, Firestore, Authentication, sign-in pages, application code, and draft Security Rules with user approval. The announcement also describes a new Google AI Studio coding agent for multi-step code edits and connections to services such as payment processors and Google Maps. ### Source excerpt Today, we're announcing that Firebase is now integrated with Google AI Studio, accelerating your path from prompt to production so you can turn your vibe-coded ideas into fully functional apps with robust backends. Read on to learn how this works and what this means for Firebase Studio. ## Gemini 3 Flash: frontier intelligence built for speed DevFeed: [Gemini 3 Flash: frontier intelligence built for speed]() Original publisher: [Read original article]() Author: Tulsee Doshi Published: 2025-12-17T11:58:17Z Content type: release Language: en Sources: [Google DeepMind News]() Topics: [Google AI](), [Artificial Intelligence](), [agentic workflows](), [multimodal](), [API](), [Code](), [Google](), [google-antigravity]() Tags: [agentic](), [agentic-workflows](), [ai](), [ai-studio](), [antigravity](), [api](), [benchmarks](), [cost](), [development](), [efficiency](), [gemini](), [google-ai](), [google-antigravity](), [latency](), [none](), [performance](), [platform](), [reasoning](), [release](), [speed](), [tokens]() ### AI overview Google announces Gemini 3 Flash, a faster and more efficient model in the Gemini 3 family. The release targets developers, consumers, and enterprises across Google's platforms, with support for reasoning, multimodal understanding, and agentic workflows. ### Source excerpt Gemini 3 Flash offers frontier intelligence built for speed at a fraction of the cost. ## Antigravity and Firebase MCP accelerate app development DevFeed: [Antigravity and Firebase MCP accelerate app development]() Original publisher: [Read original article]() Author: Alexander Nohe Published: 2025-11-21T00:00:00Z Content type: tutorial Language: en Sources: [Firebase Blog]() Topics: [Firebase](), [MCP Server](), [Development](), [ide](), [Angular](), [Firestore](), [hosting](), [API]() Tags: [ai](), [angular](), [antigravity](), [api-keys](), [app-development](), [development](), [firebase](), [firebase-cli](), [firestore](), [hosting](), [how-to](), [mcp](), [mcp-server](), [next-js]() ### AI overview This tutorial explains how to add the Firebase MCP server to Google's Antigravity IDE, initialize Firebase in an existing project, build an application with Firebase services, and deploy it with Firebase Hosting. It describes an example racing game using email-and-password sign-in and Cloud Firestore for a leaderboard, and notes support for App Hosting for server-rendered Next.js and Angular apps. ### Source excerpt Learn how to enable the Firebase MCP server in Antigravity to accelerate app development ## Start building with Gemini 3 DevFeed: [Start building with Gemini 3]() Original publisher: [Read original article]() Author: Logan Kilpatrick Published: 2025-11-18T17:49:13Z Content type: release Language: en Sources: [Google DeepMind News]() Topics: [Google AI](), [agentic-coding](), [Development](), [Command-line interface](), [ide](), [Benchmark]() Tags: [agentic-coding](), [agentic-development](), [antigravity](), [benchmark](), [cli](), [gemini](), [google](), [google-antigravity](), [jetbrains](), [linux](), [macos](), [none](), [preview](), [windows]() ### AI overview Google introduces Gemini 3, highlighting Gemini 3 Pro's reasoning, coding, agentic workflow, and benchmark performance. The model is available in preview through the Gemini API, Google AI Studio, and Vertex AI, with integration across developer tools. ### Source excerpt Gemini 3 is introducing advanced agentic coding capabilities, plus Google Antigravity, a new agentic development platform. ## Introducing Google Antigravity DevFeed: [Introducing Google Antigravity]() Original publisher: [Read original article]() Author: The Antigravity Team Published: 2025-11-18T16:06:32Z Content type: release Language: en Sources: [Google DeepMind News]() Topics: [agentic-coding](), [Google](), [AI Development](), [ide](), [software-development](), [browser](), [cursor]() Tags: [agent](), [agentic](), [agentic-coding](), [ai](), [antigravity](), [browser](), [gemini](), [google](), [ide]() ### AI overview Google introduces Antigravity, an agentic development platform built around Gemini 3. It combines an AI-powered IDE with browser control and asynchronous interaction so agents can plan and execute complex, end-to-end software tasks. The platform is available in public preview at no charge and emphasizes trust, autonomy, feedback, and self-improvement through task-level context, artifacts, and verification results. ### Source excerpt Introducing Google Antigravity, a New Era in AI-Assisted Software Development