Google Developers Blog

Google I/O 2026 is returning May 19-20 at Shoreline Amphitheatre in Mountain View, CA. But before the keynotes begin, you can get into the spirit of the event with our annual tradition: the save the date puzzle. This year's experience highlights how AI can empower and accelerate

Google has released version 1.0.0 of the Agent Development Kit (ADK) for Java, introducing powerful new features like Google Maps grounding, built-in URL fetching, and a standardized Agent2Agent protocol for cross-framework collaboration. The update enhances agent control through a new "App" and "Plugin" architecture, which allows for global logging, automated context window management via event compaction, and "Human-in-the-Loop" workflows for action confirmations. Additionally, the release provides robust session and memory services using Google Cloud integrations like Firestore and Vertex AI to manage long-term state and large data artifacts.

The newly released Gemma 4 12B is a dense, multimodal model designed for high-performance local AI execution on consumer devices. By introducing a novel, encoder-free architecture, it bypasses traditional visual and audio encoders to feed multimodal data directly into the LLM backbone.

Google has announced the general availability of Gemini Embedding 2, a unified model that maps text, images, video, audio, and documents into a single semantic space. This model allows developers to process interleaved multimodal inputs in a single request, significantly improving performance for tasks like agentic RAG, visual search, and content moderation. By supporting over 100 languages and offering features like task-specific prefixes and Matryoshka dimensionality reduction, the model provides a highly efficient and accurate foundation for building complex AI agents.

How a Python agent and a Go agent collaborate on contract compliance using the Agent2Agent protocolY...

Gemini CLI has introduced subagents, specialized expert agents that handle complex or high-volume tasks in isolated context windows to keep the primary session fast and focused. These agents can be customized via Markdown files, run in parallel to boost productivity, and are easily invoked using the @agent syntax for targeted delegation. This architecture prevents "context rot" by consolidating intricate multi-step executions into concise summaries for the main orchestrator.

Celebrating the first anniversary of the Agent-to-Agent (A2A) protocol, this blog post highlights how the framework enables autonomous AI agents to securely collaborate and hand off tasks without the rigidity of traditional APIs. By delegating complex workflows to specialized peer agents, A2A prevents context pollution, ensures data privacy, and simplifies application design through modularity. To demonstrate this ecosystem in action, the post spotlights FoldRun—an agentic interface for life sciences that orchestrates complex protein structure predictions—alongside diverse A2A use cases spanning commerce, data streaming, DevOps, and telecommunications.

This blog post introduces a workflow for extracting high-quality data from complex, unstructured documents by combining LlamaParse with Gemini 3.1 models. It demonstrates an event-driven architecture that uses Gemini 3.1 Pro for agentic parsing of dense financial tables and Gemini 3.1 Flash for cost-effective summarization. By following the provided tutorial, developers can build a personal finance assistant capable of transforming messy brokerage statements into structured, human-readable insights.

AI coding agents are rapidly shifting from reactive assistants that complete tasks when prompted to ...

MaxText has introduced new support for Supervised Fine-Tuning (SFT) and Reinforcement Learning (RL) on single-host TPU configurations, leveraging JAX and the Tunix library for high-performance model refinement. These features enable developers to easily adapt pre-trained models for specialized tasks and complex reasoning using efficient algorithms like GRPO and GSPO. This update streamlines the post-training workflow, offering a scalable path from single-host setups to larger multi-host configurations.

The newly introduced continuous checkpointing feature in Orbax and MaxText is designed to optimize the balance between reliability and performance during model training, addressing issues with conventional fixed-frequency checkpointing. Unlike fixed intervals—which can either compromise reliability or bottleneck performance—continuous checkpointing maximizes I/O bandwidth and minimizes failure risk by asynchronously initiating a new save operation only after the previous one successfully completes. Benchmarks demonstrate that this approach significantly reduces checkpoint intervals and results in substantial resource conservation, especially in large-scale training jobs where mean-time-between-failure (MTBF) is short.

The Google Tunix Hackathon on Kaggle challenged developers to transform small, non-reasoning base models into general reasoning engines using Kaggle TPUs and a limited compute budget. The winning teams achieved this by implementing multi-stage post-training pipelines that combined Supervised Fine-Tuning (SFT) with advanced alignment techniques like GRPO and SimPO. Ultimately, the competition democratized AI development by proving that highly capable, structured reasoning models can be successfully trained by the community using accessible, open-source resources.

Google is enhancing Sign in with Google by introducing new OIDC standard claims—specifically auth_time and amr (Authentication Methods Reference) to provide developers with deeper session metadata. These updates allow verified apps to verify the "freshness" of a user's login and the specific authentication methods used (such as MFA or hardware keys), enabling more dynamic, risk-based access controls. By leveraging these federated identity signals, platforms can better prevent account takeover and fraud while implementing granular security policies like step-up authentication for sensitive actions.

Google announced the transition from assistive AI to independent agents, highlighting the launch of the Gemini 3.5 series and major updates to its Antigravity agent-first development platform. For mobile developers, the post introduces new Android CLI tools, the Android Bench evaluation leaderboard, and an automated Migration agent designed to rapidly convert various frameworks into native Kotlin code. Web development is also being transformed through Chrome DevTools for agents, the HTML-in-Canvas API, and the proposal of WebMCP, an open web standard that enables browser-based AI agents to execute complex tasks.

When you’re prototyping locally with AI agents like Gemini CLI, Claude Code, or your own agent, thei...

Conductor for the Gemini CLI has introduced a new Automated Review feature designed to verify the quality and accuracy of AI-generated code. This update addresses the challenge of validating agentic development by automatically checking implementations against original plans, enforcing style guides, and identifying security risks or bugs. by incorporating test-suite validation and providing actionable reports, Conductor helps developers ensure that their AI agents deliver safe, predictable, and architecturally sound code before it is finalized.

Google Cloud has introduced a high-performance integration that connects Rapid Storage directly to PyTorch via the fsspec interface to eliminate AI training bottlenecks. By utilizing Google’s Colossus architecture and bidirectional gRPC streaming, the solution offers up to 15 TiB/s aggregate throughput and significant reductions in latency. These improvements allow developers to speed up total training time by 23% with zero code changes required beyond updating the storage bucket type.

TorchTPU is a new engineering stack designed to provide a native, high-performance experience for running PyTorch workloads on Google’s TPU infrastructure with minimal code changes. It features an "Eager First" approach with multiple execution modes and utilizes the XLA compiler to optimize distributed training across massive clusters. Moving into 2026, the project aims to further reduce compilation overhead and expand support for dynamic shapes and custom kernels to ensure seamless scalability for the next generation of AI.

We are excited to bring Express checkout with Google Pay for Android native apps enabling developers...

An open specification for finding and verifying tools, skills, and agents across the web.Agents are ...

Google has announced the new Google Pay & Wallet Developer MCP server, an open-standard tool designed to securely connect AI development assistants and IDEs with real-time API and account context. The server allows developers to remain within their development environment to search official documentation, validate Wallet pass definitions, check integration status, and manage merchant accounts. Ultimately, this integration aims to reduce friction and accelerate development workflows by minimizing context switching and providing up-to-date, grounded AI support.

This blog post introduces a suite of six protocols, such as MCP and A2A, designed to eliminate custom integration code by standardizing how AI agents access data and communicate. Using a "kitchen manager" agent as a practical example, it demonstrates how these tools handle complex tasks like real-time inventory checks, wholesale commerce via UCP, and secure payment authorization through AP2. By leveraging the Agent Development Kit (ADK), developers can also implement A2UI and AG-UI to deliver interactive dashboards and seamless streaming interfaces to users.

To bridge the gap between static model knowledge and rapidly evolving software practices, Google DeepMind developed a "Gemini API developer skill" that provides agents with live documentation and SDK guidance. Evaluation results show a massive performance boost, with the gemini-3.1-pro-preview model jumping from a 28.2% to a 96.6% success rate when equipped with the skill. This lightweight approach demonstrates how giving models strong reasoning capabilities and access to a "source of truth" can effectively eliminate outdated coding patterns.

Google has officially launched LiteRT, the successor to TFLite, which offers significantly faster GPU and NPU acceleration alongside seamless support for PyTorch and JAX. The update also introduces lower-precision data type support for increased efficiency and a commitment to more frequent security and dependency updates across the TensorFlow ecosystem. This transition solidifies LiteRT as Google's primary high-performance framework for deploying GenAI and advanced on-device inference.

The Google Cloud and NVIDIA developer community is celebrating its first anniversary with 100,000 members and a renewed focus on providing builders with advanced AI infrastructure and resources. To accelerate development, the community offers curated learning pathways for mastering LLM optimization, GPU-accelerated data analytics, and monthly expert-led webinars. Moving into its second year, the initiative will expand to include hands-on labs, engineering events, and specialized content focused on the growth of agentic AI.

To simplify the user experience and prevent startup failures, the Gemini CLI has introduced structured extension settings that eliminate the need for manual environment variable configuration. This update enables extensions to automatically prompt users for required details during installation and securely stores sensitive information, such as API keys, directly in the system keychain. Users can now easily manage and override these configurations globally or per project using the new Gemini extensions config command.

The Gemini Code Assist team has introduced a suite of updates focused on streamlining the core coding workflow through high-velocity tools like Agent Mode with Auto Approve and Inline Diff Views. These enhancements, along with new features for precise context management and custom commands, aim to transform the AI from a general assistant into a highly tailored, seamless collaborator that adapts to your specific development style.

Google DeepMind has launched Gemma 4, a family of state-of-the-art open models designed to enable multi-step planning and autonomous agentic workflows directly on-device. The release includes the Google AI Edge Gallery for experimenting with "Agent Skills" and the LiteRT-LM library, which offers a significant speed boost and structured output for developers. Available under an Apache 2.0 license, Gemma 4 supports over 140 languages and is compatible with a wide range of hardware, including mobile devices, desktops, and IoT platforms like Raspberry Pi.

The launch of Agent Development Kit (ADK) for Go 1.0 marks a significant shift from experimental AI scripts to production-ready services by prioritizing observability, security, and extensibility. Key updates include native OpenTelemetry integration for deep tracing, a new plugin system for self-healing logic, and "Human-in-the-Loop" confirmations to ensure safety during sensitive operations. Additionally, the release introduces YAML-based configurations for rapid iteration and refined Agent2Agent (A2A) protocols to support seamless communication across different programming languages. This framework empowers developers to build complex, reliable multi-agent systems using the high-performance engineering standards of Golang.

Researchers at UCSD have successfully implemented DFlash, a block-diffusion speculative decoding method, on Google TPUs to bypass the sequential bottlenecks of traditional autoregressive drafting. By "painting" entire blocks of candidate tokens in a single forward pass rather than predicting them one-by-one, the system achieved average speedups of 3.13x, with peak performance nearly doubling that of existing methods like EAGLE-3. This open-source integration into the vLLM ecosystem optimizes TPU hardware by leveraging "free" parallel verification and high-quality draft predictions for complex reasoning tasks.

Google has officially launched the TPU Developer Hub, a centralized educational resource designed to help model builders and developers maximize the performance of Google Cloud TPUs. The hub offers code-first resources, open-source recipes, and deep-dive documentation covering hardware architecture, software optimization, debugging, parallelism, and networking. These materials are tailored for both human developers and AI-assisted tools to streamline everything from large-scale training to low-latency inference workloads.

This post introduces three architectural patterns designed to integrate Model Context Protocol (MCP) Apps and Agent-to-User Interface (A2UI) to solve the tradeoff between highly custom iframe environments and native, declarative rendering. By combining these approaches, developers can serve native-feeling UIs directly over MCP servers, embed complex and stateful iframe apps securely inside declarative views, or inject generative UI components into legacy systems. Ultimately, these hybrid frameworks empower engineering teams to deliver secure, performant, and brand-consistent agentic user experiences tailored to their specific project constraints.

The Google Cloud AI Agent Bake-Off highlights a shift from simple prompt engineering to rigorous agentic engineering, emphasizing that production-ready AI requires a modular, multi-agent architecture. The post outlines five key developer tips, including decomposing complex tasks into specialized sub-agents and using deterministic code for execution to prevent probabilistic errors. Furthermore, it advises developers to prioritize multimodality and open-source protocols like MCP to ensure agents are scalable, integrated, and future-proof against rapidly evolving model capabilities.

Google Pay is evolving for "agentic commerce" by introducing the Universal Commerce Protocol and a new MCP server that allows AI agents to manage integrations and analyze trends. New Android updates introduce dynamic callbacks for seamless express checkouts and extend payment support into social media apps via WebViews. Additionally, the platform is launching cross-device biometric authentication and new transaction signals to help merchants reduce friction and optimize processing costs.

Google has announced the Google Colab Command-Line Interface (CLI), a new tool that allows developers and AI agents to connect local terminals to remote Colab runtimes for frictionless execution. The lightweight CLI enables users to easily request high-powered GPUs, run local Python scripts remotely, and seamlessly retrieve artifact logs or models like fine-tuned Gemma 3 adapters. By integrating directly into standard terminal environments, the tool is highly programmable and ready to be used by AI agents such as Antigravity or Claude Code to manage complex machine learning pipelines.

Integration of Arm Scalable Matrix Extension 2 (SME2) and the Google AI Edge software stack enables high-performance, on-device generative AI by turning the CPU into a powerful matrix-compute accelerator. Using Stability AI’s "stable-audio-open-small" model as a case study, it outlines a streamlined "Convert, Optimize, and Deploy" pipeline that utilizes LiteRT, XNNPACK, and KleidiAI to automate hardware acceleration. The resulting implementation achieves over a 2x speedup in audio generation and a 4x reduction in memory usage while maintaining high audio quality on Arm-powered mobile devices and laptops.

Google I/O returns May 19–20 to showcase major updates in AI, Android, Chrome, and Cloud, beginning with a keynote on the "agentic era" of development. The event will focus on new tools designed to automate complex workflows and simplify the creation of high-quality, AI-ready applications. Attendees can register to access live sessions, technical demos, and professional development resources both live and on-demand.

Genkit is an open-source framework designed to help developers build production-ready, agentic AI applications using TypeScript, Go, Dart, and Python. The framework utilizes a powerful middleware system that intercepts generation calls to inject custom behaviors like retries, model fallbacks, and human-in-the-loop tool approvals. By attaching hooks at the generate, model, and tool layers, developers can ensure high reliability and deterministic control over model outputs. Furthermore, Genkit allows for the creation and stacking of custom middleware, all of which can be inspected and debugged through a dedicated Developer UI.

The blog post outlines the transition of a brittle sales research prototype into a robust production agent using Google’s Agent Development Kit (ADK). By replacing monolithic scripts with orchestrated sub-agents and structured Pydantic outputs, the developers eliminated silent failures and fragile parsing. Additionally, the post highlights the necessity of dynamic RAG pipelines and OpenTelemetry observability to ensure AI agents are scalable, cost-effective, and transparent in real-world applications.

A2UI v0.9 introduces a framework-agnostic standard designed to help AI agents generate real-time, tailored UI widgets using a company’s existing design system. This update simplifies the developer experience with a new Agent SDK for Python, a shared web-core library, and official support for renderers like React, Flutter, and Angular. By decoupling UI intent from specific platforms, the release enables seamless, low-latency streaming of generative interfaces across web and mobile applications. Integrating with broader ecosystems like AG2 and Vercel, A2UI v0.9 aims to move generative UI from experimental demos to production-ready digital products.

The Google AI Edge Gallery app has expanded its on-device AI capabilities by introducing experimental support for the open-source Model Context Protocol (MCP) on Android, allowing Gemma 4 to coordinate complex tasks across external data sources like Google Workspace and Google Maps. To enable more proactive and persistent user interactions, the update adds a "Schedule Notification" skill for automating routines and a persistent chat history feature that restores long session contexts nearly instantly. Driven by an open-source toolkit, the platform encourages community developers to build and share custom utility-focused workflows, prompt configurations, and tool integrations via its GitHub repository.

Google DeepMind’s Gemma 4 12B model brings agentic, multimodal AI capabilities to everyday laptops with 16GB of RAM, enabling local data processing and visual insight generation. Users can leverage this model on macOS through the Google AI Edge Gallery for dynamic Python code execution and visualization, as well as via Google AI Edge Eloquent for completely offline voice dictation and text editing. Additionally, developer workflows are enhanced by the LiteRT-LM CLI's new serve command, which creates an industry-compatible local endpoint to power fully-local AI tools and agents.

Google has updated its account settings to allow U.S. users to change their @gmail.com usernames while keeping all existing account data and inboxes intact. For developers, this means that while old email addresses will remain active as aliases, apps that rely solely on email addresses for identification may face issues with account duplication or lost access. To ensure a seamless user experience, Google recommends migrating to the "subject ID" as the primary user identifier and allowing users to manually update their contact information within app settings.

Google Cloud has introduced the Agents CLI, a specialized tool designed to bridge the gap between local development and production-grade AI agent deployment. The CLI provides coding assistants with machine-readable access to the full Google Cloud stack, reducing context overload and token waste during the scaffolding process. By streamlining evaluation, infrastructure provisioning, and deployment into a single programmatic backbone, the tool enables developers to move from initial concept to a live service in hours rather than weeks.

LiteRT is a production-ready framework designed to help mobile developers unlock the power of Neural Processing Units (NPUs), overcoming the performance and battery limitations of traditional CPU or GPU processing. By providing a unified API that abstracts away hardware complexities, it allows industry leaders like Google Meet and Epic Games to deploy sophisticated AI models for real-time video, animation, and speech recognition with significantly higher efficiency. The platform further supports developers through benchmarking tools and cross-platform compatibility, enabling seamless AI deployment across mobile devices, AI PCs, and industrial IoT hardware.

DiffusionGemma is an experimental text-generation model built on the Gemma 4 architecture that uses diffusion-based parallel generation instead of token-by-token autoregression, enabling much faster inference, bidirectional context awareness, and real-time self-correction while remaining deployable on consumer GPUs. Its architecture generates and refines 256-token blocks in parallel through iterative denoising, allowing it to handle complex constraint-based tasks such as Sudoku more effectively than traditional language models and demonstrating strong gains from fine-tuning. The model integrates with vLLM and other popular inference frameworks, giving developers access to a new non-autoregressive approach that combines high performance, efficient long-context scaling, and straightforward customization and deployment.

How to transition from stateless chatbots to production-grade agents capable of managing long-running enterprise workflows, such as HR onboarding, that span days or weeks. It introduces the Agent Development Kit (ADK) and its architectural shifts, specifically using durable state machines and persistent session storage to ensure an agent never loses context during "idle time" or server restarts. By leveraging event-driven webhooks and multi-agent delegation, the tutorial demonstrates how to build resilient systems that "sleep" during pauses and wake up to resume complex tasks with high reasoning accuracy.

The Agent Development Kit (ADK) SkillToolset introduces a "progressive disclosure" architecture that allows AI agents to load domain expertise on demand, reducing token usage by up to 90% compared to traditional monolithic prompts. Through four distinct patterns—ranging from simple inline checklists to "skill factories" where agents write their own code—the system enables agents to dynamically expand their capabilities at runtime using the universal agentskills.io specification. This modular approach ensures that complex instructions and external resources are only accessed when relevant, creating a scalable and self-extending framework for modern AI development.

Google I/O returns May 19-20. Watch the livestreams for updates on Android, AI, Chrome, and Cloud. Registration is open on the Google I/O website.

Google has introduced FunctionGemma, a specialized 270M parameter model designed to bring efficient, action-oriented AI experiences directly to mobile devices through on-device function calling. By leveraging Google AI Edge and LiteRT-LM, the model enables complex tasks—such as managing calendars, controlling device hardware, or executing specific game logic in the "Tiny Garden" demo—to be performed entirely offline with high speed and low latency. Available for testing in the Google AI Edge Gallery app on both Android and iOS, FunctionGemma allows developers to move beyond simple text generation toward building responsive, "agentic" applications that interact seamlessly with the physical and digital world without relying on cloud processing.

Google AI Edge’s LiteRT-LM provides a production-proven, highly optimized infrastructure for running Gemma 4 across cross-platform mobile and edge environments. It actively unlocks the model's native multimodal and agentic features on-device by utilizing memory-efficient dynamic loading, Multi-Token Prediction for up to a 2.2x speedup, and advanced orchestration tools like Thinking Mode and Constrained Decoding. Furthermore, the engine is rapidly expanding its integration surfaces beyond Android, introducing new native Swift APIs for Apple ecosystems and WebGPU-accelerated JavaScript APIs for high-performance, serverless browser inference.

Agent Development Kit (ADK) now supports a robust ecosystem of third-party tools and integrations. Connect your agents to GitHub, Notion, Hugging Face, and more to build capable, real-world applications.

The Google Tensor ML SDK is graduating to its Beta phase, allowing developers to build and deploy high-performance machine learning models directly onto the TPU of Google Pixel 10 devices. By integrating with LiteRT, Google's edge deployment framework, the SDK provides a unified workflow for developers to convert, compile, and run PyTorch or TFLite models with robust fallback options. Additionally, a new model garden offers over 100 classic and generative AI models, including Gemma 3, enabling low-latency, private features like speech recognition, computer vision, and text generation.

Google is unifying its AI terminal tools by transitioning the community-focused Gemini CLI into Antigravity CLI, a new agent-first platform built for complex, multi-agent workflows. This new Go-based tool offers faster execution, asynchronous processing, and a unified architecture that syncs with the Antigravity 2.0 desktop application. While enterprise customers will maintain existing access, individual and free users must transition to the new platform before Gemini CLI stops serving requests on June 18, 2026.

Gemini CLI now features Plan Mode, a read-only environment that allows the AI to analyze complex codebases and map out architectural changes without the risk of accidental execution. By leveraging the new ask_user tool and expanded Model Context Protocol (MCP) support, developers can collaboratively refine strategies and pull in external data before committing to implementation.

While keynotes are available online, Google Cloud Next '26 in Las Vegas offers an irreplaceable in-person experience centered on networking, hands-on problem solving, and the transition to agentic AI. The event features specialized technical tracks covering everything from Gemini multimodal breakthroughs to zero-trust security on Cloud Run, providing developers with the tools to balance individual speed with organizational stability. Beyond formal sessions, the "in-person advantage" lies in over 20 developer meetups and collaborative whiteboard sessions designed to foster serendipitous breakthroughs. Ultimately, the conference serves as a high-energy hub for engineers to move beyond the hype and master the modern building blocks of software architecture together.

ADK for Kotlin brings agentic workflows to your backend projects, while ADK for Android provides spe...

The Android XR team is using Gemini's Canvas feature to make creating immersive extended reality (XR) experiences more accessible. This allows developers to rapidly prototype interactive 3D environments and models on a Samsung Galaxy XR headset using simple creative prompts.

Google has introduced Finish Changes and Outlines for Gemini Code Assist in IntelliJ and VS Code to reduce developer friction and eliminate the need for long, manual prompting. Finish Changes acts as an AI pair programmer that completes code, implements pseudocode, and applies refactoring patterns by observing your current edits and context. Meanwhile, Outlines improves code comprehension by generating interactive, high-level English summaries interleaved directly within the source code to help engineers navigate and understand complex files.

Wednesday Build Hour is a weekly, interactive "technical gym session" led by Google Cloud experts to help developers and architects sharpen their cloud skills. Moving beyond passive slide decks, the program focuses on hands-on building, covering advanced topics like AI agents, Vertex AI, and developer productivity tools. Each hour-long session is designed to provide tangible results that participants can immediately deploy into their own workflows. It serves as a consistent, dedicated space for builders to stay ahead of the curve and connect with a community of cloud engineers.

Google is expanding its smart home ecosystem by launching a full-stack Gemini AI offering that integrates advanced camera intelligence, natural language queries, and daily activity summaries. This initiative provides service providers and hardware manufacturers with turnkey reference designs and APIs to build proactive, branded services without extensive research and development. Ultimately, the program aims to move beyond basic device control toward an AI-native home that can understand context and care for users' needs in real time.

Google has introduced enhancements to the Google Pay API to provide developers with greater flexibility and control over merchant-initiated transactions (MIT). The update includes new objects within the PaymentDataRequest to specifically handle recurring subscriptions, deferred payments like hotel bookings, and automatic account reloads. By allowing merchants to clearly define future payment terms, these changes improve transparency for users and help reduce transaction declines through better token management. Developers can now implement these features to create more seamless and secure long-term payment experiences.

The provided workflow streamlines motion-controlled game development by using Gemini Canvas to rapidly prototype mechanics like the MediaPipe Pose Landmarker through high-level prompting. Developers can refine these prototypes in Google AI Studio by optimizing for low-latency "lite" models and stable tracking points, such as shoulder landmarks, to ensure responsive gameplay. The process concludes by using Gemini Code Assist to refactor experimental code into a modular, production-ready application capable of supporting various multimodal inputs.