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.

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.

FunctionGemma is a specialized AI model for function calling. This post explains why fine-tuning is key to resolving tool selection ambiguity (e.g., internal vs. Google search) and achieving ultra-specialization, transforming it into a strict, enterprise-compliant agent. A case study demonstrates the improved logic. It also introduces the "FunctionGemma Tuning Lab," a no-code demo on Hugging Face Spaces, which streamlines the entire fine-tuning process for developers.

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.

At Thunderhill Raceway Park, a team of Google Developer Experts (GDEs) put a new "Trustable AI Framework" to the test. Here is how they used GCP, Gemini and Antigravity to turn high-velocity racing into a masterclass for agentic architecture.

A practical guide to debugging and profiling JAX on Cloud TPUs. It outlines core components (libtpu, JAX/jaxlib) and essential techniques. Tools covered include: Verbose Logging (via libtpu env vars), TPU Monitoring Library for performance metrics, tpu-info for real-time utilization, XLA HLO Dumps for compiler debugging, and the XProf suite for in-depth performance analysis.

Gemini 3 is powering the next generation of reliable, production-ready AI agents. This post highlights 6 open-source framework collaborations (ADK, Agno, Browser Use, Eigent, Letta, mem0), demonstrating practical agentic workflows for tasks like deep search, multi-agent systems, browser and enterprise automation, and stateful agents with advanced memory. Clone the examples and start building today.

The Universal Commerce Protocol (UCP) is a new, open-source standard for agentic commerce, co-developed by Google and industry leaders. It establishes a common, secure language to connect consumer surfaces (like Gemini and AI Mode in Search) with business backends, enabling seamless shopping from product discovery to purchase. UCP simplifies integration for businesses, supports various payment providers, and is designed to power the next generation of conversational commerce experiences.

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.

LiteRT, the evolution of TFLite, is now the universal framework for on-device AI. It delivers up to 1.4x faster GPU, new NPU support, and streamlined GenAI deployment for models like Gemma.

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.

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

New Gemini CLI hooks (v0.26.0+) let you tailor the agentic loop. Add context, enforce policies, and block secrets with custom scripts that run at predefined points in your workflow.

Conductor is a new Gemini CLI extension that promotes context-driven development. It shifts project context from chat logs to persistent Markdown files for formal specs and plans, ensuring AI agents adhere to project goals, style, and tech stack. This structured workflow is great for "brownfield" projects and teams, allowing for safe iteration and consistent code contributions while keeping the human developer in control.

Data Commons has launched a free, hosted Model Context Protocol (MCP) service on Google Cloud Platform, eliminating the need for users to manage complex local server installations. This update simplifies connecting AI agents and the Gemini CLI to Data Commons, allowing Google to handle security, updates, and resource management while users query data natively.

Google is launching the Developer Knowledge API and MCP Server in public preview. This new toolset provides a canonical, machine-readable way for AI assistants and agentic platforms to search and retrieve up-to-date documentation across Firebase, Google Cloud, Android, and more. By using the official MCP server, developers can connect tools directly to Google’s documentation corpus, ensuring that AI-generated code and guidance are based on authoritative, real-time context.

Finetuning the FunctionGemma model is made fast and easy using the lightweight JAX-based Tunix library on Google TPUs, a process demonstrated here using LoRA for supervised finetuning. This approach delivers significant accuracy improvements with high TPU efficiency, culminating in a model ready for deployment.

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 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.

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.