Google code homepage
Google Pay inside sandboxed iframe for PCI DSS v4 compliance
Use a sandboxed iframe to implement Google Pay on checkout pages, which helps comply with PCI DSS v4 requirements by isolating scripts. Shopify successfully implemented this method and passed the PCI DSS v4 audit.
LiteRT: Maximum performance, simplified
LiteRT has been improved to boost AI model performance and efficiency on mobile devices by effectively utilizing GPUs and NPUs, now requiring significantly less code, enabling simplified hardware accelerator selection, and more for optimal on-device performance.
Google Cloud announces general availability of APIM Operator for Apigee
The Apigee APIM Operator is now generally available, bringing API Management and Gateway capabilities to GKE environments using Kubernetes-like YAML configuration, providing developer-native tooling, reducing friction, and offering policy management comparable to Apigee Hybrid.
Build and train a recommender system in 10 minutes using Keras and JAX
Keras Recommenders (KerasRS) is a new library announced to help developers build recommendation systems using APIs with building blocks for ranking and retrieval, and it can be installed via pip with support for JAX, TensorFlow, or PyTorch backends.
On-device small language models with multimodality, RAG, and Function Calling
Google AI Edge advancements, include new Gemma 3 models, broader model support, and features like on-device RAG and Function Calling to enhance on-device generative AI capabilities.
What's new with Agents: ADK, Agent Engine, and A2A Enhancements
Updates to Google's agent technologies include the Agent Development Kit (ADK) with new Python and Java versions, an improved Agent Engine UI for management, and enhancements to the Agent2Agent (A2A) protocol for better agent communication and security.
Building agents with Google Gemini and open source frameworks
Google Gemini models offer several advantages when building AI agents, such as advanced reasoning, function calling, multimodality, and large context window capabilities. Open-source frameworks like LangGraph, CrewAI, LlamaIndex, and Composio can be used with Gemini for agent development.
What you should know from the Google I/O 2025 Developer keynote
Top announcements from Google I/O 2025 focus on building across Google platforms and innovating with AI models from Google DeepMind, with key focus on new tools, APIs, and features designed to enhance developer productivity and create AI-powered experiences using Gemini, Android, Firebase, and web.
Fully Reimagined: AI-First Google Colab
Google Colab is launching a reimagined AI-first version at Google I/O, featuring an agentic collaborator powered by Gemini 2.5 Flash with iterative querying capabilities, an upgraded Data Science Agent, effortless code transformation, and flexible interaction methods, aiming to significantly improve coding workflows.
From idea to app: Introducing Stitch, a new way to design UIs
Stitch, a new Google Labs experiment, uses AI to generate UI designs and frontend code from text prompts and images, aiming to streamline the design and development workflow, offering features like UI generation from natural language or images, rapid iteration, and seamless paste to Figma and front-end code.