Feed Items
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.
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.
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 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.
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.
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.
Revisit announcements from this year's Games Developer Conference (GDC). Explore how Gemma and Gemini models can aid in building AI experiences in games with the launch of Gemma 3, the Unity plugin, its application in a sample game, and scaling games with generative AI in Google Cloud.
Gemini 2.5 marks a major leap in video understanding, achieving state-of-the-art performance on key video understanding benchmarks and being able to seamlessly use audio-visual information with code and other data formats.
The rollout of implicit caching in the Gemini API expands on the existing explicit caching API, providing an "always on" caching system which offers automatic cost savings to developers using Gemini 2.5 models and continued availability of the explicit caching API for guaranteed savings.
Gemini 2.0 Flash's image generation capabilities, now available in preview in Google AI Studio and Vertex AI, feature higher rate limits, enhanced visual quality, more precise text rendering, and more, allowing developers to create applications for product recontextualization, collaborative image editing, and dynamic SKU generation.