Gemini CLI is our new #OpenSource AI agent that brings the power of Gemini directly into your terminal!. Access Gemini 2.5 Pro with 1M token context window, 60 requests/min, and 1,000 requests/day—at no cost with a free Gemini Code Assist license →

RT @ggalloro: Published a new medium blog on using @GoogleCloudTech #Gemini Code Assist agent mode and #GeminiCLI: ..

Now playing: The AI Assistant Manager with Google Distributed Cloud, Gemma & K8s. Learn how to leverage AI, cloud infrastructure, and K8s to build, train, and deploy apps on the cloud and extend them at the edge for a fast and connected experience for customers and staff alike ↓

Google Cloud Hyperdisk offers high-performance, workload-optimized block storage for your applications that is cost-efficient, easily managed at scale, and enterprise-ready. Read this guide to help you choose the optimal Hyperdisk for your environment →

Three new transactional features to simplify your workflows and unlock new possibilities within BigQuery:. 1) Efficient fine-grained DML mutations.2) Change history support for updates & deletes.3) Real-time updates with DML over streaming data. Dive in ↓

______ is an open standard designed to standardize how LLMs interact with external data sources, APIs, and resources as agent tools. Check out our guide to Google ADK and _____ integration with an external server →

Big news for BigLake:. 1) Formerly BigQuery metastore, the fully managed, serverless, scalable BigLake Metastore, is now GA.2) Introducing support for the Iceberg REST Catalog API (Preview).3) BigLake tables for Apache Iceberg in BigQuery is GA. ➕ more →

Host MCP servers on Cloud Run!. Need a hosting platform to support the tools and resources your AI agents interact with? Deploy MCP servers to Cloud Run to take advantage of Cloud Run's pay-per-use, automatic scaling infrastructure with GPU instances →

Check this out: The Python SDK for A2A provides the tools you need to interact with and build using A2A, simplifying the integration of these powerful communication capabilities into your Python-based agents. Dive in and start building on @github ↓

RT @meteatamel: In the second post in the Vertex AI's Gen AI evaluation service series, I dive into computation-based metrics, what they pr….

Turn a document into an engaging experience in seconds with Gemini 2.5 Flash-Lite—the most cost-effective Gemini 2.5 model yet! Watch this demo to learn how ↓. Read about Gemini 2.5 Flash-Lite—now in public preview →

RT @MazlumTosun3: 🚀 New video drop!. Built a real-world FastAPI app on Cloud Run with @martinomander — now live on the @GoogleCloudTech cha….

Reminder: Gemini 2.5 Flash and 2.5 Pro are now stable and generally available + Gemini 2.5 Flash-Lite is in public preview. Try them out →

Challenge: Create a multi-agent AI assistant for complex financial research. Solution: We helped @Schroders develop a successful prototype with Vertex AI Agent Builder, reducing the time to complete a detailed company analysis from days to minutes →

RT @meteatamel: In my next few posts, I will talk about the Gen AI evaluation service in Vertex AI. In the first post, I give an overview o….

Go under the hood of BigQuery: Enhanced vectorization. This example shows how a tight integration between enhanced vectorization runtime + Capacitor + optimization techniques leads to 21x query performance improvements ↓

Bigtable just got even faster!. We've pushed single-row read throughput up to 17,000 point reads/sec – a 1.7x improvement. That means 70% more traffic per node at no extra cost, boosting your efficiency without sacrificing low latency. Learn more →

Out with the old way of thinking: BigQuery is only for analysis. In with the new BigQuery transactional features for fewer complex workarounds, faster reactions to changing data, and the ability to build dynamic + responsive apps where your data lives ↓

Don't just write code faster, build better software. Here's how to unlock software delivery excellence and quality with Gemini Code Assist agents ↓

The advancements in ADK, Agent Engine, and A2A protocol are designed to provide you with a comprehensive and flexible platform to bring your most ambitious agent-driven projects to life! . Which one will you dive into and start building with first?.

Work with raster data using Earth Engine in BigQuery!. This guide explains how to combine raster and vector data by using the ST_REGIONSTATS function, which calls Google Earth Engine to perform geospatial analysis in BigQuery →