Google Developers Blog

Beyond Request-Response: Architecting Real-time Bidirectional Streaming Multi-agent System

Introducing the Jules extension for Gemini CLI

Introducing Veo 3.1 and new creative capabilities in the Gemini API

Say hello to a new level of interactivity in Gemini CLI

Introducing Coral NPU: A full-stack platform for Edge AI

Own your AI: Learn how to fine-tune Gemma 3 270M and run it on-device

Announcing the Genkit Extension for Gemini CLI

Building High-Performance Data Pipelines with Grain and ArrayRecord

Level Up Your Dev Game: The Jules API is Here!

Meet Jules Tools: A Command Line Companion for Google’s Async Coding Agent

Gemini 2.5 Flash Image now ready for production with new aspect ratios

Unlocking Multi-Spectral Data with Gemini

Gemini for Home: Expanding the Platform for a New Era of Smart Home AI

Introducing Tunix: A JAX-Native Library for LLM Post-Training

Gemma explained: EmbeddingGemma Architecture and Recipe

Your AI is now a local expert: Grounding with Google Maps is now GA

Delight users by combining ADK Agents with Fancy Frontends using AG-UI

Apigee Operator for Kubernetes and GKE Inference Gateway integration for Auth and AI/LLM policies

Continuing to bring you our latest models, with an improved Gemini 2.5 Flash and Flash-Lite release

Building the Next Generation of Physical Agents with Gemini Robotics-ER 1.5

Building the Next Generation of Physical Agents with Gemini Robotics-ER 1.5

On-device GenAI in Chrome, Chromebook Plus, and Pixel Watch with LiteRT-LM

Introducing the Data Commons Model Context Protocol (MCP) Server: Streamlining Public Data Access for AI Developers

Google Colab Adds More Back to School Improvements!

Gemini CLI 🤝 FastMCP: Simplifying MCP server development

ADK for Java opening up to third-party language models via LangChain4j integration

Gemini Batch API now supports Embeddings and OpenAI Compatibility

Announcing Genkit Go 1.0 and Enhanced AI-Assisted Development

A2A Extensions: Empowering Custom Agent Functionality

Google AI Edge Gallery: Now with audio and on Google Play

Beyond backpropagation: JAX’s symbolic power unlocks new frontiers in scientific computing

Veo 3 and Veo 3 Fast – new pricing, new configurations and better resolution

From Fine-Tuning to Production: A Scalable Embedding Pipeline with Dataflow

Introducing EmbeddingGemma: The Best-in-Class Open Model for On-Device Embeddings

How to prompt Gemini 2.5 Flash Image Generation for the best results

Stop “vibe testing” your LLMs. It’s time for real evals.

Beyond the terminal: Gemini CLI comes to Zed

Introducing Gemini 2.5 Flash Image, our state-of-the-art image model

What’s new in Gemini Code Assist

Train a GPT2 model with JAX on TPU for free

URL context tool for Gemini API now generally available

Announcing Imagen 4 Fast and the generally availability of the Imagen 4 family in the Gemini API

Introducing Gemma 3 270M: The compact model for hyper-efficient AI

Gemini CLI + VS Code: Native diffing and context-aware workflows

Meet Jules’ sharpest critic and most valuable ally

The Google Developer Program is evolving

Veo 3 Fast and new image-to-video capabilities

Gemini Embedding: Powering RAG and context engineering

Introducing LangExtract: A Gemini powered information extraction library

A roboticist’s journey with JAX: Finding efficiency in optimal control and simulation

The agentic experience: Is MCP the right tool for your AI future?

Introducing Opal: describe, create, and share your AI mini-apps

People of AI podcast Season 5 is here: Meet the builders shaping the future

Unleashing new AI capabilities for popular frameworks in Firebase Studio

Gemini 2.5 Flash-Lite is now stable and generally available

Conversational image segmentation with Gemini 2.5

Build with Veo 3, now available in the Gemini API

Unlock Gemini’s reasoning: A step-by-step guide to logprobs on Vertex AI

Simplify your Agent “vibe building” flow with ADK and Gemini CLI

Stanford’s Marin foundation model: The first fully open model developed using JAX