Google Developers Blog
Updates on changes and additions to the Google Developers Blog.
Introducing Coral NPU: A full-stack platform for Edge AI
15 Oct 2025
Coral NPU is a full-stack platform for Edge AI, addressing performance, fragmentation, and user trust deficits. It's an AI-first architecture, prioritizing ML matrix engines, and offers a unified
Announcing the Genkit Extension for Gemini CLI
15 Oct 2025
The new Genkit Extension for Gemini CLI gives the command line deep knowledge of Genkit's architecture. It helps you build, debug, and iterate on AI apps with intelligent code generation,
Own your AI: Learn how to fine-tune Gemma 3 270M and run it on-device
15 Oct 2025
This guide shows you how to fine-tune the Gemma 3 270M model for custom tasks, like an emoji translator. Learn to quantize and convert the model for on-device use, deploying it in a web app with
Building High-Performance Data Pipelines with Grain and ArrayRecord
15 Oct 2025
To avoid data bottlenecks when training large models, this guide introduces Grain and ArrayRecord for building high-performance data pipelines.
Level Up Your Dev Game: The Jules API is Here!
4 Oct 2025
Ready to help turbocharge your workflow? We’re excited to introduce the Jules API—a new way to autom...
Meet Jules Tools: A Command Line Companion for Google’s Async Coding Agent
4 Oct 2025
You can now work with Jules directly in your command line. Jules is our asynchronous coding agent th...
Gemini 2.5 Flash Image now ready for production with new aspect ratios
4 Oct 2025
Our state-of-the-art image generation and editing model which has captured the imagination of the wo...
Gemini for Home: Expanding the Platform for a New Era of Smart Home AI
4 Oct 2025
Google Home is enabling new Gemini-powered features for our partners’ devices and launching a new program to help them build the next generation of AI cameras.
Unlocking Multi-Spectral Data with Gemini
4 Oct 2025
Multi-spectral imagery, which captures wavelengths beyond human vision, offers a "superhuman" way to understand the world, and Google's Gemini models make this accessible without specialized
Introducing Tunix: A JAX-Native Library for LLM Post-Training
4 Oct 2025
For developers and researchers in the JAX ecosystem, the path from a pre-trained model to a fully al...
Gemma explained: EmbeddingGemma Architecture and Recipe
4 Oct 2025
The previous posts in the “Gemma explained” series provided a detailed overview of the Gemma model f...
Delight users by combining ADK Agents with Fancy Frontends using AG-UI
4 Oct 2025
Delight users by combining ADK Agents with Fancy Frontends using AG-UIFor developers building genera...
Your AI is now a local expert: Grounding with Google Maps is now GA
4 Oct 2025
We are excited to announce Grounding with Google Maps in Vertex AI is now Generally Available (GA). ...
Apigee Operator for Kubernetes and GKE Inference Gateway integration for Auth and AI/LLM policies
4 Oct 2025
No AI/Agents without APIs!Many users interact with generative AI daily without realizing the crucial...
Continuing to bring you our latest models, with an improved Gemini 2.5 Flash and Flash-Lite release
4 Oct 2025
Google is releasing updated Gemini 2.5 Flash and Flash-Lite preview models with improved quality, speed, and efficiency. These releases introduce a "-latest" alias for easy access to the newest
Building the Next Generation of Physical Agents with Gemini Robotics-ER 1.5
4 Oct 2025
Gemini Robotics-ER 1.5, now available to developers, is a state-of-the-art embodied reasoning model for robots. It excels in visual, spatial understanding, task planning, and progress estimation,
On-device GenAI in Chrome, Chromebook Plus, and Pixel Watch with LiteRT-LM
4 Oct 2025
Google AI Edge provides the tools to run AI features on-device, and its new LiteRT-LM runtime is a significant leap forward for generative AI. LiteRT-LM is an open-source C++ API, cross-platform
Introducing the Data Commons Model Context Protocol (MCP) Server: Streamlining Public Data Access for AI Developers
4 Oct 2025
Data Commons announces the availability of its MCP Server, which is a major milestone in making all of Data Commons’ vast public datasets instantly accessible and actionable for AI developers
Google Colab Adds More Back to School Improvements!
4 Oct 2025
Colab is back with a few new and exciting features meant to simplify and enhance your notebook-based...
Gemini CLI 🤝 FastMCP: Simplifying MCP server development
4 Oct 2025
Gemini CLI now seamlessly integrates with FastMCP, Python's leading library for building MCP servers. We’re thrilled to announce this integration between two open-source projects that empowers you
ADK for Java opening up to third-party language models via LangChain4j integration
4 Oct 2025
The recent 0.2.0 release of Google’s Agent Development Kit (ADK) for Java adds an integration with t...
Gemini Batch API now supports Embeddings and OpenAI Compatibility
4 Oct 2025
Batch API now supports Embeddings and OpenAI CompatibilityToday we are extending the Gemini Batch AP...
A2A Extensions: Empowering Custom Agent Functionality
4 Oct 2025
A2A Extensions provide a flexible way to add custom functionalities to agent-to-agent communication, going beyond the core A2A protocol. They enable specialized features and are openly defined and
Beyond backpropagation: JAX's symbolic power unlocks new frontiers in scientific computing
4 Oct 2025
JAX, a framework known for large-scale AI model development, is proving to be a powerful tool in scientific computing, particularly for solving complex Partial Differential Equations (PDEs), now