News
LiteRT: The Universal Framework for On-Device AI
1+ hour, 28+ min ago (795+ words) At Google I/O "25, we shared a preview of this evolution: a high-performance runtime designed specifically for advanced hardware acceleration. Today, we are excited to announce that these advanced acceleration capabilities have fully graduated into the LiteRT production stack, available…...
Tailor Gemini CLI to your workflow with hooks- Google Developers Blog
1+ day, 9+ hour ago (577+ words) Efficiency in the age of agents isn't just about writing code faster; it's about building custom tools that adapt to your specific environment. Whether you need to inject custom project context, enforce strict security policies, or automate testing workflows, a…...
A Guide to Fine-Tuning FunctionGemma
1+ week, 5+ day ago (667+ words) In the world of Agentic AI, the ability to call tools is what translates natural language into executable software actions. Last month, we released FunctionGemma, a specialized version of our Gemma 3 270M model explicitly fine-tuned for function calling. It is designed…...
A Developer's Guide to Debugging JAX on Cloud TPUs: Essential Tools and Techniques - Google Developers Blog
3+ week, 1+ day ago (426+ words) JAX on Cloud TPUs provides powerful acceleration for machine learning workflows. When working in distributed cloud environments, you need specialized tools to debug your workflows, including accessing logs, hardware metrics, and more. This blog post serves as a practical guide…...
Architecting efficient context-aware multi-agent framework for production
1+ mon, 3+ week ago (1637+ words) That ambition immediately runs into a bottleneck: context. As agents run longer, the amount of information they need to track'chat history, tool outputs, external documents, intermediate reasoning'explodes. The prevailing "solution" has been to lean on ever-larger context windows in foundation…...
Building AI Agents with Google Gemini 3 and Open Source Frameworks - Google Developers Blog
2+ mon, 1+ week ago (647+ words) The world of AI agents is rapidly evolving from simple chatbots to sophisticated, (semi)-autonomous systems that can make complex decisions in the real-world. This week, we introduced Gemini 3 Pro Preview, our most powerful agentic model designed to act as…...
5 things to try with Gemini 3 Pro in Gemini CLI
2+ mon, 1+ week ago (887+ words) Gemini 3 Pro is now available in Gemini CLI We've integrated Gemini 3 Pro, our most intelligent model, directly into Gemini CLI to unlock a new level of performance and productivity in the terminal. This powerful combination delivers state-of-the-art reasoning for executing…...
Google Colab is Coming to VS Code- Google Developers Blog
2+ mon, 2+ week ago (338+ words) Today, we are incredibly excited to announce the launch of the new Google Colab extension for Visual Studio Code. This work is the culmination of two key trends that have become apparent in the last few years. First, VS Code…...
Level Up Your Dev Game: The Jules API is Here!
3+ mon, 3+ week ago (234+ words) Ready to help turbocharge your workflow? We're excited to introduce the Jules API'a new way to automate, integrate, and innovate across the entire software development lifecycle. The Jules API is built around a few simple, powerful concepts: This isn't just…...
Meet Jules Tools: A Command Line Companion for Google’s Async Coding Agent
3+ mon, 3+ week ago (343+ words) You can now work with Jules directly in your command line. Jules is our asynchronous coding agent that integrates directly with your existing repositories, understands the full context of your project, and performs tasks such as writing tests, building new…...