How Google Uses Shell

Deploying secure, real-time Edge AI on Raspberry Pi is now simplified using LiteRT and lightweight Gemma open models. LiteRT optimizes CPU and GPU performance, delivering fast token speeds for models like Gemma4, enabling real-time local reasoning for robotics. Developers can quickly convert, quantize, and run these models using the lightweight LiteRT CLI tool. Support for Hailo AI accelerators is also coming very soon.

The 2026-07-28 Model Context Protocol (MCP) specification replaces legacy stateful constraints with a fully stateless core, enabling cloud-native horizontal scaling, serverless deployments, and standard round-robin load balancing. This architectural shift introduces standardized HTTP headers for efficient routing without deep packet inspection, caching controls, and Multi Round-Trip Requests (MRTR) to handle interactive and long-running tasks without blocking connections. Developers can immediately begin migrating their agentic applications to this highly scalable infrastructure using the newly available beta SDKs for Python, TypeScript, Go, and C#.

Google Cloud API Gateway now offers a model routing feature in Public Preview, allowing developers to dynamically route traffic to models like Gemini, Claude, or OpenAI OSS-GPT without hardcoding endpoints or managing open-source proxies. Developers can easily configure these routing rules directly within their OpenAPI 3.x specifications by mapping virtual model names to specific backend targets on a shared host. Once deployed, the Gateway acts as a serverless ingress layer that accepts standard OpenAI-compatible requests, automatically transcodes the payload to the native schema of the target model, and routes the traffic on the fly.

To prevent context window bloat and reduce token consumption, Genkit Go introduces Agent Skills based on a progressive disclosure architecture. Developers can package specialized instructions, scripts, and references into modular SKILL.md bundles where only the frontmatter metadata is initially exposed to the agent's system prompt. When a task matches the skill's description, Genkit's middleware dynamically loads the full instruction body and associated assets, ensuring the model accesses precise workflows exactly when needed.

Google's open-source TPU microbenchmark suite provides developers with granular performance metrics across Network, Compute, HBM, Host Transfer, and Attention components to validate real-world hardware capabilities. By leveraging these benchmarks to establish a Roofline model, engineers can accurately diagnose whether their machine learning workloads are compute-, memory-, or network-bound. This empirical baseline directly guides targeted software optimizations—such as kernel tuning, mesh sharding, and rematerialization—to maximize hardware utilization for large-scale model deployments.

Ray 2.55 introduces official, first-class support for Google Cloud TPUs, enabling developers to run distributed Python workloads on Google's accelerators using the familiar Ray task-and-actor APIs. To handle the strict networking requirement of keeping multi-host TPU "slices" together over their Inter-Chip Interconnect (ICI), the KubeRay Operator on GKE automatically provisions and labels the underlying hardware layout. Ray Core utilizes these labels via its slice_placement_group() primitive to atomically reserve complete slices, allowing developers to deploy jobs through KubeRay, Ray Train, or Ray Serve simply by declaring a hardware topology (like "4x4") without writing custom placement code.

Distributed AI training is notoriously fragile because losing a single machine typically crashes the entire multi-node job, forcing a time-consuming, full-workload infrastructure restart. To address this, Google’s JAX ecosystem utilizes elastic training via Pathways, which converts a hardware failure into a catchable Python exception so the running process can survive. When an unplanned failure occurs, the system automatically replaces only the broken worker, restores the last viable checkpoint from Cloud Storage, and resumes training in place—minimizing total downtime to under two minutes without ever restarting the main controller process.

The Agent Development Kit (ADK) for Go 2.0 has been released, introducing a first-class, graph-based workflow engine to help developers compose complex, multi-agent applications. This update adds built-in primitives for human-in-the-loop (HITL) orchestration, dynamic execution using plain Go code, and automated resilience features like exponential backoff retries. By unifying the execution model, both single-agent applications and intricate graphs now run on the same runtime, simplifying telemetry and state persistence.

Building AI agents often leaves developers uncertain if prompt tweaks to fix single errors will accidentally cause widespread regressions in production. To bridge this gap, Google has introduced a new developer skill for coding agents that automates a five-stage evaluation flywheel: preparing data, running inference, grading with adaptive AutoRaters, analyzing failure clusters, and executing targeted optimizations. Running continuously against production traffic or on-demand via synthetic scenarios, this tool allows developers to describe testing goals in plain language while an independent evaluation service safely validates and counts actual performance improvements.

DiffusionGemma is an experimental text-generation model built on the Gemma 4 architecture that uses diffusion-based parallel generation instead of token-by-token autoregression, enabling much faster inference, bidirectional context awareness, and real-time self-correction while remaining deployable on consumer GPUs. Its architecture generates and refines 256-token blocks in parallel through iterative denoising, allowing it to handle complex constraint-based tasks such as Sudoku more effectively than traditional language models and demonstrating strong gains from fine-tuning. The model integrates with vLLM and other popular inference frameworks, giving developers access to a new non-autoregressive approach that combines high performance, efficient long-context scaling, and straightforward customization and deployment.

Google has announced the Google Colab Command-Line Interface (CLI), a new tool that allows developers and AI agents to connect local terminals to remote Colab runtimes for frictionless execution. The lightweight CLI enables users to easily request high-powered GPUs, run local Python scripts remotely, and seamlessly retrieve artifact logs or models like fine-tuned Gemma 3 adapters. By integrating directly into standard terminal environments, the tool is highly programmable and ready to be used by AI agents such as Antigravity or Claude Code to manage complex machine learning pipelines.

Google DeepMind’s Gemma 4 12B model brings agentic, multimodal AI capabilities to everyday laptops with 16GB of RAM, enabling local data processing and visual insight generation. Users can leverage this model on macOS through the Google AI Edge Gallery for dynamic Python code execution and visualization, as well as via Google AI Edge Eloquent for completely offline voice dictation and text editing. Additionally, developer workflows are enhanced by the LiteRT-LM CLI's new serve command, which creates an industry-compatible local endpoint to power fully-local AI tools and agents.

The newly released Gemma 4 12B is a dense, multimodal model designed for high-performance local AI execution on consumer devices. By introducing a novel, encoder-free architecture, it bypasses traditional visual and audio encoders to feed multimodal data directly into the LLM backbone.

How to transition from stateless chatbots to production-grade agents capable of managing long-running enterprise workflows, such as HR onboarding, that span days or weeks. It introduces the Agent Development Kit (ADK) and its architectural shifts, specifically using durable state machines and persistent session storage to ensure an agent never loses context during "idle time" or server restarts. By leveraging event-driven webhooks and multi-agent delegation, the tutorial demonstrates how to build resilient systems that "sleep" during pauses and wake up to resume complex tasks with high reasoning accuracy.

A2UI v0.9 introduces a framework-agnostic standard designed to help AI agents generate real-time, tailored UI widgets using a company’s existing design system. This update simplifies the developer experience with a new Agent SDK for Python, a shared web-core library, and official support for renderers like React, Flutter, and Angular. By decoupling UI intent from specific platforms, the release enables seamless, low-latency streaming of generative interfaces across web and mobile applications. Integrating with broader ecosystems like AG2 and Vercel, A2UI v0.9 aims to move generative UI from experimental demos to production-ready digital products.

MaxText has introduced new support for Supervised Fine-Tuning (SFT) and Reinforcement Learning (RL) on single-host TPU configurations, leveraging JAX and the Tunix library for high-performance model refinement. These features enable developers to easily adapt pre-trained models for specialized tasks and complex reasoning using efficient algorithms like GRPO and GSPO. This update streamlines the post-training workflow, offering a scalable path from single-host setups to larger multi-host configurations.

To bridge the gap between static model knowledge and rapidly evolving software practices, Google DeepMind developed a "Gemini API developer skill" that provides agents with live documentation and SDK guidance. Evaluation results show a massive performance boost, with the gemini-3.1-pro-preview model jumping from a 28.2% to a 96.6% success rate when equipped with the skill. This lightweight approach demonstrates how giving models strong reasoning capabilities and access to a "source of truth" can effectively eliminate outdated coding patterns.

This blog post introduces a workflow for extracting high-quality data from complex, unstructured documents by combining LlamaParse with Gemini 3.1 models. It demonstrates an event-driven architecture that uses Gemini 3.1 Pro for agentic parsing of dense financial tables and Gemini 3.1 Flash for cost-effective summarization. By following the provided tutorial, developers can build a personal finance assistant capable of transforming messy brokerage statements into structured, human-readable insights.

When you’re prototyping locally with AI agents like Gemini CLI, Claude Code, or your own agent, thei...

Google introduces extension settings for Gemini CLI, a structured configuration system that prompts users for required settings (API keys, URLs, project IDs) during extension installation.

This article introduces Gemini CLI hooks, a customization mechanism that lets developers control and extend the agentic loop of Gemini CLI without modifying its source code.

This article demonstrates how to fine-tune FunctionGemma, a specialized 270M parameter Gemma 3 model designed for function calling in agentic AI systems.

The Universal Commerce Protocol (UCP) is an open-source standard developed by Google to facilitate seamless commerce experiences across various platforms.

This article serves as a practical guide for developers working with JAX on Cloud TPUs, focusing on essential tools and techniques for debugging and profiling machine learning workflows.

The article introduces A2UI, an open-source project designed for agent-driven interfaces that allows agents to generate contextually relevant user interfaces.

The article discusses the new Session Management feature in Gemini CLI, which allows users to automatically save their sessions and resume work without losing context.

The article discusses optimizing performance on Qualcomm's Neural Processing Unit (NPU) using LiteRT, Google's high-performance on-device ML framework.

The article discusses the integration of Gemini 3 Pro into Gemini CLI, highlighting its capabilities to enhance productivity and performance in terminal operations.

The article introduces the Jules extension for Gemini CLI, designed to enhance coding workflows by allowing developers to offload tasks asynchronously.

The article introduces enhancements to Gemini CLI, allowing users to run complex interactive commands directly within the CLI environment.

The article announces the Genkit Extension for Gemini CLI, which enhances the development of AI applications by providing deep integration with Genkit's architecture and tools.

The article discusses building high-performance data pipelines using Grain, a data loading library for JAX, and ArrayRecord, an efficient file format.

The article introduces the Jules API, a new tool designed to enhance automation, integration, and innovation throughout the software development lifecycle.

Jules Tools is a command line interface that allows developers to interact with Google's asynchronous coding agent, Jules, directly from their terminal.

The article discusses the integration of the Agent Development Kit (ADK) with AG-UI, an open protocol for creating interactive AI user experiences.

The article discusses the integration of Gemini CLI with FastMCP, a Python library for building Model Context Protocol (MCP) servers.

The article discusses the integration of Google’s Agent Development Kit (ADK) for Java with the LangChain4j LLM framework, enabling developers to utilize a variety of Large Language Models (LLMs) f...

The article announces the release of Genkit Go 1. 0, a stable, production-ready open-source AI development framework for the Go ecosystem.

The article discusses the use of multimodal embeddings to enhance visual search capabilities, particularly for artists and enterprise-scale document search.

The article introduces Keras Hub, a unified library for pretrained models that simplifies access to both natural language processing (NLP) and computer vision (CV) architectures.

The article discusses the implementation of Gemma 2, a lightweight large language model (LLM) by Google, for processing streaming data with Dataflow.

The article discusses the release of MediaPipe Solutions for Raspberry Pi and iOS, highlighting the capabilities of the new iOS SDK and the updated Python SDK for Raspberry Pi.