https://developers.googleblog.comGoogle Developers Blog - Powered by AtomRSSAtomRSScontact@atomgroup.dev (AtomRSS)enSat, 08 Aug 2026 05:41:36 GMT5Agent Plugins 1.0.0 is a new, vendor-neutral directory specification—backed by Google, Amazon, Microsoft, and others—for packaging Agent Skills and MCP servers into a single portable unit. By standardizing the manifest (plugin.json) and utilizing a fixed directory layout, it eliminates the need for developers to maintain separate wrappers or configurations to support different AI coding agents and IDEs. Google has officially joined as a Core Maintainer and already rolled out support in the Agents CLI and Data Agent Kit, allowing developers to start building and distributing interoperable plugins today.https://developers.googleblog.com/en/agent-plugins-package-your-skills-tools-and-more/https://developers.googleblog.com/en/agent-plugins-package-your-skills-tools-and-more/Wed, 05 Aug 2026 16:00:00 GMTGoogleAIThe 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#.https://developers.googleblog.com/en/scaling-ai-agent-infrastructure-with-the-mcp-stateless-updates/https://developers.googleblog.com/en/scaling-ai-agent-infrastructure-with-the-mcp-stateless-updates/Tue, 04 Aug 2026 16:00:00 GMTGoogleAIGoogle 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.https://developers.googleblog.com/en/a-unified-api-for-ai-model-routing/https://developers.googleblog.com/en/a-unified-api-for-ai-model-routing/Mon, 03 Aug 2026 16:00:00 GMTGoogleAIReal-time AI agents break traditional request-response load balancing paradigms because they rely on long-lived, stateful bidirectional streams that obscure true server capacity. To solve this, developers must implement application-level session tracking directly within the runtime to accurately measure the committed concurrent workload of active conversations. By feeding these precise session counts alongside standard CPU utilization metrics into a hybrid routing algorithm, infrastructure can effectively distribute stateful AI traffic and prevent individual backend bottlenecks.https://developers.googleblog.com/en/scaling-real-time-ai-agents-with-session-aware-load-balancing/https://developers.googleblog.com/en/scaling-real-time-ai-agents-with-session-aware-load-balancing/Sun, 02 Aug 2026 16:00:00 GMTGoogleAITo 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.https://developers.googleblog.com/en/enable-on-demand-expertise-with-agent-skills-in-genkit-go/https://developers.googleblog.com/en/enable-on-demand-expertise-with-agent-skills-in-genkit-go/Thu, 30 Jul 2026 16:00:00 GMTGoogleAIAgent Platform's evaluation service is now generally available, providing developers with a unified engine to measure agent quality consistently across local development experiments and live production traffic. You can evaluate agents using over 20 pre-built metrics, DeepMind-backed adaptive rubrics, or custom code-based and LLM-as-a-judge metrics stored in a centralized, versioned registry. The service integrates directly into existing workflows via the Agent Platform SDK, agents-cli, and ADK, offering built-in user and environment simulators to automate complex multi-turn testing and streamline CI pipelines.https://developers.googleblog.com/en/agent-and-model-evaluations-in-gemini-enterprise-agent-platform-are-now-ga/https://developers.googleblog.com/en/agent-and-model-evaluations-in-gemini-enterprise-agent-platform-are-now-ga/Thu, 30 Jul 2026 16:00:00 GMTGoogleAIGoogle'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.https://developers.googleblog.com/en/how-to-use-google-microbenchmarks-for-evaluating-tpu-performance/https://developers.googleblog.com/en/how-to-use-google-microbenchmarks-for-evaluating-tpu-performance/Wed, 29 Jul 2026 16:00:00 GMTGoogleAIThis second installment explores how Ray’s higher-level libraries—Serve, Data, and Train—abstract the complexities of running AI workloads on Google's TPU slices. Ray Serve uses a simple topology configuration to correctly gang-schedule large multi-host models, while Ray Data eliminates data-loading bottlenecks by feeding accelerators directly with native JAX batches. Finally, JaxTrainer streamlines distributed training across TPUs by automatically handling cross-slice coordination, checkpointing, and fault tolerance.https://developers.googleblog.com/en/run-ray-on-tpu-part-2-ray-ai-libraries/https://developers.googleblog.com/en/run-ray-on-tpu-part-2-ray-ai-libraries/Thu, 23 Jul 2026 16:00:00 GMTGoogleAITunix is Google’s new JAX-native post-training library designed to eliminate TPU idling bottlenecks when training multi-turn, tool-using LLM reasoning agents. It maximizes hardware throughput by combining highly concurrent, asynchronous rollouts with a decoupled producer-consumer pipeline, ensuring the trainer is constantly fed even while agents wait on network I/O or environment steps. Additionally, Tunix provides plug-and-play abstractions and continuous macro-level profiling, allowing developers to easily integrate custom open-source environments and optimize complex distributed workflows without massive code rewrites.https://developers.googleblog.com/en/scaling-agentic-rl-high-throughput-agentic-training-with-tunix/https://developers.googleblog.com/en/scaling-agentic-rl-high-throughput-agentic-training-with-tunix/Mon, 20 Jul 2026 16:00:00 GMTGoogleAIRay 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.https://developers.googleblog.com/en/run-ray-on-tpu-part-1-the-foundations/https://developers.googleblog.com/en/run-ray-on-tpu-part-1-the-foundations/Sun, 19 Jul 2026 16:00:00 GMTGoogleAI