Tech Radar
Bring multimodal semantic search to the edge with EmbeddingGemma 2
EmbeddingGemma 2 is a new 740M open-weight multimodal model that maps text, images, video, and audio into a unified vector space for privacy-first, on-device retrieval. Developers can easily integrate these capabilities cross-platform using MediaPipe Tasks or optimize fine-grained performance across CPU, GPU, and NPU accelerators…
EmbeddingGemma 2: The Developer Guide
EmbeddingGemma 2 is a compact, open-source multimodal embedding model that maps text, code, images, video, and audio into a unified 768-dimensional space. Developers can use the sentence-transformers library to selectively load modular modality encoders—ranging from 270M to 740M parameters—to optimize memory usage. Additionally, Matryoshka Representation…
Supercharge your development with the Google Developer Knowledge API ecosystem
Google is launching the Developer Knowledge API and MCP Server in public preview. This new toolset provides a canonical, machine-readable way for AI assistants and agentic platforms to search and retrieve up-to-date documentation across Firebase, Google Cloud, Android, and more. By using the official MCP…
The Outer Loop, Insights First: An Ambient Quality Agent That Diagnoses Your Production Agent
How do you keep improving an AI agent after the first 80%, once it serves real production traffic and silent quality regressions return HTTP 200 OK? We are open-sourcing AQuA (Ambient Quality Agent), a reference implementation that runs beside your production agent in Google Cloud,…
ML Drift: Next-Gen GPU AI/ML Inference at the Edge
Google AI Edge has introduced ML Drift, a high-performance, universal GPU compute framework designed to accelerate on-device AI and machine learning inference. By abstracting the complexities of hardware and low-level APIs—including OpenGL ES, OpenCL, Metal, and WebGPU—ML Drift enables developers to build real-time, interactive ML…
Gemini 4 Argon for Robotics
Gemini 4 Argon is a general-purpose physical reasoning model designed to enhance workflows across the robotics stack with advanced capabilities in physical understanding, code generation, and visual-semantic reasoning. Developers can access and integrate Argon across Google's developer platforms—including Google AI Studio, the Gemini API, and…
Optimizing a 200,000-line Python codebase overnight with Gemini 4 Argon
How our engineering team ran Gemini 4 Argon unattended overnight with .agents/skills and /goal mode to cut in-memory session prep overhead by 40% in long sessions and speed up cold imports by 21% in Google's open-source Python Agent Development Kit (ADK).
Announcing MCP support in Apigee hybrid: agentic tools that run in your own cluster
Apigee hybrid 1.17.0 introduces native Model Context Protocol (MCP) support, enabling the MCP data plane to run directly within your own Kubernetes cluster. This architecture ensures that AI agent request traffic and tool execution remain entirely inside your infrastructure while pulling configuration updates from the…
Three layers, one repo: a tour of google/adk-recipes
The google/adk-recipes repository unifies Agent Development Kit (ADK) resources into three structured layers—core/, plugins/, and contrib/—serving as a single source of truth for building AI agents. Developers can leverage reference patterns, install modular vertical skills (such as retail product search and virtual try-on) directly into…
Evaluating AI agents: moving past the vibe check
A practical engineering guide and reference architecture for establishing continuous evaluation pipelines for multi-turn AI agents using Gemini Enterprise Agent Platform, Google ADK, and OpenInference standards.
Announcing DPoP Support for Google OAuth: Securing Refresh Tokens
Google OAuth Platform now supports DPoP (Demonstrating Proof-of-Possession) to sender-constrain refresh tokens, neutralizing Infostealer malware and adversary-in-the-middle attacks. By cryptographically binding long-lived refresh tokens while maintaining short-lived access tokens as standard Bearer tokens, developers achieve robust credential security without incurring high-QPS API…
Step by Step guide: Build a Voice Agent That Never Goes Silent using ADK
The open-source Agent Development Kit (ADK) and gemini-3.8-live enable developers to build responsive voice agents by implementing non-blocking tools in Python. Developers can use streaming tools to yield progress updates or background execution patterns to keep conversations fluid during long-running backend queries. Additionally, configuring response…
Native Model Authoring for Edge with LiteRT Tensor API
Meet the LiteRT Tensor API: giving developers native C++ control over the model graph to unify end-to-end ML computations on heterogeneous edge hardware.
Integrating TorchTPU into TorchTitan and Optimizing Models for TPU
TorchTPU integrates a native torch.device("tpu") backend directly into PyTorch, allowing developers to train large-scale models on Google Cloud TPUs without rewriting code in JAX. The TorchTitan TPU fork enhances this with production-grade scaling primitives like SimpleFSDP, Graph Trainer, and custom Pallas kernels that achieve high…
Unifying Edge AI: How Coral NPU’s open standard brings portable, energy-viable intelligence from model to silicon
Google Research has completed the 32-bit open-source Coral NPU RISC-V architecture with the introduction of its Matrix Execution Unit, which delivers up to 1 TOPS while targeting 10 mW average power for edge inference. Alongside this architecture, the release of the v1.0 open-source IREE/MLIR compiler…
Bringing Visual Graph Debugging to Custom Edge Compilers with Model Explorer
Google AI Edge Model Explorer now supports custom compiler intermediate representations and open-source adapters like TOSA, VGF, and PTE for on-device machine learning. Developers can leverage hierarchical graph visualization, split-pane views, and per-node trace overlays to catch export regressions and verify hardware delegation. These tools…
Announcing New vLLM and SGLang Inference Engines on TPU
This post announces native PyTorch backends for vLLM and SGLang powered by TorchTPU, enabling developers to run and optimize serving workloads using familiar PyTorch tools. Built in collaboration with open-source project maintainers, these engines include optimized TPU kernel implementations, production-ready features like KV cache management…
Powering the Agent Development Lifecycle with any framework, from ADK to LangChain and beyond
The Agents CLI Extension System enables developers to use frameworks like LangChain, LangGraph, or custom enterprise stacks while retaining a unified deployment and evaluation workflow. It details a first-party LangChain template that scaffolds, runs, and deploys agents without requiring the Agent Development Kit (ADK). Additionally,…
Architecting Governed, Self-Evolving AI Agents on Google Cloud
Learn how Project Chrysalis combines Google Cloud's Gemini Enterprise Agent Platform, Agent Development Kit (ADK), BigQuery, and a four-gate defense-in-depth security stack (Model Armor, Cloud KMS, Binary Authorization, and OPA) to build governed, self-evolving AI agents that remediate live production outages in 1.8 seconds.
Streaming comes to API Gateway: real-time and AI-ready APIs, without changing your spec
API Gateway now supports real-time streaming—including Server-Sent Events, WebSockets, gRPC, and chunked transfer encoding—in Public Preview without requiring changes to your existing API specifications. This update allows developers to route long-lived, bi-directional streams and AI workloads directly through the gateway while maintaining consistent authentication, rate…
Usage metrics API adds usage from tools like OpenCode
The Copilot usage metrics API now reports model usage from more of the tools your developers use with Copilot, including tools like OpenCode that weren’t previously captured in your reports.… The post Usage metrics API adds usage from tools like OpenCode appeared first on The…
AI that understands your business: Dataverse and Work IQ at PPCC 2026
With business applications in Work IQ, now in public preview, Copilot and agents understand your business too. The post AI that understands your business: Dataverse and Work IQ at PPCC 2026 appeared first on Microsoft Power Platform Blog .
Turn notifications into code with GitHub Copilot in Teams
The new GitHub app in Teams brings notifications and Copilot together, helping teams turn issues into fixes and ship code faster without leaving the conversation. Get notified in channels, group… The post Turn notifications into code with GitHub Copilot in Teams appeared first on The…
Web Search on Amazon Bedrock now supports domain filtering and user location controls
Web Search on Amazon Bedrock now supports two new controls that give you more precision over the results that ground a model's response: domain filtering and user location. Both are configured directly on the web_search tool in your existing OpenAI Responses API request. With domain…
At MIT, Martha Minow speaks on sustaining democracy, both by using and overcoming AI
In Compton Lecture, the distinguished legal scholar warns of potential “loss of the Enlightenment” while suggesting ways innovations can meet our civic and cultural needs.
Reinforcing the value of human understanding at MIT
During the School of Humanities, Arts, and Social Sciences’ 75th Anniversary Symposium, President Sally Kornbluth said “MIT has never needed your particular insight and guidance more than we do now.”
EMU deletions fix
Between June 1 and June 13, 2026, some Enterprise Managed User accounts that were deprovisioned through SCIM were incorrectly deleted instead of being suspended and obfuscated as expected. As a… The post EMU deletions fix appeared first on The GitHub Blog .
Origin Range Requests: Serving large files without range-request tuning
Naive byte-range caching can waste gigabytes of origin bandwidth on small requests. We rebuilt our cache architecture in Pingora to coordinate partial fetches automatically, cutting R2 p99 latency in half.
Inside the LiteLLM 1.107.0 supply chain compromise: Credential theft through Python startup hooks
Microsoft Threat Intelligence analyzes the LiteLLM 1.107.0 compromise, including Python startup hooks, credential theft, remote code loading, detections, and mitigations. The post Inside the LiteLLM 1.107.0 supply chain compromise: Credential theft through Python startup hooks appeared first on Microsoft Security Blog .
Bringing post-quantum cryptography to geographically fenced key management
Cloudflare's new post-quantum GeoKey Manager protects geographically fenced decryption keys from harvest now, decrypt later attacks. Learn how we redesigned our cryptography stack to support strict data sovereignty in a post-quantum world.
