标签：#Go

Google AI recently became the official AI Model and Platform Partner of DEV Community. As someone building an AI routing platform, I paid attention. Google's Gemini Enterprise Agent Platform (formerly Vertex AI) promises enterprise-grade AI agent orchestration — and with the DEV partnership, there's never been a better time to explore it. In this article, I'll share how I integrated Google Cloud's Agent Platform with my existing AI router (built on Neon PostgreSQL), what I learned about Gemini's enterprise capabilities, and why the Google AI + Neon + Algolia trifecta is the ideal stack for AI-first applications in 2026. Why Google Cloud's Agent Platform? The Gemini Enterprise Agent Platform is Google's answer to the question: "How do I orchestrate multiple AI agents in production?" It provides: Pre-built agent templates for common workflows (customer support, code review, data analysis) Grounding with Google Search — your agents can cite real, current sources Context caching — reduce costs by reusing conversation context across turns Multimodal understanding — Gemini processes text, images, audio, and video in one call Enterprise security — VPC controls, data residency, IAM integration For QuantumFlow AI (my AI routing platform), the Agent Platform solved a critical problem: how to orchestrate 26 different AI models without building a custom orchestration layer from scratch. The Architecture: Google Cloud + Neon + Next.js Here's the stack I built: User Request → Google Cloud Agent Platform (Gemini orchestration) → QuantumFlow Router (selects optimal model) → Local models (Ollama — free, sovereign) → Cloud models (GPT-4o, Claude, DeepSeek, Gemini) → Neon PostgreSQL (logs, analytics, cost tracking) → Algolia (search across all AI responses) Why Neon (DEV's Database Partner)? Neon is dev.to's official database partner, and for good reason. It's serverless PostgreSQL with: Database branching — create a full database copy in seconds (like git for data) Bottomless storage

I’ve been thinking about a small image-processing problem lately: how to reduce an image to a limited palette without making it look muddy. This comes up in a lot of places: pixel art tools printable pattern generators low-color previews LED matrix displays icons and small thumbnails craft or grid-based workflows The easy version is: pick the nearest color for every pixel. The hard version is: keep the important shapes readable after the palette gets much smaller. Nearest color is only the baseline A simple nearest-color pass usually works like this: Take each pixel. Compare it with every color in the target palette. Pick the closest one. Replace the pixel. That gives you a valid output, but not always a good one. The problem is that closest is local. It does not know whether the whole image still reads well. A face can lose warm midtones. A shadow can turn into a flat dark blob. A small highlight can disappear. Skin, fur, fabric, and background colors can collapse into the same bucket. So palette reduction is not just a color problem. It is also a structure problem. RGB distance can be misleading A common first attempt is Euclidean distance in RGB: function rgbDistance(a, b) { return Math.sqrt( (a.r - b.r) ** 2 + (a.g - b.g) ** 2 + (a.b - b.b) ** 2 ); } This is easy to implement, but it does not match human perception very well. Two colors can be numerically close in RGB and still feel different. Other colors can be farther apart numerically but visually acceptable. A better approach is to compare colors in a more perceptual color space, such as Lab or OKLab. You still have to be careful, but the distance metric starts closer to what the eye notices. Dithering helps, but it changes the style Error diffusion, like Floyd-Steinberg dithering, can preserve gradients and perceived detail with fewer colors. That is useful when the output is meant to look like a low-color image. But dithering is not always desirable. In grid-based outputs, it can create scattered single-p

If you’re looking for a relatively affordable way to cut down on cooling costs, Google’s Nest Thermostat can help. It’s packed with smart controls and energy-saving features, and right now it’s on sale in white for $79 ($50 off), which is its best price of the year, at Amazon. The smart thermostat is quick to […]

GitHub had over 14,000 repositories. Fewer than half had clear ownership. Here's how we gave every active repository a validated owner in under 45 days, archived the rest, and made ownership the foundation for everything that followed. The post How GitHub gave every repository a durable owner appeared first on The GitHub Blog .

State attorneys general said they found that Block misled users by falsely advertising that Cash App provided bank-like protections, including advanced fraud detection.

State agency's delay could mean free robotaxi rides in company’s new Ojai vehicle for a few months.

GitHub热门项目 | Fully autonomous AI Agents system capable of performing complex penetration testing tasks | Stars: 19,091 | 454 stars today | 语言: Go

Because of the way they are trained, large language models capture only a slice of human language. They’re trained on the written word, from textbooks to social media posts, and our speech as captured in movies and on television. These models have minimal access to the unscripted conversations we have face to face or voice to voice. This is the vast majority of speech, and a vital component of human culture. There’s a risk to this. The increased use of large language models means we humans will encounter much more AI-generated text. We humans, in turn, will begin to adopt the linguistic patterns and behaviors of these models. This will affect not just how we communicate with one another, but also how we ...

Google shipped AlloyDB AI functions GA with a proxy model architecture that trains a lightweight local model from LLM outputs, then runs queries at database speed without external calls. Smart batching delivers 2,400x throughput improvement. The proxy model reaches 100,000 rows per second in preview, but benchmark numbers apply only to ai.if in internal testing. By Steef-Jan Wiggers

Are you building a trading dashboard, a market sentiment tracker, or a financial data pipeline in Go? If so, you know that gathering reliable social intelligence and market data is often a complex, messy process. You have to juggle raw HTTP requests, decode deeply nested JSON payloads, and manually handle rate limits. But what if you could access a wealth of crypto and stock social intelligence idiomatically, right where your Go code lives? Enter lunarcrush-go , a powerful, zero-dependency SDK designed to seamlessly integrate the LunarCrush API v4 into your Golang applications. In this article, we will explore why lunarcrush-go is the ultimate tool for developers looking to tap into social and market intelligence, how to get started in under 60 seconds, and why its zero-dependency architecture makes it a robust choice for production workloads. Why LunarCrush? Before diving into the SDK, it is worth understanding what LunarCrush brings to the table. LunarCrush goes beyond traditional price charts. It measures what the internet is actually saying about Bitcoin, Ethereum, Tesla, and thousands of other assets. By analyzing social buzz, creator impact, and overall market sentiment across various platforms, LunarCrush provides a holistic view of the market 1 . Whether you want to know the Galaxy Score of a specific coin, track the hourly social time-series of a stock, or get AI-generated insights on a trending topic, LunarCrush has you covered. Introducing lunarcrush-go The lunarcrush-go library was built with one primary goal: to provide clean, typed, and production-ready access to every LunarCrush endpoint without pulling in a single third-party dependency. It speaks Go natively, meaning you do not have to wrestle with raw JSON or hand-roll your own retry loops. Key Features Here is what makes lunarcrush-go stand out: Complete API Coverage: The SDK supports every LunarCrush endpoint, including Coins, Stocks, Topics, Categories, Creators, Posts, Searches, AI summaries, a

The caller ID company says users are increasingly ignoring and blocking calls from India's dedicated business number series.

The saga of Musk's tussle with the SEC over how he disclosed his growing stake in Twitter (now X) has come to an end.

The feature can do things like apply cinematic relighting to brighten up a dark clip, swap out a plain background for something fun, or add artistic styles to videos.

The company's streaming devices aren't quite keeping up with competitors in several important categories.

It allows you to reimagine videos stored in Google Photos using Gemini Omni.

Android Bench is evolving, and developers can help guide that process.

Google's upcoming Pixel lineup might cost more than last year's. A report from Dealabs spotted by 9to5Google suggests that Google could raise the starting price of its 41mm Pixel Watch 5 to $399, while adding LTE could bump the price to $499. That's a $50 jump from the base Pixel Watch 4, which starts at […]

GitHub热门项目 | Declarative Continuous Deployment for Kubernetes | Stars: 23,361 | 20 stars today | 语言: Go

Last week, national security agencies from the Five Eyes—that’s the rich, English-language-speaking countries club—jointly released a statement warning of the increasing cyber risks of AI models: in particular, their ability to autonomously hack into systems and networks. The statement was more measured than some of the breathless headlines about it, and the advice they gave is pretty much the standard advice everyone gives—albeit with newfound urgency. Internet risks are nothing new, and cyberattacks—both large and small—have been a significant issue since long before the current crop of generative AI models...

Scammers are hijacking government websites to upload ads for “leaked” OnlyFans content. Thousands of copyright complaints from adult creators are helping people avoid malicious links.