When I debuted Webnerd.ai last weekend, the goal was pretty straightforward: bring back the fast, high-signal, human-curated morning reading ritual I loved in the heyday of classic RSS, updated for how the open web actually works in 2026. But just as much as I've enjoyed returning to that routine,  I've appreciated steering the roadmap with Antigravity. A decade plus ago, I'd point to companies that blogged weekly with their updates and bug fixes as leaders in their space, communicating to readers what was new. Now, I can make multiple updates daily, or make fixes in minutes myself -- and have even debuted a release notes section you can subscribe to from right within the app. It's an RSS inception, basically.

Over the last few weeks of living inside Webnerd.ai whenever possible, curating my shared stream and pushing links out to LG Stream on Bluesky, every "I wish it did this" or "I wonder if it could..." moment has turned into working code rapidly. Sean Goedecke, whose blog has rapidly become one of my favorites of 2026, published a piece today titled "You can just ask AI to do things", and honestly, there is no better summary of the world we live in now. If you can think it, you can build it.

Because things have moved fast since the weekend, here is a quick highlight reel of new features in Webnerd.ai right now.

First-Class Open Identity: AT Protocol OAuth, PDS Sync, and Standard.site

If you're going to build a home for the open web, you shouldn't lock people's reading identity behind a single provider. Current employer aside, I started with Google sign-in because that's what I knew. But in fast response to public request,  Sign in with Google now sits side-by-side with native Sign in with AT Protocol. Whether you use a bsky.social address or verify with your own domain like louisgray.com, you can jump straight in without extra modals or app-password gymnastics.

One click with Google, or bring your decentralized AT Protocol ID.

Even better, your decentralized identity isn't just a login badge, it carries your reading graph. Inside the OPML & Subscriptions hub, you can still drag and drop a classic XML file, or you can hit Sync PDS to pull decentralized subscription lists straight from your Personal Data Server across tools like Skyreader, Standard Reader, and Standard.site. Think about that for a second. Am I an expert on those? No. Could I work with Antigravity to build support here? Yes. So I did.

Classic OPML portability meets one-click AT Protocol PDS subscription sync.

Webnerd.ai also now speaks native at:// and standard:domain publications directly in the Subscribe dialog, and when you share a story from a Standard.site publication, Webnerd automatically writes a cryptographic site.standard.graph.recommend endorsement record to your PDS (and cleans it up if you unshare). Open standards work best when apps actually interoperate instead of just talking about it or seeing an acronymn as a checkbox.

Rescuing Newsletters from Inbox Purgatory

As much as I appreciate newsletter platforms like Substack and Beehiiv quietly keeping RSS alive under the hood, plenty of great writers still send email-only newsletters, and in my view, an email inbox sandwiched between flight confirmations, calendar invites, and shipping receipts is not the best place to read long-form writing.

Every account now gets a personal @webnerd.ai newsletter address that turns email dispatches into clean RSS feeds.

You can now open + Subscribe and switch to the new Personal Newsletters tab, and you'll find your own dedicated @webnerd.ai address. Use it when signing up for newsletters (or forward existing ones via Gmail filters or the included one-click Cloudflare Email Routing snippet), and Webnerd automatically spins up a separate, clean feed for each sender inside your Newsletters folder. Newsletters belong alongside the rest of your reading, not competing with work email.

Listening to Your Stream & Real Power-Reader Triage

Sometimes even my eyes need a break from screens, or I want to catch up on my feeds while walking the dog. Hitting the new Listen button in the top bar (or on any individual post) launches a docked audio player right at the bottom of your stream.

Listening through my morning feeds with the docked Audio & Spoken TTS queue.

If a feed item includes a native podcast or audio enclosure (flagged with an Audio badge), Webnerd plays the original audio directly; if it's a written post, it seamlessly reads the article aloud via a spoken Text-to-Speech queue with 1x to 2x playback speeds, an Up Next drawer, and automatic mark-as-read as each story finishes.

And because anyone subscribing to 100+ feeds may eventually face inbox-style bankruptcy, I've gone deep on power-reader ergonomics:

• Granular Mark-as-Read: A new split dropdown lets you clear items Older than 1 day, 3 days, 1 week, or 2 weeks, or Mark above as read as you scroll — so you can declare peace on Tuesday's news while keeping this morning's stories untouched.
• Folder & Subscription Management: You can now add, rename, drag-and-drop, delete, and merge folders inline or from a dedicated Manage Subscriptions view, toggle Newest / Oldest sort order, and pull Full Text readability views on stub feeds that only publish a sentence or two in XML.
• More Classic Themes: Alongside Cloud Nine, Warm Sepia, and OLED Black, desktop nostalgia nerds can also switch into Mac Classic, Mac OS X Aqua, BeOS, and Green Android.

AI on Your Terms — Never Between You and Your Feeds

I wrote earlier this month about how filtertainment eviscerated our informed monoculture. The whole point of an RSS reader is that you choose the sources, and nobody hides a post  because an algorithm decided outrage would keep you scrolling longer.

Where AI does shine in a reader is synthesis on demand — when you explicitly ask for it.

Optional Executive Briefings synthesize what happened across your feeds.

Tap Briefing in the toolbar (or hit B on your keyboard) and Gemini 3.8 Flash synthesizes an executive summary across your unread stream — scoped to your Last 100 items, Last 200 items, Last 12 hours, or Last 24 hours — clustering breaking storylines and citing the exact outlets in your subscriptions. Every expanded card also has an optional one-tap TL;DR button when a 4,000-word essay drops five minutes before your next meeting. AI acts as your research assistant, never your gatekeeper.

Mobile Overhaul, Instant Startup, and Eating Our Own RSS Dogfood

Under the hood, Webnerd.ai now boots through a single-round-trip bootstrap endpoint paired with a local snapshot cache for sub-16ms first-frame paint — so opening the tab feels instantaneous even on spotty mobile Wi-Fi.

On phones, we replaced cramped desktop menus with a thumb-friendly 4-tab mobile layout (Feeds, Search, Shared, and Folders), edge-swipe gestures, and a guided Add to Home Screen full-screen web app setup on iOS while I continue working on a native Android companion app - coming soon.

The redesigned four-tab mobile experience and full-screen iPhone web app.

Finally, you can't build an RSS reader and not publish your own changelog via RSS. Webnerd.ai now has an official Release Notes & Product Blog at webnerd.ai/releases, complete with a one-click + Follow in Webnerd.ai button and its own RSS feed at webnerd.ai/releases/rss.xml.

Eating our own dogfood: Webnerd.ai's product changelog lives at /releases with its own RSS feed.

If you tried Webnerd.ai over the weekend, or haven't yet, take the new audio player, newsletter inbox, or AT Protocol sync for a spin. If something bugs you or you have an idea for what an RSS reader in 2026 ought to do next, ping me on Bluesky — there's a pretty good chance Antigravity and I will have it shipped by the next weekend.

In the Web 2.0 era, I always started my day in my RSS reader. A mainstay of this blog at its peak was covering the debuts and new features from many different approaches to staying caught up on friends and the news, not just from Google Reader (RIP), but Feedly, Lazyfeed, Flipboard, TweetDeck, Shyftr, my6sense and too many others to mention.

I am not an engineer and I didn't major in computer science. There comes a point in understanding and using technology where I have a limit, and even with my years of experience in Silicon Valley, it's not impossible to run into issues that I just can't solve.

After a failed attempt a few years ago to move my blog to a new host and restart it on Wordpress, following general bit rot and content decay, the blog went completely dark -- an embarrassing development if I ever tried to point people to old stories or reference previous work, forced to look at my Blogspot backup or the Internet Archive to find some old content or try to prove my one-time relevance. 

While the world of blogging has changed in the last decade plus, my complete lack of new content wasn't an issue of a lack of ideas or a lack of time to write. It was straight up broken and I'd just about given up on getting it fixed, unwilling to turn my back on 3,000 posts only to start over somewhere else from scratch. But each attempt I'd make to run Blogger to Wordpress importers or adjust DNS settings failed. Until I turned to Antigravity.

My initial prompt that started the rebuild.

Antigravity is Google's AI-centric software development platform - very similar to Anthropic's Claude and OpenAI's Codex. Each of those products has its own champions, but the purpose is roughly the same. Simplify the ability for people to create, and leverage the latest models to understand user intent quickly and build smartly. I use Antigravity all the time at work, so with the new Googlebook being designed explicitly for working with Gemini, I thought I'd ask Antigravity to tackle this major project, and it didn't blink.

Rebuilding the blog, to me, meant fixing everything.

My expectations were initially low, as they often are after having tried the same thing over and over and gotten absolutely nowhere. I told Antigravity I wanted to rebuild the blog at the same domain and bring along my 3,000+ posts, along with all the images I'd used in those posts. I also needed to not just recreate a frozen point in time, where I had left off in 2019, but have a foundation to keep going. I didn't expect it to work, and I definitely didn't expect it to work so quickly.

Antigravity asked me a few questions, such as where my domain was currently hosted, if I had my Blogger archive from Google Takeout (I did), and how I wanted my domain setup. As Antigravity, using Gemini, churned away, it very quickly sussed out exactly how to solve my DNS issues and found me a new host in Cloudflare, which enabled easy read/write from Antigravity, and we were able to import my blog history. Not only did it very confidently tell me what was needed, but it guided me to which pages and options to choose from, both in my old host and my new one, that I needed to get what I wanted.

After seven years without posts and years of the domain just absolutely not working, I had my blog back to life, with all historical posts, in about two hours.

With that major milestone out of the way, I asked Antigravity how I was supposed to make new posts, and did my Cloudflare installation come with a content management system (CMS)? Reader, it did not.

Showing a blog CMS while in the CMS is so meta, but Antigravity built this.
Antigravity didn't miss a beat, saying, would you like me to build one for you? I said yes. So it made one. I logged in and saw it didn't have any of my old posts automatically saved, as I would have expected. Not a problem. I asked Antigravity to add them, and it did. I had gone from a totally dead domain and buried blog to a live domain and a blank slate to start over and make new posts again, without any missing history. I was no longer blocked.

From there, the only limitations have been what I ask for. Like any good blogger, I got to optimizing the look and feel of the site right away, asking Antigravity to feed me some new modern layouts and color palettes for 2026. I asked it to build in full-feed RSS, to supporting subscriptions and the open web. It rebuilt all my static pages, my yearly archives, and keeps a live count of total posts from my very first attempts back in 2006. It added a native commenting system and imported conversations from decades past, successfully. Antigravity also understood my previous style, and we've stuck with my tradition of the 125 x 125 image at the top left of posts to signal what each post is about.

Should something surprise me, or act in a way I didn't expect, I just go back to my ongoing conversation with Antigravity, and provide that feedback -- if posts aren't displaying how I expected, if numbers don't change, or basic functionality, like saving drafts in the CMS, had been missing from the first round.

The speed of creation and iteration and improvement is really unprecedented, and hasn't required daunting technology hassles. As I come up with ideas for the blog's functionality or its CMS, I just ask Antigravity. If Antigravity needs approval for permissions, I get the option to grant or deny them, and often found Antigravity giving me options to choose from, with a give and take that always leaves me in control.

Antigravity understands my input and takes action, with intentional follow-up.

Like I wrote last week, the opportunity to use natural language to simply build, or what some call "vibe coding", is changing our relationship with developers. If you can think it you can build it. Spoiled by my work environment, I was excited to see Gemini 4.0 (Argon) make its way into Antigravity this last week, making my conversations around this project (and others) even more in depth. And before you ask, yes, I pay for Google's AI Ultra subscription, and no, I don't have a discount. Having Antigravity available to me, with the latest models, baked into my Googlebook, is an absolute must in 2026.

I took my Twitter account private four years ago. It's over.

A common refrain through the rise of social media in the Web 2.0 surge was that "you are who you follow". Your personal choices of what you post and who you engage with are an echo of your personality and your interests, and it becomes a reinforcing loop. The people you follow select what you choose to consume, and what they share becomes part of what you believe to be true. An extension of that view is that "you are where you engage" and where you choose to engage is as much a descriptor at this point as the people you engage with -- especially as large-scale social networks and platforms have increasingly been identified with specific political leanings, or, unfortunately, their billionaire owners.