The next evolution of Hermes Agent is here!
Introducing Hermes Desktop: everything you love about Hermes, now native on your machine.
First demoed in Jensen's GTC keynote, it's now in public preview.
In the last 6 months at @Ahrefs, we analyzed over 1 billion data points across 14 studies. Here's what we learned about AI search optimization:
1) "Best X" blog listicles are the single most prominent content format cited by AI chatbots. They make up 43.8% of all page types cited by ChatGPT specifically.
2) 67% of ChatGPT's top 1,000 citations come from sources marketers can't influence: Wikipedia (29.7%), homepages (23.8%), app stores (6.6%). Only 32.3% are influenceable content like educational pages, reviews, news, and blog posts.
3) 28.3% of ChatGPT's most-cited pages have zero Google organic visibility. These pages get cited repeatedly by ChatGPT despite not ranking in Google at all. A completely separate discovery layer.
4) ChatGPT only cites about 50% of the URLs it retrieves. It fetches dozens of pages per query but uses half as background context without attribution. This means that being retrieved and being cited are very different things.
5) Adding schema markup had zero meaningful impact on AI citations. AI Overviews actually dipped โ4.6%, while AI Mode (+2.4%) and ChatGPT (+2.2%) showed changes indistinguishable from zero.
6) YouTube mentions have the highest correlation (0.737) with AI brand visibility out of all the factors we studied (including all the conventional SEO metrics like backlinks, page count, DR, etc). This held true for both Google-owned and OpenAI products.
7) AI Overviews reduce clicks to the #1 result by 58%. Thatโs up from 34.5% just 10 months earlier. The trend is accelerating.
8) 99.9% of AI Overviews appear on informational intent queries. Transactional, navigational, and local searches are almost entirely AIO-free. Shopping triggers AIOs just 3.2% of the time.
9) For a given search query, Googleโs AI Mode and AI Overviews reach the same conclusions 86% of the time โ but cite almost entirely different sources (only 13.7% citation overlap).
10) AI Overviews change every 2.15 days on average, with 70% of content differing between consecutive observations. But semantic similarity stays at 0.95. The words, sources, and entities constantly shuffle, but the actual meaning barely moves.
Agents make ugly UIs because they've never seen good design.
We've been fixing that, 2,000 DESIGN.md files from the world's best products, structured for a model to read and learn. Colors, type, spacing, layouts and more.
Free. https://t.co/mJaKNHba0O
Introducing Flue โ The First Agent Harness Framework
Flue is a TypeScript framework for building the next generation of agents, designed around a built-in agent harness.
Flue is like Claude Code, but 100% headless and programmable. There's no baked in assumption like requiring a human operator to function. No TUI. No GUI. Just TypeScript.
But using Flue feels like using Claude Code. The agents you build act autonomously to solve problems and complete tasks. They require very little code to run. Most of the "logic" lives in Markdown: skills and context and AGENTS.md.
Flue is like Astro or Next.js for agents (not surprising, given my background ๐). It's not another AI SDK. It's a proper runtime-agnostic framework. Write once, build, and deploy your agents anywhere (Node.js, Cloudflare, GitHub Actions, GitLab CI/CD, etc).
We originally built Flue to power AI workflows inside of the Astro GitHub repo. But then @_bgiori got his hands on it, and we realized that every agent needs a framework like Flue, not just us.
Check it out! It's early, but I'm curious to hear what people think. Are agents ready for their library -> framework moment?
Introducing Mesa: the most powerful filesystem ever built, designed specifically for enterprise AI agents.
Every team building agents eventually hits the same wall: where do the files live?
Not the chat history, the actual artifacts the agent works on.
> The contracts your agent redlined
> The claim files it updated
> The 200-page audit report it edited overnight while you were asleep
Today those documents live in a sandbox that dies in 30 minutes, an S3 bucket where concurrent writes clobber each other, or a GitHub repo that was never built to absorb agent-scale traffic.
So we built Mesa.
The world's first POSIX-compatible filesystem with built-in version control, designed from the ground up for agents. You mount it into your sandbox like any other filesystem. Your agent reads and writes files normally. Behind the scenes every change is versioned, branchable, reviewable, and rollback-able โ like a codebase, for any file type.
Mesa provides
โ Branches so agents work in parallel without locking
โ Durable storage that survives sandbox death
โ Sparse materialization so massive document sets load instantly
โ Fine-grained access control per agent
โ Full history for human review and audit
Design partners are running Mesa in production across legal, healthcare, GTM, business ops, and coding agents.
Private beta is open: link in the comments
There's lots of good memory options for agents, very happy with that (https://t.co/le2YkFZFww, https://t.co/o9WPhJym6Y, etc).
But is there an `emotions` framework for agents? Something that can help prompt feelings or emotions?
Someone on BreachForums claiming to be ShinyHunters is selling what they say is Vercel's internal database, access keys, and source code for $2M. ShinyHunters is a black-hat hacker group known for a significant number of breaches and a "pay or leak" model. Vercel has confirmed a security incident. Here's the breakdown:
> The listing claims to include employee accounts with access to internal deployments, API keys, NPM tokens, and GitHub tokens, with a $500k BTC starting price
> ShinyHunters posted the listing on April 19, 2026, claiming verified access keys "for a potential global supply chain attack"
> The listing includes screenshots from what appears to be Vercel's internal Linear instance and an internal user member system showing fields like id, name, email, admin status, and timestamps
> The seller explicitly pitched the supply chain angle, noting Vercel owns Next.js, Turbo.js, and the broader ecosystem, with 6 million weekly downloads for Next.js alone
> Screenshots show Vercel reached out to ShinyHunters on Telegram asking them to stop contacting employees, confirming Vercel is aware and engaged
> Vercel's official statement confirms "unauthorized access to certain internal Vercel systems" and says they've engaged incident response experts and notified law enforcement
> Vercel says a "limited subset of customers" were impacted and they're reaching out directly
> Vercel is recommending all customers review environment variables and enable the sensitive environment variable feature
Since we open-sourced pi-autoresearch, @Shopify teams have been running it on everything.
Results so far:
Unit tests: 300x faster
React component mounting: 20% faster
CI build time: 65% reduction
Made pnpm run faster
Autoresearch never stops trying things you'd never have time to try.
Repo: https://t.co/473UFWKanV
Shoe company Allbirds just announced that it's planning to
- Sell all of its brands and footwear assets
- Rebrand the company to Newbird AI
- Use a $50M convertible financing facility to "acquire high-performance GPU assets"