@DataDeLaurier@Teknium@JoelDeTeves Roger that. Going on almost a full month with Hermes not asking for a damn thing, multiple location changes without notice, had it connected to Starlink in middle of the Atlantic and WhatApp channel stayed rocking the whole time. Super impressed
@Teknium@JoelDeTeves@DataDeLaurier Question - I'm still rocking and rolling on the CLI Hermes and love it, pretty much keeps me out of Codex app. Is there a real reason for me to jump into Hermes Desktop?
Building apps has never been easier.
With Sites, Codex can turn your work, ideas, and plans into an interactive website or app your team can explore, use, and share with a URL.
Rolling out to Business and Enterprise plans, before expanding more broadly.
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.
is Hermes Agent ready for enterprises?
NVIDIA built OpenShell, a runtime that wraps AI agents in the security IT teams need before they let anything touch sensitive systems. it plugs directly into Microsoft's enterprise security stack. Hermes Agent now runs inside it.
what this changes for marketers building with agents:
> the marketing agents you've been prototyping can now go to Fortune 500 clients
> the security review that used to kill the deal is handled at the runtime layer
> the same Hermes setup that runs on your laptop can run inside any enterprise IT environment
> you do not have to rebuild your workflow for each client's compliance requirements
I deploy vertical marketing agents for growth teams and the biggest blocker on enterprise work has always been "your AI stack is amazing but our IT won't let us touch it."
that's the wall coming down.
for AI marketing infra builders, this opens enterprise marketing budgets. for in-house teams at enterprises, it's the green light to deploy Hermes agents.
🚨do you understand what just happened with NVIDIA RTX Spark..
Jensen Huang walked on stage and pulled an entire gaming PC out of his pocket.
NVIDIA merged the CPU, RTX GPU, AI hardware and up to 128GB of memory into one Windows-on-ARM superchip and called it the end of the PC as you know it.
> 20-core Grace CPU plus a Blackwell GPU with 6,144 CUDA cores - RTX 5070-tier graphics in a 14mm body.
> NVIDIA claims 100+ FPS at 1440p in 007 First Light and Forza Horizon 6, on battery.
> It runs a 120-billion-parameter AI model locally, no cloud needed.
> ASUS, Dell, HP, Lenovo, MSI and Microsoft already have 30+ laptops lined up for this fall.
The whole internet has two questions: is it real, and how much. Nobody's asking the third - what happens to every other chipmaker if it is.
You read the docs and didn't know that it is a read only skill - that cannot gamble, cannot use money, cannot place bids - it can only read the predicted outcome of events.
jfc I heard you were a troll of opensource prjoects (and bad at it given the ffmpeg scenario) but jfc this is absurd lmao
I built a skill that runs comprehensive SEO audits — technical foundation, on-page optimization, content quality, site architecture, international SEO, and backlink analysis.
You point it at a site and it checks everything: crawlability, Core Web Vitals, title tags, internal linking, content depth, hreflang implementation, and backlink health. It prioritizes fixes by impact.
Most SEO audits are 50-page PDFs nobody reads. This gives you a prioritized action plan — quick wins first, structural fixes second.
It's called /seo-audit and it's part of Marketing Skills — a free, open source collection of 40 marketing skills for AI agents like Claude Code, Cursor, and Codex.
npx skills add coreyhaines31/marketingskills
if you want claude to be able to make slides for you, don't use claude design, use revealjs and have claude make them with html and markdown
it's such a nice experience
Los founders que saben codear pero envían demos con cursor de Windows acaban de quedarse sin excusa.
Un repo open-source graba tu pantalla, mete zooms automáticos, pule el cursor y pone fondos cinemáticos. 15.5k estrellas.
Se llama Recordly.
You don't understand how BIG this is.
The same OWASP security audit that used to take a consultant 3 days now happens in 30 seconds with ONE prompt:
"Review my app against OWASP standards and highlight vulnerabilities."
→ SQL injection
→ XSS
→ Broken auth
→ Insecure dependencies
Watch what happens when you paste it into Cursor.
Most vibe coders do not even know this exists.
(full breakdown in the article)
Step 3.7 Flash is now free for 30 days via Nous Portal
It is a new MoE vision-language model focused on agent efficiency, coding, search, and multimodal workflows — and Hermes Agent users have been loving it, so thank you to @StepFun_ai for hooking them up!
I built a skill that implements schema markup — JSON-LD structured data for rich results, entity linking, and AI discoverability across every page type.
You describe your site structure and it generates the correct schema for each page type: Organization, Product, Article, FAQ, HowTo, Review, and BreadcrumbList — all in JSON-LD format.
Schema markup is the most overlooked SEO lever. It's the difference between a plain blue link and a rich result with ratings, FAQs, and how-to steps.
It's called /schema-markup and it's part of Marketing Skills — a free, open source collection of 40 marketing skills for AI agents like Claude Code, Cursor, and Codex.
npx skills add coreyhaines31/marketingskills
Introducing Impeccable 3.5, the best way to design in production: iterate on real UI with your AI agent, in the codebase you actually ship.
Turns out many popular design skills, including Impeccable and Anthropic's frontend-design, weren't actually very good at...design (the workflow was valuable, but the output didn't magically make LLMs like GPT great designers). We measured it across thousands of generations: 74% of pages used the cream AI-default background, 76% reached for extreme letter-spacing, 90%+ failed the contrast floor.
So we started fixing slop systematically, specific to each model. The skill now compiles rules for the exact defects each model makes, instead of shipping one generic file to everyone. The biggest jump is in GPT-5.5 and Codex.
Also new:
◆ It now knows the difference between a new project and an existing one. Existing codebase, it reads your design system and preserves your identity. Greenfield, it seeds a fresh palette from 129 hand-curated anchors so every cold start doesn't drift to the same safe colors.
◆ Live Mode is now in beta, and works at two scales. Type a direction into the new Steer bar, or speak it, and the agent reads the whole page and edits it in place. Or pick a single element, steer it with a sub-command, live-edit any copy, and accept the variant straight back to source. Insert mode scaffolds brand-new elements between the ones already there. Recovery survives HMR, hidden heroes, and dev-tool overlays.
◆ A rebuilt anti-pattern detector. Torn off jsdom and onto a real CSS cascade resolver: roughly 20x faster, dependency-free, and now small enough to run inline inside the skill, not just the CLI and extension. 14 new rules, 41 total.
◆ The skill keeps itself current, checking once a day and offering to update. Plus /impeccable init and a bare /impeccable that reads your repo and tells you the next move.
Free, open source. Claude Code, Codex, Cursor, and more.
https://t.co/Q5dmE5wB7X
Standard tests fail on generative AI because one input can lead to thousands of answers. WebMCP evals can help. Test your LLM touchpoints to verify your agent understands tool schemas, picks the right parameters, and completes user journeys before production → https://t.co/GhTi1wqyZo
#GoogleIO
Big SEO News: Google has officially posted an "LLMs.txt" page to the Chrome Developers site.
"Without this file, agents may spend more time crawling the site to understand its high-level structure and primary content."