Adam Denenberg
906 posts
Adam Denenberg
@denen
CTO @VistaPrint Former VP Eng @Fastly, CTO @iheartRadio, CTO @ Rithum
Katılım Kasım 2007
503 Takip Edilen448 Takipçiler
The agency owners who figure out Hermes in the next 90 days are going to look like geniuses in 2027.
The problem is most agency owners don't have time to figure out the install, where to start, or what to actually hand it first.
So my team built an 83-page playbook that does it for you.
Inside:
— The 5 daily prompts that turn it into a second brain
— Plain English setup for Mac, Linux, and Android
— How to lock it down without torching client data
— 8 copy-paste workflows across reporting, outreach, sales, and ops
— The cron trick that drops token spend by 90%
Your competitors are sleeping on this.
Comment HERMES and I'll send it.
GREG ISENBERG@gregisenberg
how to set up hermes agent step by step. built-in memory, 40+ tools, works on your phone, and what to think of hermes vs openclaw: 1. hermes is a personal AI agent that runs in your terminal. think of it like open claw but with built-in memory, 40+ tools out of the box, and 90% cheaper token costs. you install it with one command. 2. the 3 problems with open claw that hermes solves: no memory (you keep repeating yourself), constant gateway restarts, and zero visibility into what you're spending on tokens. 3. hermes remembers everything. every completed task gets saved to memory. it searches through past logs to find solutions. over time it literally gets smarter at your specific workflows. 4. connect it to open router. you see exact costs per model per task. free models rotate weekly. one founder went from $130 every five days on open claw to $10 on hermes. same output. 5. it comes preloaded with skills. apple notes, imessage, find my, browser, web search, image generation, cron jobs. no hunting for plugins. 6. connect it to obsidian so it reads your entire vault. connect it to gstack for your dev environment. create custom skills for your specific workflows. 7. the biggest money saver: have it write code once for recurring tasks. then it runs without burning tokens every time. stop paying an LLM to do the same scrape or report daily. 8. run it on android via telegram. name your agents. talk to them like coworkers. in this episode imran shows you how to set this up. 9. you can run it bare metal, in docker, or serverless on modal. pick your risk level. i begged @imranye to come on @startupideaspod and walk through the full installation live. he made it impossibly clear. if you've heard of Hermes Agent and want the clearest explanation of how to get set up like a pro let me know what you want me to cover on the next ep this is the best personal agent setup video on the internet right now. watch
English
I fully reverse-engineered Ramp's internal AI operating system for marketing agencies.
Their system — called Glass — is how they got 99% of their entire company using AI every single day.
350+ reusable workflows.
Every tool connected at first login.
Memory that refreshes every 24 hours.
Automations running while everyone sleeps.
I partnered with my engineering team and we broke down every component inside it.
Then we rebuilt the whole thing for marketing agencies.
76 pages.
Every system.
Every layer.
Every step.
Steal it.
Comment "OS" and I'll send it directly.
Must be a following to receive auto DM
Eric Glyman@eglyman
99% of Ramp uses ai daily. but we noticed most people were stuck — not because the models weren't good enough, but because the setup was too painful and unintuitive for most. terminal configs, mcp servers, everyone figuring it out alone. so we built Glass. every employee gets a fully configured ai workspace on day one — integrations connected via sso, a marketplace of 350+ reusable skills built by colleagues, persistent memory, scheduled automations. when one person on a team figures out a better workflow, everyone on that team gets it and gets more productive. the companies that make every employee effective with ai will compound advantages their competitors can't match. most are waiting for vendors to solve this. we decided to own it.
English
I fully reverse-engineered Ramp's internal AI operating system.
Their system — called Glass — is how they got 99% of their entire company using AI every single day.
350+ reusable workflows.
Every tool connected at first login.
Memory that refreshes every 24 hours.
Automations running while everyone sleeps.
I partnered with my engineering team and we broke down every component inside it.
Then we rebuilt the whole thing for marketing agencies.
76 pages.
Every system.
Every layer.
Every step.
Steal it.
Comment "OS" and I'll send it directly.
Must be a following to receive auto DM
Eric Glyman@eglyman
99% of Ramp uses ai daily. but we noticed most people were stuck — not because the models weren't good enough, but because the setup was too painful and unintuitive for most. terminal configs, mcp servers, everyone figuring it out alone. so we built Glass. every employee gets a fully configured ai workspace on day one — integrations connected via sso, a marketplace of 350+ reusable skills built by colleagues, persistent memory, scheduled automations. when one person on a team figures out a better workflow, everyone on that team gets it and gets more productive. the companies that make every employee effective with ai will compound advantages their competitors can't match. most are waiting for vendors to solve this. we decided to own it.
English
@sdand Is this just an implementation of what RAMPA posted on their blog ? Looks like an identical pattern
English
Introducing vmux - incredibly fast, stateful cloud sandboxes for coding agents
for the first time you get persistent GPU/CPU sandboxes via Modal/CF backed by Durable Objects to stream logs live, native preview URLs, and attach a real shell
spin up a notebook or train nanogpt via codex - with a Modal sandbox spun up in seconds
English
Adam Denenberg retweetledi
𝗜𝗻𝘁𝗿𝗼𝗱𝘂𝗰𝗶𝗻𝗴 𝗧𝘄𝗶𝗻 — 𝘁𝗵𝗲 𝗔𝗜 𝗰𝗼𝗺𝗽𝗮𝗻𝘆 𝗯𝘂𝗶𝗹𝗱𝗲𝗿.
No setup. Secure. Infinitely scalable.
We just raised a $𝟭𝟬𝗠 𝘀𝗲𝗲𝗱.
After a beta with 𝟭𝟬𝟬,𝟬𝟬𝟬+ 𝗮𝗴𝗲𝗻𝘁𝘀 𝗱𝗲𝗽𝗹𝗼𝘆𝗲𝗱, we’re now opening to everyone.
RT and comment “Twin” — first agents on us. 👇
English
Thank you @ryancarson for merging my Claude code support in your awesome ralph tool! Ryan's tool now supports amp and claude code :) github.com/snarktank/ralph
English
@GergelyOrosz 100% agree. Hoping augmented engineering or similar picks up momentum.
English
We should stop calling it “vibe coding” when it’s software engineers writing production software, paying close attention, thinking a lot, validating before committing, closing the loop… and yes they prompt an agent/work with it.
Very different from “let it rip” w 0 validation
Deedy@deedydas
Today was proof that fully polished new products can be built entirely with “vibe coding” tools like Claude Code. Many people, espp in BigTech, who still don’t believe it: – you haven’t tried the latest models – you don’t have the right setup – codebase is still too large – your code style is not well-represented in the training data All 4 of these are entirely self-imposed problems. You will be outrun on product velocity if you aren’t adopting these tools.
English
I just compiled 10 AI automations that 10x your work output (with n8n)
Grab the workflows for lead gen, project ops, reporting, content, and more
These save founders and business owners at least 30+ hours monthly
Like + Comment "FREE" to get the full list and the 10 AI workflows
(Must be following)
English
This Facebook Ads Spy + n8n is absolutely wild 🤯
This AI agent monitors your competitor's Facebook ads on autopilot every single day.
And sends daily digests to Slack each morning.
Perfect for e-comm brands & agencies who need to know what's working in their niche.
Here's the problem:
Your competitors are launching new ads every day.
By the time you manually check the Facebook Ad Library, you've already missed the testing window.
This n8n automation solves it:
→ Runs every morning at 8am
→ Scrapes your competitor's newest Facebook ads via Foreplay API
→ AI analyzes each ad (format, hook, CTA, offer)
→ Sends a Slack digest with breakdowns
→ You see what's working before your coffee gets cold
No manual checking.
No spreadsheets.
No missing winning angles.
Built 100% in n8n.
Want the complete Facebook ad spy workflow?
> Comment "SPY"
> Like this post
And I'll send it over (must be following so I can DM)
English
I spent weeks researching 2025's hottest AI opportunities.
Found 50 business ideas that actually make money using current tech.
Each idea includes revenue paths, MVP scope, and exact tech stack needed.
Perfect for solopreneurs ready to capitalize on the AI boom before everyone else catches on.
Skip months of market research and failed experiments.
Comment "IDEAS" and I'll DM it to you (must be following)
English
I never run out of content to post anymore.
Built an automation that monitors 50+ news sources, scores articles for relevance, and writes social posts automatically.
It finds trending topics in my niche before they explode everywhere else.
Saves me 15-20 hours monthly and keeps me ahead of every trend.
Comment "NEWS" and I'll DM it to you (must be following)
English
Okay, I found this INSANE app that builds any n8n workflow in plain English.
And before you motherfuckers start thinking "oh great, another Claude fanboy"...
This shit is BETTER than Claude for automation.
Why? Because it actually has REAL-TIME n8n documentation baked in. Not some outdated 2024 bullshit.
I just told it: "build me a workflow that scrapes competitor prices and undercuts them automatically"
17 seconds later: WORKING WORKFLOW. Ready to deploy.
While you're still googling "n8n webhook authentication error"...
Someone else already built, tested, and shipped 5 automations using this thing.
The craziest part? It knows EVERY node, EVERY integration, EVERY edge case.
Your $5K consultant is about to shit themselves when they realize a free tool does their job better.
I'm not gatekeeping this one.
Comment "BUILDER" and I'll DM you the link.
(Following required for DMs)
The automation game just changed forever.
English
Just had a discussion at work and realized I coined a new meaning for MVP in the AI era.
Minimal Vibeable Product
English
Adam Denenberg retweetledi
Gary Neville reacts to Oxford Utd 0-3 Arsenal FA CUP 🏆
gooners, give me your thoughts on the performance 👀
English
Real nostalgia seeing this even though oracle ruined Solaris. I remember the days of having to download a binary package of gcc from sunfreeware just so you could compile Apache :) to all my OG engineers out there 👊🏻
phoronix.com/scan.php?page=…
English
@AMPeters06 My daughter has a quest 2. She really likes it for games but having tried it out I couldn’t imagine working out with the headset. Just too awkward and heavy to do anything high impact. For me personally every time I use it I get dizzy and have a 2 day headache. YMMV :)
English
Adam Denenberg retweetledi
After years of perf optimizations, JS is running way faster in the browser
Today, we're starting work to optimize JS perf in places where different rules apply, like Serverless and iOS devices
And this is possible because of WebAssembly 🚀
bytecodealliance.org/articles/makin…
English
@NBCSports for gods sake nobody watching the #NEWARS game cares about the manu protest. Turn the split screen off !!
English