Steven

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

So I realized Jason is talking about me here lol… I do not look at our daily media dash bc it’s either euphoria or panic. But it was nice to see the P&L the next day! Here’s some more about what went into a ~10k new customers day: - we’ve been selling to this customer for six years now, so we know them very well, and that is reflected at every single messaging point. (the counterpoint is that I’ve been working on another category for over a year now, and it’s still not cracked… understanding the customer just takes time.) - We’ve been working on this offer for like three years now. I wrote the initial VSL, and got the big idea right, but my brilliant CRO chief has been working on it literally every week. This is far from the first time we’ve hit high scores on this one. Fact is, a good offer (product/market fit, great big idea) is gonna be good for a long time, but you can’t CRO a bad offer into good one. - Notably, most the CRO efforts have been focused on Jason‘s traffic because of how much volume he can drive and how well our teams work together. So everything about our funnel, pricing, post purchase sequence, even something as unexpected as the close of the VSL… It’s all been optimized for Jason’s campaigns and pixel. Others have tried this offer and not had nearly the same success. - our products are actually great, our customer support is A+, and our fulfillment, processing and anti-fraud our battle-hardened. Days like this have ruined us in the past because of operational weakness. - Our back end is extremely robust. We have dedicated email/SMS teams, a dozen additional offers, and even phone sales team, full salesforce implementation, etc. We are competing in ad auctions with guys who will flat out lie, deep fake, and do other stuff that I won’t do for both legal and ethical reasons, so several years ago, we made the decision to invest heavily in profit drivers that are hard to build and difficult to copy. That all said, here’s where the “luck” happens (aka opportunity meeting preparedness) … What Jason is describing is what I call a “traffic honeyhole”. It’s when an offer, a buyer, a network and a specific type of ad all come together to make high scale magic. It can last for anywhere from 3 to 9 months, and most of the direct response game is spent at breakeven or loss, trying to find it. If you’re lucky and good, you get one of these a year. Really good or really lucky, you get two. The honeyhole can dry up as quick as you find it. Years ago, I was consistently spending 25k/day on YouTube with @bratinceptly and @cronag805 . It was a full 45+ minute VSL, instream as an ad. Every month, we’d shoot 8 new leads, and inevitably one of them would hit. Then we just cycled two winning offers behind them every few months. It was such a beautiful thing… then YouTube slapped like a 200% cpm penalty on any ads over 2 minutes, and our campaign died within a week! Much as I love those guys, we never made anything work together after that. Sometimes thats how it goes, but just like Rick and Ilsa will always have Paris, I’ll always have YouTube 2019 with Brat and Ian :) Here’s something else: I am not a great media buyer, and I’ve worked with many over the years - both individuals, and agencies. I feel extremely lucky to work with Jason (and to know him - everything you said back at you 100x homie). Our teams work incredibly well together, and he’s very good at running traffic for the offers we write. I’ve worked with a lot of other agencies and affiliates who have done major, major scale with others like me, and just haven’t been able to make it work. The mismatch could be anything from the teams not working well together, to them not really knowing our customer, to a simple timing mismatch - they’re focused on other stuff, and so are we, and the campaign just doesn’t get the attention it needs for scale. A huge part of this game is truly finding the right partnership between buyer and offer owner. But one thing about Jason and his team: they are obsessive. We’ve been through good times and bad with them, and whenever it’s bad, I still have confidence. I remember this talk I had with my team back in early Jan when everyone was down bad - “guys, if someone is going to figure this out, it’s Kutasi”. And hey, he did! I love these high scores too and they’re fun to celebrate, but to paraphrase Naval, we see ourselves playing long term games with long term people. And I think that mindset, as much as anything else, is what contributes to the big days.

We've currently launched over 3k ads in the last 7 days, not slop, perfect static imagery using @alexgoughcooper's framework. Although one difference we make to ensure every ad is perfect, is the framework below. 👇 The funniest part is, you can tell Claude to make it for you, it usually comes out perfect from just the URL, but it cuts hallucinations down by 90%. Comment 'STATICS' for the full framework.

For the last two years, I’ve been building a project in the shadows with my co-founder @itmebenjamin. Meet @mengotomars, the most potent and natural testosterone stack on earth. Today, I’m excited to share that we partnered with L Catterton to send Mars Men to new heights. Next stop, Mars. 🚀