Agents already run unsupervised, and they can code unsupervised too. The real question is what worthwhile work we should point these capabilities at. Nobody has really cracked that yet.
The same worthwhile things we were working on before agents. I’m personally using them to autonomously build open-source Shopify for every vertical. I set out building it before AI, but AI actually makes the dream feel achievable.
Yes we have provided custom storefronts for people running the SaaS on-prem and we have a handful of people using our cloud hosting. This is all without any marketing efforts and word of mouth. Albeit, we launched the Shopify alternative in Dec 2025 and the Toast alternative in May 2026. The gym and grocery ones in the works.
My main goal is to first get all of these open-source alternatives to start building themselves autonomously using loops and a Hermes-like scheduler before I focused on marketing. This is almost complete.
For marketing, we are building a GTM engine using an open-source CRM (Twenty). We have LLMs use the Twenty CRM API to bring in leads from X, LinkedIn, and the Web.
The cloud hosting is not the only monetization. We’re going to use these open-source SaaS to build a decentralized, interoperable marketplace where the people actually bring value, the sellers, can sell without those rent-seeking entities like Amazon taking a piece of every sale. LLMs are already going to start jumping across these marketplace moats.
The other monetization is going to be letting agents actually run these SaaS and see if they run a business autonomously. Like VendBench but an actual online business. I’m thinking of starting a designer brand, connecting to a POD (print on demand) and then let the agent create seasonal lines, handle customer service, and make sure orders are going to the POD and being processed. Doing this with restaurants and other verticals will probably need some human supervision.
Interesting. Where is this product located? If I'm looking at your profile correctly, this appears to be Openship[1], which is just a collection of starter templates from something from Nextjs and something called Keystone for each vertical. Is this what it is you are talking about?
I'm very curious how much revenue this is generating.
Yes, it’s built on the shoulders of giants, Next.js[0] and lesser-known Keystone.js[1].
Next is a full stack framework and Keystone is a CMS built on top of Prisma and GraphQL. Keystone was created by this Australian company called Thinkmill. They have used it to help businesses build custom backend systems for more than a decade. But it needed to be deployed separately from Next and they were using emotion css for their dashboard and I wanted to use Tailwind/Shadcn. So first, I had to make the Next Keystone Starter that brought in Keystone into Next so each SaaS is just 1 Next app with a built-in storefront, GraphQL API, and dashboard.
Once that was built (and it took a while tbh), I started to build the Shopify and Toast alternative. But the itch to get these built quickly and autonomously had me working on the harness in the past months and now that is nearly complete.
Here is the e-commerce[2] and restaurant[3] repos. They have a link to deployed demos you can check out as well.
As far as revenue, I don’t feel comfortable relaying that right now. We have other revenue streams like fractional CTO where companies give us equity to manage all their tech and that is quite hard to quantify. Before Openfronts being built, I built Openship, and e-commerce OMS and that has exceeded 5M orders processed since its inception in 2019. That’s not counting orders by businesses running it on-prem.
I actually posted about this vision on HN[4] when I launched Openship and the response is what kept me building.
Second, take this for what it is: your product may not be compelling in its current form. Building it to many different markets will not make it compelling. If you had a stronger revenue, please share it. This sounds incredibly thin.
Third, dont mistake building the same thing 20 times for different verticals for bonifide software skills. When a SWE builds the thing they have built before its usually to learn a language which is the easiest part of software. There is a reason a common adage in software is "9 women cant make a baby in a month". Breath is no replacement for depth.
That’s the neat part, you can use it headlessly. The built in dashboard and storefront are using the GraphQL API but you can deploy your own external dashboard and storefront using the same API.
We’re also very bullish that the chat interface is the universal UX now. Instead of sifting through the dashboard to change a product price or sell in a new region, you can use the built-in agent and just tell it to do that. Every Openfront comes with an MCP server that interfaces with the API so the agent can literally do anything you can do using the dashboard and API. This is where an agent running the business autonomously comes in.
And even then if you’re not satisfied with the backend API for each vertical, these Next apps can be forked and adapted to tightly fit your business instead of you messing with configs, you can make the app your own.