{"slug": "is-open-mercato-ai-slop", "title": "Is Open Mercato AI Slop?", "summary": "A developer who won the Best Cezar Feature track at the Open Mercato HackOn in Wrocław concluded that Open Mercato is not AI slop, describing it as a plausible model of greenfield software development built around specs, reusable skills, isolated execution and human review. The author, who has submitted ten PRs to Cezar with only two merged upstream, also shipped a QR-code-plus-private-mesh feature that lets a remote Cezar instance open its mobile cockpit on an iPhone via Tailscale without a new account or password.", "body_md": "is-open-mercato-an-ai-slop\n\n# Is Open Mercato AI Slop?\n\nI went to the Open Mercato HackOn to find out whether agent-built software is the future of engineering or just AI slop at industrial scale. A hackathon win, ten Cezar PRs and several clouds later, I have an answer.\n\n**TLDR:** Open Mercato is not AI slop. Quite the opposite. After using it in anger, my conclusion is that it shows one plausible future of greenfield software development - agentic AI engineering built around specs, reusable skills, isolated execution, review and human decisions.\n\n## The most useful little hack I shipped this week\n\nYesterday I shipped probably the smallest feature I have built for Cezar so far, and somehow it changed the way I use it more than many much larger features. Nothing here is revolutionary on its own. I connected three things that already almost fit together: **Cezar + a QR code + a private mesh network.**\n\nCezar already had a mobile-friendly web cockpit. The missing part was making the route from a remote Cezar instance to my phone stupidly simple. Now I can start Cezar on a remote machine, get a QR code directly in the terminal, scan it with my iPhone and - bang - the cockpit is on my phone.\n\n```\nremote machine\n      ↓\n   Cezar\n      ↓\nprivate mesh\n      ↓\n QR in terminal\n      ↓\n     📱\n```\n\nThe implementation adds an explicit trusted-host mechanism for private fronts and a scannable startup URL. Tailscale is my network of choice, but the design is intentionally not Tailscale-specific. A tailnet, WireGuard mesh or a similar private network can provide the transport. Cezar stays in local mode instead of becoming a publicly exposed authenticated service.\n\nMy setup uses Tailscale because the Personal plan is currently free and extremely convenient for this kind of private network. There are separate plan limits depending on the kind of resources you use, so read the pricing page before deploying your personal hyperscaler. 😎\n\nThe important part for me is the developer experience. No new Cezar account. No new Cezar password. No copying URLs from a terminal into a phone. Scan, open, work.\n\nWhen development is happening in the cloud and agents are distributed across remote machines, that tiny change matters a lot. Thanks, Tailscale. You changed a surprisingly large part of how I work. 🫶🏻\n\nPRs:\n\n[https://github.com/open-mercato/cezar/pull/1070](https://github.com/open-mercato/cezar/pull/1070)\n\n[https://github.com/open-mercato/cezar/pull/1071](https://github.com/open-mercato/cezar/pull/1071)\n\n## I went to Wrocław to test a hypothesis\n\nA few days earlier I was at the Open Mercato HackOn in Wrocław. Together with [Mateusz Wiatrzyk](https://pl.linkedin.com/in/mateusz-wiatrzyk-91637516b), as part of #aveCezar, we won the **Best Cezar Feature** track and came second in People’s Choice.\n\nMateusz published a very good write-up about the whole weekend here:\n\nThe funny part is that we were developing Cezar using Cezar. That sounds like a marketing sentence. Unfortunately for my skepticism, it actually worked.\n\nAfterwards I asked [Patryk Lewczuk](https://github.com/pat-lewczuk) about potentially developing further with the Open Mercato Core Team. The answer was basically no.\n\nWhich I understand. At the time of writing I have ten PRs for Cezar and only two of them have made it upstream. Apparently winning the Cezar track at a hackathon does not automatically unlock a secret employment contract.\n\nI’m 36 and still this naive. 🤡😎\n\nI was devastated for approximately two minutes. Then I went back to my Cezars.\n\nMateusz did too. His #1045 adds Jira and Linear tracker integration, including browsing issues, launching workflows with ticket context and tracker-triggered automations. His #1047 is another substantial piece - a workspace dashboard with activity, reported usage and costs, outcomes, exports and observability.\n\n[https://github.com/open-mercato/cezar/pull/1045](https://github.com/open-mercato/cezar/pull/1045)\n\n[https://github.com/open-mercato/cezar/pull/1047](https://github.com/open-mercato/cezar/pull/1047)\n\nAutonomous development driven from issue trackers is getting uncomfortably close. And all of this can eventually sit in Cezar on a phone, while the actual work happens somewhere in the cloud. 🤯\n\n## My factory is becoming geographically distributed\n\nCurrently I use four public cloud providers:\n\n- [https://www.hetzner.com/](https://www.hetzner.com/)\n- [https://upcloud.com/](https://upcloud.com/)\n- [https://www.ovhcloud.com/](https://www.ovhcloud.com/)\n- [https://www.digitalocean.com/](https://www.digitalocean.com/)\n\nAnd I have my own thing in development. It will probably live at:\n\nThis is absolutely not an announcement, despite the fact that I am announcing its existence in a public blog post.\n\n`tiny-cloud` is still very much WIP. My control plane and scheduler are a mess. Go is new to me. There will be more on that later. 🤓 The idea is simple: I want a tiny control plane for machines running my agent workloads.\n\nRight now my agents are already distributed across three continents.\n\nWhy? I like redundancy. That’s all. 🐳\n\n## Then Open Mercato launched a cloud\n\nDuring HackOn, Open Mercato also presented [Open Mercato Cloud](https://openmercatocloud.com/). It is essentially a browser-accessible development environment aimed at AI engineering - sandbox infrastructure without requiring the developer to build and operate the infrastructure layer personally.\n\nAs winners of the Cezar track, Mateusz and I received three months of Sandbox access. Combined with the month available to hackathon participants, that gives us a rather comfortable playground for experiments.\n\nWe received access to the Developer tier. My first reaction was that the price feels a bit high for an individual developer.\n\nThen again, maybe I am not the target developer. 🤣\n\nI already have accounts at four cloud providers and I am writing my own control plane for fun. That is not normal customer behavior. For somebody who wants to build software instead of spending Saturday debugging a scheduler, Open Mercato Sandboxes make much more sense.\n\nAnd I have to give them credit: the product influenced my own architecture. After probing the Sandbox, I changed several assumptions in the control plane and scheduler for tiny-cloud.\n\nDominik Pałatyński, one of the main people behind Sandboxes, also thanked me directly for the auto-scaling governor contribution I built for Cezar during the hackathon:\n\n[https://blog.cygankiewicz.com/en/cezar-agent-orchestrator/](https://blog.cygankiewicz.com/en/cezar-agent-orchestrator/)\n\nThat felt good. 🙏🏼☺️\n\nI may write a proper Sandbox review one day.\n\n## This blog is twelve days old\n\nI started this blog on September 13, 2026. Twelve days later, I already have readers in Europe, North America, Asia and South America.\n\n2026 is crazy. Maybe it is just me, but I have never had to update my mental model this quickly. Products change, models change, economics change and my own plans change. The velocity is ridiculous.\n\nMy previous post, [Ethics of Agent Exploitation](https://blog.cygankiewicz.com/en/ethics-of-agent-exploitation/), got surprisingly good feedback. One sentence in particular stayed with Mateusz:\n\n“But for a huge class of small software projects, the marginal cost of getting to the first useful version is approaching something that feels very close to zero. And in my opinion, that is awesome.”\n\nHe told me that this sentence moved him. But there is another side to it.\n\nFor many developers, programmers and people working broadly in IT, that sentence does not necessarily sound awesome. After another two days of thinking about it, I understand that ambiguity much better.\n\n## I still think we are heading toward extraordinary abundance\n\nI am not a prodigy or a fortune teller. But I do have a working hypothesis.\n\nI think we may be heading toward a level of abundance that would have been difficult to imagine even recently. It will not be distributed evenly. It never was. I have plenty of complaints about our corporate-capitalist reality. 🤮 But complaining about the distribution mechanism does not make the technological shift disappear.\n\nSo what do we do?\n\nI started a blog. Yesterday a colleague told me: “I thought blogs were dead.” He is wrong, but there is something important hidden in that observation. For him, blogs are dead because he does not read blogs. For me, they are obviously alive because I love them. There are fascinating individuals all over the world writing on their own little pieces of the internet instead of putting every thought into Instagram, Facebook, LinkedIn or X.\n\nAnd still - blogging is difficult for me. I started writing this post at 04:40 AM CET. At 07:30 AM it was still work in progress. I write these posts in English first, not because English is faster for me. It definitely is not. I do it because I want my English to become better.\n\nNot everyone needs to become a blogger. Not everyone needs to become a programmer. Not everyone needs a CS degree. And despite what my current browser history may suggest, not everyone needs to become a **full-stack AI architect**. 🤪\n\nThere will still be an enormous amount of work in services. Probably very strange services.\n\n## I need a cat concierge\n\nLet me give you a deliberately stupid example. I have a cat. 🐈 I love him very much, but I have better things to do than physically taking him to a routine veterinary appointment.\n\nSo what do I actually want? A **cat concierge**.\n\nA human picks him up, takes him to the vet and sends me a structured report afterwards. AI in the loop. My own AI probably processes that report before the cat arrives back home.\n\nYes, I have something with reports. I cannot help it. Almost everything I do in life eventually becomes data.\n\nThat job is not “programmer”. It is not “prompt engineer”. It is a service built around trust, physical presence and responsibility, augmented by software that becomes almost free to create.\n\nI suspect we are going to see a lot of things like that.\n\n## So - is Open Mercato AI slop?\n\nThis is actually why I went to the hackathon. I wanted first-hand experience.\n\nOpen Mercato talks openly about agentic engineering. The project describes itself as an AI-engineering foundation framework and emphasizes architecture-aware agents, reusable skills and spec-first development.\n\nThat sounds great in a README. I wanted to see what happens when people actually use it.\n\nMy answer after HackOn is:\n\n**No. Open Mercato is not AI slop.**\n\nAnd importantly, I do not say this because every piece of code is perfect. It isn’t. Nothing interesting is.\n\nI say it because the interesting part of Open Mercato is not “AI generated a lot of code”. The interesting part is the **system around generation**.\n\n### Open Mercato itself\n\nThe main [Open Mercato](https://github.com/open-mercato/open-mercato) framework is an impressive codebase for CRM, ERP and commerce applications.\n\nPerfect? No. Finished? Also no. It is WIP, and that is visible.\n\nBut its architectural bet makes sense to me: if agents are going to generate a significant part of a greenfield system, then architecture, conventions and specifications need to exist **before** the agent starts inventing them.\n\nThe project calls this spec-first development and an architecture-aware AI harness.\n\nThis is almost the opposite of slop.\n\nAI slop is:\n\n```\nprompt\n  ↓\nhuge blob of output\n  ↓\nship it 🤡\n```\n\nAgentic engineering should look more like:\n\n```\nintent\n  ↓\nspec\n  ↓\narchitecture\n  ↓\nagent\n  ↓\nisolated implementation\n  ↓\ntests\n  ↓\nreview\n  ↓\nhuman decision\n  ↓\nmerge\n```\n\nThat distinction matters.\n\n## Cezar\n\n[Cezar](https://github.com/open-mercato/cezar) is a GOAT. 🐐\n\nI already wrote an entire post about it, so I will spare you another love letter. It runs coding agents in parallel, gives tasks isolated Git worktrees, provides queues, workflows and live visibility, and works locally or on a VPS.\n\nFor me it has become the execution layer of my little factory.\n\nNothing more to add. 🐐\n\n## Open Mercato Skills\n\nThis is probably the biggest mindfuck for me:\n\n[https://github.com/open-mercato/skills/](https://github.com/open-mercato/skills/)\n\nBefore HackOn, I almost never used Skills. I did not really have a place for them in my workflow. I had also seen comments online dismissing skills as something for amateurs, and for a while I bought into that framing.\n\nI was wrong.\n\nOpen Mercato Skills package repeatable engineering procedures as agent-readable instructions: PR creation, code review, CI stabilization, spec writing, integration testing, merge management and more. The only reason I finished my Cezar feature during the hackathon weekend in anything resembling a controlled process was their Skills.\n\nThat changed my opinion completely.\n\nThe model matters. The prompt matters. But increasingly the real leverage is:\n\n**what procedures does the agent already know how to execute reliably?**\n\nThat is much closer to organizational knowledge than prompting.\n\n## Sandboxes\n\nSandboxes are the third piece. They are probably not optimized for someone like me, because I already enjoy operating infrastructure and, apparently, consider writing a scheduler in Go recreational activity.\n\nFor businesses, teams and developers who do **not** want to maintain their own control plane, the proposition is much clearer.\n\nIt works. That has value.\n\nIf you are a full-stack person who enjoys doing everything yourself, paying someone else for this may initially look funny. Then you realize that they are selling exactly the part of the stack you should probably stop rebuilding.\n\nI am still not sure I am the customer. I am quite sure there are many people who are.\n\n## So what is Open Mercato actually showing?\n\nThis is the part I find more interesting than CRM or ERP.\n\nOpen Mercato is an experiment in what software engineering looks like when agents become normal participants in the development process. Not autocomplete. Not “write me a React component”.\n\nAgents receiving specs. Agents following shared skills. Agents working in isolated environments. Agents reviewing other agents. Humans deciding what goes upstream.\n\nThat is the thesis I came to Wrocław to test.\n\nMy conclusion is that **greenfield software development is moving toward spec-first, agentic engineering**.\n\nNot every project. Not tomorrow. Not without human judgment. But directionally, yes.\n\nAnd that is not AI slop.\n\nSlop is uncontrolled output.\n\nThis is an attempt to engineer the factory.\n\n## There is one more thing\n\nSince apparently there is no obvious job-shaped slot for me in my country 😎, I decided it is time to create one.\n\nI am incorporating.\n\nFor years I had my head in the clouds about where that should happen. Switzerland? Luxembourg? Malta? UAE? Delaware LLC?\n\nI have spent an unreasonable part of my life reading about taxes and international commerce. Strange interests for a kid, I know. I cannot do anything about it. 🤷🏻\n\nBut today I have clarity.\n\n**Gliwice, Poland.**\n\nA Polish `sp. z o.o.`.\n\nTaxes suck, obviously. But my father used to say something that stayed with me:\n\n“If you pay taxes - even high taxes - that is actually awesome. It means you have revenue and profits.”\n\nFair enough.\n\n## Ventures Originals\n\nThe company will be AI-native.\n\nOn August 9 I watched **Aula Polska #194: Fireside Chat o Agentach AI | Bartek Pucek & Piotr Nowosielski**:\n\n[https://www.youtube.com/watch?v=w52Q64HXyOU](https://www.youtube.com/watch?v=w52Q64HXyOU)\n\nOne framework from that discussion that stuck with me was the distinction between companies that lag on AI adoption, companies that embed AI into existing operations and companies that are genuinely AI-native.\n\nI know which one I want to build.\n\nThe working direction for [Ventures Originals](https://venturesoriginals.com/) is AI research around:\n\n- safety\n- operations\n- inference\n- economics\n\nAnd the first product thesis is increasingly clear.\n\n## An orchestrator of orchestrators\n\nThe execution layer already exists. Cezar can be one runtime. Others can exist beside it.\n\nThe product I am interested in sits one level above them:\n\n```\n        Orchestration Control Plane\n\n        ┌─────────────────────────────┐\n        │ Desired state / Policies    │\n        │ Scheduling / Routing        │\n        │ Budgets / SLOs / Security   │\n        │ Registry / Discovery        │\n        │ Observability / Audit       │\n        └──────────────┬──────────────┘\n                       │\n           ┌───────────┼───────────┐\n           ▼           ▼           ▼\n        Cezar       LangGraph    Temporal\n        runtime      agents       workers\n           │           │           │\n      Claude/Codex  models/tools  services\n```\n\nA control plane for orchestrators. Not another agent UI. Not another wrapper around one model.\n\nPolicies, routing, scheduling, budgets, SLOs, security, observability and discovery across execution systems.\n\nI know that is not easy.\n\nThat is precisely why I am interested.\n\n## I am looking for a co-founder\n\nI am not in a hurry. The kind of person I would particularly like to hear from is rare:\n\n- a technical founder with meaningful exit experience\n- a former CTO or staff-level engineer from a strong acquired company\n- somebody unusually deep in distributed systems, AI infrastructure or capital deployment\n- or, because life should remain interesting, a Bitcoin whale or Solana wizard who actually operates infrastructure rather than only posting charts 😎\n\nThe skill overlap I care about most:\n\n- distributed systems\n- effective capital deployment\n- digital transformation\n- AI\n\nAt this stage, what I need first is expertise and approximately **20 minutes of conversation per week**. No pitch deck circus. No need to rush.\n\nMy current incorporation sketch is PLN 100,000 of initial capital. I am considering reserving a 5% founding stake for the right co-founder at a PLN 5,000 contribution, subject to the actual incorporation documents and legal/accounting setup.\n\nA Polish individual or company would make the mechanics easiest, but geography is not a hard constraint. If you are in Asia or North America, that is fine too.\n\nThis is an experiment.\n\nIf Ventures Originals cannot become profitable within one year of incorporation, I will dissolve it.\n\nSimple.\n\n## See you after a small offline window\n\nI will be away from my computer for the next week or two, so I may be slower to respond. I will still keep an eye on my inbox.\n\nThe factory can survive without me for a while.\n\nI hope. 🏭🤖💪🏻", "url": "https://wpnews.pro/news/is-open-mercato-ai-slop", "canonical_source": "https://blog.cygankiewicz.com/en/is-open-mercato-an-ai-slop/", "published_at": "2026-09-25 00:00:00+00:00", "updated_at": "2026-09-25 07:58:53.090401+00:00", "lang": "en", "topics": ["ai-agents", "ai-tools", "developer-tools"], "entities": ["Open Mercato", "Cezar", "Mateusz Wiatrzyk", "Patryk Lewczuk", "Tailscale", "Wrocław", "GitHub", "Jira"], "also_reported_by": [], "alternates": {"html": "https://wpnews.pro/news/is-open-mercato-ai-slop", "markdown": "https://wpnews.pro/news/is-open-mercato-ai-slop.md", "text": "https://wpnews.pro/news/is-open-mercato-ai-slop.txt", "jsonld": "https://wpnews.pro/news/is-open-mercato-ai-slop.jsonld"}}