Launching today
Running even one online store is a full-time job. SellerClaw is a team of AI agents that runs it for you: specialized agents for product sourcing, store management, and advertising, coordinated by a supervisor you direct. Tell it what to sell — the agents build listings, manage ads and pricing, and handle fulfillment and support across Shopify, eBay, and more. You stay in control: every action is visible and approvable, and you set how much runs on its own. Free to start.
SellerClaw
Hey Product Hunt! 👋
Artem here, co-founder of SellerClaw. My journey in e-commerce started when I was 18, selling on Amazon. Later, I co-founded Zonesmart, where we helped over 1,000 sellers scale across borders before exiting in 2022.
Despite all the tech we had, one thing never changed: running a store is a relentless, manual grind. Sourcing, pricing, managing ads, and handling support across multiple channels like Shopify and eBay is a 24/7 job. My co-founder Kamil and I realized that to truly scale, we didn't need more tools - we needed more hands.
That’s why we built SellerClaw - a team of AI agents that actually runs the store for you.
🛠 Key Features:
👉 Specialized Agents - Dedicated AI agents for product sourcing, store management, advertising, and customer support.
👉 The Supervisor Model - You direct a "Supervisor" agent who coordinates the rest of the team.
👉 Multi-Channel - Seamless operations across Shopify, eBay, and more.
👉 Human-in-the-Loop - You stay in control. Every action is visible and can be set for your approval before it goes live. No "rogue" AI pricing.
Who is this for?
- Solo-founders who want to run multiple stores without hiring a massive team.
- Cross-border sellers struggling with local payment methods, customs, and international support.
- Growing brands that want to automate the "boring stuff" to focus on brand strategy.
Our Goal & Offer 🎁 We are in the early stages and launching to real sellers this week. We believe this changes the economics of e-commerce - decoupling revenue growth from headcount.
SellerClaw is free to start, and no credit card is required.
We need your feedback! As we refine our agents, we want to know:
Which part of your e-commerce workflow is the biggest "pain in the neck" that you'd hand over to an agent today?
What specific platforms (beyond Shopify/eBay) should our agents learn next?
We’ll be here all day to answer your questions. Let us know what you think! 👇
@artem_kosilov Congrats on the launch, Just a quick que: when agents operate cross-border, how do you handle multi-currency and local payment method edge cases without forcing the user to manually override per market?
SellerClaw
@swati_paliwal
Thanks! Good question. Short answer: we're not a Merchant of Record, so multi-currency and local payment methods never actually land on our plate.
All the money between buyer and seller moves through the marketplace's own payment rails, not ours. A US seller on Amazon, eBay, or Etsy gets paid straight to their bank account. Sellers in other regions usually settle through the marketplace's payment partner (Payoneer and similar), and currency conversion and local payment edge cases are handled there.
SellerClaw sits on top of that. We automate the day-to-day operations, but we don't touch the financial settlement between the buyer and the marketplace, so there's nothing for the user to override per market.
SellerClaw
@swati_paliwal @tolstov_gleb
One thing to add: beyond settlement, there's the operational layer where we do touch numbers — supplier cost, sell price, margin. The agent keeps each in its own currency and converts the cost into the store's currency when pricing or computing margin, so a 30% margin stays 30% and profit shows in your store's currency. So mixed currencies reconcile even on the part we own.
SellerClaw
@swati_paliwal Thank you so much!
@artem_kosilov I'm getting an error when trying to connect google ads.
SellerClaw
@ravi_sheth1 Sorry to hear that, please send us a screenshot of the error to hello@sellerai.com - we will fix it right away.
@artem_kosilov Congrats on your launch - very cool product! This is very timely as I'm about to move one of my companies over to Shopify. Currently, it's single channel - would you say SellerClaw is overkill or would it be helpful?
SellerClaw
@anna_ludwinowski Absolutely — it can still be very helpful even for a single-channel Shopify store. It’s not just about multi-channel sync; it can save a lot of time on day-to-day operations, especially if you’re running the store solo.
Things like product research, listing updates, order workflows, customer replies, pricing checks, and ad-related tasks are all areas where it can take work off your plate pretty quickly.
Product Hunt
SellerClaw
@curiouskitty
Great question, though worth clarifying which side we're on. SellerClaw is the seller-side agent, it works in place of a marketplace manager (listings, pricing, ads, inventory, customer replies), rather than the buyer-side agent shopping through chat.
That said, the core challenge you're describing, keeping a promise consistent from chat → checkout → delivery, is exactly the kind of thing we're building toward. Our current focus is SellerClaw, but a follow-up product, SellerCart, is designed to address the agentic-shopping side directly.
Even today the same discipline applies on our end: the agent never invents numbers, it reads from the platform when they're needed, inventory stays synced, and settlement runs on the marketplace's own rails. So what the agent promises always reconciles with the system that actually fulfills it.
SellerClaw
@curiouskitty Thank you for your support; it means a lot to us.
SellerClaw
@curiouskitty Totally agree — keeping the promise consistent end-to-end is the hard part.
On the seller side, I think the biggest operational risk is availability and post-purchase state staying in sync across systems. Totals/tax/shipping can usually be computed deterministically at checkout, but inventory, fulfillment status, cancellations, and returns are where things drift fast if the agent is not grounded in live system data.
Our approach is to keep the agent decision-making layer separate from the source-of-truth transaction layer: the agent can decide and act, but the final numbers, inventory state, order status, and settlement always come from the platform or connected system itself. So the promise is only made off live data, and every action has to reconcile back to the system that will actually fulfill it.
Most "AI runs your store" pitches mean "AI drafts your listings and reminds you to restock." The multi-channel part is where it gets genuinely hard, because inventory state has to stay consistent across Amazon, Shopify, wherever else, and any lag there turns into oversells or missed repricing windows. Curious whether SellerClaw owns that sync layer directly or sits on top of something like a middleware feed. Also wondering how it handles channel-specific policy differences, like Amazon's title length rules versus what Shopify tolerates, when the same SKU needs to live in both places.
SellerClaw
@fberrez1 SellerClaw connects directly via API where it exists, and through browser automation where it doesn't, without a feed aggregator in between.
Inventory and pricing sync runs through the Supplier Agent on that layer. The lag window question across Amazon and Shopify running simultaneously is a fair stress test and worth a detailed answer in the comments here. On channel-specific content: listings are generated per-channel, not from a single template. How Amazon's title length constraints get handled versus Shopify is a good follow-up to press on.
SellerClaw
@fberrez1
Really good question. On inventory sync: yes, we update stock levels across platforms. If someone buys a unit on Shopify and you're running FBM (fulfillment by merchant), the count on your warehouse drops by one everywhere it's listed.
The nuance is your shipping model. If you use a third-party fulfillment provider, that service usually has its own stock-sync layer already. Where SellerClaw really earns its keep is when you ship from your own warehouse and don't have that middleware, our software handles the cross-channel sync directly. And we also have our own fulfillment solution, so if you want it fully connected, we can wire the fulfillment and the agent together end to end.
On channel-specific policy differences: our agents are trained specifically for the requirements of each platform. They account for the full set of rules a given marketplace imposes and adapt every listing to fit them, so the same SKU lands correctly whether it's on Amazon or Shopify. On top of that, we pull from external data sources to build SEO descriptions, not just the marketplace's own algorithms. Today we use DataForSEO on Shopify, and we're rolling out Helium 10 keyword data for Amazon next, so your listings are optimized against real external analytics and have a shot at ranking number one.
SellerClaw
@fberrez1 Thank you. We look forward to hearing your feedback 👍
SellerClaw
@veerhunt_agai Thank you for breaking that down so specifically. Pricing is part of the agent scope and you configure what it optimizes for, with guardrails on what it can change on its own.
SellerClaw
@veerhunt_agai Yes — it depends on where the competitor pricing lives. If the platform exposes usable pricing data, the agent can pull it via API; if not, it can use browser automation to read prices directly from the competitor’s site.
On the optimization side, the user can choose the target metric, but the default logic is to maximize Buy Box win rate while still respecting the minimum margin threshold set by the user. So it’s not just a one-time suggestion — it can operate as an actual repricing loop within the guardrails you define.
SellerClaw
@veerhunt_agai Good question. Short answer: API where the marketplace exposes pricing, browser automation where it doesn't, so you're covered even on platforms that lock their data down.
Default logic targets Buy Box win rate but never below the margin floor you set, and you can switch the target metric per your strategy. It's a live repricing loop inside your guardrails, not a one-off suggestion.
Happy to go deeper on the thin-margin case if useful.
There are already workflow automations and AI copilots in e-commerce. What makes your multi-agent ‘store operating system’ fundamentally more than orchestration on top of existing tools—and what is the hardest real-world edge case where your system still fails today?
SellerClaw
@md_khayruzzaman Great question. The difference for us is that SellerClaw is not just a workflow layer that calls tools when a user asks — it is built to operate as an actual execution system with persistent context, specialized agents, and a supervisor layer coordinating them around business goals and guardrails.
So instead of “suggest next action” or “run this automation,” the system can monitor signals, decide, and act across pricing, listings, fulfillment, ads, and customer workflows within boundaries the merchant sets. That’s the jump from copilot/orchestration to something closer to a store operating system.
The hardest edge case today is when the real world changes faster than connected systems reflect it — for example inventory, supplier availability, or marketplace state drifting out of sync across multiple sources. That’s where any autonomous system can still fail if it acts on stale data. Our approach there is to keep platforms and connected systems as the source of truth, add guardrails around what the agent can do on its own, and require reconciliation before critical actions.
Well done team! Question on whether the browser-automation half failing silently (eg - the marketplace ships a UI tweak, the agent thinks it repriced or paused a listing and nothing actually landed). How do you verify an action took effect on the channels you drive through the browser? How fast do you catch it when a layout change breaks the flow?
SellerClaw
@artstavenka1 The browser path exists for channels where there's no API to hit. For those, actions are logged and failures come through as Telegram notifications before the next cycle runs.
When a marketplace ships a UI update that breaks a flow, the agent reaches an error state and flags it. How fast that gets caught depends on how the failure looks. A clean error surfaces faster than a silent wrong-page interaction. We haven't fully solved that and won't pretend we have.
SellerClaw
@artstavenka1 Sharp question, and exactly the right thing to poke at.
The browser path only exists for channels that don't expose an API, so it's the fallback, not the default. For those, every action is logged, and failures surface as Telegram notifications before the next cycle runs, so a broken step doesn't just disappear into the void.
When a marketplace ships a UI change that breaks a flow, the agent hits an error state and flags it. How fast we catch it honestly depends on how the failure presents: a clean error surfaces immediately, while a silent wrong-page interaction (the agent "thinks" it repriced but nothing landed) is the harder case. That's the exact gap you're pointing at, and we haven't fully solved it, won't pretend we have. Tightening post-action verification on the browser-driven channels is an active area for us.
Appreciate you raising the silent-failure case specifically. It's the one that matters most and the one most people don't think to ask about.
SellerClaw
@artstavenka1 Thank you✨
FlowMarket
Congrats on the launch! SellerClaw tackles a real pain point, managing multiple e-commerce channels is overwhelming, and having a team of AI agents handle the heavy lifting while keeping you in control is a smart approach. My question for you: how does the supervisor agent resolve conflicting priorities between specialized agents, say when the advertising agent pushes for higher spend while the pricing agent recommends thinner margins?
SellerClaw
@davitausberlin The Supervisor agent doesn't resolve this unilaterally. When two agents are pulling in opposite directions on something consequential, it surfaces the conflict for your approval rather than making the call. Neither agent can push through an irreversible action without confirmed context.
You set the budget rails and the goals each agent operates within. Genuine conflicts outside those rules come to you.
SellerClaw
@davitausberlin Great question. The short answer: the supervisor resolves it through unit economics, not by picking a favorite agent.
The moment we list a product, we map every non-recoverable cost: category commission, fulfillment and shipping. (Those differ by model, FBA carries Amazon's own fees, while self-fulfilled orders on Shopify or other channels run on USPS, UPS, FedEx, or FBA rates depending on item dimensions and the state you ship from.) Once that full P&L picture is in place, the supervisor knows the allowable ACoS/TACoS and exactly how much of the margin can go to ads.
So in your example, profitability comes first. The pricing and advertising agents don't fight, they operate inside the same economic envelope. The system won't green-light ad spend that pushes a SKU into the red. The one deliberate exception is an investment window, where the supervisor may approve heavier ad spend on purpose to gather early reviews and build organic ranking that pays back later. But that's a conscious call, not an agent winning a tug-of-war.
In short: economics sets the boundaries, and the agents optimize within them rather than against each other.