Tabstack by Mozilla
Extract web data and automate browsers, no scraper required.
Start new thread

Tabstack Browser Automation - Automate the web in your app or agent, no browser to host

by•
Give /automate a task in plain English and it drives a real browser to do it: navigate a site, click through a multi-step flow, fill a form, reach a page that only renders after interaction. The result streams back in one API call. It's an API you call, not a framework you install. Browser and LLM included, nothing to host, no concurrency ceiling. Accessibility-tree automation spends 60 to 80% fewer tokens than screenshot-based agents. Built by Mozilla. Ephemeral, no training on your data.

Add a comment

Replies

Best
Maker
📌

Hey Product Hunt 👋 Tessa here from

Most web automation tools hand you a browser and leave the hard parts to you: hosting it, driving it, and paying for vision tokens on every screenshot. Automate flips that. You send a task in plain language plus a URL, we run the browser on our side, and you get finished output back in one streaming API call. Drop it into an agent or wire it into an app you already ship in a matter of a few minutes.

It can book a meeting, fill a multi-step form, or pull data from a page that only renders after you click around. The engine reads the page's accessibility tree instead of screenshots, so it spends 60 to 80% fewer tokens than screenshot-based agents. That's a different cost model once you're running this at scale.

Free to get started at

If you're building agents or adding web actions to an app, I'd genuinely love to know: what's the first task you'd point it at? I'll be here all day answering everything. Thank you for taking a look 🙏

 Probably something like filling out a form that's different on site.

Curious about the failure side though. If the task has five steps and it gets stuck on step three, does the response tell you where it stopped, or is it more of a pass/fail? Asking because with a regular scraper you can at least see which selector broke, but with a natural-language task I wouldn't know where to start looking.

Maker
we have interactive mode, so if it gets stuck at step three, it can stream back and ask for help! It actually streams every step along the way, too, so you know what’s going on the entire run.
Maker

   you can learn more about Interactive Mode here btw (currently in beta):

hope it helps!

Maker

   great addition, Flo!

 For the /research endpoint, when it returns cited answers, does it verify the citation actually still supports the claim at the time of the call, or can it cite a source whose content has since changed or gone stale?

 Hosting headless browsers is the worst part of every automation stack I've ever run, so if you've genuinely abstracted that away with real reliability, this is a big deal. How do you handle sites with aggressive bot detection?

Maker

We're launchmaxxing on Product Hunt! Browser Automation is the 6th launch here, and it's the most ambitious one to date. No pressure.

S/O to and team for the great work. Looking forward to seeing what the community is building with it.

Get started for free:

Maker

This is a really nice tool! I would like to ask about pricing: since it is pay-as-you-go on credits, can I set a hard spend cap per task or per month? My worry with autonomous agents is one looping and quietly running up credits. Thank you!

Maker

 great question re: pricing!

The team recently updated it to handle this exactly. It now includes a free 10k credit trial, pay-as-you-go individual plan ($0.35 / 1k credits), and monthly subscriptions (starting at $99/ month, 500k credits included). Hope fully this brings more control and flexibility.

This blog post details the reasoning:

Maker

 Curious what your preferences are? Pay-as-you-go plans or monthly subscriptions?

See this related discussion in /p/tabstack:

Maker

 Yeah, you can cap both.

Per month: The free Individual plan is hard-capped at $99/month (~282,857 credits) and requests just stop there, so it can't quietly bill past it. On Team and Pro you set a spend threshold in the console (by percentage or a dollar amount) and pick Notify and Stop to halt requests when you hit it.

Per task: For the looping-agent worry specifically, /automate takes a maxIterations param that bounds how many steps a single run can take, so one task can't spin forever. Every call also reports its action count, so you can see what each run cost.

And if this is for personal use, the free tier is pretty generous: every account starts with 10,000 credits, no card, and Individual stays pay-as-you-go after that, so you only pay for what you actually run. Plenty of room to build and experiment before you're paying anything.

Thanks for asking, it's a smart thing to check before pointing an agent at anything.

 Thank you, that is a thorough answer - the spend cap and maxIterations are exactly what I wanted to hear.
On your question: for now I would prefer pay-as-you-go. As a small team still experimenting, I like paying only for what I actually use, and would move to a subscription later once usage is steady and predictable

Maker

As a small team still experimenting, I like paying only for what I actually use, and would move to a subscription later once usage is steady and predictable

 this makes so much sense! also mentioned the (generous) free 10k credits to test the waters, build a proof of concept, and see exactly how fits into your stack before spending a dime.

Get started (for free) at - Enjoy!

Congrats on the launch and good luck!

Maker

 thank you, friend! Appreciate your support!

Maker

 thanks for your continuous support! it means the world

Great product!

Maker

 thanks for your support, Darko! you rock

Maker

 much appreciation!

You had me at fewer tokens! 😁

Maker

friends don't let friends waste tokens 🫶

Maker

  exactly!!!!!

Maker

 right?!

Super cool! Is it safe to use with authenticated workflows? What's the security model?

Maker
we do not currently have session or credential management built into the API functionality. However, you can use the open-source version of this endpoint locally if you wanted to try authenticated workflows. Authentication capabilities is something we are considering, though.
Maker

 thanks for the support, Raphaël! appreciate it

Hi Tessa, the fact that whatever I pull off the web stays mine is what makes this stand out to me. Anyone who has watched a scraper quietly break overnight will feel the relief here.

Maker

 right?! Mozilla for the win. Their ethics around humans owning their data and being privacy-focused is a huge win for developers using Tabstack.

 🙏🙏

Maker

The fact that whatever I pull off the web stays mine is what makes this stand out to me.

Spot on. There are multiple products in the browser automation category. is different. Private by default. Transparent by design. Every call runs on a Mozilla-backed platform. The pages you extract, the answers you research, and the tasks you automate stay yours, handled responsibly and never used to train models.

Not sure that my feedback can be useful, because I`m not too deep in the topic. But I love homepade of your website - it is clear and has all information needed. Keeping instruction near the start button was a very smart decision.

Maker

 you just made my heart so happy! That website is a labor of love. I've been building each stack page as we've launched on Product Hunt. I strategized the approach, wrote the messaging, designed it (from where it was), and built it. I'm so proud of the work and I'm really really thankful for your kind words. Let me know if you try Tabstack or if you need anything. Always here to help. 🫶

 Tessa, it's so great that you put so much love into your product and made it so thoughtful! I always admire people who fearlessly bring new ideas into the world.

Wishing you all the best with it! And I'm curious - what happens after the Product Hunt launch? Are you taking a break to collect feedback first, and then jump straight into improvements?

Maker

What happens after the Product Hunt launch?

We start planning the next launch 🔥

Maker

 we are continually taking in feedback. Its a focus for our GTM efforts to truly understand the market and give people what they actually need and want. Like said, though, plan the next launch!

Maker

S/O to for the awesome work crafting !

Maker

 😍

Feels like a small tool but solves a daily frustration pretty well. How does this compare with just using Chrome tab groups in real workflows?

Maker
Exactly. I have an agent OS for working day to day and a Hermes agent. I have Tabstack installed in both so it consistently uses Tabstack when making calls. It’s so handy to have as a functionality. CLI, MCP, SDK, or through Raycast even! We made sure Tabstack is available however you prefer to work.
Maker

"Ditch your scraper. Make one API call with any tool." -

123
•••
Next
Last