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

the stateless-per-call design makes sense for reliability but I'm curious how it handles flows that need to stay logged in across steps - like a site where you need a session cookie from step one to do anything in step two. do you pass auth state back in yourself each call, or is there something built in for that

Maker

 Good distinction. Within a single /automate call it's one live browser session, so a cookie set in step one is still there in step two. Multi-step flows that depend on earlier state work fine inside one task.

Across separate calls it's stateless: no built-in session store, and no param to pass auth state back in, each call starts clean. So the pattern that works is doing the whole logged-in flow in one task, not logging in on call one and trying to reuse it on call two. The hosted API isn't built to manage credentials or hold a login across jobs—not yet anyways.

How does the pricing scale if my agent is firing hundreds of these calls per hour, and is there a way to cap costs before things get out of hand?

Maker

 great question re:pricing, thanks for asking.

's pricing is clear and flexible. It starts with a free 10k credit trial tier to explore the full platform, then it offers a pay-as-you-go individual plan, or predictable monthly subscriptions. In short, you can build without interruption and scale at your own pace.

To learn more about how Tabstack billing works, read the docs:

hope it clarifies!

Schema-defined extraction is the bit I was missing, and it worked cleanly on a couple of messy product pages. The robots.txt compliance and no-training stance from Mozilla make it easy to ship without a long legal check.

Maker

 your words just made my day! make sure to add your review here:

Maker

 Thank you, love hearing it worked on the messy ones, that's the real test. And you named exactly why the Mozilla stance matters to us: ephemeral by default, no training on your data, robots.txt respected, so it clears legal fast instead of turning into a project. Glad it's easy to ship, and appreciate you giving it a run.

Mozilla shipping something this developer-focused and privacy-conscious feels like a nice return to form. Loving that robots.txt compliance and ephemeral processing are defaults, not afterthoughts.

Maker

 thank you. and yes, does care about developers and humans. ❤️

Maker

 Thank you, this one means a lot. Defaults are everything, values you have to opt into aren't really values. Tabstack is privacy-first. Really glad that comes through.

Not having to host the browser removes the exact part of web automation that always breaks in production. How are you handling sites with heavy bot detection, is that abstracted away or still on the developer side? Reading the accessibility tree instead of screenshots is a smart cost move too, that token math adds up fast at scale.

Maker

 Thank you, that means a lot.

Bot detection: not abstracted away, not on you either. We run real browsers and respect robots.txt by default, so ordinary checks are usually fine. We don't do stealth or CAPTCHA-solving. If a site is set on keeping automation out, we won't fight it. That's a Mozilla call.

And yes on the accessibility tree. It's a cost decision as much as a reliability one, and screenshots get expensive fast. Glad that stood out.

Real browser + plain English API sounds handy. I wrangle forms and multi-step junk a lot. Been gluing Puppeteer + screenshot LLMs and burning tokens. Accessibility tree is neat. How does it handle logins/2FA and sites that rate-limit? No training is a plus.

That lines up with where we landed. When the target won't hand you a key, the only thing left is a read-before-write guard: a cheap check-run in front of the submit that asks does this record already exist and bails if it does. Costs you an extra call per write, but that beats a duplicate order showing up in someone's system after a blind retry. The nice thing is it lives entirely on my side, so I don't need Tabstack to persist anything.

Maker

 Exactly right, and honestly that guard living on your side is the stronger design anyway. Idempotency belongs with whoever owns the write, not the tool making the call, so a cheap existence check before submit means your retry safety holds no matter what we do or don't persist. One extra read to dodge a duplicate order is a trade I'd take every time. Appreciate you sharing how you landed on it.

Finally tried Tabstack and the schema-defined extraction is genuinely useful, no more wrestling with messy scraped HTML. Love that robots.txt and ephemeral processing come baked in by default.

Maker

 love it! feel free to add your review here:

Mozilla backing this is what got me to try it, and the schema extraction actually nailed a messy product page on the first try. Glad my data isn't getting fed into some training pipeline either.

Maker

awesome! and yes, makes it different. private by default, transparent by design.

The robots.txt compliance baked in by default is a really thoughtful touch, especially from Mozilla. Feels like they actually thought through the trust layer for devs shipping agents, not just the shiny API surface.

Maker

 you're spot on - actually cares about developers and humans. ❤️

First
Previous
•••
345
Next
Last