alt Hacker NewsShow HN: Tabstack – Browser infrastructure for AI agents (by Mozilla)
Hi HN,
My team and I are building Tabstack to handle the "web layer" for AI agents. Launch Post: https://tabstack.ai/blog/intro-browsing-infrastructure-ai-ag...
Maintaining a complex infrastructure stack for web browsing is one of the biggest bottlenecks in building reliable agents. You start with a simple fetch, but quickly end up managing a complex stack of proxies, handling client-side hydration, and debugging brittle selectors. and writing custom parsing logic for every site.
Tabstack is an API that abstracts that infrastructure. You send a URL and an intent; we handle the rendering and return clean, structured data for the LLM.
How it works under the hood:
- Escalation Logic: We don't spin up a full browser instance for every request (which is slow and expensive). We attempt lightweight fetches first, escalating to full browser automation only when the site requires JS execution/hydration.
- Token Optimization: Raw HTML is noisy and burns context window tokens. We process the DOM to strip non-content elements and return a markdown-friendly structure that is optimized for LLM consumption.
- Infrastructure Stability: Scaling headless browsers is notoriously hard (zombie processes, memory leaks, crashing instances). We manage the fleet lifecycle and orchestration so you can run thousands of concurrent requests without maintaining the underlying grid.
On Ethics: Since we are backed by Mozilla, we are strict about how this interacts with the open web.
- We respect robots.txt rules.
- We identify our User Agent.
- We do not use requests/content to train models.
- Data is ephemeral and discarded after the task.
The linked post goes into more detail on the infrastructure and why we think browsing needs to be a distinct layer in the AI stack.
This is obviously a very new space and we're all learning together. There are plenty of known unknowns (and likely even more unknown unknowns) when it comes to agentic browsing, so we’d genuinely appreciate your feedback, questions, and tips.
Happy to answer questions about the stack, our architecture, or the challenges of building browser infrastructure.
Comments
Pricing page is hidden behind a registration form. Why?
I also wanted to see how/if it handled semantic data (schema.org and Wikidata ontologies), but the hidden pricing threw me off.
This looks good , but if Pay-as-you-go pricing can have some more information about what your actual are charges are per unit or whatever metrics, that would be helpful. I signed up but still can not find the actual pricing.
> We don't spin up a full browser instance for every request (which is slow and expensive)
there's really no excuse for not spinning up a browser every request. a Firecracker VM boots ~50ms nowadays
> We respect robots.txt rules.
you might, but most companies in the market for your service don't want this
Congrats on the launch! It would be useful to have a matrix somewhere showing how this compares to Jina, Firecrawl, etc.
Uncertain what you have to do with Mozilla.
The escalation logic (lightweight fetch → full browser only when needed) is a nice optimization. That's exactly the kind of thing that's painful to build yourself.
Curious about debugging: when an agent's request fails or returns unexpected data, how do you surface what actually happened in the browser? We've found that visibility into the actual request/response chain is often the missing piece when debugging agent behavior.
Good call on the ethics stance with robots.txt and User-Agent identification.
With all respect to Mozilla, "respects robots.txt" makes this effectively DoA. AI agents are a form of user agent like any other when initiated by a human, no matter the personal opinion of the content publisher (unlike the egregious automated /scraping/ done for model training).