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.
Ditch your scraper. One API gives your code everything it needs from the web: structured JSON, clean markdown, cited research, and browser automation. No browser, LLM, or pipeline for you to run. Use it from the tools you already work in: an MCP server, CLI, Raycast extension, or as an Agent Skill. Grab a key and make your first call in less than three minutes. Mozilla-backed. Your data is never sold, never trained on.
Define a schema, pass a URL, get back JSON that matches. Tabstack's extract endpoint turns any web page into structured output, no parsing code and no LLM call to maintain. generate endpoint adds AI instructions for reasoned answers, not raw fields. Both enforce your schema on every call, even when the page changes. Tune speed with effort levels, target any country with geo_target. Mozilla-backed: your data is never sold or used to train models. 10,000 free credits to start.
/research gives your app or agent cited answers from the live web in one API call. Not a pre-indexed corpus: the actual live web. Every request comes back with source URL's users can verify. Source selection, synthesis, and citation formatting are all inside the call. You write or maintain none of that code. Built for legal, financial, and competitive intel, where a wrong answer is a liability. Free to try.
Tabstack is a web data and automation API that delivers reliable structured output. Pass a URL and a schema, get back JSON that matches every time. Run research in one call and get cited answers back. Automate browsers without running infrastructure. The intelligence is built into every API call. No scraper to build, maintain, or watch break when a site changes. Built at Mozilla.
Get the JSON Schema for any URL. Paste a link and get a ready-to-use schema as JSON Schema, a Zod object, or a Pydantic model. Copy it straight into your extraction or validation code.
Schema Source learns each site's URL patterns, so results come back fast and stay consistent across pages of the same shape.
Every result is also an API: request the same URL with JSON content negotiation and get the cached schema back, no key required.
Free, by the team behind Tabstack—backed by Mozilla.
I joined Tabstack four weeks ago. The fastest way I know to understand a product is to build something real with it not tutorials, not toy examples, but an actual app that uses the API under real conditions and breaks in interesting ways.
So I built Rival. Open-source competitive intelligence dashboard that tracks competitor pricing, changelogs, careers, docs, and GitHub signals, diffs what changes, and generates intelligence briefs automatically.
