Keywords x402 REST usage
Extract keywords, topics, tags, and entities from any text
Retrieval and parsing services: fetch a page, render JavaScript, extract structured fields. Check each entry’s terms before pointing it at a site you do not own.
Extract keywords, topics, tags, and entities from any text
Use this to read up to 8 public URLs in one call (~$0.0019/url vs $0.002 single): Readability markdown + title/word_count per URL, concurrency 4, ~8s timeout, markdown capped. GET urls=comma-list or POST {urls:[...]}. Pr...
Read any public web page as clean Markdown for an LLM: main content without menus, scripts or ads, plus title, description, language and links. For agents without a browser.
Read a public web page and return just the fields you name as JSON (e.g. price, author, date, address). Missing fields come back null; values are taken from the page, never invented. Respects robots.txt.
Read a public web page and return just the fields you name as JSON (e.g. price, author, date, address). Missing fields come back null; values are taken from the page, never invented. Respects robots.txt.
Scrape any public URL into clean markdown, HTML or text, with optional CSS selector targeting. No headless browser to run. Pay per call with USDC (x402) or credits - archtools.dev
Fetches a URL and returns the requested format(s): markdown, html, links, images, summary, json, branding, screenshot.
Get detailed company information from a domain including name, logo, headcount, location, industry, and more.
Everything to vet a domain in one call: DNS records + email posture, RDAP registration/age/registrar, IP network/ASN/geo (from the resolved A record) and public threat-intel on the site. Four AgentBIT tools, merged. $0.0...
Render a URL in a headless browser and return HTML, markdown or screenshot.
An agent preparing a native HTML form reset needs missing required choice groups after radio ownership/name grouping and select placeholder/reset selection are combined, without user values or submitting anything.
Randomness for agents: flip coins, roll dice, draw numbers in a range, pick from a list or shuffle it. Cryptographically secure by default; with verificable=true it is derived from the latest finalized Ethereum block has...
US inflation (CPI-U): year-on-year headline, core (ex food and energy), energy and food rates, month by month. US Bureau of Labor Statistics, public domain.
Parse a site's robots.txt: whether a user-agent may crawl a path, which AI crawlers (GPTBot, ClaudeBot, Google-Extended, PerplexityBot, CCBot...) are blocked, and declared sitemaps. Check before your agent scrapes.
Read 2 to 5 pages whose URLs you already know in one call, each as clean Markdown with title and description, fetched in parallel. Cheaper and faster than calling web-scrape once per URL; for 6 to 20 URLs use web-scrape-...
Website crawler: read a whole website or one section of it (for example every page under /docs) as clean Markdown: starts at a URL, follows same-site links breadth-first and returns up to 20 pages with title and descript...
Read a public static HTTPS webpage as clean text with headings, links, timestamp and content hash. Use to ground an answer or ingest documentation. Respects robots.txt; no JavaScript or login.
Use when an agent has several options and no reason to prefer any, and the choice has to be defensible: picks one or more items from the list you send, with or without repeats, and tells you how many it had to choose fro...
Scrape a public webpage and extract clean readable text. Use this web scraping endpoint when an AI agent needs page content for summarization, research, retrieval, content extraction, indexing, or downstream analysis wit...
Verify a URL: does it resolve, what's the final status and redirect chain, is it archived on the Wayback Machine, and (optionally) does expected text appear on the page. Checked via direct fetch and the Internet Archive.
Verifiable Random shuffle — a uniform Fisher-Yates permutation bound to a future drand round the server waits for (typically 3-6s) and verifies locally, with original indices and a reproducible proof transcript.
Call this before committing to a trend or range strategy, so you don't trade a regime only one coin is in — checks whether BTC, ETH and SOL agree (confluence 1-3, WEAK/MODERATE/STRONG) and returns the dominant regime, th...
Validate and parse phone numbers in international E.164 form: extract the country calling code and region, the national number, and the canonical +E.164 string. Single number or a batch of up to 50. Format validation, no...
Fetch any public web page and return its main readable content as clean Markdown or plain text plus metadata (title), stripping nav/ads/boilerplate (trafilatura). Optional JS rendering via headless browser for SPAs; mark...