Website technology detection: CMS, e-commerce platform, analytics, tag managers, CDN, hosting, chat, payments, A/B testing, consent tools and the e-mail provider, each with version, confidence 0-100 and evidence, from 231 own fingerprints over the home page, headers, cookies and the domain's MX/TXT records. For lead filtering and competitor research.

US product recalls in one schema from openFDA enforcement reports (food, drug, device) and CPSC: date, product, firm, reason, FDA Class I/II/III mapped to high/medium/low (CPSC severity is derived from the hazard text), distribution and states, and the official link. Filter by keyword, since date (default 30 days), source and classification; up to 100 rows.

Active EU public tenders from TED matching words, optionally for one buyer country: notice number, title, buyer, country, publication date, deadline, CPV codes and link, newest first. Country is an ISO alpha-3 code (DEU, FRA, POL). Attribution: TED, EU open data.

Safety check of a text or a chat turn with Llama Guard 3: safe or unsafe, and the violated categories (S1 to S14, named in plain words). Send text, or messages (up to 20 turns). Classifies only; it does not change or block anything.

Reads the text of an image (JPEG, PNG, GIF or WEBP, up to 4 MB) with Llama 3.2 11B Vision on Workers AI. Send an https url or base64 image, and optionally a language hint. Returns the full text with its line breaks, the lines, a language guess and the model that answered. An image with no readable text is a 422 and is not charged.

On-chain facts about an ERC-20 contract on Base (default), Ethereum, Arbitrum, Optimism or Polygon, read over RPC: name, symbol, decimals, total supply, code size, whether it is a proxy (EIP-1967, EIP-1822 or the pre-1967 OpenZeppelin slots) with its implementation and admin, owner() and whether ownership is renounced, risky functions found in the bytecode, and plain warning flags. No paid security service is called.

Companies from the official registers of Norway, Finland, the Czech Republic and Poland. Search by name (Norway, Finland, Czech Republic) or look up one company by its number: Norway 9 digits, Finland Y-tunnus, Czech IČO, Poland KRS (Poland by number only). Answers give name, id, status, legal form, address, incorporation date and industry; Norway lookups by number also list managers. France is not included (see the PR).

Native balance and the major tokens (USDC, USDT, EURC, DAI, WETH, cbBTC and WBTC where listed) of an EVM address on Base (default), Ethereum, Arbitrum, Optimism, Polygon, or chain=all, with USD values from Coinbase spot prices. One Multicall3 call per chain. Zero balances are omitted, and only the listed tokens are checked, not every token the wallet holds.

A summary of a web page (url) or your own text (up to 12,000 characters) as short, medium or bullets, in the language you name, with key points. Llama 3.3 70B. A page is read as in /api/read, robots.txt respected.

ERC-20 transfers into and out of an address in a window of recent blocks (default 2,000, max 10,000), from Transfer logs, newest first, max 100 rows with token symbols. token limits the search to one contract. A busy address can be truncated: narrow the window to see the rest.

Current TLS certificates for a domain from Certificate Transparency logs (via CertSpotter): issuer, validity dates and days left, DNS names (up to 100 per certificate), and the distinct subdomains seen. Keyless tier: one request per call; answers are cached an hour.

US federal grant opportunities from Grants.gov matching keywords: number, title, agency, open and close dates (YYYY-MM-DD), status and link, newest opening date first. Grants.gov matches keywords anywhere in the full listing, not only the title. Posted and forecasted opportunities by default. US government data.

Labels up to 20 texts with 2 to 20 labels you choose, with a confidence from 0 to 1 and a one-line reason per text. One label per text, or several with multi true. Uses the chat model with JSON output; labels are as good as the model's reading of them.

Third-party script and iframe hosts on a page, each classified (analytics, ads, tag manager, chat, session replay, social, consent, CDN), the cookies its first response sets (names and flags only, never values) and whether a known consent manager is present. Static HTML only: scripts added at run time are not seen.

The latest releases of a GitHub repository: tag, name, date, pre-release flag, the first 1,500 characters of the notes, and the number of assets. Needs the GITHUB_TOKEN secret on the deployment; without it the call answers 503 and is not charged.

Runs a read-only SPARQL query on Wikidata and returns the rows as plain values (ASK returns true or false). Only SELECT and ASK are allowed; updates are refused. A LIMIT of 100 or less is added when missing. 8-second limit. Data is CC0.

Replaces personal data in a text with placeholders: e-mail addresses, phone numbers, IBANs (mod 97 checked), payment card numbers (Luhn checked only), IPv4 addresses and, with names true, person names found by the chat model. Returns the redacted text and counts per type. Original values are never returned.

For eleven AI crawlers (GPTBot, ClaudeBot, PerplexityBot, Google-Extended and others): allowed or blocked for the page's path under robots.txt, plus the noai and noimageai opt-outs in meta and X-Robots-Tag, and whether llms.txt exists. Reads the page as static HTML; no JavaScript runs.

Event logs of a contract over recent blocks (default 1,000, max 5,000), newest first, max 100: block, transaction hash, topics and data. topic0 takes an event signature such as Transfer(address,address,uint256) or a 32-byte hash. Public nodes refuse very large results: narrow the range or add topic0.

Every HTML table of a web page as JSON: caption, headers and rows, up to 10 tables with 200 rows each. Tables that a script draws are not included. robots.txt is respected; a page it disallows answers 403, not charged.