26 services carry this tag in their source record. Tags come from the provider, not from us — a tag is a claim about what the service does, not proof that it does it well.
Full website audit in one call: accessibility (WCAG 2.1 A/AA via axe-core), on-page SEO, HTTP security headers and page speed / page weight, from a single browser load of one URL. Cheaper than four separate calls; if any...
Email deliverability & domain security check — validates SPF, DKIM (multi-selector), and DMARC, detects spoofing and misconfigurations, and returns an A–F email security grade with transparent deductions. Anti-spam / ant...
CUDA, driver and Ollama compatibility - GPU support, model memory fit and proof inference uses the GPU
Federal Register activity on a topic: what published recently, final vs proposed, which agencies, what takes effect.
$0.002/page. Pull text and structure out of a PDF — clean input for LLMs and search. 1¢ x402 min; remainder auto-credits — relaystation.ai/penny
Fetch a reviewed public page and return its HTML tables as arrays of rows and cells. Bounded to ten tables, fifty rows each and twenty cells per row, and every bound that is reached is named in the warnings so a truncate...
Structured data extraction with local AI: give a text and a list of field names, get a JSON object with those fields (null when absent).
Repair broken JSON, typical of LLM output: strips ```json fences, comments and surrounding text, trailing commas, single quotes, unquoted keys, Python True/None and unclosed brackets. Returns the object and clean JSON an...
Repair malformed JSON (trailing commas, single quotes, unquoted keys, code fences, truncated output) and optionally validate the result against a supplied JSON Schema. Returns the parsed value, the canonical text, a chan...
Recall tenant memory
Metadata and structure of a PDF (URL): pages, page size, title, author, creator, dates, version, encryption, form fields, attachments, bookmarks (table of contents) and whether it has extractable text or is a scan.
Turn a public web page into an LLM-ready document: clean markdown with nav/cookie/script boilerplate removed, parsed JSON-LD, OpenGraph, heading outline, tables, link graph, word and token counts, and embedding-ready chu...
Test a regular expression against a text: every match with position, groups and named groups, plus the result of a substitution if you pass a replacement. Flags i, m, s, x. Time-limited, safe against catastrophic backtra...
Turn an iCal/ICS calendar URL (Google Calendar, Outlook, holidays, events...) into JSON: upcoming events with title, start and end, all-day flag, location, description and link over the next N days; text filter.
Validate JSON (with line and column of the error), pretty-print or minify it, describe its structure (depth, keys, value types) and extract a value by path such as data.items[0].price.
Parse a User-Agent string: browser and version, OS and version, device brand and model, device type (mobile, tablet, desktop) and whether it is a bot, an AI crawler (GPTBot, ClaudeBot...) or an HTTP library.
Structured extraction: give a JSON Schema plus a URL or raw text, get back JSON matching the schema.
Extract from any text, without AI: emails, URLs, phone numbers, IBANs, EVM/Bitcoin/Solana addresses, transaction hashes, IPs, dates, amounts, hashtags, mentions and Spanish tax IDs, deduplicated.
Extract and normalize every number in a text: amounts with currency (€, $, USDC, BTC...), percentages, multipliers (k, million, bn) and plain figures, understanding both 1.234,56 and 1,234.56, with totals per currency.
Test a regular expression against text and return every match with numbered and named capture groups. Deterministic.
Repair malformed JSON text into valid parsed JSON: markdown code fences, single quotes, smart quotes, unquoted keys, trailing commas, comments, Python literals (True/None), raw newlines in strings, and truncated output (...
Extract structured JSON from unstructured text (invoices, emails, ads, CVs...): name the fields you want, get clean JSON back. Any language, up to 6,000 characters.
Convert caller-supplied HTML to clean markdown with title, excerpt and site metadata. The caller fetches the page; this endpoint only parses the supplied document (no server-side fetching).
Token compression for LLMs