Every agent-payable API.

Change history for a company's pricing, terms, privacy and subprocessor pages: what changed and when, plus current prices.

Vendor security & privacy profile from a domain: claimed certifications (SOC 2, ISO 27001…), AI training on customer data (with quote), subprocessors, DPA, data residency, security features and a transparency score.

Is this store ready for AI shopping agents (ChatGPT/ACP, Google/UCP)? Score, readiness level and fix list.

Why is this US stock moving? Ranked catalysts from the last 48h of SEC filings (8-K events in plain English, press-release headline, offerings/dilution, insider buys and sells, 5%+ stakes) plus current or same-day trading halts, each with time and filing link. Facts only.

Company profile from a domain: name, what it does, key pages (pricing, docs, contact, careers), social profiles, pricing signals, tech stack, generic contact emails and AI-readiness. Built from the company's own public website.

US stock trading halts now and earlier today (Nasdaq, NYSE, NYSE American): reason in plain English, halt time, resume times, status. Filter by tickers or get all. Refreshed every minute.

x402 marketplace prices and top sellers: typical price paying wallets accept, price distribution, top sellers by distinct paying wallets (30 days), new listings already being paid, for a category (scraping, web_search, llm, market_data, onchain…) or the whole Bazaar. Refreshed hourly.

Which paid API should your agent call? Describe the need ("web search", "weather forecast", "verify an email") and get the top x402 endpoints ranked by repeat paid use (calls per wallet, not one-off sampling), recency and price, each checked live, with URL, price and why.

Score 0-100 for how well ChatGPT, Claude, Perplexity and Gemini can find, read and cite a page, with a prioritized fix list.

Is this npm or PyPI package safe to install? Exists or made-up name, malicious-package reports, known vulnerabilities for the version (with fix), deprecated/yanked, age, install scripts, downloads, typosquat look-alikes. Verdict with reasons.

Is this email address or domain legitimate? Verdict with reasons: syntax, role address, disposable or free provider, MX / null MX, mail provider, SPF, DMARC, website live, domain age. No mailbox probing.

Use when a topic, goal, problem or question needs a quick set of ideas that are already ranked: 3-5 ideas each scored 1-10 on three criteria that fit the kind of brainstorm (business: market size, ease to start, profit potential; problem: impact, feasibility, cost), an overall score, optional sub-ideas under the top 3 (depth=2), and a link to an interactive bubble map of the result. Errors: 400 bad_input, 502 model unavailable. Failed calls are not charged.

Strait of Hormuz bunker & marine-fuel feed: current VLSFO, IFO380, and MGO prices ($/tonne) for Fujairah (the world's #2-3 bunkering hub, just outside the strait and the physical fueling alternative when transit is disrupted), benchmarked against Singapore and Rotterdam, plus the derived Fujairah premium over each comparison hub. The physical-commodity read on Hormuz stress that the Brent and insurance signals do not capture.

Strait of Hormuz shadow-fleet risk screen: the live-AIS vessel population (vessels seen on AIS within the last activeWindowHours, currently 1.5) ranked worst-first, each hull with its risk band, the typed reasons behind it (ofac_sdn, ais_dark, foc_tanker, imo_spoofed), which sanctions bodies list it (US OFAC and/or UK/FCDO), and a lastSeenAt timestamp (when the hull was last listed, not necessarily its last true AIS fix) so listing recency can be checked per row. A transparent rules engine (not ML) fusing OFAC + UK sanctions, live AIS, AIS-dark gaps, and spoofed-IMO detection into one compliance-grade screen. counts cover the screened population, that is every hull seen on AIS inside the active window, not every hull ever tracked; vessels lists only the flagged hulls (high + moderate) by default, ?all=1 adds the cleared low-band hulls. Quality-gated on live AIS; flags are best-effort from the MMSI MID (ITU-T M.585). Because the screen is bounded to the active AIS window, an ais_dark re

Strait of Hormuz war-risk transit premium nowcast: a live MODELED war-risk insurance multiple (Nx over the peace baseline, on the published 1x-80x scale) for moving a tanker through the strait, recomputed every 5 minutes from throughput deviation (IMF PortWatch), the escalation forecast (Polymarket + Kalshi + Manifold + Brent-WTI spread), crude implied volatility (OVX), and event pressure (news and maritime RSS feeds, the PGSA incident feed and GDELT). The standing straits.live insurance-estimate multiple is carried only as a static reference (it is set manually and changes infrequently); the modeled figure is the live signal, not a divergence from that anchor. Returns a band, a curated VLCC war-premium band ($/voyage, estimated separately from the modeled multiple and not derived from it), per-driver detail, and a confidence that degrades on stale feeds or thin market volume. A modeled situational-awareness indicator, not an insurance quote.

Run a bounded declarative historical spot strategy backtest.

Grid-search up to 50 parameter combos of a backtest strategy; ranks by worst-half (H1/H2) return with neighbourhood smoothing, flags overfitting, and recommends the most robust parameters rather than the best-fit ones.

Street (parallel-market) rate — USD-NGN or USD-GHS. Street rate for USD-NGN or USD-GHS: the median VWAP of Bybit's public USDT/fiat P2P order book, divided by a USDT/USD spot basis, plus the Frankfurter official reference rate and the spread. OKX is archived and does not set the price. Not a central-bank rate and not a bureau de change quote.

Street Corn — Simple pleasure food for appreciating uncomplicated satisfaction.

String utilities. Transform one string every common way at once: camelCase, PascalCase, snake_case, kebab-case, CONSTANT_CASE, dot.case, path/case, Title Case, Sentence case, upper and lower; a URL slug (accents removed); reversed; trimmed and whitespace-collapsed; and counts of characters, letters, digits, words and lines. Splits identifiers like userIDValue or XMLHttpRequest correctly. Use when naming fields, files and routes or cleaning user input.

Use when you need a sanitized JPEG with EXIF, GPS, XMP, ICC and comment metadata removed.

Strip HTML tags to plain text for $0.001 USDC. Call when you need this bounded result without an API key or subscription. Returns machine-readable JSON via x402 on Base or Solana. Limitation: results cover only the supplied input or one bounded public endpoint at request time; callers must verify before acting.

Remove all HTML tags, returning the plain text content. Entities are decoded to real characters by default (set decodeEntities=false to keep them encoded).

Strip markdown to plain text for $0.001 USDC. Call when you need this bounded result without an API key or subscription. Returns machine-readable JSON via x402 on Base or Solana. Limitation: results cover only the supplied input or one bounded public endpoint at request time; callers must verify before acting.

Stripe Prohibited & Restricted Business list, MCC classification, and underwriting readiness checker. Pass ?business_model=saas_ai|marketplace|dropshipping|supplements (default saas_ai). Returns restricted status, likely MCC code, rolling-reserve triggers (prepayments, money-transmission traps), and mandatory checkout/website readiness items.

Structural diff of two JSON values: dotted-path lists of added, removed and changed fields, plus an equal flag. Input JSON strings or objects.

Extract a page's machine-readable self-description in one call: every JSON-LD block (schema.org), OpenGraph and Twitter Card metadata, canonical URL, title, meta description, H1, hreflang alternates and RSS/Atom feed links — parsed server-side into clean JSON. Where text extraction gives you prose, this gives you structured facts.

Structured data extractor (JSON-LD, microdata, RDFa): Extracts schema.org data from one page: every JSON-LD item (Product, Article, Organization, FAQPage, Event, Recipe and others) as parsed JSON with missing required / recommended properties, invalid JSON-LD blocks, microdata itemtypes and RDFa typ

Extract schema.org structured data from a public HTML page: JSON-LD (@graph flattened), top-level microdata, and Open Graph / Twitter meta. Normalizes Product/Offer, Article, Organization, Event, FAQ, and breadcrumbs. POST JSON {"url":"https://example.com"}. No structured data is HTTP 200 with empty arrays, not an error. Public http(s) only. $0.01 USDC on Base (eip155:8453). No API key.

Give it URLs. For each it extracts the JSON-LD structured data, lists every schema.org type, and validates the required and recommended properties Google needs for rich results (Product, Article, FAQ, Recipe, Organization, Event, JobPosting and more) - with findings. Keyless, read-only. Up to 3 items per call; failed lookups are not charged.

Structured diff of two text blocks: per-line additions, deletions and changes, plus an identical flag. Use it to detect whether a contract, policy or spec changed between two fetches.

Extract structured JSON fields into YOUR schema from pasted text or a public URL. When to use: turn messy public text into typed JSON with confidence + warnings. Refuses login/paywall sources. USDC on Base via x402 — no API key.

Structured JSON from any webpage. Name the fields you want — company data, job listings, product specs, contact details, financial figures — and get them back with confidence scores. No scraper configuration needed.

Takes an audio or video file by URL or inline base64 and returns the transcript: the full text, every word with start and end time and its own confidence, the utterances and paragraphs the recogniser separated, and the detected language with its confidence where no language was specified.

Takes 2 to 15 recordings by URL or inline base64, each with its declared length, and returns one transcript per file in the order given: full text, detected language, paragraphs, utterances, a confidence summary naming the weakest words with timestamps, and optionally every word with its timing. Billing is per started audio minute across the whole batch, at 0.017 USDC instead of the 0.02 USDC of a single /v1/stt call, at most 60 minutes per call.

Takes a public URL of an audio or video file of up to 120 minutes and 150 MB and returns the transcript: full text, paragraphs with sentences and timings, utterances, the detected language, and a confidence breakdown naming the weakest words with timestamps; every word with its timing on request. The file is downloaded and its running time measured locally with ffprobe before anything is sent, so a recording longer than declared is refused with its real length and nothing is charged.

Takes an audio or video file by URL or inline base64 and returns subtitles in the target language with the timing of the original speech. The recording is transcribed with word timestamps, split into subtitle cues at pauses, six seconds or 84 characters, and every cue is translated on its own so that the number and timing of cues stay identical — this is checked on every model answer and a mismatch is retried once and otherwise refused without charge.

Automatically extract comprehensive design system information from a brand’s website including colors, typography, spacing, shadows, and UI components.

Prüft am Objekt stylesheet den Befund DNS-Auflösungszeit.

Prüft am Objekt stylesheet den Befund Zeit bis zum ersten Byte.

Prüft am Objekt stylesheet den Befund Zahl geladener Ressourcen.

Prüft am Objekt stylesheet den Befund Zeit bis zum sichtbaren Renderstart.

Prüft am Objekt stylesheet den Befund Verbindungsaufbauzeit.

Prüft am Objekt stylesheet den Befund TLS-Aushandlungszeit.

Prüft am Objekt stylesheet den Befund Zahl renderblockierender Ressourcen.

Prüft am Objekt stylesheet den Befund Anteil moderner Bildformate.

Prüft am Objekt stylesheet den Befund übertragene Bytemenge.

Business Frameworks business-frameworks/cash-flow/band/sub-1m@1.0 — Cash flow below $1M: pay the owner first. Call when an agent needs how cash flow behaves at this revenue scale, for a business it is running or advising. Returns 250 tokens of original synthesis with public citations and child handles; free layer at /catalogue.

Business Frameworks business-frameworks/value/band/sub-1m@1.0 — Value below $1M: the owner is the business. Call when an agent needs how value behaves at this revenue scale, for a business it is running or advising. Returns 300 tokens of original synthesis with public citations and child handles; free layer at /catalogue.

Business Frameworks business-frameworks/risk/band/sub-5m@1.0 — Risk below $5M: the chance of survival. Call when an agent needs how risk behaves at this revenue scale, for a business it is running or advising. Returns 350 tokens of original synthesis with public citations and child handles; free layer at /catalogue.