Unified scientific literature search across arXiv (preprints), PubMed (biomedical), and Semantic Scholar (cross-field, with citation counts). Returns a flat array of papers with stable schema: source, sourceId, doi, title, authors, abstract, year, publishedAt, citationCount, url, pdfUrl. Partial failures surface in the errors array rather than failing the whole call. Optional filters: since (YYYY-MM-DD), sources (subset), limit (max 20 per source).

Unified read API over US National Park Service developer.nps.gov. Pick a resource: parks (every NPS unit — historical parks, monuments, seashores, etc.), alerts (closures, dangers, info), campgrounds (NPS-operated campgrounds with reservation links), events (talks, walks, ranger programs), newsreleases (park news), thingstodo (activities by park), visitorcenters. Filter by parkCode (CSV — e.g. "acad,yose,grca"), state, or free-text query. Returns the upstream NPS payload verbatim (rich nested objects with images, addresses, operating hours, etc.).

Full US patent application file-wrapper detail by application number. Returns bibliographic data (title, inventors, applicants, dates, status, examiner, art unit, docket #, confirmation #) plus the file-wrapper event timeline (filing, IDS, Office Actions, allowance, abandonment, …), continuity chain (parent / continuation / divisional / national stage), recorded assignments (assignor → assignee with reel/frame + conveyance text), and foreign priority claims under 35 USC § 119. Application number is the 6-10 digit USPTO ID (e.g. 18566276).

List every document in the file wrapper for a US patent application. Returns each document with its USPTO code (e.g. CTNF non-final OA, CTFR final OA, IDS, WCLM claims worksheet, NOA notice of allowance), human-readable description, official date, direction (INTERNAL/INCOMING/OUTGOING), and available formats with page counts. Includes patentCenterUrl pointing at the public USPTO Patent Center documents page for direct PDF download. Application number is the 6-10 digit USPTO ID.

Search US patent applications and grants via the USPTO Open Data Portal. Query: q (required, 2+ chars), yearFrom / yearTo (optional filing-year bounds), applicationType (optional: Utility|Design|Plant|Reissue), limit (1-100, default 10), offset (0-based, default 0). Returns { total, returned, offset, limit, hits[{ applicationNumber, title, applicationType, firstInventor, inventors[], applicants[], filingDate, effectiveFilingDate, status:{ code, description, updatedAt }, cpcSymbols[], uspcSymbol, url }] }. URLs link to USPTO Patent Center for the public file wrapper.

Sweep a person's name across five US public registries in one call: FINRA securities brokers, federal-court attorneys (CourtListener), federal inmates (BOP), Texas trade licenses (TDLR), and Texas real-estate licenses (TREC). Returns one block per registry with found/error status, match count, and the matching records — name-matched CANDIDATES, deliberately not merged into one identity (same name does not mean same person; verify with each registry's identifier before acting). Due-diligence, KYC screening triage, and background-research staple. Each registry is also a standalone endpoint (/api/license/broker, /api/law/attorney-lookup, /api/gov/inmate-locator, /api/license/trades, /api/license/real-estate) for follow-up by identifier.

Parse, validate and canonicalize a phone number using Google's libphonenumber metadata. Query: number (required; E.164 like "+14155552671" or national like "(415) 555-2671"), country (optional ISO 3166-1 alpha-2 like US/GB/JP — required when number is not E.164). Returns {input, valid (matches a real number range), possible (right shape/length), e164, national, international, rfc3966, country, countryCallingCode, type (mobile|fixed_line|fixed_line_or_mobile|toll_free|premium_rate|shared_cost|voip|personal_number|pager|uan|voicemail|unknown), possibleCountries[]}. Returns valid:false (not an error) for unparseable input.

Find points of interest near a coordinate. Backed by OpenStreetMap via the Overpass API (free, public, ODbL). Returns name, OSM id (e.g. node/123 — deep-linkable to openstreetmap.org), latitude, longitude, distance in meters, composed street address (when present), phone, website, opening hours, brand, and cuisine tags. Results sorted nearest-first. Supported categories: restaurant, cafe, bar, fast_food, gas_station, ev_charging, parking, atm, bank, hospital, pharmacy, clinic, doctor, dentist, police, fire_station, post_office, library, toilets, school, university, supermarket, convenience, hotel, hostel, museum, attraction, park, playground. Query: lat (-90..90), lon (-180..180), category (one of the supported names), radius_m (1-10000, default 1000), limit (1-100, default 20).

NYC deed + mortgage history for a tax lot via ACRIS (Automated City Register Information System) legals dataset, keyed by BBL. Each row carries a unique documentId you can use to drill into the ACRIS master dataset (the master URL pattern is included in the response) for full details: parties, consideration amount, document type (DEED, MORTGAGE, ASSIGNMENT OF MORTGAGE, etc.). Use `property.nyc-parcel-lookup` first to convert an address to a BBL. Returns most-recent records first.

NYC tax-lot lookup via PLUTO (Primary Land Use Tax Lot Output) — every tax lot in the city with owner, zoning, lot/building area, year built, classification, lat/lon, community + school + council + police districts. Pass `bbl` (10-digit Borough-Block-Lot composite, e.g. 1010110001 for the Empire State Building) for an exact lookup, OR pass `address` (partial-match) optionally constrained by `borough` (name or 2-letter code MN/BX/BK/QN/SI). The BBL returned here is the universal join key for all other property.nyc-* endpoints — fetch parcels first, then chain into deed-history, permits, or violations.

NYC Department of Buildings permit issuance — every construction, alteration, or demolition permit ever issued. Search by `bbl` (10-digit) or `address` (street_name substring). Filter by jobType (A1=Major Alteration, A2=Minor Alteration, A3=Minor Cosmetic, NB=New Building, DM=Demolition, etc.) or permitStatus (ISSUED, IN PROCESS, RE-ISSUED, REVOKED, etc.). Each row carries job + permit numbers, work type, building type, residential flag, filing/issuance/expiration dates, estimated fee. Use for construction-history agents, code-enforcement research, and zoning compliance checks.

NYC Housing Preservation & Development (HPD) violations — every notice of violation issued at a multi-family building. Search by `bbl` (10-digit) or `address` (street_name substring). Filter by `classCode` (A=least severe, B=hazardous, C=immediately hazardous) and `currentStatusOnly=true` to limit to open violations. Each row carries violation id, building id, full address + apartment + story, inspection + approved + certify-by + correct-by dates, current status + status date, and the narrative NOV description. Use for landlord-history, code-enforcement, and tenant-rights agents.

Recent earthquakes near a coordinate. Returns each quake with magnitude, place name, time (ISO), latitude/longitude/depth, tsunami flag, USGS event URL, and distance-from-query in km — sorted by time descending. Real-time data, post-LLM-training-cutoff. Backed by USGS FDSN event API (public domain). Query: lat (-90..90), lon (-180..180), radius_km (1-1000, default 500), hours (1-720, default 24), min_magnitude (0-10, default 2.0).

Search the Recreation Information Database (RIDB) — the single source of truth for federal recreation lands and programs across NPS, USFS, BLM, USACE, BOR, FWS, NARA. Pick a resource: recareas (designated recreation areas), facilities (individual sites — campgrounds, day-use, visitor centers), campsites (individual reservable campsites with attributes), permits (special-use permits, lotteries), tours, events, activities (taxonomy lookup). Filter by free-text query, state, activity ID, or lat/lon + radius (miles, max 50). Used by every federal-recreation-related agent: trip planning, permit chasers, fishing/hunting locator, campground availability tools.

Look up an npm package by name (supports scoped packages like @sentry/node). Returns description, homepage, repository, license, author + maintainers list, keywords, distTags (latest/beta/rc/etc.), latest version + publication date, and the 50 most recent versions with their publish dates + deprecation status. ~3M JavaScript/TypeScript packages. npm public registry.

Look up a Python package on PyPI by name. Returns version, summary + long description, content-type, project URLs (Homepage, Source, Bug Tracker, Docs, etc.), license, author + maintainer (with emails), keywords, classifiers (top 30), requires-python spec, requires-dist (top 100 runtime deps), the 50 most recent releases with publish dates, and any yanked versions in that window. PyPI public registry.

Live web search. Returns ranked results with title, URL, snippet description, site name, and page age — fresh information past any model training cutoff. Supports count (1-20), offset for paging, country (2-letter, e.g. US), freshness (pd=past day, pw=past week, pm=past month, py=past year, or a YYYY-MM-DDtoYYYY-MM-DD range), and safesearch (off/moderate/strict). Use for current events, fact verification, finding documentation, and research. Independent search index. For news-specific results with sources and timestamps see /api/news/search.

Look up any asteroid or comet in NASA JPL's Small-Body Database by designation, number, or name (e.g. "433", "Eros", "433 Eros", "1P/Halley", "2024 YR4"). Returns full name + kind + orbit class (e.g. Amor, Apollo, Jupiter-family comet), NEO and potentially-hazardous-asteroid flags, physical params (absolute magnitude H, diameter, extent, rotation period, albedo, density, spectral type), and orbital elements (eccentricity, semi-major axis, perihelion/aphelion, inclination, period, Earth MOID, observation arc). Astronomy, planetary-defense, and mission-planning research. Public-domain NASA/JPL data; for a body's near-Earth close approaches see /api/space/close-approaches.

List near-Earth asteroid/comet close approaches to Earth within a date window and maximum distance, from NASA JPL's Close-Approach Data API. Filter by dateMin / dateMax (YYYY-MM-DD) and distMaxAu (max approach distance in AU; default 0.05 AU ≈ 19.5 lunar distances). Each approach: object designation, close-approach date (UTC), nominal + minimum distance in AU and lunar distances, relative velocity (km/s), and absolute magnitude H (a size proxy). Sorted nearest-first. Planetary-defense, observation planning, and "what's passing by this month" queries. Public-domain NASA/JPL data; for full physical/orbital params of a listed object see /api/space/body.

Search confirmed exoplanets in the NASA Exoplanet Archive (~6,000, updated weekly — past any LLM training cutoff). Filter by name (planet, partial), hostStar (partial), discoveryYear, or method (e.g. "Transit", "Radial Velocity", "Microlensing"). Each planet: name, host star + how many stars/planets in the system, discovery method/year/facility, orbital period, semi-major axis, radius (Earth radii), mass (Earth masses), equilibrium temperature, insolation; host-star spectral type/temperature/radius/mass; distance in parsecs + light-years; and RA/dec. Astronomy, habitability research, science education. Public-domain NASA data.

Upcoming or recent orbital rocket launches from The Space Devs' Launch Library 2 — the live manifest behind most launch-tracking apps. `when`=upcoming (default) or previous. Optional `search` filters by rocket, provider, or mission text (e.g. "Starship", "SpaceX", "Artemis"). Each launch: name, status (Go/TBD/Success/Failure), NET launch time + window (UTC), launch provider, rocket configuration, pad + location, mission name/type/orbit/description, and whether a webcast is live. Real-time data agents can't get from training. Public CC-BY data (attribute The Space Devs).

Compute where any asteroid or comet is in the sky and whether you can see it. Give a body (designation/number/name, e.g. "433 Eros", "Ceres", "2024 YR4") and optionally your lat/lon and a time (ISO, default now). Returns the body's identity (NEO/PHA flags, orbit class, absolute magnitude H), its geocentric right ascension + declination, the constellation it's in, geocentric + heliocentric distance (AU), solar phase angle, and its apparent visual magnitude (IAU H-G model — how bright it appears now). With lat/lon it adds altitude/azimuth, whether it's above your horizon, a visible-now flag (up AND sky dark), and the best viewing window in the next 24 hours (when it's highest during darkness). Orbital position is computed locally from JPL elements — VALIDATED against JPL Horizons to <0.1 arcminute. Stargazing, astrophotography planning, occultation/observation prep. For the body's static physical + orbital params see /api/space/body.

Compute the current position of any cataloged Earth-orbiting satellite by NORAD catalog number (e.g. 25544 = ISS, 20580 = Hubble), using fresh Celestrak orbital elements propagated with SGP4. Returns sub-point latitude/longitude, altitude (km), and speed (km/s) for the requested instant (default: now; pass `at` as an ISO timestamp for any time within a few days of the elements' epoch). Supply observer `lat`/`lon` (and optional altKm) to also get look angles — azimuth, elevation, slant range, and whether the satellite is above your horizon — for visual/antenna pointing. Satellite tracking, pass prediction, ground-station planning. Public-domain orbital data; physical/mission metadata is not included.

Observer-local sky almanac for any lat/lon and time (default now). Returns the Sun's next rise/set + current altitude/azimuth; the Moon's rise/set, current alt/az, phase angle, phase name (New → Full → Waning Crescent), illuminated fraction, and next moon quarter; and for all seven non-Earth planets (Mercury→Neptune): altitude, azimuth, RA/dec, distance (AU), apparent magnitude, and whether each is currently above the horizon. Computed from first principles (astronomy-engine, sub-arcminute) — no external service, no key. Stargazing, astrophotography planning, 'what's up right now', is-it-dark-yet. `at` accepts any ISO timestamp.

One call → what's notable in YOUR sky right now, for a lat/lon. Synthesizes three sources: (1) the live almanac — sun up/down, moon phase + illumination, and which of the 7 naked-eye planets are currently above your horizon with their altitude/azimuth/magnitude; (2) near-Earth asteroid close approaches over the next 7 days (designation, date, distance in lunar distances); and (3) the ISS — its current sub-point, and whether it is above your horizon right now with look angles. Each section reports found/error independently. The "is it dark, what's up, anything passing" digest for stargazers and astrophotographers. For the raw almanac alone see /api/space/sky-tonight.

Profile a confirmed exoplanetary system by host-star name (e.g. "TRAPPIST-1", "Kepler-90", "TOI-700"). Groups all the star's known planets into one view, summarizes the host star (spectral type, temperature, radius, mass, distance in light-years), and COMPUTES the star's habitable ("Goldilocks") zone — inner and outer boundary in AU, derived from the stellar luminosity (effective temperature + radius vs. the Sun) — then flags which planets orbit within it. Each planet: radius/mass (Earth units), orbital period, semi-major axis, equilibrium temperature, and in-habitable-zone flag. Astronomy, habitability research, education. Built from the NASA Exoplanet Archive (the same data as /api/space/exoplanet) plus the computed HZ. Public-domain NASA data.

Latest daily stock quote for a US-listed ticker. Returns the most recent completed trading session: open, high, low, close, volume, VWAP, and trade count, plus the change and percent change versus the prior session, and company reference data (name, primary exchange, security type, currency, market cap). NOTE: this plan tier serves end-of-day / delayed data (the response flags delayed=true), suitable for daily snapshots, fundamentals context, and post-close analysis rather than real-time trading. Pass ticker as a US symbol (e.g. AAPL, MSFT, BRK.B). Market data by Massive (formerly Polygon.io).

Compute sunrise, sunset, solar noon, and civil/nautical/astronomical twilight times for a coordinate + date. Query: lat (-90..90), lon (-180..180), date (YYYY-MM-DD). All times returned as ISO 8601 UTC. At high latitudes near solstices an event may not occur (polar day/night) — those fields return null and a note is included. dayLengthMinutes is the sunrise→sunset interval.

Next high/low tide predictions near a coordinate. Query: lat (-90..90), lon (-180..180), radius_km (1-500, default 100), hours (1-72, default 24). Returns { query, station:{ id, name, latitude, longitude, state, distanceKm }, predictions[{ time (station local), type: "high"|"low", heightMeters }], source }. Returns 404 NO_STATION if no NOAA tide station is within radius. Heights are referenced to MLLW (Mean Lower-Low Water).

TLD registry intelligence and public-suffix analysis. Mode 1 (tld=io): IANA root-zone metadata — type (generic / country-code / sponsored), managing organization, unicode form for IDN TLDs. Mode 2 (domain=shop.example.co.uk): full Public Suffix List algorithm — the effective public suffix (co.uk), the registrable domain (example.co.uk), the subdomain part, the matched PSL rule, and whether the suffix is ICANN (registry) or private (corporate, e.g. github.io / s3.amazonaws.com) — plus the root-zone metadata for its TLD. Correctly handles wildcard and exception rules and IDN/punycode input. Use for cookie scoping, per-registrant rate limiting, URL dedup, and abuse/phishing analysis. Data: IANA root zone + Mozilla PSL, refreshed weekly.

Open a live TLS connection to a host and return its certificate. Give a host (and optional port, default 443). Returns the negotiated TLS protocol + cipher, whether the chain validates against system roots, and the leaf certificate's subject + issuer (CN/O/C), validity window (valid-from / valid-to), days until expiry + expired flag, serial number, SHA-256 fingerprint, Subject Alternative Names, and the chain length. A genuine network probe agents can't do from their sandbox — for cert-expiry monitoring, TLS audits, and verifying who issued a site's certificate. SSRF-guarded: the host must resolve to a public address. Self-signed and expired certs are reported (not rejected).

Daily Treasury Statement (DTS) operating cash balance via US Treasury Fiscal Data. Returns daily snapshots of the Treasury General Account (TGA) at the Federal Reserve plus tax-and-loan accounts and Federal Reserve deposit accounts. Each row carries record_date, account_type, close_today_bal, open_today_bal, open_month_bal, open_fiscal_year_bal. Useful for liquidity-tracking agents and macro researchers watching the Treasury Cash Balance heading into Treasury auctions, debt-ceiling pinch-points, etc. Fiscal Data filter syntax.

US National Debt — daily "Debt to the Penny" via US Treasury Fiscal Data. Each row carries record_date, debt held by public, intragovernmental holdings, and total public debt outstanding (all USD, signed integers as strings to preserve precision). Optional `filter` uses Fiscal Data syntax: `col:op:val` joined by commas (ops: eq, lt, lte, gt, gte, in). Default sort is `-record_date` (newest first). Authoritative source for "how much does the US owe?" — every weekday since 1993.

Official US Treasury exchange rates via US Treasury Fiscal Data. Used by federal agencies to report foreign-currency transactions in USD. Quarterly + ad-hoc updates per country/currency pair. Each row carries record_date, country, currency, country_currency_desc, exchange_rate, effective_date. Pair with `/api/fx/rates` (ECB Frankfurter, daily market rates) for cross-validation. Use Fiscal Data filter syntax — e.g. `filter=country:eq:Brazil` to scope to a single country.

Monthly Treasury Statement (MTS) — Table 4: receipts by source via US Treasury Fiscal Data. Returns monthly totals of federal government receipts grouped by classification (individual income tax, corporate income tax, social-insurance receipts, excise, customs, estate-and-gift, miscellaneous). Each row carries record_date, classification_id, classification_desc, current_month + current_fytd (fiscal year-to-date) gross_rcpt / refund / net_rcpt amounts, plus prior_fytd comparisons. Backbone of any "how much money is the federal government bringing in" question. Use Fiscal Data filter syntax.

Fetch any URL and return its article content with the clutter stripped — nav, ads, sidebars, footers, scripts, styles, comments removed via heuristic extraction (<article> / <main> / role=main / densest block). Choose the output with `format`: markdown (default), text, both (JSON envelope), html (a self-contained readable reader-view page, raw text/html), or pdf (a clean typeset reading document, raw application/pdf). html/pdf are built from the same cleaned content, so they carry no live page, no third-party assets, no trackers. SSRF-guarded, 512KB body cap, 8s timeout, 5 redirects max. JSON formats return { url, finalUrl, title, markdown?, text?, wordCount, sourceBytes }. For a pixel-perfect render of the live page use /api/ai/screenshot instead.

Discover the URLs a page or sitemap points at in a single fetch. Point it at an XML sitemap or sitemap-index and it returns the <loc> URLs; point it at an HTML page and it returns the <a href> links — auto-detected. URLs are resolved to absolute, de-duplicated, fragment-stripped, and http(s)-only. `limit` (1-2000, default 200) caps the count; `sameHostOnly` keeps only links on the same host. Single SSRF-guarded fetch, no JavaScript, stateless — NOT a recursive crawler: to go deeper, call map again on a child sitemap or a discovered page. Returns { url, finalUrl, source: "sitemap"|"links", count, capped, urls }.

Render a URL in a real headless browser (JavaScript executed) and return its article content with the clutter stripped — same cleaning + output formats as /api/url/clean, but for client-rendered / SPA pages whose content only appears after JS runs (where a raw HTTP fetch returns an empty shell). `format`: markdown (default), text, both (JSON envelope), html (self-contained reader page, raw text/html), or pdf (typeset reading doc, raw application/pdf). Optional `waitUntil` (load|domcontentloaded|networkidle0|networkidle2, default networkidle2) and `timeoutMs` (1000-15000, default 12000) control how long to let JS settle. Use /api/url/clean instead for server-rendered pages — it is Tier 0 and ~10× cheaper; only reach for render when JS rendering is required.

Fetch any URL and extract structured page metadata: title, description, og:image, canonical, favicon, site name, author, published time, language, and the first ~500 chars of body text. SSRF-guarded against private networks. 8s timeout, 512 KB max body. Returns the parsed metadata plus the raw og:/twitter:/itemprop meta dictionary for inspection.

NHTSA consumer complaints for a US vehicle by (make, model, modelYear). Returns the top N records (newest-filed first) with ODI number, affected component, plain-English summary, crash/fire flags, injury and death counts, partial VIN, and incident + filing dates. Backed by NHTSA's public complaints database; data is public-domain US government records.

Chronological feed of NHTSA ODI (Office of Defects Investigation) investigations, newest first. Returns preliminary evaluations (PE), engineering analyses (EA), defect petitions (DP), and recall queries (RQ) — each with NHTSA ID, type code, open/close dates, status, subject, and full description (HTML stripped + raw). Useful for tracking what NHTSA is currently investigating (Tesla FSD, autonomous-vehicle crashes, Rivian suspension, etc.). NOTE: NHTSA's endpoint does NOT support make/model/year filtering — use vehicle.recalls or vehicle.complaints for vehicle-scoped lookups. Public-domain US government records.

Paginated list of every motor vehicle manufacturer NHTSA tracks via vPIC. Each record includes the canonical Mfr_ID, full legal name, common short name (e.g., "Honda"), country, and the list of vehicle types the manufacturer produces (Passenger Car, Truck, Motorcycle, Bus, MPV, etc.). Pass the optional `manufacturer` param to substring-search Mfr_Name. 100 records per page. Backed by NHTSA.gov; data is public-domain US government records.

Enumerate every model a manufacturer sold in a given model year via NHTSA's vPIC taxonomy database. Returns canonical NHTSA Model IDs + names plus the Make ID + name for reference. Useful as a discovery step before VIN decode (when the agent only knows make + year) or as input validation for vehicle.recalls / vehicle.complaints. Backed by NHTSA.gov; data is public-domain US government records.

Vehicle 360 — decode a VIN and get its full safety picture in one call. Returns the decoded vehicle (make, model, year, trim, engine, plant, body class, drivetrain — NHTSA vPIC) plus that exact make/model/year's open safety recalls (with park-it / park-outside / over-the-air-update flags) and NHTSA owner complaints (crash/fire/injury/death flags). recalls and complaints are keyed to the decoded make+model+year, so they describe THIS vehicle, not a generic feed. Each section reports found/error independently. Pass vin (17 chars); optional modelYear disambiguates pre-1980 VINs. Used for used-car due diligence, fleet safety, insurance. Individual sources: /api/vehicle/vin-decode, /api/vehicle/recalls, /api/vehicle/complaints.

NHTSA recall campaigns for a US vehicle by (make, model, modelYear). Returns every open + historical campaign with the NHTSA campaign number, manufacturer, affected component, plain-English summary/consequence/remedy text, and the parkIt / parkOutside fire-risk advisories. Backed by NHTSA's public recalls database; data is public-domain US government records.

Live US severe-weather alerts from the National Weather Service. Pass a point ("lat,lon") to get every active watch, warning, and advisory for that exact location, or an area (2-letter US state or marine zone code) for area-wide alerts. Optionally filter by severity or urgency. Each alert returns the event type, severity, urgency, certainty, headline, affected-area description, issuing office, recommended public response, onset / expiry / end times, and the full hazard description plus protective-action instructions. Results are sorted most-severe first and capped by limit, with the true total reported. Public-domain NOAA / National Weather Service data, refreshed in real time.

Current weather conditions for a US ZIP code (temperature, wind, humidity, conditions). Backed by the US National Weather Service (api.weather.gov) — public domain, no rate-limit pressure on commercial use.

Fetch a Wikidata entity (Q42, P31, etc.) — structured knowledge-graph record with labels + descriptions + aliases in selectable languages, claims (property → value statements grouped by property ID), sitelinks (Wikipedia article title per language). 110M+ entities. CC0 public domain. Pass languages= as comma-separated codes (default "en") to control which language strings are included; pass maxClaimsPerProperty to cap how many statements come back per property (default 10).

Fetch a Wikipedia article summary in any of 30 supported languages. Returns title, displayTitle, lang, pageId, description, extract (plain text), extractHtml, lead image, canonical URLs, last-modified timestamp, word count, license, and an attribution string. Backed by https://<lang>.wikipedia.org/api/rest_v1/page/summary. Content is CC BY-SA 4.0 with attribution provided.

English dictionary lookup via dictionaryapi.dev (Wiktionary-sourced). Returns full entries with IPA phonetic transcription(s), audio pronunciation URLs, and meanings grouped by part of speech. Each meaning carries definitions with usage examples and per-definition synonyms + antonyms. CC BY-SA 3.0/4.0 — attribute when redistributing. Useful for vocabulary agents, writing assistants, language-learning tools.