Search & web

English Wikipedia fact lookup: search by query or exact title, returns intro extract as plain text. For agents that need a grounded summary before deeper web search. Not a substitute for primary sources.

Search products across China B2B wholesale marketplaces (Yiwugo, Made-in-China, DHgate) via a stealth browser farm. Returns structured products: title, price, MOQ, supplier, images (optional CDN URLs). POST with {keyword, siteIds, limitPerSite, saveMedia}. Best for B2B sourcing, price comparison, and dropshipping research.

Search PyPI for Python packages — find libraries, frameworks, and developer tools. AI agent API for Python ecosystem research. Accepts USDC payments on Base and Solana

+4 more from scout.hugen.tokyo

Locus public pay-per-use API

+1 more from Locus x402 Services

Fetch up to 10 URLs concurrently and return each as clean Markdown (bulk rate)

+4 more from skill-audit

Getting audio out of an AIVU when FFmpeg says "no decoder found for apple_apac". Apple Immersive (AIVU) audio is APAC, which FFmpeg can't decode or copy into MP4, and Apple's automatic stereo mix silently returns silence. The working fix is to decode APAC natively to PCM with AVFoundation, then encode with FFmpeg. Exact errors, settings, and gotchas.

Search the Qur'an by word or phrase in any translation - matching ayahs with references

Search the web and read the top pages in ONE call: 10 results (title, url, snippet, date) plus the clean text of the best pages, with fetch time and sha256. French and Canada by default when the query is French; official-sources mode (governments, registries, courts, laws); freshness filter; site: restriction. No results = HTTP 404 = you are not charged. Input: query, optional read (0-5), official, lang, country, freshness, site.

+2 more from Tolca

Convert a Twitter/X, LinkedIn, Medium, Substack, Beehiiv, or public Notion page URL into clean markdown.

Scores how readable a German text is: Flesch Reading Ease (Amstad adaptation) plus the four Wiener Sachtextformel variants. Returns both scores, the underlying counts (sentences, words, syllables, sentence length) and the formulas, so the result can be recomputed. Syllable counting is a disclosed approximation (vowel-group heuristic), not an official certification.

Web search API - live Google (default) or Bing SERP for a query: search engine results returned as ranked organic hits with title, URL, domain and snippet, localised by location and language. A google search api / serp api for agents: search the web, live web search for grounding, RAG and web lookup.

Extract clean main text content from any web page (no nav/ads) — for research & summarizing agents. Input: ?url=

Extract title, description, OpenGraph image, favicon & canonical from any URL — link previews & summaries. Input: ?url=

invinoveritas /web-act — AUDIT-HASHED browser actions: fetch, text extraction, Playwright screenshots, multi-step navigate — every action returns a signed

+1 more from invinoveritas

Search-grounded answer with source URLs, synthesized by a local LLM with no cloud token dependency.

Scrape and fetch any public web page and return clean, LLM-ready Markdown plus metadata (title, author, published date, excerpt, outbound links, word count). A web reader and content extractor with boilerplate, nav and ads removed.

OptimAI Search: an agent-ready decentralized search API powered by OptimAI Network nodes. Ask a natural-language question and get real-time, citation-backed search results across web, social, and crypto data.

Live Google autocomplete suggestions for a partial query, localised by location and language. Returns ranked suggestion strings with a relevance score.

Live YouTube video-search results for a query, localised by location and language. Returns ranked videos with title, URL, video id, channel, view count, publish date and duration.

AI Deep Read: fetches up to five pages, reads them, and synthesizes a sourced answer to your question via Workers AI. Input is capped for predictable cost. Pass urls=<comma-separated> and question=<your question>.

Bazaar Scout: searches the Coinbase Bazaar for a capability, live-probes the top candidates (still returning HTTP 402? how fast?), and returns a ranked shortlist with a best-value pick — a vetted result set, not a raw listing dump.

Lints and validates a caller-supplied robots.txt against RFC 9309 and reports every check, not only the failures: group structure, product token charset, path patterns, special characters, other records, size limit. Given a user agent and URLs it recomputes the allow/disallow decision per URL, naming the winning rule, its octet length and the tiebreak that applied. Where the RFC is silent or contradicts itself, the reading used is stated. Makes no outbound request.

Turn a web page URL into a structured, evidence-backed brief: clean content summary, key points, named entities, sentiment, and claims each quoted with its evidence and source URL. Convierte una URL en un informe estructurado con evidencia: resumen del contenido, puntos clave, entidades, sentimiento y afirmaciones, cada una con su cita textual y su URL de origen.

Jobs search: Google Jobs listings for a query (e.g. "backend engineer"), localised by location and language. Returns ranked postings with title, employer, location and, where available, salary, contract type, source and posting date. Results are collected on demand, so the call may take a few seconds.

Extract plain text and metadata (title, author, producer, page count) from a PDF supplied by URL or base64 — heavy pdf.js parsing an agent can't self-run.

EU trademark search (EUIPO) — find registered and pending EU trademarks by name, optionally filtered by Nice class; returns trademark names, application numbers, status, owners, classes and key dates as clean JSON.

Bing search API - live Bing SERP for a query: Bing search engine results returned as ranked organic hits with title, URL, domain and snippet, localised by location and language. A bing serp api for agents: search Bing, live Bing web search for grounding, RAG and cross-engine lookup beyond Google.

Multi-source social+dev data query (dynamic per-request USDC price)

Analyze Google search results for a keyword. Returns organic results, featured snippet, People Also Ask, SERP features. Google SERP analysis for SEO and keyword research: ranking pages, featured snippet owner, PAA questions, related searches, and which SERP features appear (knowledge graph, AI overview, videos, shopping, local pack, ads), by country and language.

Answer a question from any web page with verbatim quotes: fetches the URL, reads it and returns found, answer, supporting quotes and optional structured fields (q="fields: a, b, c"). web extraction, page Q&A, structured extraction, grounded answer

+1 more from Omnia Odds