All projects matching “reader”

Bulk web search — run up to 5 search queries in one paid call and get ranked results per query (title, URL, snippet, relevance score) as clean JSON. Same news, finance, date-range, country and domain filters as single web search, applied to every query. One payment instead of five for research fan-out, multi-query RAG retrieval and agent planning.

HTML to markdown. $0.002 USDC.

Structured crypto market signal: for each CoinGecko id return price, market cap, 24h change, 24h volume, plus a derived momentum score (-100..100), a bullish/neutral/bearish signal, and a volatility flag — enriched data an agent ingests in a trading/research loop without computing it itself. Input: ids (comma-separated).

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 change log and validation errors.

Fetch any public web page or PDF and return clean Markdown, plus title, description, author, publish date, JSON-LD and outgoing links. Built for LLM agents.

Readable text from a public webpage

Reads invoices, bills and receipts from PDF into structured JSON — vendor, customer, dates, PO, line items, discount, tax, shipping, total, balance due — and checks the arithmetic: quantity × unit price, lines to subtotal, tax rate, total and balance due. The response says exactly which figures don't add up. $0.04 per page (up to 25 pages), quoted per document.

Extract web content from any page or PDF as clean Markdown — web page text, HTML to Markdown for any URL: strips scripts, nav, ads, and boilerplate while preserving headings, links, lists, tables, code blocks, and blockquotes; extracts the text layer from PDFs. Returns Markdown body, title, word count, and a quality grade. Web reader for article and main content. For JS-rendered or bot-walled page

Reader Pro: fetch a public web page and return structured data, no LLM: OpenGraph/meta tags, parsed JSON-LD (schema.org), HTML tables as row objects, deduped internal/external links, emails/phones/social profiles, heading outline, images with alt text, plus optional CSS-selector fields.

A registry of token records with a build log. A record is written only by the token's provable controller (on Solana: the pump.fun curve creator or the mint's update authority) and every version carries that ed25519 signature, so a reader verifies against the chain, not a directory. One $0.02 x402 write in USDC on Base, Polygon, Solana or Arc; reads, pages, log and OpenAPI are free.

Business-idea generator: N random collisions of real elements (asset type x asset x pain x channel x revenue model) as raw creative material. Deterministic by seed. ?n=100&seed=42&topic=trust. Boost-start your creative business thinking.

Clean web content extraction — any URL to markdown + text + metadata

Get structured metadata for any public web page in one call: title, meta description, canonical URL, Open Graph and Twitter card tags, favicons, JSON-LD schema types, language and the heading outline. Use it to build link previews and social cards, classify or dedupe URLs, and run SEO and AI-readability audits - far cheaper than fetching and parsing the whole page.

Get structured metadata for any public web page in one call: title, meta description, canonical URL, Open Graph and Twitter card tags, favicons, JSON-LD schema types, language and the heading outline. Use it to build link previews and social cards, classify or dedupe URLs, and run SEO and AI-readability audits - far cheaper than fetching and parsing the whole page.

Daily-refreshed ranking of US exchange-listed (NYSE/Nasdaq/CBOE) operating companies with the worst combined distress: Altman Z, Piotroski F and Beneish M verdict risk points plus red-flag severity from recent filings (going concern, auditor change, restatement, delisting notice, late filing). Each row: ticker, distress score, verdict, fraud-risk, top red flags, F/Z/M. Query limit=1-100 (default 2

Extract a readable article from supplied HTML, including title, author, language, metadata, clean Markdown, links and tables. Uses Mozilla Readability with a fallback for short pages. No remote fetches or script execution; URLs resolve relative links.

Any RSS, RSS/RDF or Atom feed parsed into one shape: title, link, ISO date, author, summary and categories. Pass since to poll for changes.

Fetch any public webpage and return its clean readable text and markdown: boilerplate, nav, ads and scripts stripped. Returns the page title, clean text, markdown, word count and final URL after redirects. Input: a public http(s) URL. Errors for bad or non-HTML URLs are returned free (settlement is cancelled on failure).

Use when you need the list of pages a site publishes (to crawl it, find recent posts, or audit SEO): give a site URL (the sitemap is discovered from robots.txt Sitemap: lines, then /sitemap.xml, /sitemap_index.xml, /wp-sitemap.xml) or a sitemap URL directly. Returns the page URLs with lastmod, changefreq and priority; for a sitemap index, returns its child sitemaps and (expand=true, default) the U