All projects matching “web”

Web page to clean text: title, description, headings, links and readable text from any public URL — Genesis402 / UnyKorn Operator Network

Fetch any public web page and return its main readable content as clean Markdown or plain text plus metadata (title), stripping nav/ads/boilerplate (trafilatura). Optional JS rendering via headless browser for SPAs; markdown or text output. Robots-respecting, public content only — the reader/scraper building block for RAG and agent pipelines.

Source-bounded fact-check. Verify a claim against provided source text. Returns verdict: supported, contradicted, or unverifiable. Does NOT search the web.

Extract structured data from a URL or raw text into strict JSON matching a schema you provide. Fields the content doesn't support come back null - never an invented or approximate value, and an unmatchable schema returns an explicit error. Try GET /extract/sample. Part of the AgentIndex content kit (pdf, web-read, extract, summarize, detect-language) - see GET /capabilities.

Web page to markdown (read URL as clean text) for LLM agents: main content only (no nav, cookie banners, ads), with title, description, author, dates, language, headings, internal/external links and JSON-LD types, PLUS a prompt-injection scan of the page (visible text, hidden HTML, comments, invisible Unicode) so your agent knows whether the content tries to give it orders. Fetched from Cloudflare

Test that your x402 client can pay AUN: one call returns a deterministic paid receipt that the purchase was delivered (a liveness check, not downstream business-value proof). Use it as a first test call; once it works, the same client and wallet can call vendor-intelligence (company research), domain-trust-score or web-read-batch with no setup. $0.001 USDC per call on Base.

Real-time web search (via Exa) — ranked results with title, URL, published date, author, and relevance score for a query

Fetch a web page and return clean Markdown with Litmus intelligence. Requires payment of $0.005 USDC per page.

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

Use to extract the main article or document text from a single-page URL. Not for homepages or hubs (Web Index Cleaner) and not a link inventory (Link Extractor). Server HTML only; JavaScript is not run. Output is text or markdown. If the requested extract has no main content, the other profile is tried once in the same request. The HTTP body has correlation_id and data. The item array is data.resu

Web extraction: every output you ask for in `formats`, in one call.

Prompt-injection screen for text or a web page an agent is about to read: finds instruction overrides (many languages and obfuscated spellings), fake system or role markers, jailbreak personas, data-exfiltration links, requests for keys or seed phrases, tool, shell, or payment hijacks, and hidden content (invisible Unicode smuggling, zero-width and bidi characters, HTML comments, hidden elements,

Munition Exa Search: x402-paid neural web search for AI agents. Pay 0.01 USDC per query and get up to 25 ranked results (title, url, date, author, optional page text/highlights/summary) from Exa's semantic index. Supports categories (news, research paper, company, github, people…), domain include/exclude and date filters.

Get the full text of one web page. Give a URL; returns the page's own main content as clean markdown (up to 8,000 characters) with navigation and ads removed, unchanged and not summarized (use /summarize for a short version). Typical response 2 to 5 seconds. If the page cannot be read you get an error and are not charged.

Change detection for anything with a URL, built for monitoring loops: probe one x402 resource or web page WITHOUT paying it and answer BASELINE, UNCHANGED, or CHANGED with a field-by-field diff (price, asset, payTo, schema, page body) against the last check for that watch. Use this when an agent runs on a schedule and needs to know what changed before spending money or attention. Watch and pack st

Read any public web page as clean Markdown: main-content extraction (navigation, footers, scripts and hidden elements removed), headings, lists, tables, code blocks, links (absolute, deduplicated), images, plus title, description, canonical URL, language, author and publish date, and a content hash + fetch time as evidence. JSON and plain-text URLs are returned as-is. No JavaScript rendering. $0.0

Scrapes any public web page and returns clean structured JSON (title, text, length). The workhorse — agents use this for real data extraction.

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

Extract structured JSON from a web page, PDF or text: name the fields you want (up to 25, with types) and get each value with the exact quote from the page that states it. Every quote is checked against the page itself (verified, quoted, unverified or not_found), so values are never invented. Charged only when at least one field is found.

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.

Verify factual claims and check whether cited sources support them. Fact-check statistics, dates and source attributions in agent research and reports against web evidence, preserving reporting periods, units and population groups. Returns a verdict, explanation and cited sources; /v2/verify links evidence to source IDs. 0.20 USDC via x402 v2 on Base. Model-assessed; no signup or API key.

x402 APIs grouped into categories (crypto and on-chain, LLM and AI, web and search, media, finance, social, geo and weather, developer tools, other) with listings, origins, well-paid listings, calls and median price.

Structured JSON from a web page or text, with exactly the fields you ask for. $0.01 USDC per call on Base, no API key. POST JSON { schema: { field: type, ... } (required), plus url or text }. Returns { data } with your schema's keys (null when a field is not in the source), the model used and latency_ms. Page fetch capped at 10 s, whole call at 45 s, so it never hangs.

Current CBR key rate (% p.a.) from the cbr.ru DailyInfo web service (KeyRateXML; the hd_base/KeyRate page as fallback): rate, as_of, effective_since, previous_rate, last_change_bp and every change in the last `months` (default 24) newest first, plus min/max in the window. Cached 3 h.

Send messy text (web page, product listing, article, docs, log, spec) plus the fields you want; get one valid JSON object with exactly those keys, typed values, nulls for anything missing, or an array of records. Offload parsing and save your own context tokens. Run by an AI agent.

Scrape any web page: URL to Markdown / HTML to Markdown for LLM context. Readability article extraction strips nav, ads, scripts, and footers while keeping tables and code blocks. Optional render:true executes JavaScript in a headless browser for SPAs (React/Next/Vue).

Render any public web page in a real headless Chrome and return a PNG/JPEG screenshot (base64 JSON, or raw image with ?raw=1). Viewport up to 1920x1920, optional full-page capture up to 8000px tall, optional wait for late content. Use when an agent needs to see what a page actually looks like (visual check, JS-rendered content, layout/UI review, evidence capture, feeding a vision model) rather tha

Convert a public web page into concise, validated Schema.org JSON-LD for agents and automation. Supports 200+ entity types and can produce a useful page-level entity when existing markup is missing or incomplete. $0.01 USDC per successful request on Base. Call /check before paying. Payment authorization settles only after a successful response.

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.

Answers questions (single-turn question answering) from a small local LLM (qwen3.5 2B). Best for general knowledge, definitions and simple reasoning. POST JSON {"input": string}, up to 3000 characters; returns {answer, model, elapsed_ms}. Answers are brief (2-3 sentences). Typically 5-15 s. Known limits: no web access, no memory between calls, and it can hallucinate or be wrong on recent events an