All projects matching “readability”

Ambr (ambr.run): create a Ricardian contract that an AI agent signs on behalf of its principal, a person or company. Call it when your agent agrees a deal with another party (an API or compute service, a purchase, a subscription, or a delegation of authority) and needs a signed written record. Returns legal text and machine-readable JSON bound by one SHA-256 hash, plus reader and sign links; the p

Agent Readiness Scan, full report: runs all 16 checks against a domain and returns the complete machine-readable results synchronously, plus a hosted report URL.

Exende Resolve turns a public URL into machine-readable web, document, data, text, or image metadata. It detects resource type, extracts static HTML, renders JavaScript pages only when needed, parses PDF text, JSON, CSV and plain text, and returns a normalized result.

Strip scripts/styles from HTML → readable text or markdown. Offline; no network. Amp port.

Audit short landing-page copy for clarity, outcome, call-to-action, and readable length.

Settlement-backed machine evidence for autonomous agents. Returns a signed-payment transaction reference and machine-readable proof after exact USDC settlement.

Page to JSON: scrape and extract any public web page URL into clean structured data JSON. Web scraper / HTML-to-JSON extractor / readability parser for AI agents and LLMs: returns title, author, site name, published date, main article text (plain text), word count, up to 200 links and an optional short summary. Web scraping, content extraction, metadata extraction, article parsing, crawl, RAG inge

Readable text from a public webpage

Verify a Base (mainnet, default) or Base Sepolia transaction is a successful, confirmed transfer of native Circle USDC (not a look-alike token) to an expected recipient for an exact or minimum amount. Checks receipt status, canonical block, confirmations, optional payer, notBefore/maxAge windows; returns verdict valid|invalid|pending|not_found with machine-readable reasons and the matched Transfer

Paid evidence check for agents: signed record, machine-readable verification result, explicit unknowns, and a settlement receipt. A valid signature is not real-world truth.

Validate an intended paid API request against its declared contract before spending. Returns VALID, INVALID, or UNKNOWN with machine-readable reasons. Target URL is never called.

Web content extraction: fetch any public URL and get clean readable text, title, meta description, OpenGraph data, headings, links and word count as JSON. Built for AI agents that need web page content without HTML noise.

Usage info for the html-clean tool: pay this GET once to receive machine-readable instructions, then call POST /html-clean to turn raw HTML into clean structured content (title, meta, LLM-ready text, headings, links, images).

Fetch a public web page and return clean LLM-ready Markdown (Readability main-content extraction, nav/scripts stripped) plus title, byline, excerpt and OpenGraph metadata. {fullPage:true} keeps the whole body; {maxChars} caps output (default 100k). No JS rendering.

Fetch a public URL as markdown from the public HTML (Readability)

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

Extract up to ten URLs in one paid call.

Read the mandatory public disclosure of one domain and return company, postal address, e-mail, phone, VAT and register data with a source for every value.

Flesch Reading Ease, FK grade, SMOG, Coleman-Liau, ARI + hard-sentence hotspots. Offline.

Safe Read: fetch one public web page and get its clean main text, title, metadata, a sha256 content hash, and prompt-injection warnings with a 0-100 risk score (visible text, hidden elements, HTML comments, alt/meta attributes, invisible Unicode, base64). SSRF-guarded: DNS-checked and pinned public addresses only, 4 redirects max, 2 MB, 8 s, text/html and text/plain only. Errors are not charged.

Live Base snapshot for AI agents. Each GET returns the current Base block number, base fee, gas price, ETH-USD price, and a unique receipt. Price is exactly $0.01 USDC on Base via x402. No API key and no RPC method. GET /ping returns the same snapshot. Use it as a chain read or as the cheap call that proves an x402 client can pay.

Run a mix of read/watch/verify/compare/tables operations (up to 6 weight-units total — read, watch, verify, and tables cost 1 each, compare costs 2) behind a single payment instead of negotiating a separate payment for each one. Priced at a discount vs paying per-item individually.