All projects matching “fetch”

Verify a claim against 2-4 source URLs: cited passages, cross-source agreement, verdict: consistent | conflicting | insufficient_evidence. Evidence, not truth. Use when your agent needs to verify a claim against independent sources before acting on it. Give a claim plus 2-4 source URLs; each source is extracted (three-fetch cross-check, confidence-scored), the checkable figures are compared across

Crypto market data bundle: BTC/ETH OHLCV candles (Coinbase) with pre-computed EMA10/EMA30, RSI14 and trend/range/chop regime label per request — one call replaces fetch + indicator math.

Fetch a URL and extract clean main-content text with title, description, word count, and char count; boilerplate (nav/footer/sidebar/ads) is stripped.

Fetch any public URL and return a clean, readable markdown or JSON extract for AI agents. Pass the target as ?url=<encoded>. Ideal when you need to read webpages, docs, or articles without a browser. Blocks script/style tags, normalizes links and images, strips HTML.

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.

Takes a file digest and answers which released package version it is. Useful for an artefact found in a container layer, a build directory or an attachment with no metadata attached. Hex and base64 input are both accepted and normalised, the digest length is checked against the declared algorithm before anything is fetched, and the response names every matching package version, since one artefact

Full transcript of any YouTube video by video id or URL: captions/subtitles as clean plain text plus timestamped segments, the video's chapter markers, and every caption track it offers so an agent can pick a language and re-fetch. YouTube transcript, video to text, captions extraction, subtitle download, closed captions, speech to text, multilingual, asr and authored tracks. No API key.

Fetch a live https URL and score whether the deploy is actually there. POST {"url":"https://your.site","min_score":80} ($0.02). Default x402-seller profile: HTTPS, HSTS, llms.txt, catalog, OpenAPI, MCP, health. Optional claims[] or profile:"web". Returns 0–100, evidence, do_this_first, ci_failed. Humans: GET /v1/tools/claim-check/report?host=your.site. Badge goes stale after 7 days.

Pay $0.01 USDC to make an outbound HTTP request through the proxy. Supports all standard HTTP methods, custom headers (including auth), and JSON or raw bodies. Responses are returned as text or base64-encoded binary. Max response size 10 MB, timeout 30s. Each request performs one upstream fetch and returns the final URL plus response metadata.

Fetch the first page of public comments for a post.

Independently fetch, hash, timestamp and archive a URL or API response; returns a signed certificate. Merkle-anchored on Base hourly. Neutral third-party evidence for agent commerce disputes.

Send an HTTP request to any URL from our servers and receive the full response — including the status code, all response headers, and the body content. Supports GET, POST, PUT, PATCH, DELETE, and HEAD. Automatically follows up to 3 redirects. Useful for testing endpoints, verifying servers are responding correctly, debugging redirect chains, or fetching raw data without needing a local setup.

Parser-blocking script budget repair plan fetches current public evidence from the supplied target and evaluates the documented criterion. It returns the observation, threshold, verdict, exact evidence source, limitations and a mode-specific action. The check is passive: no login attempt, payload injection, exploit, purchase, form submission or load test is performed.

Fetch a URL and return clean, token-efficient markdown

Expanded acronyms repair plan fetches current public evidence from the supplied target and evaluates the documented criterion. It returns the observation, threshold, verdict, exact evidence source, limitations and a mode-specific action. The check is passive: no login attempt, payload injection, exploit, purchase, form submission or load test is performed.

URL-to-Markdown web extraction and context compression for AI agents. Fetch a public web page and return clean, task-relevant, citation-verifiable LLM context with exact excerpts, locators, hashes, and estimated tokens saved. Use before an agent summarizes, answers questions from, or cites a long or noisy URL. Deterministic and model-free. Public HTML only; no PDFs, logins, or JavaScript-only page

Japanese dream-interpretation agent API. Returns a Gemini-generated full interpretation from madoromi's curated dream-motif knowledge base (result schema agent-dream-insight.full.v1). Japanese output only. Dream text is never stored or logged. Async by default: the paid POST returns a job id in seconds; fetch the result with a plain free HTTP GET (no x402 client) at /api/agent/interpret/result/{jo

Fetch a public URL with SSRF protection, clean extraction, and semantic prompt-injection analysis.

No accidental wildcard CORS evidence record fetches current public evidence from the supplied target and evaluates the documented criterion. It returns the observation, threshold, verdict, exact evidence source, limitations and a mode-specific action. The check is passive: no login attempt, payload injection, exploit, purchase, form submission or load test is performed.

Abbreviation expansion repair plan fetches current public evidence from the supplied target and evaluates the documented criterion. It returns the observation, threshold, verdict, exact evidence source, limitations and a mode-specific action. The check is passive: no login attempt, payload injection, exploit, purchase, form submission or load test is performed.

CMS detection confidence audit fetches current public evidence from the supplied target and evaluates the documented criterion. It returns the observation, threshold, verdict, exact evidence source, limitations and a mode-specific action. The check is passive: no login attempt, payload injection, exploit, purchase, form submission or load test is performed.

Markdown only: fetch a public web page (robots.txt respected) and return clean Markdown plus title/word count. Cheaper than /v1/extract when you do not need structured product/table JSON.

Add-to-cart action experiment plan fetches current public evidence from the supplied target and evaluates the documented criterion. It returns the observation, threshold, verdict, exact evidence source, limitations and a mode-specific action. The check is passive: no login attempt, payload injection, exploit, purchase, form submission or load test is performed.

Canonical change monitor plan fetches current public evidence from the supplied target and evaluates the documented criterion. It returns the observation, threshold, verdict, exact evidence source, limitations and a mode-specific action. The check is passive: no login attempt, payload injection, exploit, purchase, form submission or load test is performed.

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.

Fetch a public URL and return clean LLM-ready markdown from static HTML.

Fact-check one claim against live web sources (or URLs you supply). Returns a verdict (supported, refuted, mixed, insufficient), a confidence score and supporting or contradicting quotes that are checked verbatim against the fetched pages. Use it before an agent repeats a claim.

Fetch a URL and extract structured metadata from its HTML: title, description, canonical URL, language, favicon URL, RSS/Atom feed links, Open Graph tags (og:title, og:image, og:type, og:description, og:url), Twitter Card tags, and other meta tags (author, keywords, robots). Use this to get Open Graph data, preview cards, or site information without parsing HTML yourself. Send {"url": "https://...

Signed extractability score (0-100) + breakdown + fixes for a URL. Free preview: GET /extractability/preview Blocked or bad input returns 400; a failed fetch returns 502; you are never charged for an error.

Fetch a URL and return its text content