Web & Data

Fetch a public HTTP(S) page with private-network blocking and extract its title, description, Open Graph image, status, and content type.

Read contract event logs across a strictly bounded block range with an optional topic0 filter and capped response count.

IP geolocation via ipwho.is. Returns country, region, city, lat/lon, timezone, ASN, ISP. Pass empty string to geolocate caller IP.

Today's full ranked CVE priorities (scores, KEV, EPSS, patch status, methodology) — or unlock every CVE route with an AIS CVE key ($19/30d): https://aislabs.ai/gateway/

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

Web content extraction: fetch any public web page and get its readable article content as clean markdown — boilerplate, nav, and ads stripped automatically. For "get me the readable text of this page" requests. Honors robots.txt and Content-Signal/aipref declarations (explicit disallow returns an unpaid 403). SSRF-guarded, 2MB cap.

Fetches a public file URL, up to 50MB, and returns its SHA-256, SHA-512, SHA-1, or MD5 digest so you can confirm a download matches its published checksum before trusting it. A supply-chain safety step for agents pulling packages, models, or binaries from the open web.

Track newly published US regulations by keyword: the latest proposed and final rules, notices, and presidential documents mentioning your topic, with issuing agency, publication date, abstract, and official document links as structured JSON. Regulatory early-warning for compliance and market agents.

Video-to-audio extraction: pulls the audio track out of any public video or audio URL (up to 25MB) and returns it as an MP3, encoded on request rather than pulled from a pre-made library. Source files are deleted the moment processing finishes. Use it to prep clips for transcription, strip audio from screen recordings, or normalize mixed formats before a media pipeline.

Bulk historical window (up to 24h) of 1-minute DEX spread statistics for a given pair, in one call. Useful for slippage calibration and backtesting. Descriptive statistics only; not investment advice.

Fetch data rows from a specific e-Stat statistical table (by id from estat.search), with all category codes (region, item, time period, etc.) pre-resolved to their human-readable Japanese labels in a single call — normally requires a separate metadata lookup and manual code-matching against the raw e-Stat API. Source: e-Stat API, government standard terms of use (CC BY-compatible, commercial use permitted). Factual statistical data only; not investment or economic advice.

Public GitHub facts: repo stats with latest release, a user/org profile, or a star-ranked repo search

Knowledge search via Wikipedia + DuckDuckGo Instant Answer. Returns article summaries, snippets, factual entities. Great for AI agent knowledge lookups.

Computed repo maintenance/abandonment verdict (score + reasoning) from live GitHub data

Search a privacy-safe metadata index derived from 77,053 archived census rows and deduplicated to 23,370 unique content hashes. Includes readiness, quarantine, domain, file type, field names and provenance hashes; does not redistribute raw fields, media or third-party content.

Validates a cron expression and lists its next several scheduled run times as ISO timestamps in any timezone, so you can confirm a schedule does what it's supposed to before deploying it. For automation and DevOps agents building or auditing recurring jobs.

Website health probe: checks whether any URL is currently reachable and returns its response time, content type, and caching behavior. Runs safely against arbitrary user-supplied addresses thanks to built-in request guarding. A lightweight heartbeat for monitoring dashboards, CI pipelines, and pre-fetch validation before a larger crawl.

Identifies which of 60+ languages a piece of text is written in, returning a confidence score and the top three candidate languages rather than a single guess. Computed locally with the input never stored. For routing multilingual support tickets, pre-checking content before translation, and moderation pipelines.

URL status checker: send any web address and get back its HTTP status code, response latency in milliseconds, and key response headers in one call. Built-in SSRF protections make it safe to point at user-submitted links. Useful for dependency health dashboards, broken-link audits, and confirming an endpoint responds before a scheduled job depends on it.

Returns rhyming words, sound-alikes, or commonly paired adjectives for any input word, ranked by strength of association. Useful for crossword and word-game agents, poetry generation, and naming brainstorms that need a wider candidate list than a model would produce unprompted.

Finds words related to any input word, similar meanings, words that sound alike, or adjectives commonly paired with it, ranked by association strength, up to 20 results per call. For copywriters, product namers, and word-game agents looking for options beyond an LLM's usual first guesses.

Financial math API: compound interest with any compounding frequency, monthly loan/mortgage payment and total interest, or ROI. Exact, deterministic.

Language detection API: identify the language of any text (60+ languages) with confidence scores and top-3 candidates — computed locally in milliseconds, text never stored. For routing multilingual content, translation pre-checks, and moderation pipelines.

Vector embeddings API: converts up to 64 pieces of text per call into 768-dimensional numeric vectors suitable for similarity comparison, no separate provider account or key needed. Pay per call in USDC, and nothing submitted is retained afterward. Use it to build semantic search indexes, cluster related documents, or de-duplicate near-identical text at scale.