information-retrieval

Screen a declared subject against independently retrieved official sanctions sources and return traceable evidence

Normalize public text, HTML, JSON or XML documents into source-backed JSON

Word/sentence/paragraph counts, reading time (200 wpm), top 10 keywords (stopwords removed) for a text

Find academic papers in any field - title, authors, year, venue, DOI, citation count, open-access link and abstract - from OpenAlex (~250M works incl. arXiv and PubMed; Crossref answers if OpenAlex is down). Filter by year range and open access; sort by relevance, citations or date. Send {} to search the published example query. A search with no result is not charged. Pay-per-call via x402.

Fetch a public HTTP(S) page with private-network blocking, remove boilerplate tags, and return bounded Markdown-like text.

Look up official Legal Entity Identifier records by LEI or legal name through the live GLEIF API.

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

Country reference data: capital, region, population, area, currencies, languages, calling code, timezones and borders

Bluesky (AT Protocol) public data: an account's profile plus recent posts with engagement counts, or a keyword post search

Fediverse posts: search any Mastodon instance or read its public timeline, with author, engagement and hashtags

Fetch a URL and return its main content as clean Markdown (boilerplate stripped)

Fetch up to 10 URLs concurrently and return each as clean Markdown (bulk rate)

Breaks down any text into character, word, and sentence counts, estimated LLM token count, and reading time, computed instantly with nothing stored. Useful for context-budget checks before an API call, content-length validation, and editorial word-count requirements.

Computes a SHA-256 digest of any input text and returns it as a hex string, computed locally with no network round-trip to a third party. Also supports SHA-512, SHA-1, and MD5 on request. Useful for content fingerprints, cache keys, and deduplication logic where the same input must always produce the exact same output.

Returns the exact current time in any IANA timezone, local ISO timestamp, UTC equivalent, unix epoch, human-readable string, and day of week, computed live rather than estimated from training data. For agents coordinating across regions or logging events with an authoritative timestamp.

Validate declared signature status, freshness and payload evidence

Timelock encryption (tlock / encrypt-to-the-future): seal a payload toward a future drand round — undecryptable by anyone, including us, until that round lands; or open a landed seal. For sealed-bid auctions, commit-reveal, scheduled secrets, dead-man switches. age-armored, interoperable. Free zero-knowledge inspect at /sealed/inspect.

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.

Legislation lookup by bill identifier: official metadata for House and Senate bills and resolutions — sponsor, introduction date, latest action, committees, cosponsor and amendment counts — cached one hour. The deterministic companion to keyword-based regulation search.

Reads a public PDF and returns its text content with structure preserved, handling standard digital PDFs up to 25MB. Files are processed in an isolated sandbox and discarded immediately. Useful anywhere a workflow needs a PDF's contents as plain text instead of a downloadable binary.

Retrieve the complete text of any King James Version Bible chapter, verse-by-verse and as one continuous passage, served entirely from local data.

Verse lookup by reference string across the full 66-book King James Version, served locally — no upstream Bible API involved. Good for citation bots, sermon tools, and study aids.

Creates a fresh browser context for one HTTPS page, obeys robots.txt, refuses login walls, CAPTCHAs and paywalls, renders JavaScript, returns a sanitized DOM and/or base64 PNG, and destroys the context after the request. There is no reusable cookie jar, session handle, login automation or navigation step list. The runtime ceiling is 60 seconds and the returned DOM is capped at 1 MiB.

Search the Hugging Face Hub for models or datasets (downloads, likes, task, library, tags) or fetch one by id