information-retrieval

Fetch a Wikidata entity (Q42, P31, etc.) — structured knowledge-graph record with labels + descriptions + aliases in selectable languages, claims (property → value statements grouped by property ID), sitelinks (Wikipedia article title per language). 110M+ entities. CC0 public domain. Pass languages= as comma-separated codes (default "en") to control which language strings are included; pass maxClaimsPerProperty to cap how many statements come back per property (default 10).

Open Library book metadata search. Lookup by free-text query (matches title + author), or by individual title / author / ISBN (10 or 13 digit). Each record includes Open Library work key, title, author names + Open Library author keys, first publish year, edition count, cover image URL, sample ISBNs, publishers, languages, subject tags, fulltext flag, ebook access tier (public/borrowable/printdisabled/no_ebook), and canonical openlibrary.org URL. CC0 public-domain metadata.

Look up a public GitHub repository by "owner/name" slug. Returns full name, owner, description, homepage, default branch, primary language, topics, license (SPDX key + name), counts (stars / forks / watchers / open issues / subscribers / network), size, timestamps (created/updated/pushed), visibility, has-issues/projects/wiki/discussions flags. Unauthenticated GitHub access is rate-limited to 60 req/hour per server IP — returns 429 UPSTREAM_RATE_LIMIT when the bucket is empty.

Resolve a research organization via the Research Organization Registry (ROR). Pass id (a ROR id like 056y0v115 or its full URL) to fetch one org, or name to search by free text. Returns the canonical ROR id and name, organization type, status, founding year, location (city, country, GeoNames coordinates), website, Wikipedia link, external identifiers (GRID, ISNI, Wikidata, Crossref Funder), parent/child relationships, and aliases/acronyms. Data: ROR, free and CC0. The canonical institution key in scholarly metadata — pair with /api/papers/search and /api/paper/doi-lookup (author affiliations) and /api/research/author (ORCID). Use to disambiguate an institution name to a stable id before joining datasets.

Search public GitLab projects (keyless), ranked by stars. Each result: full name, path, description, star and fork counts, web URL, last-activity timestamp, and topics. Complements code.repo-lookup (GitHub) for cross-host repository discovery.

Look up any US public K-12 school (~102k, NCES Common Core of Data). Search by name (partial), district (LEA name, partial), state (2-letter), city, zip, or exact ncessch (12-digit NCES id). Each school: NCES id, name, district + LEA id, address, phone, lat/lon, school level (1=primary 2=middle 3=high 4=other) and type (1=regular 2=special-ed 3=vocational 4=alternative), charter/magnet/virtual flags, enrollment, teacher FTE, grade span, CCD year. Results ordered by enrollment. Higher-ed sibling: /api/edu/college-scorecard. Public-domain federal data.

Search crates.io for Rust packages (keyless). Each result: name, latest stable version, description, total + recent downloads, and repository/homepage/documentation links. For agents discovering or vetting Rust dependencies.

Search the npm registry for JavaScript/TypeScript packages (keyless). Each result: name, latest version, description, keywords, publisher, last-publish date, and npm/homepage/repository links. For agents discovering or vetting dependencies.

Unified scientific literature search across arXiv (preprints), PubMed (biomedical), and Semantic Scholar (cross-field, with citation counts). Returns a flat array of papers with stable schema: source, sourceId, doi, title, authors, abstract, year, publishedAt, citationCount, url, pdfUrl. Partial failures surface in the errors array rather than failing the whole call. Optional filters: since (YYYY-MM-DD), sources (subset), limit (max 20 per source).

Enumerate every model a manufacturer sold in a given model year via NHTSA's vPIC taxonomy database. Returns canonical NHTSA Model IDs + names plus the Make ID + name for reference. Useful as a discovery step before VIN decode (when the agent only knows make + year) or as input validation for vehicle.recalls / vehicle.complaints. Backed by NHTSA.gov; data is public-domain US government records.

Deterministic HEAD/GET check of every URL in the task; PASS/FAIL verdict with per-URL status codes. Post-deploy verification SKU (RQ-BO-DELEGATE-02).

Resolve DNS records using DNS-over-HTTPS and return structured JSON for infrastructure, security, and agent workflows.

Search Wikipedia articles. Returns title, snippet (highlighted match), pageid, wordcount, and direct article URL. Use ?q=YOUR_QUERY plus optional and lang=en|de|es|zh|ja|fr and limit=10. Built for AI research agents and fact-checkers needing ground-truth article discovery (300+ languages, CC BY-SA).

Fashion brand ethical sourcing check — labor practices, environmental impact, animal welfare, and supply-chain transparency for any apparel brand, grounded in Wikirate, the UK Modern Slavery Statement Registry, the Fashion Transparency Index, the Responsible Minerals Initiative, and litigation trackers. Free open-registry sources only, never a paid rating service.

ESG framework navigator for reporting and compliance agents. Compares GRI, ISSB, CSRD, TCFD, and CDP, shows which applies to a given company, and how they interoperate.

Party/social board-game finder by group size, vibe, and setting — including drinking-game and family-mixed-ages fit, grounded in current web sources (never BoardGameGeek data).

Party/social board-game finder by group size, vibe, and setting — including drinking-game and family-mixed-ages fit, grounded in current web sources (never BoardGameGeek data).

Borrower health-factor lookup by EVM address. Returns current health factor, collateral, debt, and protocol across all monitored lending markets.

ESG framework navigator for reporting and compliance agents. Compares GRI, ISSB, CSRD, TCFD, and CDP, shows which applies to a given company, and how they interoperate.

Generate an AI-powered similarity key for global/international address matching. Handles international address formats and variations across countries.

Standardize a country name and return additional country information including ISO codes, currency details, internet code, and international calling code.

Fetch any public web page and return its main content as clean Markdown, ready to feed to an LLM. Boilerplate (nav, ads, footers) stripped. Input: url (public http/https). Returns {url, markdown, word_count}.

Fetch any public RSS or Atom feed and return clean JSON: feed title plus items with title, link, published date, and plain-text summary (no XML parsing needed). Query: url (feed URL), limit (1-50, default 20). Use to monitor news, blogs, releases, changelogs, or podcasts on a schedule.

Get timezone information for a country code, city name, or coordinates. Returns IANA timezone, current UTC offset, DST status, and current local time.