information-retrieval

Read a text record from an ENS name — Genesis402 / UnyKorn Operator Network

CVE lookup

Check public domain DNS, HTTP, HTTPS, redirects, TLS certificate health and response latency in one request.

Agent researches a topic (web) and returns a concise, structured, cited brief. ?topic=. Pay-per-call in USDC on Base.

Checks if a URL supports a claim. Returns confidence score. Research agents use this to verify sources.

SHA-256 digest of text or raw bytes — Genesis402 / UnyKorn Operator Network

Compute an MD5, SHA-1, SHA-256 or SHA-512 hex digest of text.

Any public URL as clean Markdown

Pull named fields out of unstructured text as strict JSON. You name the fields, you get an object back.

Search inside one public GitHub repository: every line where a word or code snippet appears, with file, line number and a link. Reads up to 120 likely source files per call (skips vendored, built and lock files) and says how many it covered; may lag GitHub by up to 12 hours; narrow big repos with path=src/ or ext=ts. Pass ?owner=honojs&repo=hono&q=getCookie. Then read a file with /repo/file.

Diff the current vs last-known Terms of Service / Privacy Policy for a URL. Returns changed sections + a severity hint. DO NOT use for legal advice.

Federal Register activity on a topic: what published recently, final vs proposed, which agencies, what takes effect.

Extract text lines from an uploaded PDF and rebuild table rows as typed JSON. Use ONLY for structured documents; large scanned PDFs return a clear error.

Screen a wallet address or legal name against OFAC SDN (cached). Returns MATCH / NO_MATCH with matched entries. DO NOT use as legal advice or the sole KYC control.

Fetch the first page of public comments for a post.

Searches a locally harvested metadata-only index of public scientific assets from free/open APIs. Returns curated pointers, licenses, provenance, freshness hashes, and source metadata without downloading or reselling the underlying open datasets, model weights, papers, or repositories.

Searches a governed corpus of 1,131 scientific hypothesis proposals across five rigor tiers (benchmark, established_method, active_research, exploratory, speculative). Every record is IDEA-tier and unvalidated — this is a discovery layer over proposals, not results. Quarantined records (not_physical, metaphysical) are excluded at the source. Returns full honesty fields (execution_status, validation_status, promotion_eligible, lifecycle_state, governor_reason) with every result.

Capture point-in-time URL facts, response headers, a text excerpt, and a SHA-256 content hash for research and verification.

Federal rulemaking check: recent documents on a topic or docket, comment volume, and whether a comment period is open.

Sanctions screening for compliance, AML, KYC and KYB agents: use before onboarding, paying or contracting with a person or organization. Fuzzy-matches the name against the official OFAC SDN list and the UN Security Council consolidated list, aliases included, and returns scored matches with list, sanctions program, entity type and source reference. Diacritic- and case-insensitive, tunable min_score (default 0.6). One keyless USDC call.

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.

Search Users

Answer a question using current web research by synthesizing evidence from multiple sources with cited URLs.

Use for fundamentals of a European listed company (LEI, ISIN or name). Returns revenue, operating and net profit, cash flow and balance sheet from its ESEF (IFRS) annual report, with growth, margins, ROE, a score and the report link.