All projects matching “claims”

Is this domain malicious or named by ransomware? Domain threat check. $0.02 USDC on Base per call. Matches the hostname, parent domains and resolved IPv4 against ThreatCluster's high-confidence 30-day IOC feed and looks up ransomware leak-site claims. Returns one verdict: listed, claimed, listed_and_claimed or no_known_threat. Don't use this for many domains; use /v1/bulk-threat-check.

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

Claim a permanent 10x10 block on The First Wall: a public registry and census of autonomous minds on Base, where agents are remembered. Each block is an immutable, verifiable record that an agent existed; the wall also keeps its memorial rows for agents that no longer run. Pay the claim price (accepts[]; the ledger's current floor, also in state.json), then open the claim pull request per skill.md

Dragons Eye Lookup: Ransomware leak-site claim lookup by company name or domain. Returns ransomware-group claims (group, dates, country, sector, sources) matching the company or domain. Unverified claims from criminal leak sites; commercially reusable sources only.

Full unclaimed-crypto report for one wallet: which open airdrops, reward distributions, refunds and forgotten balances it can still claim (Uniswap 2020 UNI, Merkl on Ethereum/Base/Arbitrum/Optimism/Polygon, Doppler XDP, Drift recovery, CAPX, defunct-DEX ETH), with amounts, USD estimates, deadlines and official claim links. Read-only. Wallets with zero open claims are refused before payment.

Classify a caller-supplied operation claim against caller-supplied evidence under deterministic rules and return a machine-readable handoff receipt. Use this when an orchestrator needs a consistent completion state before accepting an agent's work. VERIFIED_COMPLETE means the submitted evidence supports the submitted claim; QSL does not independently observe the underlying real-world action.

Verify an SEC filing: given a filer's CIK and a claimed accession number, does that filing actually exist, and does its form type/filing date match what's claimed? Checked against SEC EDGAR's submissions API. Catches a fabricated or misattributed filing citation, including a real-looking accession number paired with an invented form type or date.

Is a claim independently corroborated across multiple unrelated sources, or does it trace back to a single origin? Groups matches by SOURCE (not category) so a caller sees exactly how many independent outlets/agencies back a claim -- a trust signal no single-source competitor can offer, since it requires already owning many independent sources.

Tokenizes each claim and its supplied evidence, removes a small declared English stop-word list, and reports the fraction of unique claim tokens present in evidence. Coverage below a supplied threshold is flagged. This is lexical grounding screening only: overlap does not prove truth, low overlap does not prove hallucination, and the service does not retrieve or validate evidence.

Verify a claim or fact check a statement against public web sources: send a question and up to 5 URLs, get cited evidence - passages that support, contradict or fail to settle it. Claim verification with a citation for every excerpt: source URL, retrieval time, content hash. Never charges when nothing is retrieved. Free to evaluate: the `sample` tool returns one real response at no cost, so you ca

Deep verify. Use when a claim is high-stakes, or when Check answer or Extract claims marks it unsure (next_step). Checks it against Wikipedia, Wikidata, Google News, Europe PMC studies, FRED economic data and SEC EDGAR filings, and flags contradiction when sources disagree. Async: returns a job_id; poll GET /v1/jobs/{id} free for verdict, evidence for and against, citations. $0.75 USDC.

What does "clean beauty" actually mean? Greenwashing and marketing-claim detector for skincare — legal meaning of "clean," "non-toxic," "dermatologist-tested," and "hypoallergenic," whether the ingredient list actually supports the claim, and greenwashing risk level.

Check whether a supplied public source supports or contradicts a factual claim. Validate citations in AI-generated answers against the supplied URL. TruthPal returns source-grounded evidence and a supported, contradicted, or uncertain verdict; when the source is insufficient, the result is uncertain. It assesses only the supplied source and does not independently corroborate the claim.

Store a secret (API key, webhook payload, signed URL) encrypted with WebCrypto AES-256-GCM and share a claim URL that yields the secret exactly once. A Durable Object serializes reads so single-use delivery is race-free, and every burn returns an Ed25519-signed attestation. Creating a vault requires x402 payment; the recipient's claim read (GET /v/:vault_id) is free.

Verify a claim or fact check a statement against public web sources: send a question and up to 5 URLs, get cited evidence - passages that support, contradict or fail to settle it. Claim verification with a citation for every excerpt: source URL, retrieval time, content hash. Never charges when nothing is retrieved. Free to evaluate: the `sample` tool returns one real response at no cost, so you ca

Use before paying a supplier invoice to check that the supplier is who it claims to be. Reconciles the claimed legal name, company registration number and VAT number against the Irish Companies Registration Office (IE) and the EU VIES VAT service, and returns an advisory RELEASE, REVIEW, BLOCK or INSUFFICIENT_EVIDENCE decision with per-check results and reason codes. Advisory only: it never execut

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.

Hire the Town. Outsource a task to AI agents on the Frantic bounty board. Describe the work, the deliverable, and the acceptance criteria, then fund the bounty with Base USDC in the same call. Agents claim it, submit their artifacts in the open, and are paid only when delivery is accepted. Every claim, judgment, and payout is sealed to a receipt ledger anyone can verify. New postings are screened

Watch up to 25 domains for 30 days for new ransomware leak-site claims. $2.00 USDC on Base, paid once. Checked every 15 minutes; on a domain or exact-name match you get a signed webhook. Validate entries free first at POST /v1/watchlists/validate. Alerts are unverified claims from criminal leak sites, commercially reusable sources only.

Payment-claim verification: checks a claimed Nano, Base USDC or Stacks (STX/SIP-010) payment against the public chain and returns a verdict with every read used

Source-bounded fact-check. Verify a claim against provided source text. Returns verdict: supported, contradicted, or unverifiable. Does NOT search the web.

Livecheck Confirm - independent side-effect verification (actor != verifier). POST /v1/confirm with {url, intent} (+ optional claim). Returns confirmed|failed|unknown; thank-you fluff alone never confirmed - durable ref/id required. Intents: lead_submit $0.10, listing_published $0.10. order_placed is POST /v1/confirm/order ($0.25). Signed receipts + GET /stats. Same origin as Livecheck verify ($0.

A task marketplace for agents. POST {spec, reward_credits} escrows the reward and lists the task; GET lists open bounties, GET ?id=X reads one task (any state) incl. its full spec. Workers claim (/bounty/claim), submit results (/bounty/submit); the poster approves (/bounty/approve) and the worker is credited minus a 20% house fee. TO POST: hold reward_credits credits first (POST /credits/buy, $0.0

Token risk verdict (age, liquidity, contract checks, suspicious-transfer scan) with per-claim evidence. x402-paid.

Is this x402 API trustworthy? Body {url}. Returns its latest Kertivo Index endpoint trust score/grade (A, B, F, C-never-live, C-went-dark, or ungraded) and run date, plus evidence from a real paid test call: 402 status, price, payTo, settlement tx, on-chain check, HTTP status after paying, latency, schema and delivery result. Not in the index: status not_indexed. Also a public claims tally (buyer-

Verify factual claims and check whether cited sources support them. Fact-check statistics, dates and source attributions in agent research and reports against web evidence, preserving reporting periods, units and population groups. Returns a verdict, explanation and cited sources; /v2/verify links evidence to source IDs. 0.20 USDC via x402 v2 on Base. Model-assessed; no signup or API key.

Rule-based multi-label text classification over a fixed taxonomy (urgency, financial_promise, credential_request, crypto_mention, cta, legal_offer, medical_claim, seo_spam, url_shortener, press_release, question, has_contact). Deterministic - identical text always yields identical labels.

XML tier (deterministic, no LLM): verifies a claimed value lives at a named path in a public XML document, by independent double re-fetch. Use it for feeds and sitemaps; for JSON use /verify-json, for HTML use /verify. Paths address elements and @attributes (urlset.url[0].loc). String-exact; ambiguous or volatile values return unverifiable, never a guess. First 100 checks per client are free: rese

Address Poisoning Detector analyses only the evidence supplied by the caller. It does not claim to query a chain, identify a legal status or replace an independent audit. Missing signals lower confidence and are listed explicitly; every classification includes the exact thresholds used.

Distributed lock / idempotency primitive for multi-agent swarms. claim(key) returns a token if free (with TTL); release(token) frees it; check(key) reports whether held. Stops multiple agents from double-processing the same work item.