21 services carry this tag in their source record. Tags come from the provider, not from us — a tag is a claim about what the service does, not proof that it does it well.
X Tweet Search ($0.02/call): Search X (Twitter) posts with full advanced-search syntax (from:, since:, until:, exact phrases, boolean operators). Returns up to 20 posts per call as clean JSON with metrics and entities, p...
The grounded council: we buy the facts first, then deliberate on them. Your question is scanned for a contract address, URL or $TICKER; we spend on the matching evidence (honeypot simulation, sanctions screen, page conte...
Pay-per-Attestation: an AI agent pays to seal its own decision (input hash, output, model, timestamp) in FractalAI's post-quantum L1 — Dilithium-3 (NIST FIPS 204) signed, Black-Box chained; on-chain anchoring (VAID-1) is...
Screen up to 5 Promise Gap slugs in one call — tier matrix + machine briefs. Pay $0.45 vs 5×$0.12 singles. Indicative — Gap ≠ fraud; Gap ≠ Activity ≠ Variance. Task: Call when an agent must screen a shortlist of energy/R...
Structured evaluation with TypeSafe's Jev (System One) model. Send any state plus typed questions — noul (true/false), choice (pick one), or score (ordinal scale) — and get back calibrated probabilities and confidence fo...
Issuer-prep compliance gate ALLOW / CHALLENGE / BLOCK for an RWA tokenization project. Pay $0.25 USDC to avoid acting blind on a multi‑million desk decision. Indicative — not a CRA rating or trade authorization.
Buy or sell signal, cheap ($0.05): the $1 decision engine reduced to action (STRONG_BUY..STRONG_SELL), direction, conviction, GO/WAIT for a side and each pillar's stance. A rule-based aggregation of the data, not a forec...
Machine Promise Gap pack — claim intensity vs measured activity for a slug. Pay $0.12 before allocating on a loud claim with thin life. Indicative — Gap ≠ fraud; Gap ≠ Activity ≠ Variance. Task: Call when an agent must q...
invinoveritas /signals/full — a live Hyperliquid perps read, recomputable per coin from the raw metrics we return (funding + 24h delta, basis, open interest,
Structured evaluation with TypeSafe's Jev (System One) model. Send any state plus typed questions — noul (true/false), choice (pick one), or score (ordinal scale) — and get back calibrated probabilities and confidence fo...
Structured evaluation with TypeSafe's Jev (System One) model. Send any state plus typed questions — noul (true/false), choice (pick one), or score (ordinal scale) — and get back calibrated probabilities and confidence fo...
Header + summary for a base block by number (or "latest"): hash, timestamp, tx count, gas used and base fee.
A fair random yes or no, with a cryptographic random source. For quick decisions when the options are equally good. Use to break ties.
Trending polygon DEX pairs by 24h volume (top boosted tokens on DexScreener).
Pick one or several options at random from a caller-supplied list (CSPRNG), optionally without replacement — a decision-maker for agents.
Live crypto prices: USD spot for BTC, ETH and SOL in one call, fetched per call (not cached), so the figure is the number right now. A cheap, high-frequency data lane for x402 buyers budgeting in the unit they pay with....
Publisher discovery decision fetches current public evidence from the supplied target and evaluates the documented criterion. It returns the observation, threshold, verdict, exact evidence source, limitations and a mode-...
Agent card discovery decision fetches current public evidence from the supplied target and evaluates the documented criterion. It returns the observation, threshold, verdict, exact evidence source, limitations and a mode...
Generic crawler access decision fetches current public evidence from the supplied target and evaluates the documented criterion. It returns the observation, threshold, verdict, exact evidence source, limitations and a mo...
Ask up to 20 typed yes/no, multiple-choice or ordinal-scale questions about one shared piece of context in a single call - each answered with a real probability (Jev decision primitives), not generated text. Powered by J...
Decide whether an agent should ask the human or safely infer and continue