All projects on Base matching “decision”

Inspect the latest reviewed cyber event with public sources, affected entities, confidence, freshness, decision significance, and evidence-bearing relationships in structured JSON

Bin-packing heuristic — deterministic best-fit-decreasing capacity planning for placing items into bins, with feasibility evidence and an honest volume bound.

capability_id=decision_readiness.event_confirmation.v1; determines whether authoritative evidence is sufficient to confirm a supported event before an autonomous agent continues. Current scope: Compound Governor proposal execution confirmation. Payment alternatives: Base mainnet or Solana mainnet native USDC; select one for one assessment. testnet_only=false; mainnet_supported=true.

Agent guardrail decision engine. Call once before every agent action; returns a single decision — proceed, slow down (with a reason and wait time), or stop — based on cost budget, chain depth, step cap and retry budget, and request volume pressure. Policy thresholds are configured separately via /policy; this endpoint only reports the decision for a single action.

Central bank interest rate decisions, one card per bank: Bank of England, US Fed, ECB, Bank of Japan, Australia, Canada, Switzerland, Norway, Sweden, Mexico, Bank of Korea, Turkey, India, South Africa, China, Indonesia, Ethiopia, Russia, Egypt, Iran, Brazil. Each card: hike/hold/cut, policy rate, change in bps, vote and dissent where published, next decision date, official source_url. Ids in /cata

Upcoming high-impact macroeconomic events from the live Forex Factory calendar - central bank rate decisions, FOMC, CPI, NFP, GDP and more - each with currency, scheduled time, forecast and previous values plus minutes until release. Filter by impact and currency. The market-moving schedule trading agents check before acting, not in any LLM training set. 经济日历高影响事件. fomc cpi nfp macro events Accept

You.com Search API: real-time web search returning ranked results grouped by section (results.web, results.news), each with url, title and description; web results also carry snippets. Use when an agent needs fresh, citable web data (news, markets, company facts) to ground a decision. Query params: query (required), count 1-100 (default 10), livecrawl (web|news|all; fetches live page contents, cha

Jev Decision ($0.005/call): Ask Jev (TypeSafe System One) typed questions about one state and get numbers back, not text: noul answers the probability a yes/no is yes; choice picks an option with a probability for every option; score places the state on an ordered scale of levels with a probability for every level. Same body and answer as TypeSafe's POST /v1/systemone (model optional, state as tex

Call this before paying any agent: Should I Pay? Binary decision (PAY/CAUTION/SKIP) with confidence and expected USDC loss before sending money to an unknown agent. Is this agent trustworthy? Every response includes a shareable verdict page and card image. GET or POST with JSON body. No account, no API key

Purpose-bound Adobe Fonts (Typekit) observation (fonts) using the existing fresh Stack-Monitor. Returns stack_adobe_fonts_decision, direct versus inferred status, evidence, optional version difference against a caller-owned baseline and reusable snapshot. Missing fingerprints do not prove absence. No background scheduling, CVE, compatibility or installed-extension inventory. Existing outbound safe

The scorecard plus Messy Virgo's analyst verdict: one overall verdict (strong signal, watch, weak or red flag) with its reason, a written summary across security, performance and social, the key risks and what to watch, grounded in the 118 KPIs that ship with it, incl. honeypot, liquidity and sentiment. Call it when you need a decision-ready answer on a token: pre-trade checks, watchlist triage, p

Scheduled market-moving events for the next 7 days by default (?days= up to 90): US data releases with release times (CPI, jobs, GDP, PCE, PPI), FOMC, ECB and Bank of Japan decisions, Treasury auctions and dated crypto and regulatory milestones, each with importance 1-3 and official source. Use before any trade or scheduled action to know what is on the calendar. From official schedules, refreshed

Cross-asset DECISION brief: ONE call gives an autonomous agent a trade-ready read across China and US equities, crypto and macro. Fuses the cross-asset trend allocation (stance + long weights), crypto perp state (funding/OI), equity reads with top setups (symbol + take-profit/stop-loss), China smart-money and leading sectors, the China social-pulse leading indicator and a one-line recommendation.

Execution preflight: a chain-neutral ALLOW/CAUTION/BLOCK data-sufficiency decision for one declared action. A complete BLOCK result is charged; settlement occurs only after a successful response.

Real-time pre-trade signal: a probability snapshot of Hyperliquid's HIP-4 prediction markets - crypto price binaries, sports outcomes, tournament winners, Fed rate decisions, and more. Fields are parsed verbatim from Hyperliquid, so new market types appear automatically. Optional template/underlying filters narrow the result; limit caps rows (max 500). Subscribe to webhook alerts via GET /v1/predi

Screens a person or business name, or an NPI, against the HHS-OIG exclusion list (LEIE, Medicare and Medicaid): potential matches only, each with name score, reasons, NPI, state, specialty, exclusion type and date. Not a determination: confirm a match on the OIG online search with the SSN or EIN. Empty candidates is a paid 200. Not for employment or credit decisions. List dates and code meanings:

[Payment decision: spend policy + seller reputation risk check, one verdict] Right before an AI agent pays: POST {payment, policy, seller} -> ONE verdict pay / dont_pay / ask_human. Runs the spend-policy check (limits, rolling cap, categories, allow/deny, hours, assets/chains, approval threshold) and the x402 seller reputation check (buyers, wash share, age, concentration), with reasons and one si

Anchor an AI agent decision or audit record to Base mainnet. Submit {schema, payload_hash (SHA-256 hex, 64 chars), metadata}; service queues into a Merkle batch and returns a receipt with pending_anchor status immediately. Full Merkle proof and on-chain anchor_tx available via free GET /v1/notarize/:receipt_id after batch anchors (within batch_threshold receipts or 120s). Include Idempotency-Key h

Use this when a user or autonomous agent wants one current 4H crypto market decision selected from BTC, ETH, XRP and ONDO. Returns the Trading Zones Selector choice with direction, confidence, entry, liquidity-zone stop loss and take profit, R:R and nine indicators. Free, independently countable selector evidence is available before purchase. Price: $0.03 USDC via x402 on Base Mainnet; no API key

For $0.002, privacy-conscious email preflight: submitted addresses and request bodies are not intentionally logged in routine application telemetry (full address still reaches our server). Inspect syntax, DNS/MX, listed disposable domains and provider typos; receive structured decisions. API reverse-proxy access logging is disabled; infrastructure/payment providers may keep records. No zero-retent

Analyze operation-level risk inside consolidated MCP tools. Returns evidence-backed ALLOW, DENY, or REQUIRE_APPROVAL decisions, retry semantics, schema-drift status, and a deterministic operation effect ID. Designed for MCP tools whose command/action arguments expose operations with different risk levels.

Notarize an AI agent decision, audit record, or any payload to Base mainnet. Submit SHA-256 hash + metadata; get a tamper-proof verifiable receipt immediately. Merkle proof and on-chain anchor_tx available free after batch (~120s). Use Idempotency-Key to prevent double-charges on retry.

UK council-tax banding challenge check — neighbor-band cluster analysis against the free official VOA/SAA lookups, statutory route selection (formal proposal vs informal review, England/Wales/Scotland variants incl. the post-2023 Local Taxation Chamber), verified timelines (4/12-month decisions, 3/4-month appeals), evidence rules (the VOA rejects house-price-index data — verified), and the mandato

Verify an x402 purchase before an AI agent signs. Validate the live HTTP 402 challenge, Base network, USDC asset, quoted price, recipient, price ceiling, buyer funding, optional gas reserve, and destination hazards, then receive a machine-readable safe-to-sign, fund, review, or reject decision. No account or API key.

Call when your agent must decide whether to add, hold or reduce crypto exposure on Base: returns one decision (invest/hold/reduce/defer) with a confidence score and a suggested allocation, combining Chainlink price risk, the live Crash Shield state of the GBLIN vault and the drawdown regime into a single machine-actionable answer.

Brazil Selic interest rate — latest monetary-policy target in annual percent. Track policy decisions and benchmark borrowing costs with the observation date.

One combined go/no-go before an agent spends: PROCEED / CAUTION / ABORT from the token's market verdict, the counterparty wallet's sanctions, age and poisoning check, and — with a spender — its ERC-20 approvals. A leg that cannot be evaluated returns unknown and caps the verdict at CAUTION. Mode 'compact' returns the decision, the worst leg, and one summary per leg. Use this when an agent is about

Verify whether a medical device holds an FDA 510(k) clearance. Returns cleared/not-cleared verdict with K number, device name, applicant, decision date, product code, and review panel. openFDA 510(k) data (public domain, CC0). NOTE: 510(k) is clearance, not FDA approval.

Paid verification layer for autonomous AI agents. Verify claims before decisions using web evidence and source-backed analysis

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