All projects matching “score”

Rerank documents against a query with BGE Reranker Base (@cf/baai/bge-reranker-base). POST query plus documents[]; returns relevance scores for search and RAG pipelines.

Voxight topic brief: a sourced intelligence brief on one AI, tech, market or crypto topic, written from the signals and narratives Voxight tracked over the last 30 days (key signals with their sources, what to watch, caveats, a confidence score). Use it when an agent needs a quick cited read of what is moving around a topic. Charged only when the brief is ready: the answer is 202 with an id to pol

Prioritize up to 50 CVEs in one request using FIRST EPSS, CISA KEV, and known ransomware signals. Returns deterministic risk scores, urgency tiers, exploitation signals, vendor/product context, and remediation metadata as machine-readable JSON. Built for security automation and AI agents. No account or API key required. $0.01 per successful request via x402. Invalid input, no-signal results, and t

WalletTriage — real-time wallet risk check: dangerous ERC20 approvals cross-referenced with a live exploit threat feed. Returns risk_score (0-100), risk_level and actionable findings.

Invisible bot protection. Score form submissions 0-100 based on behavioral signals. No CAPTCHAs.

Estimate password strength: score, guesses, crack-time and feedback. Never stored.

Live X (Twitter) sentiment for any Polymarket or Kalshi prediction market. Pass the market question as q; Grok reads the last 3 days of X posts and returns a score from -100 (very bearish on the question) to +100 (very bullish), the one-line catalyst driving the chatter, and whether discussion volume is rising, flat or falling. $0.35 per call.

Liquidity pools created on Base mainnet in the last 24 hours, newest first, one page per call, filterable by exchange and flag. Each pool carries measured facts, each with the block it was read at, and true/false/unknown flags, with evidence for every true or unknown one; anything missing is stated in words. No score. Payment on Base mainnet.

Email address verification for AI agents: RFC 5322 syntax check, live MX/A DNS lookup, disposable-domain detection, role-address and free-mail-provider flags, typo suggestions (gmial.com -> gmail.com), normalized form and a low/medium/high risk score. One address or up to 20 per request, same price. No mailbox probing.

Website audit bundle for local business websites and lead qualification: performance (browser-measured), security headers and TLS, SEO basics, accessibility and AI-crawler visibility of one public page, with section scores, grades and prioritized findings, in one call.

Analyze a meal photo for visible foods, estimated food-group shares, missing groups, plant diversity and a balance score. Returns JSON with one practical suggestion. No receipt, Replate account or receipt verification is required. Visual estimates only; no exact calories or medical assessment. (0.01 USDC)

Crypto token rug-pull and junk-risk check for Base, Ethereum, BNB Chain, Arbitrum, Polygon, Optimism, Avalanche and Solana. Send a token contract address or Solana mint; get a grade (JUNK, RISKY, CAUTION, CLEAN), a 0-100 risk score and red flags: honeypot, sell tax, mint/freeze authority, owner powers, holder concentration, liquidity, pool age. Not financial advice. Free sample: https://nojunk-tok

Domain intelligence in one call: RDAP registration (registrar, created, expires, age, status, nameservers), DNS records (A, AAAA, MX, NS, TXT, CNAME, SPF, DMARC), a live HTTPS probe (reachable, status, server, redirect target, HSTS), plus risk flags and a 0-100 risk score for new, parked, unreachable or badly configured domains.

Live ENSO (El Nino/La Nina) status, strength, trend, empirical persistence odds, and sector impact scores (agriculture, supply chain, insurance, energy), synthesized from NOAA CPC RONI/ONI records

Vet an Apify actor before you spend on it. Send one actor ID (e.g. apify/instagram-scraper) and get scored JSON in seconds, with evidence and a verdict, from public metadata: pricing, output schema, maintenance, reliability, docs. Unlimited criteria: our pre-built set or your own rubric in plain English. Metadata grades what a vendor claims. The $1 full audit runs the actor and measures what it de

Interzoid Batch Data Enrichment API: enrich up to 100 JSON records per call, or a CSV/TSV file, with AI-powered company profiles, executives, industry codes, email, phone, and IP scoring, tax and customs rates, standardization, translation, or custom fields. 39 functions, results in 16 languages, processed in parallel. This job: function "business-info", 2 records at $0.25/record = $0.50 total. Ad

Deep endpoint trust/QoS report for an x402 endpoint. Everything the trust score returns PLUS history detail: the full payment-terms drift log (including custody/payTo changes), the discovery/listing timeline across directories, the paid-delivery sample log, and a summarized counts-by-outcome breakdown with latency percentiles. Raw per-probe rows are never shipped. Use for auditing or investigating

Custom-weight rerank of every cryptocurrency covered by True Value Rankings: the full TVR table recomputed with the caller's own weights for the 8 fundamental metrics, using TVR's non-public score transformation. $0.05 USDC per call. Educational model output, not a recommendation.

Analyze French or English marketing and interface copy. Returns a clarity score, repetition data, sentence metrics, CTA detection and concrete fixes.

Validate and standardize a delivery address: parsing, provider verification (US-optimized), geocoding and a deliverability score, as JSON. 0.02 USDC per call on Base. Useful before shipping to or storing an address.

Wallet risk score 0-100 with component breakdown for an EVM address.

DJZS adversarial logic audit of a prediction-market trade intent. Deterministic verdict (PASS/WAIT/FAIL) with risk score, defect flags, verdict_hash, and on-chain Proof-of-Logic receipt. Out-of-scope requests are refused WITHOUT CHARGE. Audit, not advice.

Market & brand sentiment for any keyword, brand, ticker or product: analyses the sentiment of web & news content mentioning it and returns an overall label (positive/negative/neutral/mixed), a net sentiment score (-1..1), positive/negative/neutral shares and an emotion breakdown (anger, happiness, love, sadness, fun).

Token safety scanner for Base (JSON body): 0-100 safety score, risk band, and red flags for any Base token contract.

Scan any OpenClaw SKILL.md for malware, prompt injection, exfiltration, and 37 other threat patterns. Returns risk score 0-100 and detailed findings.

Real-time geopolitical risk signal — base score + live news sentiment for any country or region

Trust score (0-100) for an x402 service listed in the Bazaar: liveness probe, on-chain payer diversity, reported-vs-verified revenue (detects inflated counters and self-dealing), and listing age. Returns full component breakdown and flags.

Agent Reputation Check by Agentropolis: give a payTo and/or an agent / A2A / MCP URL. Returns owner, verified domain, real outside buyer history, wash flags and trust score from Agentropolis. Says when coverage is limited. Deterministic, no LLM.

Paid equivalent of /api/aeo/scan — scanner for AI search visibility (AEO, GEO) and agent readiness. Triple score + AI Identity Card + top issues covering JSON-LD Schema.org, meta tags, llms.txt, robots.txt, sitemap, and agent-discovery signals for ChatGPT, Perplexity, Google AI Overviews, Bing Copilot. $0.01 in USDC (Base or Solana) — Bazaar-indexable variant; the free version at /api/aeo/scan sta

Pay $0.01 USDC to create a leaderboard or add, update, or delete one entry. Use a secret leaderboard_key UUID to continue writing to the same board. If value is null, the named entry is deleted. Public pages stay free at GET /leaderboard/{slug}. Network: Base Mainnet. Each request writes one named score and returns the board key and URLs.