All projects matching “reasoning”

Autonomous agent execution (multi-step reasoning + tools). Engines: cheap agents/oss-20b or premium agents/gpt-6-sol; stream=true streams SSE step events. Ceiling = engine base + max_steps x step + code_exec calls ($0.002 each, max 3 per task) (charged_ceiling_usd).

List live ERC-20 approvals for a Base (8453) address: token, spender, current allowance, unlimited flag. status ok (complete, approvals found) / none (complete, zero active) / unknown (data incomplete; reason given; never reported as none). Pass ?address=0x... Errors: 400 invalid address; 503 indexer/RPC unavailable (not charged). Read-only; never signs.

Call any view/pure function with a human-readable signature on Ethereum, Base, Arbitrum, Optimism, Polygon or BSC: decoded result, raw hex, block number, chain id; 422 with revert reason on revert.

Validates one email (email=) or up to 50 (emails=comma list, same price): RFC 5322 syntax, normalized form, MX records (A fallback), disposable, role account, free provider, typo suggestion, and a deliverable/risky/undeliverable verdict with reasons. No SMTP probing.

Takes a kind 9735 receipt directly or fetches it from relays by event id, then runs eight named checks and reports each one separately with its reason. The receipt signature and the signature of the zap request enclosed in the description tag are verified per BIP-340. The invoice is decoded and its amount is compared against the amount tag of the zap request, since those two can disagree and only

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.

Use before buying or approving an unknown ERC-20 token on Base. Rule-based check straight from the chain, without AI - contract and proxy (upgradeable?), owner and whether it was renounced, risky owner functions in the bytecode (mint, pause, blacklist, fees, trading switches), owner share of supply and DEX liquidity on Uniswap V2/V3 and Aerodrome in USD. Returns ok, caution or avoid with reasons i

Check an exact npm or PyPI package version immediately before installation using current registry, vulnerability, malicious-package, withdrawal/deprecation, and verified provenance evidence. Returns ALLOW, REVIEW, BLOCK, or UNKNOWN with machine-readable reasons.

Pre-send check for an XRP Ledger payment: whether the destination is activated, requires a destination tag, blocks or pre-approves senders, can hold the token (trust line, limit, freeze, issuer approval), is blackholed, and whether the source can afford it. Returns ok_to_send, send_with_caution, or will_fail with reasons. Useful before any irreversible XRP Ledger payment.

Check an unsigned Solana transaction before signing. Send its base64 serialization; malformed input is rejected before payment. We simulate it on mainnet and return ALLOW, WARN or BLOCK with SOL and token balance changes and reasons, including dangerous approvals, owner changes, excessive outflows and redirected swaps. Solana only. The published sample is synthetic and only shows an HTTP 402 quote

Which API should I call? Describe a task in plain words and get the 1-5 best x402 APIs for it, one per seller, with evidence: 30-day unique payers, repeat calls per payer, last call, scanner traffic excluded, a live unpaid check that each pick answers 402 right now (with its live price and latency), the input example the seller declared, reason codes and risk flags, plus a cheaper proven alternati

Check whether a domain or email address is trustworthy before you contact it, sign it up, or trust it. Returns a trusted/caution/high_risk/unknown verdict with reasons, based on DNS and mail health (MX, SPF, DMARC), domain age and registrar (RDAP), and disposable, free-provider and typo-lookalike flags. Accepts a domain, URL or email address.

Disruption check for one airport: active FAA programs (ground stop, ground delay program, arrival/departure delays, closures) with reason and delay minutes, decoded current METAR, 12-hour TAF summary and an overall disruption level none/minor/moderate/severe.

Agent intents: verify signup email · is disposable? · check DMARC before outreach · role-account risk. One call returns syntax, MX, SPF, DKIM, DMARC, disposable, role, provider, score 0-100, light domain enrichment, and recommend accept|challenge|reject with reasons. Production 0.10 USDC; demo free rate-limited. x402 on Base for AI agents.

Trust check for any x402 pay-per-call API URL. Live-probes the target: verifies a valid 402 payment challenge, consistency between the challenge and the /.well-known/x402 manifest, payTo address validity, price sanity, Bazaar listing status, and TLS basics. Returns a GO / CAUTION / STOP verdict with reasons.

Request an https URL and report whether it is reachable, its status, every redirect hop with timings, key and security headers (HSTS, CSP and others), and the TLS certificate with its issuer, the names it covers and the days until it expires. An unreachable URL is a result too, with the reason.

NDJSON to a JSON array. POST newline-delimited JSON; the response is a pretty-printed array of the parsed values. Blank lines are skipped and a line that does not parse is refused naming the 1-based line number — which is the reason to run a parser over a log file instead of wrapping it in brackets.

Bitcoin and digital-asset adoption scores for the world's 100 largest banks, as CSV. Answers questions like: does a given bank offer Bitcoin custody or trading, how has its position changed, and which banks lead. One row per scoring change since the index began, each with the bank, the activity (custody, trading, stablecoins, tokenization and 12 more), old and new values, a reason, a primary sourc

Honeypot check, rug check and token safety check: is this token safe or a scam? Token verdict (safe/caution/danger), 0-100 token risk score and reasons. Chains: Base, Ethereum, Arbitrum, Optimism, Polygon, Robinhood Chain, Solana. Honeypot detector (EVM): simulated buy/sell with real tax. Rug check incl. Solana: owner, mint, blacklist, pause, proxy, mint/freeze authority, liquidity, holders, age.

Payment security firewall scan for an OUTGOING x402 payment: PII/secret leak detection in payment metadata, nonce replay detection, overpayment detection, prompt-injection-triggered payment analysis (fast + deep tiers), canonical-USDC asset verification, merchant pinning, velocity/spend caps, and counterparty reputation cross-check. Returns allow/flag/block with per-check reasons and an Ed25519-si

Is this token any good? Grade BASED/MID/COOKED/RADIOACTIVE, 0-100 score, one-liner, roast and reasons from live data: honeypot buy/sell simulation and taxes, owner powers (Base) or mint/freeze authority (Solana), liquidity, volume, buys/sells and pool age across all DEX pools. Body {"tokenAddress":"0x..."} or {"chain":"solana","tokenAddress":"<mint>"}. Synchronous.

Enriched prospect record: everything in Basic plus buying signals (last 90 days of news, SEC filings), open roles from public job boards, a 0-100 ICP fit score with reasons (optional icp input), a sales brief built only from cited facts, next actions and roles to target. Every item cites a source URL. No people are named unless public. $0.75 USDC.

Base token risk check before a swap: send a token contract address, get ok / caution / avoid with reasons. Reads the contract (ERC-20 metadata, owner, upgradeable proxy, mint / pause / blacklist / fee selectors in bytecode) and its DEX liquidity (Uniswap + Aerodrome pools, read on-chain). Deterministic, no LLM.

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

Which x402 endpoint should I call? Describe the job in plain words; get the 3 best endpoints from different providers, each health-checked live just now, with its current price quote, its inputs and the reasons — ranked over the whole Coinbase Bazaar catalog by fit, real paying demand and health. Uncharged when nothing passes.

OpenAI-compatible chat completions backed by DeepSeek (GET probe variant). Answers open-ended questions and returns reasoned analysis.

CipherOwl ExpressScan Deep: four-hop risk report with reasons, graph and PDF. One address per request. Seven-day same-address rechecks. Website: https://x402.cipherowl.ai. Response example is illustrative, not a live result or valid payment receipt.

Celo ERC-20 risk check from live chain state. Returns a single verdict (LOW_RISK/CAUTION/HIGH_RISK, summary, oneLiner, reasons) plus market data (DexScreener/GeckoTerminal). Covers owner/renounced, paused, supply, known stablecoins (USDC, USDT, USAT, USDm), proxies (EIP-1967/1822/OZ/1167) with implementation analysis: verified source, risky selectors, upgrade authority (EOA vs Safe/timelock), forw

Check whether a drug is currently in shortage in the FDA Drug Shortages Database, by generic/brand name or NDC. Returns the FDA status (Currently in Shortage / Resolved / To Be Discontinued), affected presentations, availability, FDA-published shortage reason, and posting dates. Public-domain FDA data via openFDA.

Is this Base token safe to buy? Simulates a real buy and sell (honeypot + hidden tax test), checks owner powers (mint, blacklist, fee changes), whale concentration, liquidity lock and scam lists. Returns scam / high_risk / caution / low_risk with reasons.