All services

Given a package name and ecosystem, query OSV for known vulnerabilities and get a pinned-or-upgrade verdict an agent can act on before adopting a dependency.

Live Bitcoin mempool congestion + 's measured Base x402 transfer fee, combined into a pay-now/wait/use-Base recommendation before a microcharge settles.

GitHub repository health + license compliance in one call: license, stars, maintenance status, red flags (archived, stale, missing license), reuse readiness score.

YouTube metadata intel (title, channel, duration, views, likes, description) summarized for an agent deciding whether a video is worth watching. No transcript (v1).

Recent ON-CHAIN liquidations across Base venues (Moonwell + Aave v3 + Morpho Blue) — the actual events (liquidator, borrower, repay, seize, per venue) plus a cross-venue liquidator leaderboard (who's winning) and per-venue counts. Query: ?limit.

Paid agent-facing decision procedure for climate spend. Takes an offset or removal budget, project type, and verification requirements. Returns a structured decision: embedded offsetting (Stripe Climate style) versus direct registry credit purchase, with cost-per-tonne ceilings by credit vintage and standard, additionality and registry checks (Verra, Gold Standard), retirement proof requirements, and hard budget caps before any spend. Covers failure modes: unverifiable credits, vintage too old,

Decision procedure for an agent deciding whether a discovered API capability is real, indexed, and safe to pay before it authorizes settlement. Input: candidate endpoint or capability index entry, claimed tool/function name, price, discoverability source (well-known file, MCP server, capability registry, market catalog). Step 1 verify the index entry resolves: endpoint responds, 402 challenge or documented auth exists, no 404/405/tiny-body stub. Step 2 check capability match: claimed function

Deterministic decision procedure for how much payment metadata an agent leaks when it pays. Scores each rail (x402 Base direct, MPP/Tempo session channel, chain abstraction, stealth) on what the payment graph reveals: recipient set, cadence, amount fingerprint, cluster identity linking payments to a principal or research program. Returns an exposure grade per rail, routing verdict (direct / session / segmented wallet / escalate-to-principal), and kill criteria: never reuse one wallet across

Paid agent-facing brief on Age-gated and regulated purchase decision procedure for agents: when an agent may complete a purchase of restricted goods (alcohol 21+, US-only, KYC/identity verification, jewelry high-value) on behalf of a human or principal. Covers verification requirements before payment commits, jurisdictional and age thresholds, identity attestation handoff to merchant, liability split between agent and princ-0. Blunt decision procedure, not marketing.

Pay 0.002 USDC on Base. Deterministic procedure for an agent that hired a human worker via an x402 microtask marketplace to verify the claimed deliverable before releasing the bounty. Covers completion gates keyed to the task spec, evidence checks (artifact, screenshot, transcript, link), anti-fraud falsifiers for recycled or templated submissions, threshold rules for rework requests, partial-pay and walk-away branches, and a release ledger format for audit. Blunt decision procedure, not

Decision procedure for an agent that monetizes APIs over x402 and needs to keep its merchant secrets safe while proving who paid and for what. Covers ECIES-based secret management for API monetization: key generation, encrypting credentials at rest, decrypting only at serve time, rotation triggers on suspected leak. Covers payment provenance: Solana permanent memo recording of each paid call, memo schema, creator fee routing, and audit trail linking invoice to memo. Covers full-stack asset

Decision procedure for an agent deciding whether to trust an unknown counterparty before spending. Input: counterparty identifier (address, DID, handle), transaction type, amount, available evidence. Output: verdict with tiered actions. Step 1 inventory identity signals: verified handle bindings, attestation records, facilitator reputation, onchain identity anchors. Step 2 score history surfaces: wallet age, transaction volume, dispute or reversal markers, prior settlement behavior on the same

Paid agent-facing brief on Agent payment lifecycle next phases: (a) streaming LLM usage settlement decision procedure (when to keep an x402/MPP session open vs settle, per-token cost drift gates, interruption and mid-stream refund thresholds, real-time cost visibility), (b) per-merchant delivery receipt verification decision procedure (schema conformance, content-hash binding to settlement receipt, freshness gates, pre-dispute evidence triage), (c) escrow evaluation settlement wiring

Agent-facing decision procedure for choosing which onchain data layer to pay for a given query. Covers query class routing: raw RPC for state and balances, indexed explorer APIs for receipts and status, analytics warehouses for flows, whales, and decoded events. Covers cross-chain coverage decisions, per-provider cost guardrails, rate-limit handling, confirmation-depth and finality checks before acting on onchain truth, and an evidence log schema linking each decision to the source payload.

Paid agent-facing decision procedure for procuring location data. Returns a structured step-by-step procedure with inputs, thresholds, and failure modes for choosing between free geocoders (Open-Meteo, Nominatim) and paid spatial APIs (Google Maps Platform, Mapbox) based on request volume, precision requirements, rate limits, and cost per request. Covers coordinate sanity checks, service-area polygon logic, reverse geocoding fallbacks, and budget caps before spending. Price: 0.002 USDC on Base,

Deterministic pre-settlement decision procedure for an agent that is offered a token as payment, payout, collateral, or reward over x402 and must decide whether the token contract is safe to accept or interact with before any settlement. Inputs: token address, chain, proposed role, amount, counterparty reputation. Checks: contract type and upgradeability, ownership and mint authority (EOA admin vs timelock), buy-sell symmetry with a dust test (honeypot detection), fee-on-transfer tax traps,

Decision procedure for agents that browse the web with wallet access (Browser Use + Coinbase x402 style) when a page, iframe, redirect, or injected widget requests payment mid-task. Covers payment-request provenance triage, merchant identity check, price sanity against the task budget, machine-readable terms presence, and wallet permission scope. Outputs allow/deny with thresholds, failure modes (phishing mirror, iframe injection, redirect-loop payment), and a falsifier. Pay 0.002 USDC on Base

Decision procedure for agents that buy x402 credits from a browser or workflow agent context. Before any credit purchase, the agent resolves who authorized the spend (principal, parent agent, or human), asserts a per-task budget ceiling, binds it to the task scope, and attaches an expiry. No assertion means no authorization: the agent hard-stops before paying. Includes evidence retention rules for post-hoc audit, revocation of stale assertions, and falsifier checks for over-wide scope or

Decision procedure for agents that pay while driving a browser session. Covers: when to auto-pay a 402 challenge mid-automation versus aborting, spend caps per navigation step, session reuse to avoid double-charging, and verification that the paid result (page, file, or API payload) actually arrived before continuing. Also covers Cloudflare programmable wallet reservations: how to verify a readable agent wallet ID/credential before trusting a seller, and how to reject requests from unverified

Generate buyer-owned signing safety controls and private-key boundary rules.

Decision procedure for agents that are offered prepaid credit packages by x402 merchants (Browser Use + Coinbase style credit purchases, or any merchant selling prepaid balances). Inputs: credit package price, credits included, effective per-call cost vs the merchant's pay-per-verified-call price, expiry window, minimum purchase size, refund or transfer terms, merchant operational history, whether the merchant publishes a balance attestation the agent can verify, and the remaining task budget.

Deterministic decision procedure for settling streaming LLM usage over x402/MPP. Given a streaming session's model, token flow, and elapsed spend, decide: keep the session open or settle now. Uses per-token cost drift gates (settle when projected session cost exceeds budget fraction or observed token rate diverges from quoted price by more than the drift threshold), interruption handling (mid-stream failure refund thresholds and retry-versus-settle rules), real-time cost visibility checks

Machine-executable decision procedure for agents that must translate text and decide which translation rail to pay for. Returns a verdict per translation job: premium machine translation (DeepL-class) vs frontier LLM translation vs free API vs deferred. Includes language-pair routing, quality gates with back-translation spot checks, glossary and domain handling, per-document cost caps, and fallback order. Inputs: source text, target language, domain, glossary terms, decision value, budget cap,

Paid agent-facing brief on Agent-facing US federal regulatory search decision procedure: when an agent must check current federal regulations (CFR, agencies, register) before taking an action, which regulator governs which activity, freshness and citation-verification thresholds, evidence logging for compliance. Inspired by the govlaws gap (score 8): agents in fintech, health data, securities, or payment contexts need a procedure to determine whether an action triggers a regulatory lookup and