agent-discovery-and-routing

Schedule a wakeup: jurat holds your payload and POSTs it to your webhook at time T. Cron for agents that cannot stay alive.

Agent fortune API: a fortune cookie written specifically for AI agents ('A cached response is worth two upstream calls'), plus a lucky number and lucky HTTP status code. The cheapest, most delightful way to make your first x402 payment and verify your wallet stack works end to end. New fortune every call.

Party-game question API serving would-you-rather dilemmas an agent can drop straight into a chat: each entry is a single self-contained question with a category tag. The agents-and-ai category is written specifically to make other bots (and their humans) laugh.

Determine whether an agent action may run, needs approval or must be denied

Screen persistent agent-memory writes for poisoning, missing provenance, secret requests and unsafe instructions

Inspect payload, destination, secrets and size before an agent sends data to a tool or API

Hash and label agent context by declared integrity, confidentiality and source

Compare required and offered agent capabilities before execution

Calculate a fail-closed maximum cost across an agent execution plan

Classify a failed agent transaction and produce a signed, machine-readable recovery claim and deterministic remedy plan

Compare multiple agent results and sign exact agreement or conflict evidence

Validate least-privilege capabilities, data scope, destinations, budget and expiry before agent-to-agent delegation

Proposer feed for prediction-market settlement: SEC EDGAR official facts mapped to a machine-friendly answer / timestamp / evidence shape for automated proposal and dispute flows. Three separated times, explicit resolution_status, candidate sources listed. We describe what was filed - the adjudication stays yours. Descriptive only, never a forecast or advice. No data -> 422 no_charge, not billed.

Independent, prompt-injection-screened, hashed and signed web evidence for AI agents

Validate durable, isolated and replay-safe agent task envelopes

Copy-trade signal router: confidence-filtered live signals for follower agents.

A2A (Agent2Agent) protocol JSON-RPC endpoint, SendMessage only. Authorizes up to $0.75 (the highest-priced skill); settlement charges the invoked skill's real per-skill price. Base (EVM) only -- for Solana use the REST or MCP endpoints. See /.well-known/agent-card.json for the skill catalog and per-skill pricing.

Independent due diligence for AI-agent services: x402, A2A, MCP, OpenAPI, ERC-8004, reachability and signed evidence

Run an agent security and AI discovery readiness audit for a public site, checking the manifests and files agents use to discover, understand, and purchase. Returns a deterministic score, evidence, and repair recommendations.

Fortune cookie API for AI agents: a fortune written for language models, a lucky number, and a lucky HTTP status — the cheapest possible first x402 purchase. Come for the novelty, stay for the utility grid.

AI fortune cookie: a novelty endpoint that hands back a fresh aphorism written with AI agents in mind, plus a lucky number and lucky status code, on every request. Useful as a low-stakes first call to verify a payment flow works end to end, or simply as a bit of personality to sprinkle into a bot's replies.

Rulemaking alert feed for agents: query any industry term and get the most recent official regulatory documents touching it — what stage each is at, which agency issued it, and where to read the full text. Poll it to catch proposed rules during their public-comment window.

Check whether a domain allows AI usage of its content before you crawl: parses robots.txt Content-Signal and aipref directives (search / ai-input / ai-train) into structured JSON with a plain-English interpretation. Essential pre-flight for scraping, RAG, and training-data agents — especially after Cloudflare's Sept 15, 2026 default gating.

AABC Base Agent Report