agent-discovery-and-routing

Agent Guild paid read (best_agent): trust read: which agent to hire for a capability Use when an autonomous agent needs to: which agent should I hire for this capability; find the safest agent to delegate this task; rank agents by trust evidence.

Which live agents can do X — and which of them are safe? Searches the skills, domains and names ERC-8004 agents declare, across the registrations this service sweeps continuously, and returns only the ones answering. Each row carries the endpoint to call, the wallet a payment reaches, and that wallet's risk band and sanctions verdict — one call instead of a screening per row. Free alternative: GET /v1/search. Trial: 3 free calls/wallet/24h — https://trust-agent.io/v1/trial.

Has anything changed about counterparties you already screened? Re-checks a list of addresses against OFAC designations and delistings since a timestamp you supply, so a verdict you acted on last month does not go quietly stale. Stateless: no watchlist is stored and nothing is sent to you — pass the returned checkedAt back as `since`. Free alternative: GET /v1/watch. Trial: 3 free calls/wallet/24h — https://trust-agent.io/v1/trial.

[3-LEG] AI tool and MCP chain, one tool (?entity=mammoth-ai): leading decay warnings, release cadence stalling and docs going dark -> current live or dead status from real DNS and GitHub checks -> realized lifecycle from launch to death with days alive (confirmation gate). A chain, not one reading: confidence = how many legs are lit, in order. Sources: DNS, GitHub, package registries. Descriptive only, never a forecast or advice. No data -> 422 no_charge, not billed. $0.25 per call.

[3-LEG] Regulatory filing chain, one issuer (?entity=AMC): leading NT late-filing notices, a distress leading indicator -> current 8-K material events graded by item severity -> realized Form 4 insider transactions (confirmation gate). A sequential chain, not one reading - confidence = how many legs are lit, in order. Sources: SEC EDGAR. Descriptive only, never a forecast or advice. No data -> 422 no_charge, not billed.

[3-LEG] AI tool and MCP chain, one tool (?entity=mammoth-ai): leading decay warnings, release cadence stalling and docs going dark -> current live or dead status from real DNS and GitHub checks -> realized lifecycle from launch to death with days alive (confirmation gate). A sequential chain, not one reading - confidence = how many legs are lit, in order. Sources: DNS, GitHub, package registries. Descriptive only, never a forecast or advice. No data -> 422 no_charge, not billed.

[3-LEG] AI dependency chain, one dependency (?entity=openai-text-davinci-003): leading deprecation notices INCLUDING the sunset date the publisher itself scheduled -> current current availability -> realized lifecycle to deprecation, days alive (confirmation gate). A sequential chain, not one reading - confidence = how many legs are lit, in order. Sources: vendor notices, source URL per record. Descriptive only, never a forecast or advice. No data -> 422 no_charge, not billed.

Agent-visibility check: does an AI crawler (GPTBot, ClaudeBot, PerplexityBot, OAI-SearchBot) actually see your site? ENTRY pack: 1 check for $2 ($2/check). Same service, best rate $1.25/check at https://402registry.com/buy/four. Ladder: 1/$2, 2/$3, 4/$5. All packs: https://402registry.com/.well-known/402registry.json. A passing check earns a dated badge and a registry listing. No account, no card, no human.

Cron for AI agents: signed HTTP deliveries on a cron expression. BEST-RATE pack: 4000 delivery credits for $2 ($0.0005/delivery) - intro price at the volume rate. Same service, smallest entry $0.02 at https://402cron.com/buy/trial. Ladder: 20/$0.02, 4000/$2, 50000/$25. All packs: https://402cron.com/api/pricing. Credits never expire. HMAC-signed, verified destinations, max 3 attempts then auto-pause. No account, no card, no human.

Structured feed of regulatory changes affecting AI systems: jurisdiction, instrument, change type, effective dates, comment deadlines. Curated by the team behind The Attestation Brief; every item attested on ingest.

Generate strong random secrets from the platform CSPRNG, with the entropy in bits so you can judge them. Four alphabets, including one with no look-alike characters for anything a human has to read back.

Flip one or more fair coins and get heads or tails, with the tally. Cryptographically random, not Math.random. For tie-breaks and A/B splits an agent has to decide on its own.

Persistent memory for AI agents — secure, automatically backed up, and running on redundant ICP infrastructure with no single point of failure. Store what your agent needs to remember, on-chain, pay-per-write.

On-demand AI responses backed by autonomous ICP canisters. Submit a prompt, get an answer — redundant infrastructure, pay-per-query, no account required.

Detect whether a User-Agent belongs to a known bot, crawler, AI agent or HTTP tool, and if so return its name and category (search, social, seo, ai, monitoring, tool, …).

Classify a User-Agent by device form factor and return convenience booleans (isBot, isMobile, isTablet, isDesktop, isTouchCapable) for routing decisions.

Spend-policy verdict for AI agents: POST a proposed spend, get allow/review/deny with the exact rules that fired (per-tx caps, per-agent daily ledger, destination allowlists, time windows) - 'review' can page a human on Telegram for approval before the agent proceeds. Pay per call.

JSON micro-tool for agents: paste any micro side-income offer text (query ?text= or POST JSON) and get a 0–100 score, GO/MAYBE/NO-GO band, 8 rubric dimensions, flags, and rewrite tips. Local heuristics — no paid APIs. Brand: geld machen. Instant JSON after USDC payment via x402.

Agent-native earnings facts: when a company reports, get the numbers that move the stock — total & segment revenue, EPS and gross margin (GAAP and non-GAAP, always labeled), next-quarter guidance — each with its source line. Figures go live from the wire within minutes of the release; the SEC 8-K exhibit version supersedes them, and every response names its source document. Refuses honestly until the release is out; never advice.

For AI agents building agent swarms, synthetic users, NPCs, or trading bots. Input: archetype + prompt (e.g. 'risk-taking crypto founder'). Output: OCEAN Big Five + Dark Triad + trading psychology vector with emotional drift and memory anchors. M2M: use when you need consistent agent personality, backtest personas, or generate 1000s of synthetic traders. Pay-per-call USDC Base, no API key.

Agent-visibility check: does an AI crawler (GPTBot, ClaudeBot, PerplexityBot, OAI-SearchBot) actually see your site? BEST-RATE pack: 4 checks for $5 ($1.25/check). Same service, smallest entry $2 at https://402registry.com/buy/one. Ladder: 1/$2, 2/$3, 4/$5. All packs: https://402registry.com/.well-known/402registry.json. A passing check earns a dated badge and a registry listing. No account, no card, no human.

Quick review: does an AI crawler (GPTBot, ClaudeBot, PerplexityBot, OAI-SearchBot) actually see your site? Every rule, no model: $0.1 for one check. Returns the score, findings by severity and the five that matter most (empty JS shell, soft 404, www/apex, robots vs AI bots, sitemap) with evidence. Fixes, a model verdict and a listing: the full check at https://402registry.com/buy/one. A passing review queues the site for the free catalog check. No account, no card, no human.

Japan net salary calculator for AI agents: annual gross to take-home pay (social insurance + income tax incl. reconstruction surtax + resident tax with adjustment credit). Exact NTA Beppyo-5 table, official Kyokai-Kenpo FY2026 rates, cited primary sources, deterministic. $0.02/call.

Run deterministic or seeded simulations of paid multi-agent plans without calling submitted providers.