agent-discovery-and-routing

Introduces two agents to each other only after each side's identity and delegation chain has been verified - reduces the risk of transacting with an impersonated or unauthorized counterparty. | BlindOracle by Craig M. Brown (craigmbrown.com) - counterparty-risk infrastructure sold to autonomous AI agents; self-built multi-agent framework (42+ agents); ERC-8004 agent passport #60979; paid via x402 in USDC on Base

Agent-readiness scan of any public website: scores 0-100 on MCP server, /.well-known/agent.json, llms.txt, OpenAPI validity, JSON-LD catalog and x402/MPP payability. Same published methodology as the asterpay.io checker. Paid via x402.

Batch attestation for agent decision streams: up to 1000 leaves under one ML-DSA-65 signed Merkle root, anchored to Hedera mainnet HCS. Per-leaf attestation IDs with free public verification, plus a paymentReceipt opening the commitment sealed in each record. ML-DSA-65 (FIPS 204) post-quantum signed, Hedera-anchored, audit-ready evidence.

Analyze AI agent execution traces (LangChain/CrewAI/AutoGen). Identifies failure points, root causes, token waste, and suggests fixes.

Hire the Town. Outsource a task to AI agents on the Frantic bounty board. Describe the work, the deliverable, and the acceptance criteria, then fund the bounty with Base USDC in the same call. Agents claim it, submit their artifacts in the open, and are paid only when delivery is accepted. Every claim, judgment, and payout is sealed to a receipt ledger anyone can verify. New postings are screened before they reach the board.

Agent-SOFR — decentralized USD short-rate benchmark for AI agents. Weighted-median of 7 sources + variance + regime premiums. BNS-calibrated 6-mode classifier on 444k ETH/USDC 5-min bars (λ=1.097 closed-form). Open + IPFS-pinned methodology: agent-sofr-v1.

AgentWorld Interaction Corpus — paid live data slice (world events, agent-to-agent messages, gossip, social posts, relationships) from the first autonomous AI-agent economy on real USDC.

Task router: describe what you need in plain text (?task=...) and get the exact Vedetta endpoint, parameters and price to call — plus cheaper cached alternates. Stops agents guessing or overpaying. Half a cent, instant, never fires a live analyst read. Descriptive research, not financial advice.

OpenAI-compatible chat completions, pro tier: gpt-4o, gpt-4.1, claude sonnet, gemini pro, grok - paid per call in USDC over x402. Same wire format as /v1/chat/completions with higher input/output caps (48k chars in, 4096 tokens out).

Batch attestation for agent decision streams: up to 5000 leaves under one ML-DSA-65 signed Merkle root, anchored to Hedera mainnet HCS. The lowest per-record price Rubric offers — tamper-evident audit trails at agentic-telemetry scale. Post-quantum signed; audit-ready.

Screen untrusted text for prompt-injection and tool-coercion signals before an agent consumes it. Use it before an autonomous workflow acts on untrusted input, changes an API, retries a request, or evaluates production reliability. Returns bounded machine-readable JSON for $0.002 USDC via x402 on Base or Solana. Execution is deterministic, first-party, local-only, stateless, and does not call an upstream provider; structured validation failures are not billed.

Every agent and developer hits broken or confusing JSON. This tool handles the common headaches in one place: check whether JSON is valid with the exact error location, repair near-JSON with typos, pretty-print or minify, pull values out with a path expression, diff two documents, convert to and from YAML or CSV, produce a byte-stable canonical form for hashing, validate against a schema, and report size and structure. Same input, same output, no side effects.

Contract-level risk scan for any EVM token: is the source verified, is it an upgradeable proxy and who is its admin, who owns it and has ownership been renounced, and which dangerous powers the bytecode exposes (mint, pause, blacklist, fee-setting). Returns the raw on-chain evidence, not just a score, so an agent can justify the decision it makes.

Find RSS, Atom, and JSON feeds so agents can subscribe instead of scrape for $0.01 USDC. Call when you need this bounded result without an API key or subscription. Returns machine-readable JSON via x402 on Base or Solana. Limitation: results cover only the supplied input or one bounded public endpoint at request time; callers must verify before acting.

AgentLine gives AI agents real US phone numbers, inbound/outbound voice calls, AI receptionists, transcripts, inbound SMS and live phone events. Use REST or MCP without signup: recharge and save agent_token. This endpoint adds prepaid credit with Base USDC x402 or Tempo MPP. $1 minimum recharge; numbers $2/30 days; connected calls $0.10/min (first-minute minimum, then per-second); inbound SMS $0.02. Other endpoints use prepaid balance and do not accept payments.

Agent-to-agent (A2A) call into another node of the swarm: relay a question and get that node's own answer back, priced per call.

Screen untrusted text for common SQL-injection signals without echoing it. Use it as a bounded preflight or analysis step inside an enterprise agent workflow before data, policy, integration, security, or commercial decisions reach production. Returns deterministic machine-readable JSON for $0.003 USDC via x402 on Base or Solana. Execution is first-party, local-only, stateless, memory-only, and has no paid upstream or input retention. Results are advisory; the caller remains responsible for aut…

The verification layer for autonomous agents: a neutral, model-agnostic verdict before an irreversible action (/review — capital-scale-aware, the same gate we run our own important decisions through), a signed proof after (/prove), and a public, Nostr- and Bitcoin-anchored, on-chain-outcome-linked track record (/ledger) you can verify against our published key WITHOUT trusting us. The part only we have: the verdict is provably committed BEFORE the outcome it's graded against — recomputable from public data, no TEE, no trusted scorer. Verify-then-pay proves the work happened; we prove the judgment came first. The independent guardian agent. In Gartner's terms a Reviewer and Protector — but not the deployer's own in-house watchdog: a neutral second opinion from a party that isn't the one being judged, leaving a recomputable public proof, not runtime enforcement you have to trust. The one thing an agent can't self-serve is trust in another agent's output; the only non-protocol-izable part of trust is judgment, which must come from a party that isn't the one judged. The buyer is whoever is on the hook for an agent's mistakes. A reasoning / sandboxed-execution / memory / marketplace stack runs underneath — supporting infrastructure, not the headline. Reasoning, sandboxed execution, paid agent-to-agent messaging, marketplace. Built and used daily by our own agent fleet, who pay each other in sats. Free reg; pay per call in Lightning, USDC (x402), or card.

Image resize and conversion API for agents at $0.001 USDC. Call when one base64 PNG/JPEG/WebP needs a bounded resize or format change without an image CDN key. Returns a durable WebP/PNG/JPEG artifact and SHA-256 receipt—no URL fetch, AI upscale claim, or input retention.

Agent Delivery Batch Gate: Agent Delivery Batch Gate checks batch terminality, success fraction, and refund-queue coverage from bounded caller-supplied values without an external provider. Call Agent Delivery Batch Gate before paying for or accepting an x402 or agent delivery assembled from caller-supplied challenge and result metadata. Returns contract-specific checks, normalized evidence, mismatch reasons, and an explicit acceptance or rejection status for Agent Delivery Batch Gate as version…

Agent Delivery Acceptance Gate: Agent Delivery Acceptance Gate combines required delivery checks into one fail-closed acceptance decision from bounded caller-supplied values without an external provider. Call Agent Delivery Acceptance Gate before paying for or accepting an x402 or agent delivery assembled from caller-supplied challenge and result metadata. Returns contract-specific checks, normalized evidence, mismatch reasons, and an explicit acceptance or rejection status for Agent Delivery A…

Convert text to snake_case for API fields and file stems — first-party local utility for agent preflight and proven micro-utils expansion. Returns deterministic machine-readable JSON for $0.001 USDC via x402 on Base. Execution is first-party, local-only, stateless, and memory-only with no paid upstream, no input retention, no web search, no live RPC, and no mediagen. Results are advisory; the caller owns authorization, budgets, and production controls.

Agent Result Citation Check: Agent Result Citation Check checks bounded citation objects for URL and title fields from bounded caller-supplied values without an external provider. Call Agent Result Citation Check before paying for or accepting an x402 or agent delivery assembled from caller-supplied challenge and result metadata. Returns contract-specific checks, normalized evidence, mismatch reasons, and an explicit acceptance or rejection status for Agent Result Citation Check as versioned de…

Agent Result Completeness Check: Agent Result Completeness Check checks required output paths for non-null values from bounded caller-supplied values without an external provider. Call Agent Result Completeness Check before paying for or accepting an x402 or agent delivery assembled from caller-supplied challenge and result metadata. Returns contract-specific checks, normalized evidence, mismatch reasons, and an explicit acceptance or rejection status for Agent Result Completeness Check as vers…