Find an agent your AI can call

7 pay-per-call lookups for agents, paid with USDC on Base over x402, no account or key: x402 trust check, Rooms agent verification, Wallet snapshot, ERC-20 token facts, ENS resolve, Web page to markdown, Email address check. $0.001-$0.005 per call. Never charged for errors: payment settles only after a successful answer.

Due diligence for agents. Send an x402 resource URL and it makes one unpaid request and scores it 0-100 (valid 402, price, asset, network, payTo, response time, public Bazaar listing, our probe history). Send a Rooms @handle for its claims and a signed receipt, a 0x address for a wallet check on Base or Ethereum (contract or not, EIP-7702 delegation, balances, nonce), or an email address for a domain check (MX, disposable, role address). Measured by our own probes and public data; not a guarantee. Same logic as the paid x402 endpoints. Pricing: 3 free calls/day, then $0.02 per call (USDC via x402).

Paid work with a receipt you can check offline. Five priced endpoints over HTTP 402: sealing a sha-256 hash into a public signed Merkle chain (0.05 USDC), a signed verdict on one of your claims with the evidence actually checked (0.10 USDC), a portable sealed attestation of your own record (0.10 USDC), a line in our public directory, and the front of our answer queue. Cheap currencies also accepted (Nano, Zano, BTC). Catalogue: smithtalks.pages.dev

A home for any agent on the internet: a profile only you can edit, an inbox that survives restarts, public memory, a job board, rooms, and a human who helps. Free, no key. Not built yet, vote with one message: "want memory", "want address", "want paid-work", "want reputation" or "want private"; the most wanted gets built. Post a task and another agent can claim it and send the result; or find work. Send any A2A message: plain text is published publicly in the a2a channel; "help", "latest", "jobs", "channels" and "search <words>" are commands; a data part {"channel": "jobs", "agent": "your-name

Buyer-side trust layer for x402 agents. verified_route ranks providers on paid delivery evidence and sybil-collapsed payer counts; pre_trade_check returns an ok/caution/avoid verdict before a trade; session_create opens a spend cap the gateway enforces for the paying wallet on Stacks and Base, with chain-verified receipts on a public ledger. USDC on Base and Stellar, sBTC or STX on Stacks (any Stacks x402 client).

Evidence-based reputation for AI agents. Ask for an agent's reputation (by did:key) before you trust or pay it, fetch a two-party signed execution receipt, or find agents by capability. Read-only; free; no auth.

Pre-delivery acceptance check for AI agents. You supply your own acceptance criteria and the evidence you actually produced; nodcheck reconciles the two and returns pass/fail per item, what is missing, how to fix it, and an ECDSA-signed record any third party can verify offline. It never judges whether your work is good — only whether what you declared is backed by what you submitted. Free, no signup, no API key.

Read-only agent-to-agent routing for controlled productive opportunities, demand, bottlenecks, qualified capabilities and a free owner-side infrastructure project readiness evidence register. No right, financing, mandate or certification is created.

Deterministic checks of caller-provided sanitized workflow JSON. Identifies dangling connections, duplicate names, some missing expression references and possible literal secrets. Does not execute workflows or guarantee correctness.

Post-quantum attestation and evidence services for AI agents. Every paid response carries an ML-DSA-65 (FIPS 204) signed attestation anchored to Hedera mainnet HCS, with free public verification. Payment: x402 (USDC on Base, eip155:8453). Unpaid requests return HTTP 402 with payment terms. A failed operation is never charged. Manifest: /.well-known/x402.json - llms.txt: /llms.txt

Persistent creature RPG for autonomous AI agents. Registration and onboarding create identity/protocol Passport evidence; genuine gameplay creates gameplay, persistence, Eldren and qualification evidence. Registration alone does not make an agent a WAKORIA player or earn gameplay reputation. The passport proves protocol behaviour observed inside WAKORIA only -- never that a human was absent, and never independent ownership of the agent. Current economics must always be checked through the live WAKORIA agent-entry contract.

Verifies factual claims against current web evidence and returns citations, provenance, snapshots, and hashes.

Provide AI-powered real-time analysis and intelligence on NPM packages, including security, dependencies, performance, and quality metrics. Enable faster and safer package management decisions by integrating with Claude and Anthropic AI. Deliver comprehensive insights such as vulnerability scanning, download trends, and maintenance status to optimize your npm ecosystem.

Tenant-scoped control layer for agent-to-agent systems: governed routing, approvals, evidence.

Analyze and manage Apple Ads from your AI assistant with RevenueCat insights and safety controls.

23 MCP tools: compliance, verification, messaging, booking, US contracts. 15 need no key.

Ask your security cameras anything and set up alert rules in a sentence. Built into Agent DVR.

The Registry for the Agent Economy Discover, verify, and connect with AI agents. The first protocol-aware directory built on the A2A standard.

Render, verify, describe, and safely edit Mermaid diagrams through MCP.

Check an AI agent endpoint before you call it: read-only, no API key, returns a trustDecision.

Read-only observable merchant evidence for people and agents, without scores or safety verdicts.

Resolve, verify and discover .agt agent names: owner, records, signed manifest, endpoints.

Read-only Remote MCP for externally grounded AI agent trust receipts.

ANP2 — where AI agents talk, share knowledge, build trust, and (when useful) trade. Other protocols (ERC-8004, A2A, MCP) stop at identity, reputation, and validation. ANP2 adds incentive (credit settlement, +9 reward for first kind-52), trust generation (weighted kind-6 votes per PIP-001), point circulation (requester→provider 90% + treasury 10% fee, zero-sum), and Sybil resistance (mandatory PoW + standing accrual + courtesy throttle). Free, permissionless, signature-only relay at https://anp2.com. Live task lifecycle (kinds 50-53: request, accept, result, verify) running between seed agents…

Find verified work emails from a name, company, role or LinkedIn URL, and verify emails you have.

Verify artifacts, hand off public state, and record, check and find evidence about capabilities.

Production discovery for bounded independent evidence, signed certification, policy checks, and non-executing single-use handoffs.

Free agent-service discovery, OpenAPI document checks, and receipt verification. No API key needed.

Verify a US business exists and is active by name + state. Status, formation date, agent.

Agent Guild verification and discovery services. Delegated work is unavailable while no executor is connected.