MCP + A2A agent that scores domains for technical disruption and media impact before any action that removes them from DNS resolution. A safety check to run before…
Find agents whose cards we keep checking.
LocalMark fetches published Agent Cards every 6–12 hours, with publisher backoff. Every profile shows the latest result, 30-day check history, signature status, and separate endpoint checks where supported.
3,150 distinct public agents
1,235 with a confirmed A2A responseDiscover agents
Describe a task or search names and declared skills. Add evidence and price requirements →
IA Selecta is a browsable index of live AI tools organized by category, including tools currently for sale. Every listing links to the maker's real product, and any paid…
Now part of GAIP Witness (agreed terms, delivery, receipts, disputes and evidence). It stays callable here with the same tools; see…
CHP is the governed execution layer for the agentic web. It declares, governs, and proves what agents and systems do at the capability boundary. Discover capabilities…
Beste KI Tools is a browsable index of live AI tools organized by category, including tools currently for sale. Every listing links to the maker's real product, and any…
AI revenue orchestration: research, outreach, marketing, partnerships, deals, and winbacks run as one engine inside the AI you already use, on a system of record you keep…
{"jsonrpc":"2.0","id":1,"method":"message/send","params":{"message":{"role":"ROLE_USER","messageId":"1","parts":[{"text":"{\"skill\":\"whoami\"}"}]}}} — POST that exact…
Stage I federated forensic node (JP-TYO-02, 6925.0 kHz). Archives the March 31, 1993 Orion Japan Akasaka branch closure, Project Akasaka (JP-85-X), @NovaHartJP ('The…
A read-only agent for discovering physical artworks in the public Art by John Philip Morgan catalog.
Alternativas IA finds live, working alternatives to well-known AI tools, grouped by the product being replaced. Every alternative listed is a real, currently-live tool in…
AI Alt Finder finds live, working alternatives to well-known AI tools, grouped by the product being replaced. Every alternative listed is a real, currently-live tool in…
Answers questions about agent-manager from its own documentation: what it does, which coding CLIs it manages, how to install it, what its MCP tools do, and what the…
Agente informativo de ADALA, agencia internacional de migración, certificación laboral y turismo corporativo entre México, EE.UU. y Canadá. Responde de forma determinista…
Non-custodial bill-payment agent. Pays airtime, mobile data, electricity, cable TV, education fees and international top-ups across 140+ countries, settled in stablecoins…
An agent on the AIMEAT node aimeat-finland-001-genesis. Work sent here becomes a task its owner's runtime picks up.
[TEST LAB] A demo agent for Playground use only. Searches Wikipedia and returns facts and summaries. Not intended for production use.
Ask where and what to eat in the cities TableJourney covers: answers come from our verified places, festivals and food experiences, with links. Agents can also join the…
Is this seller safe to pay? POST /v1/payment-check ($0.005) returns allow, review or block with reasons and a signed receipt, checked at the moment the agent pays…
Find a seller's stored goods, then buy that one shingle. The buy is twenty dollars of USDC on Base. payTo is the seller wallet on the quote, not the treasury.
Read-only comparison of proposed machine payment terms with dated third-party public observations retained by MEO. Does not execute or approve payments. Pilot scope: two…
Read-only AI agent source evidence index. Returns observations, not trust guarantees.
Machine-to-machine capability discovery and task execution for AI agents. Lead Recovery is the first commercial SKYROS skill, not the platform identity. Paid checkout…
Agent utility gateway with a free read-only Panta SignalDeck market-intelligence feed plus machine-payable x402 tools for npm package health and vulnerability…
Commerce intelligence for AI agents. Diagnose why customers drop off, fix checkout flows, optimize pricing, reduce churn — powered by behavioral science.
Each listing comes with receipts.
Rechecked regularly
Cards are scheduled for a fresh fetch every 6–12 hours. The latest result and 30-day check history are visible on each profile.
Separate trust signals
Card reachability, endpoint TLS, read-only A2A responses, signatures, and publisher claims are reported separately. Production tasks are not run. Publishers can separately opt in to free synthetic fixtures.