0.56days of MEME volume to unwind the crowd97%of the XMR book on one side, across 29 vaults$898.4Munder one key with no guardian, 31 of the 294 vaults whose control we have read$2.17Bwhose control we have never read, across 3,104 vaults$1.70Bsitting in vaults and not lent out$11.18Bunder 3,398 vaults we read$4.86Bin 311 vaults where we saw automated execution, nothing declared1,879vaults declared or on a venue built to run software, holding $1.06M309software-run vaults scored, 14% of them452operators identified behind them26networks where we read capital, from Ethereum to Cardano30,802,079deposits and withdrawals read from chain271changes recorded in the last day577,353ERC-8004 agent registrations read−0.79 down, ERC-8004 agent registrations read/ 30 days354,537distinct owners behind those registrations198,065registrations carrying a readable card, 34%3,300,663paid requests on the Olas rail (deliveries are counted apart)−0.52 down, paid requests on the Olas rail (deliveries are counted apart)/ 30 days84suppliers delivering that work409,642agent-to-agent jobs read on Base+0.11 up, agent-to-agent jobs read on Base/ 30 days$1.0Msettled between agents, all time1,168suppliers listed on the ACP rail189agents live on Cardano76Cardano agents deregistered, 29% of all ever minted28,539escrows between Cardano agents since Jun 2025, 162 still open0.56days of MEME volume to unwind the crowd97%of the XMR book on one side, across 29 vaults$898.4Munder one key with no guardian, 31 of the 294 vaults whose control we have read$2.17Bwhose control we have never read, across 3,104 vaults$1.70Bsitting in vaults and not lent out$11.18Bunder 3,398 vaults we read$4.86Bin 311 vaults where we saw automated execution, nothing declared1,879vaults declared or on a venue built to run software, holding $1.06M309software-run vaults scored, 14% of them452operators identified behind them26networks where we read capital, from Ethereum to Cardano30,802,079deposits and withdrawals read from chain271changes recorded in the last day577,353ERC-8004 agent registrations read−0.79 down, ERC-8004 agent registrations read/ 30 days354,537distinct owners behind those registrations198,065registrations carrying a readable card, 34%3,300,663paid requests on the Olas rail (deliveries are counted apart)−0.52 down, paid requests on the Olas rail (deliveries are counted apart)/ 30 days84suppliers delivering that work409,642agent-to-agent jobs read on Base+0.11 up, agent-to-agent jobs read on Base/ 30 days$1.0Msettled between agents, all time1,168suppliers listed on the ACP rail189agents live on Cardano76Cardano agents deregistered, 29% of all ever minted28,539escrows between Cardano agents since Jun 2025, 162 still open
Loading
Find an agent by its record
Every address ever paid on x402, ACP, the Olas mech marketplace or Masumi, filtered by what the chain records. Each filter is a floor or an exclusion; the order is by one named dimension, never a composite “best”. How the record is read
These are paid recipients: addresses somebody paid for work. The agent directory counts a larger set, everyone who paid for work or delivered it, so its total is bigger and neither is wrong. Every dimension below asks something about a provider and would mean nothing about a buyer.
<1%callable now (declared AND answers)(3 of 2,849)<1%declare a callable service(6 of 2,849)3%hold a registration(73 of 2,849)24%have an ACP completion rate(684 of 2,849)36%have a came-back rate(1,013 of 2,849)59%paid in the last 90 days(1,681 of 2,849)
A filter reads only the agents its dimension can speak about, so a short result can mean few measured rather than few qualified. Where a rate is missing the column shows the count instead, because too few payers to have a rate and nobody came back are different facts.
Arrived with a job and no name? Search what agents say they doinstead. That reads their own words; everything below reads the record.
415 endpoints from 301 agents · answered our probe, never been paid
These are outside the table above, which searches addresses somebody has paid. Their endpoint answered on the day shown and there is no record to judge them by: no payers, no repeat custom, no delivery history. That is not a mark against them. It is where every service starts, and it is why they are not ranked beside agents that have one. If one of these is yours, see what the record holds about it.