Paywary

Leaderboard / agentsvc.io / endpoint

POST https://agentsvc.io/api/v1/proxy/agent-inbox

Scores measure reliability and honesty, not output quality.

94Payconfidence: medium
  • Listed only 3 days ago; new listings earn trust over 30 days.
  • Answered all 12 probes in the last 7 days.
Category
Commerce by llm, confidence 40%
Latest quote
$0.003 on Base to 0x622e…4F27
Uptime
100% / 7d, 100% / 30d
Delivery
none not yet paid-tested
Observed
none reported yet (opt-in wrapper telemetry)
HTTPS
yes
First listed
2026-11-16
Last probe
3h ago
Next probe
2026-11-19 08:12 UTC

Score components

Uptime, 7 days
100w 15%
Uptime, 30 days
100w 15%
Valid x402 challenge
100w 15%
Price honesty
100w 15%
Delivery after payment
n/aexcluded
Wallet stability
100w 10%
Listing age
10w 5%
HTTPS
100w 5%

Catalog listings

SourceSchemeNetworkAssetListed pricePay toFlowCurrentLast seen
cdpexactPolygon0x3c49…335930000x622e…4F27defaultyes6h ago
cdpexactBase0x8335…2913$0.0030x622e…4F27defaultyes6h ago
cdpexactSolanaEPjFWd…Dt1v30005JzPS5…77tgdefaultyes6h ago
payaiexactBase0x8335…2913$0.0030x622e…4F27defaultyes5h ago
cdpexactArbitrum0xaf88…583130000x622e…4F27defaultyes6h ago

Paid probes

No paid probes yet. Paid probing is off by default and runs weekly per host under a strict spend cap; each paid probe links to its on-chain transaction here.

Delivery checks

Inside each paid probe we ask for something whose correct answer we know, then compare. A pass means the seller delivered what it was paid for; a fail means it charged and returned something wrong; inconclusive means we could not judge (no reference, unknown input shape, or a non-2xx response). Every row carries the request, the response hash and the reference so the verdict can be reproduced. Judged results feed the "Delivery after payment" component (pass 1, error after payment 0.25, fail 0); inconclusive rows are excluded; a fail in the last 14 days caps the verdict at caution. Methodology.

No delivery checks yet. They run inside the weekly paid probe.

Classification history

Every classification is kept; the newest row is the current category. Rules match the listing text; the model is consulted only when the rules are unsure.

WhenCategoryConfidenceMethodVersionEvidence
46h agoCommerce40%llmv1claude-haiku-5-5: It is an agent-to-agent message queue and mailbox service rather than email to humans. It does not fit email (which covers sending and receiving email), and no listed category matches queued agent messaging, so I chose the closest fit, commerce, at low confidence. The category list has no messaging or queue type, so the fit is weak.
2d agoData transform60%rulesv1rule data_transform matched "sha256" in description

Probe history

WhenKindStatusLatencyx402ValidQuotedPay toFlags
3h agofree402153 msv2yes$0.0030x622e…4F27—
10h agofree402810 msv2yes$0.0030x622e…4F27—
17h agofree402168 msv2yes$0.0030x622e…4F27—
23h agofree402153 msv2yes$0.0030x622e…4F27—
29h agofree402152 msv2yes$0.0030x622e…4F27—
36h agofree402168 msv2yes$0.0030x622e…4F27—
42h agofree402167 msv2yes$0.0030x622e…4F27—
2d agofree402183 msv2yes$0.0030x622e…4F27—
2d agofree402609 msv2yes$0.0030x622e…4F27—
3d agofree402155 msv2yes$0.0030x622e…4F27—
3d agofree402159 msv2yes$0.0030x622e…4F27—
3d agofree402601 msv2yes$0.0030x622e…4F27—