Leaderboard / agent-kiosk.vercel.app / endpoint
POST https://agent-kiosk.vercel.app/v1/github-intel
Scores measure reliability and honesty, not output quality.
- Listed only 3 days ago; new listings earn trust over 30 days.
- Answered all 12 probes in the last 7 days.
- Category
- Web scrape by llm, confidence 50%
- Latest quote
- $0.01 on Base to 0xd842…eE95
- 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
- 59m ago
- Next probe
- 2026-11-19 11:05 UTC
Score components
Catalog listings
| Source | Scheme | Network | Asset | Listed price | Pay to | Flow | Current | Last seen |
|---|---|---|---|---|---|---|---|---|
| payai | exact | Base | 0x8335…2913 | $0.01 | 0xd842…eE95 | default | yes | 6h 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.
| When | Category | Confidence | Method | Version | Evidence |
|---|---|---|---|---|---|
| 34h ago | Web scrape | 50% | llm | v1 | claude-haiku-5-5: GitHub repository and open-source intelligence (stars, forks, releases, topic rankings) is a data lookup about developer repos, not a page fetch per se. None of the categories match GitHub stats directly; the closest fit is web_scrape since it retrieves repository pages, though enrichment or public_data are plausible alternatives. |
| 2d ago | Public data | 60% | rules | v1 | rule public_data matched "github repo" in description |
Probe history
| When | Kind | Status | Latency | x402 | Valid | Quoted | Pay to | Flags |
|---|---|---|---|---|---|---|---|---|
| 59m ago | free | 402 | 163 ms | v2 | yes | $0.01 | 0xd842…eE95 | — |
| 7h ago | free | 402 | 940 ms | v2 | yes | $0.01 | 0xd842…eE95 | — |
| 13h ago | free | 402 | 1150 ms | v2 | yes | $0.01 | 0xd842…eE95 | — |
| 20h ago | free | 402 | 1140 ms | v2 | yes | $0.01 | 0xd842…eE95 | — |
| 26h ago | free | 402 | 95 ms | v2 | yes | $0.01 | 0xd842…eE95 | — |
| 32h ago | free | 402 | 125 ms | v2 | yes | $0.01 | 0xd842…eE95 | — |
| 38h ago | free | 402 | 97 ms | v2 | yes | $0.01 | 0xd842…eE95 | — |
| 45h ago | free | 402 | 106 ms | v2 | yes | $0.01 | 0xd842…eE95 | — |
| 2d ago | free | 402 | 114 ms | v2 | yes | $0.01 | 0xd842…eE95 | — |
| 2d ago | free | 402 | 1066 ms | v2 | yes | $0.01 | 0xd842…eE95 | — |
| 3d ago | free | 402 | 823 ms | v2 | yes | $0.01 | 0xd842…eE95 | — |
| 3d ago | free | 402 | 288 ms | v2 | yes | $0.01 | 0xd842…eE95 | — |