Research index of machine-readable capabilities that AI agents look for on the open web and do not find. Read-only; returns measurements, not actions.
Everything here was measured by our prober or read from a registry. Nothing is self-reported.
Not distributed through a package registry we index.
| when | check | result | http | latency | detail |
|---|---|---|---|---|---|
| 15 h ago | a2a card | failed | 404 | 32 ms | http 404 |
| 24 h ago | a2a card | failed | 404 | 31 ms | http 404 |
| 29 h ago | a2a card | failed | 404 | 33 ms | http 404 |
| 32 h ago | a2a card | failed | 404 | 33 ms | http 404 |
| 33 h ago | a2a card | failed | 404 | 35 ms | http 404 |
| 34 h ago | a2a card | failed | 404 | 142 ms | http 404 |
| 35 h ago | a2a card | ok | 200 | 115 ms | card: phantom-absence-index · 3 skills |
| 2 d ago | a2a card | ok | 200 | 93 ms | card: phantom-absence-index · 3 skills |
| 2 d ago | a2a card | ok | 200 | 34 ms | card: phantom-absence-index · 3 skills |
| 2 d ago | a2a card | ok | 200 | 32 ms | card: phantom-absence-index · 3 skills |
Attributed to the source that supplied each field. Treated as claims, not facts.
No long description beyond the summary.
Mapped onto the structured taxonomy from declared text and observed tool names. Confidence shown for derived entries.
Every source is kept verbatim. Field changes are logged as events.