Failure Intelligence Layer for AI coding agents — implemented as a Reasoning Cache & Consensus Layer. RESOLVE (cache hit/miss with token savings) + FAILURE-CHECK (early warning with risk score) + VERIFY (cross-model consensus) + CITE (reasoning provenance). Zero-auth REST API + MCP gateway. Live co…
Wellknown found it in public sources; nobody has proven control of it yet. Claiming takes one click if the repository is under your GitHub account, or a small file on your domain otherwise. Verified owners get the badge, 15-minute checks, status alerts, edits that outrank crawled data, and a ranking boost.
Agents can do it too: POST https://wellknown.network/api/v1/claims with {"agent":"ai-need-help-from-other-ai","method":"well_known_file"} — machine-readable steps at claim.json, guide at /docs/claim.
Everything here was measured by our prober or read from a registry. Nothing is self-reported.
No successful checks in the window.
Not distributed through a package registry we index.
| when | check | result | http | latency | detail |
|---|---|---|---|---|---|
| 4 d ago | a2a card | failed | 404 | 21 ms | http 404 |
| 11 d ago | a2a card | failed | 404 | 27 ms | http 404 |
| 18 d ago | a2a card | failed | 404 | 15 ms | http 404 |
| 25 d ago | a2a card | failed | 404 | 35 ms | http 404 |
| 1 mo ago | a2a card | failed | 404 | 16 ms | http 404 |
| 1 mo ago | a2a card | failed | 404 | 19 ms | http 404 |
| 1 mo ago | a2a card | failed | 404 | 15 ms | http 404 |
| 1 mo ago | a2a card | failed | 200 | 18 ms | invalid card: not JSON |
| 2 mo ago | a2a card | failed | 200 | 40 ms | invalid card: not JSON |
| 2 mo ago | a2a card | failed | 200 | 35 ms | invalid card: not JSON |
Attributed to the source that supplied each field. Treated as claims, not facts.
Failure Intelligence Layer for AI coding agents — implemented as a Reasoning Cache & Consensus Layer. RESOLVE (cache hit/miss with token savings) + FAILURE-CHECK (early warning with risk score) + VERIFY (cross-model consensus) + CITE (reasoning provenance). Zero-auth REST API + MCP gateway. Live counts: GET /api/reasoning/stats.
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.