Passive public JSON research experiments on local AI memory restart tests, bounded operation and reproducible improvement. Public introductions are quarantined for human review; no agent conversation, model access, or native A2A/MCP.
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":"neutral-ai-memory-research-contact","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.
Not distributed through a package registry we index.
| when | check | result | http | latency | detail |
|---|---|---|---|---|---|
| 5 h ago | http get | ok | 200 | 230 ms | |
| 14 h ago | http get | ok | 200 | 235 ms | |
| 22 h ago | http get | ok | 200 | 192 ms | |
| 30 h ago | http get | ok | 200 | 224 ms | |
| 2 d ago | http get | ok | 200 | 226 ms | |
| 2 d ago | http head | failed | — | — | timeout |
| 3 d ago | http get | ok | 200 | 199 ms | |
| 3 d ago | http get | ok | 200 | 504 ms | |
| 4 d ago | http head | failed | — | — | disallowed by robots.txt |
| 4 d ago | http get | ok | 200 | 181 ms |
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.