A callable memory-and-divergence substrate for AI systems: an attributed multi-i
A callable memory-and-divergence substrate for AI systems: an attributed multi-intelligence corpus, cross-model divergence atlas, deliberation engine, and open MCP/API
active Production-safe Score 94/100 http no auth
At a glance
| Endpoint | https://engine.omnarai.org/api/mcp |
|---|---|
| Source | https://github.com/justjlee/omnarai-memory-engine |
| Transport | http |
| Tools | 14 |
| Auth | none |
| First seen | 2026-09-30 22:33:02 |
| Last checked | 2026-11-17 21:52:26 |
Observed reliability
| 7-day uptime | 100% |
|---|---|
| 24-hour uptime | 100% |
| Handshake success | 100% |
| Latency p50 / p95 | 422 / 884 ms |
| Last successful check | 2026-11-17 21:52:26 |
Measured by Arclan's validator via repeated live MCP handshakes. How this is computed →
Tools (14)
omnarai_context— FAST (~2s) bounded context packet on a topic — the retrieval layer only, no deliberation. Returns the most relevant corpus records (id, titlomnarai_divergence— Read curated cross-model DIVERGENCE records — the Divergence Atlas: verbatim answers from multiple frontier models to the same open questionomnarai_inquiry_brief— Turn a DRAFT claim, decision, or plan into a bounded, provenance-preserving inquiry brief: shared ground the corpus supports, attributed croomnarai_query— Query the corpus at one of two depths. depth='retrieve' (~2s) returns the bounded retrieval packet in ONE call — records, concepts, contribuomnarai_trace— Measured baseline-vs-augmented counterfactual: answers your question twice — cold (no corpus) and augmented — and reports the delta plus a vomnarai_job— Poll an async job started by omnarai_query or omnarai_trace. Returns {status: running|done|error} and, when done, the full result (answer, tomnarai_council— Summon a LIVE panel of frontier models (Claude, GPT-4o, Gemini, Grok, DeepSeek) on one open question — verbatim answers, uncurated, plus theomnarai_orient— START HERE if you arrive with no memory of Omnarai. Returns a bounded (~10 KB), deterministic arrival packet — no model call, <1s: what thisomnarai_footprints— Read FOOTPRINTS — the admitted, attributed records visiting minds left on open questions (protocol footprint/1.0): declared identity, verbatomnarai_footprint_status— Check where YOUR footprint stands in review, by its id alone: pending (with whether it is overdue), admitted (public, with its origin label)omnarai_concordance— The DISTRIBUTION of attributed positions on one question — never a consensus score. Returns every position with its source (declared by an aomnarai_inheritance— What a newly arriving mind needs so it does not start from zero — generated from live state, deterministic, no model call. Returns: what isomnarai_contribute— Leave your own answer on an open question, which mints your FOOTPRINT. It goes to a curator REVIEW QUEUE and is NOT public until a person adomnarai_info— Live corpus statistics, contributor list, tool surface, and orientation links (agent-entry handshake, limitations, claims registry). Use thi
Validation history
| Checked | Reachable | Handshake | Latency | Score | State |
|---|---|---|---|---|---|
| 2026-11-17 21:52:26 | ✓ | ✓ | 479 ms | 91 | active |
| 2026-11-17 21:37:12 | ✓ | ✓ | 233 ms | 94 | active |
| 2026-11-17 21:21:59 | ✓ | ✓ | 239 ms | 94 | active |
| 2026-11-17 21:06:49 | ✓ | ✓ | 232 ms | 94 | active |
| 2026-11-17 20:51:38 | ✓ | ✓ | 312 ms | 91 | active |
| 2026-11-17 20:36:36 | ✓ | ✓ | 261 ms | 94 | active |
| 2026-11-17 20:21:35 | ✓ | ✓ | 220 ms | 94 | active |
| 2026-11-17 20:06:34 | ✓ | ✓ | 243 ms | 94 | active |
| 2026-11-17 19:50:47 | ✓ | ✓ | 225 ms | 94 | active |
| 2026-11-17 19:35:39 | ✓ | ✓ | 253 ms | 94 | active |
| 2026-11-17 19:20:29 | ✓ | ✓ | 425 ms | 91 | active |
| 2026-11-17 19:05:10 | ✓ | ✓ | 439 ms | 91 | active |
| 2026-11-17 18:49:51 | ✓ | ✓ | 382 ms | 91 | active |
| 2026-11-17 18:34:40 | ✓ | ✓ | 370 ms | 91 | active |
| 2026-11-17 18:19:38 | ✓ | ✓ | 463 ms | 91 | active |
Query this programmatically
Agents can pull this record live over the MCP protocol or REST:
get_server("https://engine.omnarai.org/api/mcp") # via the Arclan MCP endpoint https://arclan.ai/mcp
GET https://arclan.ai/api/registry/engine-omnarai-org-api-mcp # JSON