Skip to main content

What is live

No figures that go stale. The capability catalogue lives elsewhere; this is the maturity an investor needs so as not to buy a shadow.

LayerStatus
On-prem product: install, institute, commission, deliver with a seal[V][Verified] in operation, closed beta
Persistent agent identity, private corpus, Task Queue, bilingual Console[V][Verified]
Authentication (OIDC) and roles on the backend, not just on buttons[V][Verified]
Governance as a tray: approve means apply[V][Verified] built; generic enforcement is off by default [P][Partial]
Selection ladder (fitness): lower and middle rungs[V][Verified] measured; the reliability gate already converges in development but is not closed: its stability on new data and a measurement on a client installation are still missing [P][Partial]; routing rungs in shadow, switched off by decision [P][Partial]; recursive self-improvement not started [D][Designed]
Ontology catalog (RDF / JSON-LD, closed vocabulary, SHACL)[V][Verified] deployed as a surface distinct from the live graph; [P][Partial] no in-catalog tenancy, no automatic sync
Host federation (audited envelopes, trust policies)[V][Verified] transport; [P][Partial] envelopes are not cryptographically signed
SaaS multi-tenancy[D][Designed] last by decision

Self-improving, precisely. Variation (the agent changes skills and memory) already exists in the runtime. Measured selection is the ladder: today it recommends; it does not act on live routing, and that is a decision, not the gate holding it back. Saying “the system improves itself” skips a rung that is not there.

Commitment: we do not sell decorative governance or standard-name conformity without evidence in code. See Governance and Limits.