Paradigm

OISG adequate by default

Admina is designed around the OISG paradigm — Open, Intelligent, Secure, Governed. A production-ready Admina install reaches the OISG adequate level out of the box, with the adequacy score computed automatically from the live runtime state — not a checklist, not a quarterly audit, not a PDF.

oisg.ai ↗ 0–100 adequacy score 4 pillars · 20 criteria Default: ≥ 80 (adequate)

What is OISG?

OISG is a public framework for evaluating whether an AI system is adequate to be trusted in production. It defines four pillars — Open, Intelligent, Secure, Governed — each with five technical criteria. Every criterion is worth five points; the total is a 0–100 adequacy score.

0–24 Critical gaps — system is not safe to deploy

25–49 Partial coverage — significant remediation required

50–79 Good coverage — ready for constrained production

80–100 OISG adequate — ready for governed production deployment

Why Admina ships OISG adequate by default

Every governance capability Admina shipped in v1.0.0 maps directly onto OISG criteria. The adequacy score is not a marketing metric — it is a runtime read of the features you have actually turned on. With the default Docker Compose stack plus a populated admina.yaml, Admina scores in the OISG adequate band with no additional configuration.

The four pillars

Open

25 / 25

Auditable by design — model, governance, and protocols are public and inspectable.

O1 Model documentation (capabilities, limitations, provenance) available to independent auditors
O2 Governance infrastructure (policy engines, decision logic) is open and auditable
O3 Communication protocols use open standards (MCP, OpenTelemetry, A2A)
O4 Open projects have community stewardship (contribution process, security disclosure, governance)
O5 Model provenance and training methodology are documented and reproducible

Intelligent

25 / 25

Measurable, sovereign, traceable — reasoning can be explained, not assumed.

I1 Model capabilities measured with benchmark results, known failure modes, confidence calibration
I2 Infrastructure supports sovereign execution (on-premise, private cloud, air-gapped)
I3 RAG pipelines are traceable (document version, embedding model, retrieval path)
I4 Agent autonomy scope is explicit, machine-readable, and enforced at runtime
I5 System can produce on demand a complete explanation of why it gave a specific response

Secure

25 / 25

Defence in depth — bidirectional, cryptographic, recoverable.

S1 Bidirectional injection defence operates on both request and response paths
S2 Agent identities are cryptographically verifiable (DIDs, Ed25519 key pairs)
S3 Transactional kill switch preserves forensic state and enables rollback
S4 PII redaction is enforced at infrastructure level before model endpoints
S5 Model supply chain integrity is verified (fingerprinting, SBOM, cryptographic provenance)

Governed

25 / 25

Continuous, automated compliance — not a quarterly audit PDF.

G1 Compliance verified automatically at runtime, not through periodic audits
G2 Immutable forensic log (hash-chained) records all interactions and decisions
G3 Human oversight is architecturally defined (which decisions, what info, what timeout)
G4 End-to-end observability in place (distributed tracing, SLOs, dashboards)
G5 Risk classification is proportional, automated, and auditable as capabilities evolve

How Admina maps onto OISG

OISG pillar Admina capabilities that satisfy it

Open Apache 2.0 source code, open plugin system, MCP / OpenTelemetry protocols, public contribution process, security disclosure policy.

Intelligent Data residency zones, sovereign LLM infrastructure (Ollama, vLLM), traceable RAG pipelines, machine-readable agent autonomy scope via admina.yaml, per-decision explanation.

Secure Bidirectional firewall and PII redaction (Agent Security + Data Sovereignty), encrypted secret vault, loop breaker kill switch, forensic state preservation.

Governed Automated EU AI Act classification at runtime (Compliance), SHA-256 hash-chained forensic black box, OpenTelemetry spans on every decision, Admina Score + OISG Score on the dashboard.

Verify your adequacy score

Once the proxy is running, the live OISG score is available from the dashboard and via the REST API. The result reflects the actual runtime state — flipping a capability off in admina.yaml immediately lowers the score.

curl http://localhost:8080/api/dashboard/oisg \
  -H "X-API-Key: $ADMINA_API_KEY"
# {
#   "total": 85,
#   "max_total": 100,
#   "level": "OISG adequate",
#   "pillars": { "open": {...}, "intelligent": {...}, ... }
# }