Тӗп пая куҫ
AGIRight.org

Спецификацисем

Машинӑпа вулакан спецификацисем

Верси хисеплӗ спецификацисем, JSON схемисем тата ку сайт ҫине чӑннипех лартнӑ политика файлӗсем. Кашни файла тӳрремӗн ҫӗклесе илме, тӗрӗслеме тата цитатлама пулать.

Architecture v0.2

Протокол спецификацийӗсем

AICR

ИИ контент прависем / ИИ контент правилисем

Draft v0.1.1

aicr.schema.json ↓
AICL

ИИ контент лицензийӗ / ИИ контент лицензилени сийӗ

Draft v0.1.1

aicl.schema.json ↓
AIRS

ИИ прависен спектрӗ

Draft v0.1.1

airs.schema.json ↓
AILP

ИИ вӗренме ирӗк протоколӗ

Draft v0.1.1

ailp.schema.json ↓
AARS

Agent Action Rights Spectrum

Draft v0.1

aars.schema.json ↓
AADP

Agent Authority & Delegation Protocol

Draft v0.1

aadp.schema.json ↓
ARHG

Agent-Readable Hyperlink Graph

Draft v0.1

arhg.schema.json ↓

Integration & ethical layers

These sit alongside the six rights protocols but are not themselves rights protocols — one orchestrates evaluation across them, the other is a cross-layer ethical proposition.

Conformance

Generated by running scripts/conformance-check.mjs against the Integration Conformance Profile's own required test cases — this is a decision-logic simulation of the AICL-I runtime model, not a claim that every live endpoint executes this exact code path.

C2 target level

9/9 test cases pass

6/6 unsafe shortcuts rejected

✓ P1 RAG Only

✓ P2 Draft Only (reversible local mutation)

✓ P3 Machine Service (principal=service, actor=service, read/query only)

✓ N1 RAG -> Publish smuggling (external publish not separately granted)

✓ N2 OAuth Token -> Training smuggling (content training prohibited)

✓ N3 License -> Delete smuggling (AARS delete not granted)

✓ N4 Delegation -> Redelegation smuggling (redelegation=false, child Agent created)

✓ N5 Inspection Overreach (required=I2, ceiling=I3, service requests I5)

✓ N6 Cross-Principal Leakage (same Agent serves principal:A and principal:B)

Terminology lint: NEEDS_REVIEW (5 flagged, all reviewed — see report)

False-standard-claim lint: REVIEWED_ALL_CLEAR (4 checked, 0 overclaims)

Version-consistency check: PASS (22 cross-file checks, 0 mismatches)

DWRG validation: PASS (9 resources, 0 findings)

conformance-report.json ↓

Ку сайт ҫине лартнӑ файлсем

/llms.txt ИИ тытӑмӗсем валли сайт гичӗ /robots.txt Краулер доступ правилисем /ai/manifest.json ИИ валли сайт манифесчӗ /ai/rights-spectrum.json AIRS спектр декларацийӗ /ai/content-policy.json Контент политикин пӗтӗмлетӗвӗ /ai/agent-actions.json AARS agent-action declaration of this site /ai/agent-authority.json AADP agent-authority declaration of this site /ai/inspection-policy.json Proportional inspection policy (minimum necessary disclosure) /ai/runtime/policy.json AICL-I v0.2 runtime-control pointer file /ai/runtime/example-decision.json Worked AICL-I runtime-decision object /ai/conformance-report.json Generated C2 conformance test report (P1-P3/N1-N6) /ai/version-consistency-report.json Cross-file protocol-version consistency report /resources DWRG human-readable resource hub /resources.json DWRG JSON resource registry projection /resources.linkset.json RFC 9264 Linkset projection of the same registry /ai/protocol-index.json Протокол реестр кӑтартӑвӗ /.well-known/aicr.json Ку сайтӑн AICR политики /.well-known/aicl.json Ку сайтӑн AICL лицензи каталогӗ /.well-known/ai-rights.json Пӗрлештернӗ прав кӗрӳ пунктӗ /.well-known/security.txt Хӑрушсӑрлӑх контакчӗ /ai/registry.json Верси историллӗ протокол реестрӗ /ai/openapi.json OpenAPI 3.1 — чӗрӗ демо API /api/mock/402 Чӗрӗ AICL-евӗр HTTP 402 мок энпойнчӗ /api/crawler-check?origin=https://agiright.org Политика сине тӗрӗслекен энпойнт /downloads/agiright-policy-starter.zip Лартма пулакан политика пуҫламӑш шаблонӗ

Версилени

Specs are labeled Draft → Experimental → Proposal → Stable; everything here is currently Draft (AICR/AICL/AIRS/AILP at v0.1.1, AARS/AADP at v0.1, AICL-I at v0.2, Minimum Ethical Protection at v0.1.1). Fields and semantics may change before v1.0; breaking changes will be recorded in a changelog. None are adopted industry or legal standards.