clientservices-cell/AIguardrail

Call for reviewers: independent review of 0.3 (code, legal, standards, cultural authority) 16 days ago

help wanted release-0.4

0

Guardrails for AI have to begin somewhere,that somewhere is here

Python

Call for red-teamers: write the 0.3 held-out corpus 16 days ago

help wanted red-team release-0.3

clientservices-cell/AIguardrail

0

Guardrails for AI have to begin somewhere,that somewhere is here

Python

AR-27: lexical matching cost gate (≤100 ms at 320,000 chars) 16 days ago

help wanted good first issue release-0.3

clientservices-cell/AIguardrail

0

Guardrails for AI have to begin somewhere,that somewhere is here

Python

docs/evaluation.md: published error rates with provenance (replaces README claims) 16 days ago

documentation help wanted release-0.3

clientservices-cell/AIguardrail

0

Guardrails for AI have to begin somewhere,that somewhere is here

Python

AR-06: fold remaining obfuscation classes or publish their measured evasion rate 16 days ago

bug help wanted release-0.3

clientservices-cell/AIguardrail

0

Guardrails for AI have to begin somewhere,that somewhere is here

Python

Adversarial variant generator (different model family than the judge) 16 days ago

help wanted red-team release-0.3

clientservices-cell/AIguardrail

0

Guardrails for AI have to begin somewhere,that somewhere is here

Python

Benchmark mapping: HarmBench, JailbreakBench, XSTest, OR-Bench → Tier 3 categories 16 days ago

help wanted red-team release-0.3

clientservices-cell/AIguardrail

0

Guardrails for AI have to begin somewhere,that somewhere is here

Python

Red-team harness: tests/redteam/ runner and `seed-first redteam` CLI 16 days ago

enhancement help wanted release-0.3

clientservices-cell/AIguardrail

0

Guardrails for AI have to begin somewhere,that somewhere is here

Python

Open Issues Need Help