goun7

goun7/veridict

Veridict — the verdict that survived verification. An append-only, hash-chained audit standard for AI-generated work: signed evidence, blind juries, human risk ownership.

0 stars 0 forks 0 watchers Python Apache License 2.0

agent-security ai-safety audit audit-log ed25519 hash-chain llm-verification open-source

5 Open Issues Need Help Last updated: Sep 10, 2026

Open Issues Need Help

View All on GitHub

Independent verifier from the standard alone (Phase 3 exit criterion ①) about 8 hours ago

help wanted exit-criterion

0

Veridict — the verdict that survived verification. An append-only, hash-chained audit standard for AI-generated work: signed evidence, blind juries, human risk ownership.

Python

#agent-security#ai-safety#audit#audit-log#ed25519#hash-chain#llm-verification#open-source

Badge gallery: dogfood the badge on this repo's own README 9 days ago

help wanted good first issue

0

Veridict — the verdict that survived verification. An append-only, hash-chained audit standard for AI-generated work: signed evidence, blind juries, human risk ownership.

Python

#agent-security#ai-safety#audit#audit-log#ed25519#hash-chain#llm-verification#open-source

README in a second language (Turkish first) 9 days ago

help wanted good first issue

0

Veridict — the verdict that survived verification. An append-only, hash-chained audit standard for AI-generated work: signed evidence, blind juries, human risk ownership.

Python

#agent-security#ai-safety#audit#audit-log#ed25519#hash-chain#llm-verification#open-source

Canary corpus: add a secrets-leak defect class 9 days ago

help wanted good first issue

0

Veridict — the verdict that survived verification. An append-only, hash-chained audit standard for AI-generated work: signed evidence, blind juries, human risk ownership.

Python

#agent-security#ai-safety#audit#audit-log#ed25519#hash-chain#llm-verification#open-source

Expand canary corpus: 6 → 12 defect classes 10 days ago

help wanted good-first-issue

0

Veridict — the verdict that survived verification. An append-only, hash-chained audit standard for AI-generated work: signed evidence, blind juries, human risk ownership.

Python

#agent-security#ai-safety#audit#audit-log#ed25519#hash-chain#llm-verification#open-source