LLM Governance Framework
ストックにはログインが必要です
Evaluate, score and audit AI outputs before deployment
Artificial Intelligence
GitHub
Open Source
Tech
Most teams deploying LLMs have no systematic way to evaluate if their AI is behaving correctly. LLM Governance Framework fixes that. What it does: - Enforces constitutional AI policies via YAML - Scores every response 1-5 with risk transformation - Makes PASS / REVIEW / FAIL decisions automatically - Generates hashed audit logs and JSON reports - Integrates with any LLM via API Open source. Free to use. Built by TruLogic AI.
投票数: 2