peterzsob

Sgraal Memory Governance

sgraal-ai

Deterministic pre-action verdict gate for agent memory — USE/WARN/ASK/BLOCK before an agent acts on a stored memory. Governs your existing store, doesn't replace it.

Preflight validation before every AI agent action. Block hallucinations, stop drift, prove what's safe to act on. F1=1.000 across 239 corpus cases.

PR-native API governance for AI agents. Detects breaking API changes at merge time, scores blast radius, and blocks unsafe agent tool calls before production. Preflight check, risk scoring, Decision Spec v1.0.