bureau
Turns AI sessions into a human-reviewed knowledge base with trust-tiered dossiers and consistency checks.
🛡️ AgentReady threat assessment
MAESTRO 7-layer threat model + OWASP AIVSS risk score for bureau, derived from its capabilities.
AIVSS 6.1 · Medium
View MAESTRO 7-layer threat model →Overview
A Claude Code plugin that captures AI sessions into append-only logbooks and compiles them into consistency-checked cabinet dossiers gated by trust tiers (proposed → verified). It reads session content and enforces a review/trust workflow before knowledge is promoted, which is a governance-relevant surface over agent-produced knowledge.
Key features
- Append-only session logbooks
- Trust-tiered dossier promotion
- Consistency checking
Use cases
- Build a reviewed team knowledge base
- Govern what agent output becomes canon