Governed knowledge store for autonomous organizations. Every fact has provenance, every read is verified, every write is auditable.
| Guide | Description |
|---|---|
| Getting Started | Install, first vault, add, search, grep, verify in 5 minutes |
| Architecture | Package structure, layers, data flow, Protocol interfaces |
| API Reference | Complete Python SDK: Vault, AsyncVault, all methods |
| Knowledge Graph | Entities, relationships, mentions, traversal, extraction, detection |
| Trust Tiers | CANONICAL, WORKING, EPHEMERAL, ARCHIVED and search weighting |
| Knowledge Lifecycle | State machine, supersession chains, temporal validity |
| Memory Layers | OPERATIONAL, STRATEGIC, COMPLIANCE with per-layer defaults |
| Multi-Tenancy | Tenant isolation, tenant-locked vaults, per-tenant quotas |
| Encryption | AES-256-GCM, ML-KEM-768, ML-DSA-65, hybrid encryption |
| RBAC | Reader/Writer/Admin roles, permission matrix, structured error codes |
| Membrane | Content screening pipeline (innate scan, release gate) |
| Plugin Development | @embedder, @parser, @policy decorators, air-gap loading |
| Security Model | SHA3-256, Merkle trees, input validation, threat model |
| Streaming & Telemetry | Real-time events, operation metrics |
| CLI Reference | All 15 commands |
| FastAPI Integration | 30+ REST endpoints |
| Migration Guide | Breaking changes from v0.x to v1.0 |
| Deployment Guide | PostgreSQL, SSL, encryption, production checklist |
| Troubleshooting | Error codes (VAULT_000-700), common issues |
from qp_vault import Vault
vault = Vault("./my-knowledge")
vault.add("quarterly-report.pdf", trust_tier="canonical")
results = vault.search("Q3 revenue projections")
print(results[0].content, results[0].trust_tier)pip install qp-vault # SQLite, basic search, trust tiers, knowledge graph
pip install qp-vault[postgres] # + PostgreSQL + pgvector + pg_trgm
pip install qp-vault[encryption] # + AES-256-GCM
pip install qp-vault[pq] # + ML-KEM-768, ML-DSA-65
pip install qp-vault[all] # Everything