KEYSTONE://ON_PREM_KNOWLEDGE_INFRA
On-premise AI knowledge infrastructure for organizations that can't use cloud AI.
Query across SharePoint, file shares, databases, and email using natural language — with query-time permission enforcement and complete audit trails.
Everything runs on your infrastructure.
Query: "How did we handle that equipment failure in 2019?"
Sources: SharePoint + SMB/NFS + SQL + Email archive
Gate: Query-time ACL enforcement (inherited from source systems)
Output: Answer + citations + audit log (who/what/when accessed)The knowledge fragmentation problem
Your institutional knowledge is scattered:
- — Safety procedures in SharePoint
- — Equipment manuals on file shares
- — Incident reports in email archives
- — Work orders in databases
When engineers need answers, they spend hours searching disconnected systems — or they guess. That's how avoidable incidents and audit failures happen.
Keystone enables natural language queries across all sources while enforcing access controls and maintaining audit trails.
Built for regulated environments
Permission-aware retrieval
Users only see content they're authorized to access. ACLs inherited from source systems, enforced at query time — not filtered after the fact.
Multi-source ingestion
SharePoint (Graph API with OAuth delegation), file shares (SMB/NFS with metadata), databases (Postgres / SQL Server), and email archives.
Audit-grade logging
Every query logged: user identity, sources accessed, permission checks, generated answers, and citations. Full chain of custody.
On-premise deployment
Runs entirely on your infrastructure. No external API calls. Air-gap compatible. Docker Compose orchestration.
Designed for organizations operating under
Defense contractors, federal agencies, energy operators, healthcare systems, legal firms — any environment where data sovereignty is non-negotiable.
Keystone enables compliance controls. It does not claim certification.
Production-grade infrastructure
- Inference
- Ollama — local LLM deployment on multi-GPU hardware
- Embeddings
- BGE-large-en-v1.5 — 1024-dimension vectors
- Vector storage
- Qdrant with metadata-filtered search
- Permissions
- PostgreSQL — RBAC/ABAC enforcement + sync state
- API
- FastAPI — async ingestion + query pipeline
- Security
- SOPS + age encryption, structured audit logging
Built by an enterprise infrastructure engineer
12 years at Genesys deploying contact center platforms for defense contractors, federal agencies, and Fortune 500 companies.
Built production systems handling high-volume workloads with strict uptime, security, and audit requirements.
Keystone applies enterprise deployment patterns to on-premise AI knowledge infrastructure.
Technical discussion
If your organization needs to unlock institutional knowledge while maintaining data sovereignty, let's discuss architecture.
Source code available under Business Source License 1.1 — free for non-production use, converts to Apache 2.0 in 2030.