3-server topology with local LLM inference, vector memory, and an audited relational database. All inter-server traffic flows through an encrypted WireGuard tunnel. No data ever leaves EU jurisdiction — with an encrypted disaster-recovery copy replicated nightly to an offsite Storage Box in Helsinki.
Sovereign AI · infrastructure
3-server topology · sovereign LLM
RAG · vector memory · WORM audit
Entity hierarchies · forensic relationship detection. Ownership edges are bi-temporal (valid-from/valid-to), rolling out to other edge types.
:6379
Redis
cache · queue
Sessions · rate-limit · jobs.
:9000
MinIO · S3-compat
object storage
Documents · images · PDF · scanned materials.
Write-guard triggers
BEFORE INSERT/UPDATE, targeted
Deployed where correctness is non-negotiable — brand normalization, content-safety guards. Extending to full field-level history is scoped, not blanket-claimed.
Cold backup archive · local
daily + monthly full dumps · continuous WAL archiving
Verified RPO ≤ 24h on the primary database (daily automated dump, confirmed current) plus a separate nightly job replicating to the offsite Helsinki box below. Completeness audits run periodically and are allowed to fail loudly — the last one flagged two components needing attention, which is the point of running it.
Independent nightly jobs from both compute nodes (GPU 20:00, DATA 21:00) — database dumps, LoRA adapters, configs. Both confirmed successful on the most recent run. True 3-2-1 — survives full datacenter loss.
// Agent governance — candidate until evidence promotes it
Every agent action starts as an untrusted candidate. It earns the right to execute through scope, a tool gate, evidence, human oversight, and a scoped time-bound runtime permit. Automation expands in proportion to reversibility — speed is earned, not assumed. Each action is recorded to a tamper-evident audit trail.
1
Candidate Signal
plan/step proposed
2
Passport Scope
owner + plan identity
3
Tool Gate
4-level permission
4
Toll Evidence
context + RAG grounding
5
Human Review
approval pause
6
Runtime Permit
scoped · TTL · uses
7
Broker Receipt
execution logged
8
Evidence Trail
audit, tamper-evident
Runtime permit + TTL
Each action receives a scoped, time-bound permit before execution: read-only 1h / 100 uses, mutating 5 min / 3 uses. A mutating action without a valid permit is blocked. Permit lifecycle (issued · consumed · expired) is recorded for replay and accountability.
Graduated reversibility
A tool earns a trust tier from its track record. Proven tools receive longer, larger permits; autonomous plans may use proven, reversible mutating tools once an operator marks them eligible. Permission ceiling: read-only → mutates → human approval → forbidden.
// Network & security
WireGuard VPN between all three servers, TLS 1.3 for external traffic. External access exclusively through Front. Encrypted offsite disaster-recovery replication to a geo-separated Storage Box in Helsinki (Finland) — true 3-2-1.
// Legal framework & compliance
The platform is built in accordance with Croatian and EU regulatory frameworks:
Public Procurement Act OG 120/16GDPR EU 2016/679Right to Access Information Act OG 25/13NIS2 EU 2022/2555Local & Regional Self-Government Financing Act OG 127/17GDPR Implementation Act OG 42/18
// Sovereign principles
Data never leaves EU jurisdiction.
Open-source model (Apache 2.0) — no vendor lock-in.
Every AI response is auditable and reconstructible.
The client controls what the model learns and what it discards.