Sovereign AI Stack

A fully reviewed, air-gapped AI stack with a published SBOM.

Industry	Level	Difficulty	Recommended mode
Government & defence	5 of 5	Frontier	hnsw

Coming soon

A complete, runnable Sovereign AI Stack reference implementation is in progress. The architecture and core code below already work with SrvDB 0.3.

The problem

• Supply-chain assurance is mandatory.
• Cloud AI is not an option.
• Systems must run for years.

How SrvDB powers Sovereign AI Stack

1. SrvDB has no Python runtime dependencies and ships an SBOM with every release.
2. Builds from reviewed source; Apache-2.0 licensed.
3. Versioned on-disk formats support long-lived archives.
4. Crash-safe storage.

What changes

Today	With Sovereign AI Stack on SrvDB
Opaque AI dependencies	Reviewable components
Vendor lock-in	Open source
Short-lived prototypes	Long-lived systems

How it works

1. Review source and SBOM.
2. Build internally.
3. Deploy offline.
4. Operate with local models.
5. Audit regularly.

SrvDB features it uses

• Fully offline: SrvDB runs in-process and never opens a network connection.
• Crash-safe persist(): after it returns, data survives a crash or power loss and reopens exactly as committed.
• Rust API: embed SrvDB directly in Rust services and devices.
• HNSW graph (hnsw): approximate search that visits a small part of large collections; tune with set_ef_search().

Use cases

• National archives search
• Defence knowledge bases
• Secure translation
• Intelligence linking
• Disaster-response knowledge
• Ship and vehicle deployments

Core code

embed() is your embedding model (for example sentence-transformers, or a function that turns your records into feature vectors).

import json
import srvdb

db = srvdb.Database("./sovereign-ai-stack-db", dimension=768, mode="hnsw")

def ingest(items):
    """items: list of (id, text, metadata dict)"""
    db.upsert(
        ids=[i for i, _, _ in items],
        embeddings=[embed(t) for _, t, _ in items],
        metadatas=[json.dumps(m) for _, _, m in items],
    )
    db.persist()                      # crash-safe checkpoint

def retrieve(query, k=5):
    hits = db.search(embed(query), k)
    return [(json.loads(db.get(i)), round(score, 3)) for i, score in hits]

Limits and honest notes

• Accreditation is the operator’s responsibility.

Build roadmap

1. Prototype: load a sample of real data with flat mode and check that searches return what an expert expects.
2. Measure: if you move to an approximate mode, compare its results with flat on the same queries (recall).
3. Pipeline: add continuous upsert and decide when to call persist().
4. Harden: test restarts and crashes, add logging, review every output path with domain experts.
5. Deploy: ship the database directory with the application or service.

All Government & defence projects

Level	Project	What it does
1 · Beginner	Doctrine Assistant	Air-gapped question answering over manuals and doctrine.
2 · Intermediate	Citizen Service Bot	Answers citizens’ questions from official public guidance.
3 · Advanced	Report Linker	Links related reports and requests across departments.
4 · Expert	Field Intelligence Agent	An offline agent on rugged laptops combining text and imagery.
5 · Frontier	Sovereign AI Stack (this page)	A fully reviewed, air-gapped AI stack with a published SBOM.

See also: Use cases · Live examples (coming soon)