Skip to content

Open-Research-Development-Laboratories/ordl-operator-core

Repository files navigation

ORDL Operator Core — Deterministic AI Kernel for Sovereign Infrastructure

A deterministic-first, cryptographically auditable operator platform for critical infrastructure, military C4ISR, energy grids, and government systems.

Cloud LLMs are stochastic black boxes. ORDL is a deterministic-first, adaptive-second kernel with hard safety bounds that never mutate — designed for domains where "probably safe" is not safe enough.

Tests Security Lint Python License


Why ORDL Exists

Generative AI (ChatGPT, Claude, Kimi, Moonshot) is optimized for conversational fluency and general reasoning. It is not optimized for:

  • Deterministic safety — same input, same output, every time
  • Cryptographic audit trails — every action signed and tamper-evident
  • Air-gapped sovereignty — runs on bare metal without cloud dependency
  • Native classification handling — USG, NATO, EU, UN, HIPAA built in, not bolted on
  • Immutable safety bounds — hard constraints that cannot drift via fine-tuning

ORDL fills that gap. It is not a chatbot. It is an operator kernel — like an operating system for autonomous decision-making in high-stakes environments.


LLM vs. ORDL: The Decisive Comparison

Capability Cloud LLM (GPT-4, Kimi, Moonshot) ORDL Operator Core
Output determinism ❌ Stochastic / non-reproducible ✅ Cryptographically bounded, reproducible
Action audit trail ❌ Log files only ✅ HMAC-SHA3-256 per action, verifiable chain
Air-gapped operation ❌ Requires internet + API keys ✅ Runs on bare metal, zero external dependency
Classification handling ❌ Post-hoc content filtering ✅ Native (USG, NATO, EU, UN, HIPAA, GER, BRA, JPN)
Safety guarantee ❌ Fine-tuning can drift ✅ Hard immutable bounds, promotion-gated change
Inference cost ❌ $ per token, API latency ✅ 80,820 steps/min on commodity CPU
Model size ❌ Hundreds of billions of parameters ✅ 41,000 parameters (pure NumPy)
Train time ❌ Days on GPU clusters ✅ ~30 seconds on CPU

Verified Performance

91/91 unit tests passing
4/4 chaos engineering tests passing (partition, node death, corruption, slow gossip)
12/12 federation & closed-loop tests passing
9/9 scenario replay validation passing (100% deterministic)
Extraction parity: GO — 100% coverage, 0 blockers
Bandit security scan: CLEAN
Ruff lint: CLEAN

Sustained throughput: 80,820 steps/minute (1,347/sec) on single-core CPU.


Live Data Adapters (No API Key Required)

Adapter Source Status Typical Records
NOAA Weather alerts.weather.gov ✅ Live 50+ alerts/day
USGS Earthquakes earthquake.usgs.gov ✅ Live 200+ events/day
UN OCHA HDX data.humdata.org ✅ Live 4+ datasets
GDELT Global Events data.gdeltproject.org ✅ Live 1,200+ records/15min
CISA KEV api.cisa.gov ⚠️ Environment-dependent When available

Simulation-Ready Adapters

Adapter Domain Protocols
C4ISR Tactical Military Link-16 J-Series, track fusion, SECRET+ handling
Military Logistics Military GCSS-Army, readiness calculator, NSN/UIC tracking
SCADA Monitor Critical Infrastructure Modbus TCP, DNP3, IEC 61850, OPC-UA (read-only)
Energy Grid Energy ERCOT/CAISO/PJM/ENTSO-E APIs, CIM XML, IEEE 2030.5
FOIA Tracker Government FOIA request pipeline, status tracking

Quick Start

Docker (Recommended)

git clone https://github.com/your-org/ordl-operator-core.git
cd ordl-operator-core
docker build -t ordl-operator .
docker-compose up

Kubernetes / Helm

helm install ordl-operator helm/ordl-operator/ \
  --set profile=osint-global \
  --set replicaCount=3

Bare Metal / systemd

./scripts/install_systemd.sh
systemctl start ordl-operator

Air-Gapped (No Internet)

# Copy model artifact + profiles + spool directory
cp -r artifacts/model /target/airgap/
cp -r artifacts/profiles /target/airgap/
cp -r artifacts/spool /target/airgap/
# Run with local profile only
python scripts/ordl_launch.py --profile osint-global --collect

Architecture

┌─────────────────────────────────────────────────────────────┐
│                     ORDL Operator Core                        │
├─────────────────────────────────────────────────────────────┤
│  Adapters         Kernel V2          Truth Registry           │
│  ─────────        ────────           ─────────────            │
│  NOAA             State Assembly     Layered Precedence       │
│  USGS             Planning           Conflict Detection       │
│  GDELT            Validation         Classification Filter    │
│  C4ISR            Execution          Federated Resolution     │
│  Energy           Step Logging       Air-Gap Sync             │
│  SCADA                                                      │
├─────────────────────────────────────────────────────────────┤
│  Security Layer                                               │
│  ─────────────                                                │
│  HMAC-SHA3-256 Audit Chain   │   Classification Engine        │
│  Vault-compatible Secrets    │   Peer Compatibility Filter    │
│  Tamper Detection            │   Cross-Scheme (USG/NATO/EU)   │
├─────────────────────────────────────────────────────────────┤
│  Model (41K params, NumPy)                                    │
│  ─────────────────────────                                    │
│  State Encoder (256→64)    │   Policy Bank (learned actions)  │
│  Action Encoder (128→64)   │   Contrastive Trainer            │
│  Deterministic > Learned   │   Promotion-Gated Deployment     │
└─────────────────────────────────────────────────────────────┘

Deterministic-First, Adaptive-Second

ORDL's safety architecture is promotion-gated:

  1. Observe — collect real-world observations via adapters
  2. Replay — test candidate policies against scenario packs deterministically
  3. Evaluate — measure outcomes against truth registry constraints
  4. Promote — only promoted policies enter the active policy bank

Learned models can suggest actions. They cannot override deterministic safety bounds. Ever.


Use Cases

Critical Infrastructure Operators

Monitor SCADA/ICS networks for anomaly detection and automated alerting without ever writing to control systems. Read-only by architecture.

Military C4ISR

Ingest Link-16 tracks, fuse multi-source sensor data, and generate alert queues with native SECRET+ classification handling and need-to-know enforcement.

Energy Grid Dispatch

Monitor ISO market pricing (ERCOT, CAISO, PJM, ENTSO-E), renewable generation forecasts, and line status — with NERC CIP compliance built into action preconditions.

Government Intelligence

Aggregate NOAA, USGS, GDELT, and UN OCHA feeds into a unified geopolitical picture with cryptographically verifiable provenance chains.

Healthcare (Epic FHIR Ready)

Air-gapped deployment for HIPAA-compliant clinical decision support with deterministic, auditable recommendations.


Federation & Multi-Site Deployment

  • TCP Transport — production mesh with signed messages
  • Air-Gap Spool — data diode compatible, no network required
  • In-Memory — deterministic testing harness

Chaos-tested: partition recovery, node death/rebirth, message corruption rejection, slow gossip convergence.


Model Training

python scripts/train_policy_embedder.py \
  --epochs 150 \
  --target-count 5000 \
  --output-dir artifacts/model

Trains in ~30 seconds on CPU. Produces:

  • state_encoder.json — state embedding network
  • action_encoder.json — action embedding network
  • policy_bank.json — ranked action library
  • loss_curve.json — training telemetry

Security

  • Bandit static analysis: clean (0 high/medium issues)
  • No dependencies beyond numpy and defusedxml for core operation
  • All external HTTP requests validated for scheme (http/https only)
  • XML parsing hardened against XXE/billion-laughs
  • Hash-chained step logs with per-record HMAC-SHA3-256

See SECURITY.md for the full threat model and disclosure policy.


Verification

# Run full test suite
pytest tests/ -v

# Run chaos engineering tests
pytest tests/test_chaos_engineering.py -v

# Run extraction parity scan
python scripts/verify_extraction_parity.py

# Run scenario lab
pytest tests/test_scenario_lab.py -v

# Run federated demo with live data
python demo_scripts/run_federated_demo.py --duration 120

Deployment Profiles

Six pre-configured operational profiles included:

  • osint-global — Open-source intelligence aggregation
  • military-nato — NATO-aligned C4ISR + logistics
  • critical-infra-us — US critical infrastructure monitoring
  • energy-eu — European energy grid (ENTSO-E)
  • healthcare-us — HIPAA-aligned clinical support
  • ngo-humanitarian — UN OCHA + field data

Contributing

This is an open-core project. The kernel and all adapters are MIT-licensed.

Priority areas for contribution:

  • Additional ISO API integrations (PJM, NYISO, MISO)
  • Healthcare FHIR adapter (Epic, Cerner)
  • Additional classification schemes
  • Performance benchmarking on ARM/embedded

Keywords for Discovery

deterministic ai sovereign ai air-gapped ai critical infrastructure ai scada monitoring c4isr military ai government ai energy grid ai operator kernel ai safety llm alternative deterministic operator cryptographic audit classification-aware ai nerc cip hipaa ai nato stanag air gap deployment


License

MIT — free for government and academic use.


ORDL is not a chatbot. It is infrastructure. Built for the domains where failure is not an option.