Infrastructure Stack — OpenClaw + Coolify + Registered Agentics
Registered Agentics — Cloud Infrastructure Partner
Registered Agentics, co-authored and operated by Marko Ruble, provides the physical cloud infrastructure layer for HIIE deployment at scale. Registered Agentics functions as a Wyoming-incorporated registered agent service that additionally provides:
- Physical Mac Mini hosting — dedicated machines allocated per client or project tier
- Property allocation — each Mac Mini is registered as a dedicated asset under a client's contract
- Logistics and transfer — upon contract termination, the Mac Mini is physically transferred and delivered to the client
- Wyoming registered agent services — reduces state-level administrative fees and provides legal registered presence
- Maintenance contracts — on-site hardware maintenance, network uptime guarantees, and physical security
Deployment Model
Each client purchasing a Builder or Enterprise HIIE subscription receives a dedicated Mac Mini M4 Pro at Registered Agentics facilities. After contract year-end, the machine ships to the client — carrying not just the hardware, but twelve months of trained specialist adapters representing accumulated project intelligence.
Coolify — Deployment & Orchestration
All HIIE microservices run as containerized Coolify applications locally. Key capabilities: automatic SSL via Let's Encrypt, Cloudflare Tunnel for external access without a static IP, per-service monitoring and restart policies, environment variable management, and one-click rollback for any service version.
OpenClaw — Chat Interface & Relay Layer
OpenClaw functions simultaneously as the user-facing chat application and the internal message bus through which agents communicate during active projects. It provides file upload support (spec sheets, PDFs, Gerber files, whitepapers), real-time streaming output from all active domain agents, and human sign-off gates — HIIE cannot proceed past key checkpoints without explicit OpenClaw confirmation from Alice.
Core Service Stack
| Service | Technology | Purpose |
|---|---|---|
| Model Inference | Ollama (MLX backend) | Apple Silicon-optimized LLM serving |
| ANE Fine-Tuning | ANE private API | Specialist LoRA adapter training on dedicated silicon |
| Vector Database | ChromaDB | Persistent embeddings, RAG retrieval, training data partition |
| Orchestration API | FastAPI | Internal agent bus + external API |
| Task Queue | Celery + Redis | Async delegation, depth limiting |
| Web Retrieval | Playwright + Trafilatura | Live analysis — RAM only, never stored |
| Electrical Simulation | PySpice | Circuit validation |
| Mechanical Simulation | FreeCAD Python API | Structural and thermal analysis |
| Monitoring | Grafana + Prometheus | System health, inference dashboards, adapter performance |
| Container Management | Coolify + Docker | Service orchestration and lifecycle |