Technical Deep Dive

Glass — Under the Hood

The programming languages, frameworks, databases, and infrastructure that power the Glass platform. This is the technical detail — for the sales overview, see the main Glass page.

Under the hood

The full stack

Languages & Frameworks

PHP 8.3Slim 4Go 1.25Chi Python 3.11FastAPIPydantic v2 TypeScriptJavaScriptReact 18ViteSQL

Data & AI

PostgreSQL 16pgvectorRedis 7 OllamaRAGnomic-embed-text WhisperRedis StreamsJSONB

Infra & DevOps

Docker ComposeNginxmTLSBrotli Cloudflare TunnelTailscaleCalVer

Security & Ops

Wazuh SIEMRspamdClamAV OIDC / AuthentikMFALokiGrafana MeshCentral
Polyglot Architecture

Every service, every language

Each service picks the right language for the job — PHP for domain logic, Go for high-throughput, Python for AI pipelines.

ServiceLanguage / FrameworkWhat It Does
CRU-GlassPHP 8.3 · Vite · ES6Core monolith — 11 dashboards, ticket UI, admin, AI report builder
glass-corePHP 8.3 · Slim 4 · JWT RS256Auth & identity — SSO/OIDC, MFA, 7-tier RBAC
glass-ticketsPHP 8.3 · Slim 4PSA/ITSM — lifecycle state machine, SLA sidecar, rules engine
glass-assetsPHP 8.3 · Slim 4CMDB — asset lifecycle, dynamic health scoring, warranties
glass-cyberPHP 8.2 · Slim 4 · WazuhSecurity posture — Wazuh ingestion, sandboxed remediation
glass-rmmPHP 8.3 · Slim 4 · MeshCentralRMM — remote shell, patch management, hybrid deploy scripts
glass-emailPHP 8.2 · Slim 4 · EWSEmail — Exchange ingestion, AI triage & noise scoring
glass-unifiPHP 8.2 · Slim 4 · WhisperTelephony — UniFi Talk, voicemail → text via AI transcription
glass-chatPHP 8.3 · React 18 · WebSocketReal-time messaging — WebRTC voice/video, call transcription
glass-qboPHP 8.2 · Slim 4 · OAuth2Billing — QuickBooks PKCE, AES-256 tokens, invoicing
glass-superopsPHP 8.3 · Slim 4 · GraphQLPSA sync — bidirectional SuperOps.ai with HMAC webhooks
glass-procurementPHP 8.2 · Slim 4Procurement — purchase-order lifecycle, supplier catalog
glass-feedbackPHP 8.2 · Slim 4Bug tracking — AI developer-prompt generation, threaded notes
glass-crmGo 1.25 · Chi · React SPACRM — campaigns, Redis Streams, HMAC webhooks
glass-sentinelGo 1.22+ · ChiXDR engine — Wazuh/Rspamd/ClamAV, multi-tenant security
glass-ai-workerPython 3.11 · FastAPI · PydanticAI worker — Dual-LLM sandbox, pgvector RAG

Highlighted rows = Go / Python (non-PHP)

Self-Hosted · Requirements

The hardware to run Glass

Glass runs entirely on your own hardware — two workloads: the Docker platform (~29 containers) and local AI inference on a GPU or unified-memory machine.

WorkloadMinimumRecommendedWhat CRU runs
Docker platform (no AI)8 cores · 16 GB · 256 GB SSD16 cores · 32 GB · 512 GB NVMe80 cores · 512 GB
AI inference (Ollama)16 GB VRAM / 32 GB unified48–64 GB VRAM / unified128 GB unified (Blackwell)
Combined (one machine)16 cores · 64 GB · GPU32 cores · 128 GB · GPUDGX Spark + Supermicro

Budget build

~$2,000–3,000
  • Mini PC / NUC — i7 or Ryzen 7, 32 GB RAM, 1 TB NVMe
  • Used RTX 3090/4090 (24 GB VRAM)
  • 600VA UPS

Runs the full platform; AI swaps models between requests. No deep reasoning.

Recommended build

~$5,000–8,000
  • Server — 16 cores, 64 GB ECC, 2 TB NVMe
  • RTX A6000 (48 GB) or L40
  • 1500VA UPS

Full Dual-LLM + all AI features (except deep reasoning). Best for 5–10 techs.

Premium build

~$10,000–15,000
  • NVIDIA DGX Spark — 128 GB unified Blackwell
  • Dedicated app server (16+ cores, 32+ GB)
  • NAS backup + 2000VA UPS

Everything — all models resident, deep reasoning, headroom for future models. CRU's setup.

Want the sales overview instead?

This page is for engineers who want the nitty-gritty. For the business case, feature comparison, and licensing — head back to the main pages.