I'm Sterling Schwieger — a software engineer who designs and builds end-to-end systems. My flagship work is Glass: a self-hosted, AI-native MSP platform of 25+ microservices and background daemons, local LLM inference, dual remote access, and an integrated security engine — architected and written solo.
Glass is a unified platform for managed service providers — ticketing, RMM, CMDB, billing, security, telephony, and AI triage — that replaces a stack of commercial SaaS tools like ConnectWise, Kaseya, and NinjaOne. Every byte stays on your own infrastructure, and every AI inference runs on a local GPU.
Ticket triage, email classification, voicemail transcription, and NLP→SQL reporting run on a local DGX Spark via Ollama. No client data ever leaves the network.
A sandbox model screens every untrusted input for prompt injection before the privileged model sees it — an isolation pattern no commercial MSP platform ships.
11 specialized dashboards — from an RMM matrix to a 3D facility viewer — unify tickets, assets, alerts, billing, and network topology in one UI.
25+ independently deployable services and daemons in PHP 8.3, Go, and Python, orchestrated with Docker Compose profiles and JWT/OIDC auth delegated to a central identity service.
768-dimension embeddings in pgvector power cosine-distance search across tickets and knowledge — surfacing the top similar cases at the moment a ticket is opened.
SSO/OIDC, mandatory admin MFA, a Go-based XDR engine (Wazuh + Rspamd + ClamAV), CRU CA mutual TLS, and a full Loki/Grafana observability pipeline.
Glass reaches an estimated ~97% feature parity with the major MSP platforms while keeping data sovereignty, source-code auditability, and freedom from supply-chain risk that centralized SaaS can't offer.
# Glass — profile-based orchestration services: glass-app: # PHP 8.3 monolith · 11 dashboards depends_on: [glass-core, glass-db, redis] glass-ai-worker: # Python · Dual-LLM sandbox + RAG image: ollama/local-inference glass-sentinel: # Go · XDR + security ops engine ports: ["8090"] glass-tickets: # Slim 4 · Go SLA sidecar · pub/sub glass-crm: # Go 1.25 + React · Redis Streams glass-rmm: # Go daemon · RustDesk + MeshCentral # …19 more services & daemons, 8 infra # $ docker compose --profile all up -d # ✔ 40+ containers · healthy
From database schema and Go concurrency to React frontends, LLM pipelines, and production DevOps — I design, build, and operate the entire system.
PHP 8.3 (Slim 4), Go 1.25, Python/FastAPI. REST + GraphQL, JWT/OIDC auth, event-driven pub/sub, and queue-based async processing.
PostgreSQL 16, pgvector embeddings, RAG pipelines, local LLM inference with schema-enforced outputs, and Redis caching/streams.
React 18 + TypeScript, Vite builds, WebSocket/WebRTC, Docker Compose, Nginx + mTLS, Cloudflare Tunnel, and CI-style automated deployments.
Glass is my flagship, and it's modular by design. It sits alongside a family of companion CRU products — built by my colleague Blake Thoeness — and many of Glass's own microservices are complete products in their own right, deployable standalone.
A 25+ microservice, AI-native operating system for a managed service provider — ticketing, RMM, CMDB, billing, security, and local LLM intelligence in one self-hosted stack (~160K+ LOC).
A central authentication platform: an internal certificate authority with strict mTLS, a secrets/2FA vault (OpenBao "KeyMaster"), and an OIDC/SAML identity provider — one pane of glass for certs, keys, and SSO.
A cross-platform endpoint backup product — cloud console, agent fleet, and a Wails desktop app — with Carbonite-style Explorer status overlays, a Kopia engine fork, and mTLS data-plane ingress.
Command & control for AI agents across a heterogeneous GPU fleet — routing inference, code, voice, and transcription tasks to the best-fit node by live hardware telemetry, with fleet self-update.
A high-performance gateway that unifies OpenAI, Anthropic, Gemini, and OpenAI-compatible providers under one endpoint — protocol translation, load balancing, failover, and usage tracking, transparently.
Glass is 25+ independent microservices & daemons — several are full products on their own, deployable or licensable standalone.
Multi-tenant XDR & security-ops engine — Wazuh SIEM/EDR on DMZ, blocklists, quarantine, posture tracking, and sandboxed remediation (Go).
Automated penetration testing and CVE vulnerability mapping — continuous attack simulation directly inside the platform.
Cybersecurity awareness training & testing — interactive modules & quizzes, phishing-simulation testing, per-user risk scoring, and compliance reporting.
Email campaigns, contacts, and .docx merge-tag templating with queue dispatch (Go daemon + React).
Bug & feature tracking with AI developer-prompt generation and threaded clarifications.
Real-time messaging + WebRTC voice/video with call transcription — a Go binary handling 10k+ concurrent connections, white-label ready.
ITSM ticketing with a Go SLA sidecar daemon, lifecycle state machine, rules engine, time tracking, and AI triage.
Asset lifecycle, dynamic 0–100 health scoring, warranty tracking, and RMA claims.
Remote monitoring & management via MeshCentral + RustDesk OSS dual remote access, interactive multi-shell terminal, and patch management.
SolidInvoice-powered PostgreSQL billing engine (glass-invoice) — invoices, recurring subscriptions, and quotes with zero external SaaS fees.
UniFi Talk telephony and Android meeting audio pipeline with local Whisper ASR and Pyannote speaker diarization.
Exchange (EWS) ingestion with AI classification, noise scoring, and email-to-ticket.
Purchase-order lifecycle, supplier catalog, and computed order totals tied to the CMDB.
