Infrastructure · The Matt Stack

AI infrastructure
you own.

Self-hosted inference, vector database, monitoring, and API layer on your VPS. No per-token bills. No vendor lock-in. Nobody can pull it out from under you. The smartest model you can economically own and operate.

$4K
Managed setup
$2K
Monthly managed ops
$275
Min monthly infrastructure
100%
Yours. Full ownership.
Scope your stack See the architecture

The Thesis

Sovereignty, not savings.

The Matt Stack is not "cheaper than API." It is AI infrastructure you control. Your data stays on your metal. Your inference runs on your GPU. Your costs are flat and predictable. And nobody can change the pricing, throttle your access, or deprecate your model out from under you.

Control

Data never leaves

Your business data, your customer data, your prompts. Nothing routes through a third-party API. Full privacy by architecture, not by policy.

Predictability

Flat monthly cost

No per-token surprises. No usage spikes. Your GPU runs at a fixed rate whether you send 10 requests or 10,000. Budget once, run forever.

Portability

Swap anything

Models are interchangeable services behind an OpenAI-compatible endpoint. Swap Qwen for DeepSeek without changing application code. No lock-in at any layer.


The Architecture

Twelve layers. One Docker Compose.

Every component is open-source or Apache 2.0 licensed. Battle-tested. Replaceable. The stack deploys as a single Docker Compose on any GPU VPS provider.

LayerComponentWhy
OSUbuntu 24.04 LTSMassive driver/tooling ecosystem. Boring. Correct.
ContainerDocker + ComposeThe lingua franca. Every component ships a Dockerfile.
PaaSCoolify v4280+ templates, managed DBs, auto-SSL. Free, Apache 2.0.
EdgeCloudflareDNS, CDN, DDoS, WAF. Non-negotiable at this price point.
ProxyCaddyAuto-TLS, clean config. Coolify-native.
DatabasePostgreSQL + pgvectorRelational + vector search in one engine. No extra dependency.
CacheRedisSession, queue, rate-limiting, KV cache coordination.
InferencevLLM v0.6+OpenAI-compatible API. PagedAttention v2, speculative decoding.
ModelQwen3-Coder-Next (default)Best self-hosted coding model. Apache 2.0. Swappable.
APIFastAPIAgent/API layer, business logic, auth, rate limiting.
GatewayLiteLLMRoutes local + external APIs. Fallback, cost tracking, unified interface.
MonitorPrometheus + GrafanaGPU utilization, inference latency, error rates, cost per request.

Hardware Tiers

Pick your GPU. We configure the rest.

Infrastructure cost depends on which GPU tier fits your workload. Client pays their VPS provider directly. Faction deploys and manages the stack on top of it.

Entry

RTX 4090

24GB VRAM. Fits Qwen 27B dense at Q4. Good for general-purpose inference at lower volume.

$255 - $505/mo

Performance

L40S

48GB VRAM. Fits Qwen3-Coder-Next full precision. Larger MoE models at Q4.

$525 - $630/mo

Enterprise

A100 80GB

80GB VRAM. Most MoE models, 70B dense at Q4. The workhorse for production agent workloads.

$440 - $780/mo

Maximum

H100 SXM5

80GB HBM3. Any single-GPU-feasible model at full speed. For throughput-critical production.

$750 - $1,825/mo

Pricing from neo-cloud GPU providers (Vast.ai, RunPod, Spheron). Hyperscaler pricing (AWS, Azure) runs 2-5x higher. Stack certified on both. Add $20-50/month for the non-GPU application VPS.


Pricing

Two channels. Same stack.

Faction deploys and manages it for mid-market companies. The self-serve kit puts the same architecture in the hands of builders who can run it themselves.

Builder Channel
Self-Serve Kit
$500
one-time · self-managed
  • Complete Docker Compose deployment package
  • Hardened configuration files
  • Step-by-step deployment guide
  • Companion course inside The Faction (mattmurphy.ai)
  • Provider selection guidance
  • Community support (Discord/forum)
For builders who can manage their own infrastructure. Deploy and manage independently. Upgrade to Faction managed at any time.
Get the kit

Guided deployment: $1,500 one-time. Everything in the kit, plus a 2-hour guided deployment session, provider selection help, model benchmarking on your hardware, and a post-deploy health check.


Economics

When self-hosting makes sense.

The Matt Stack sells on sovereignty and control, not cost. But the economics do work for specific use cases.

Data Privacy

Can't send data to external APIs

Regulated industries, sensitive customer data, proprietary business logic. If the data can't leave your infrastructure, self-hosting is the only option.

Predictable Costs

Flat monthly vs. variable per-token

Production agent workloads with high sustained utilization. Break-even against frontier APIs around 160-256M tokens/month at 60-70% utilization.

No Vendor Risk

Nobody can pull the rug

Model deprecation, pricing changes, rate limits, terms-of-service shifts. Your stack runs the same tomorrow regardless of what any provider announces today.


Connects To

The Matt Stack completes the Faction story.

Production Discovery finds the problems. The Conveyor Belt fixes the code. The Matt Stack provides the infrastructure. FOE monitors everything.

The Conveyor Belt

Your team vibe-codes on the Matt Stack's inference layer. The Belt finishes, stages, and audits those builds into production. Self-hosted AI meets managed engineering.

Faction AIOS

Full AI operating platform builds can deploy on Matt Stack infrastructure instead of cloud APIs. Domain services, agents, and evaluation loops running on hardware you own.


Why Not Just Use APIs

API-as-a-service vs. infrastructure you own.

API-as-a-service

Zero setup. Pay per token. Data leaves your network on every call. Provider controls pricing, model availability, rate limits, and terms. Fast to start, impossible to control at scale.

The Matt Stack.

Your GPU, your model, your data. Flat monthly cost. Swap models without changing code. No rate limits, no per-token bills, no vendor lock-in. Takes a week to deploy. Runs as long as you want it to.


Own your
AI infrastructure.

Tell us what you're running. We'll recommend the GPU tier, configure the stack, and hand you the keys to AI infrastructure nobody can take away.

Scope your stack

The Matt Stack runs the same methodology as every Faction build. The Conveyor Belt finishes your code. AIOS builds the platform. The Matt Stack provides the foundation.