Your configured private AI platform
My AICORTEX
1 capabilities · 6 unique services · New VPS
Resolved build1
Complexity4
HardwareFits
01 / Resolved build
Selected capabilities
Core and automatic prerequisites are shown separately from the capabilities you chose.
AICORTEX Core PlatformCore: always present
The governed substrate every capability deploys onto
03 / System map
Architecture preview
Internet → Cloudflare Tunnel → Traefik. Outbound-only ingress; no origin service ports exposed.
Core / Always presentAICORTEX Core Platform
Unique services (6)
PodmanAnsibleTraefikPostgreSQLcloudflarednginx
04 / Headroom
You have room for 4 more
Ranked by complementarity and current host fit. Nothing is added automatically.
Zero-Trust Edge & Identity
+0 vCPU · +0 GB RAM · +0 GB disk
Private AI Workspace
+1 vCPU · +1 GB RAM · +0 GB disk
Universal AI Gateway
+0 vCPU · +0 GB RAM · +0 GB disk
Knowledge Hub & RAG
+1 vCPU · +1 GB RAM · +18 GB disk
02 / Deployment inputs
Hardware and deployment
Host resources
0 means no GPU present
Workload assumptions
05 / Validation
Suggested deployment envelope
Planning estimate. Final sizing depends on workload, concurrency, local model choice, and retention.
vCPU
2 / 4 cores
RAM
4 / 8 GB
Disk
40 / 80 GB
VRAM
0 / , GB
Fits: works with your current hardware
Smallest matching profile: Starter (4 vCPU / 8 GB / 80 GB).
06 / Authoritative quote
Pricing unlocked at the final step
Explore, configure and validate hardware first. Authoritative pricing is computed server-side once your build is ready.
- Configuration saved before quotation
- Server-computed line items and bundles
- Self-deploy, assisted, or managed options