Skip to main content

$ stack --snapshot · updated October 3, 2026

The Stack. No Smoke.

This isn't a list of tools I read about. This is what was running on the date above — the models, services, and infrastructure I use to build everything you see on this site.
3
Active Client Builds
40+
Scheduled Automations
20+
Cloud Models
1000+
Installed Skills

Models

Claude Opus 5 + Fable 5/5.1 lead; 20+ models routed by task type

Claude Opus 5

Claude (first-party subscription)

Heavy reasoning — deep development at the desk via Claude Code

toolsthinkingvision

Fable 5.1

Claude (first-party subscription)

Frontier coding — deep dev at the desk + remote control from the phone

toolsthinkingvision

Fable 5

Claude (first-party subscription)

Agentic coding + client app builds (the salon formula app's beta loop) — desk and remote

toolsthinkingvision

GLM 5.3 Flash

Ollama Cloud

Cron fleet + delegated sub-agents

toolsthinking

GLM 5.3

Ollama Cloud

FCC proxy Opus-tier mapping + heavy cloud coding

toolsthinking

Kimi K2.7 Code

Ollama Cloud

Coding sub-agents, on demand

visiontoolsthinking

DeepSeek V4.1 Flash

Ollama Cloud

Hermes default — desk conversations + Telegram on the phone

toolsthinking

Gemma 4

Ollama Cloud

Vision + image analysis

visiontoolsthinkingaudio

Minimax M3

Ollama Cloud

Content drafting, on demand

toolsthinking

Services

All running on a single WSL2 box, 127.0.0.1 only

Hermes Gateway

:8642

AI orchestrator + Telegram bot

Python, systemd

FCC Proxy

:8082

Claude Code CLI → subscription + cloud model routing

Python, uvicorn

Ollama

:11434

Local + cloud model inference (20+ models)

Go, systemd

MemPalace

Persistent memory + knowledge graph

Python, MCP

GitNexus

Code knowledge graph

Node.js, CLI

Open WebUI

:3000

Browser-based chat interface

Docker

Open Design

:4000

Design AI stack + daemon

Node.js, systemd

Postiz

:4007

Social media scheduling (14 platforms)

Docker

Toolchain

What each layer does

Orchestration

  • ▸Hermes Agent v0.21.5
  • ▸delegate_task subagents
  • ▸Loop + Goal Mode
  • ▸40+ cron jobs

Coding

  • ▸Claude Code (Opus 5 + Fable 5/5.1 first-party)
  • ▸GitNexus code graph
  • ▸Agent-Skills (24 SDLC skills)
  • ▸Cline CLI

Client Ops

  • ▸jts-client-kit (request loop + triage cron)
  • ▸Throwaway-DB test isolation
  • ▸Gated deploys w/ health checks
  • ▸Per-client skill library

Media & Design

  • ▸Remotion storyboard video pipeline
  • ▸Mermaid diagram-as-code
  • ▸Headless-Chrome asset capture
  • ▸shotcraft motion library
  • ▸Open Design

Memory

  • ▸MemPalace MCP
  • ▸Semantic search
  • ▸Knowledge graph
  • ▸Session diary

Models

  • ▸Claude Opus 5 + Fable 5/5.1 (first-party)
  • ▸Ollama Cloud (primary)
  • ▸2-model fallback chain
  • ▸Small local models (Ollama)

Infrastructure

  • ▸WSL2 Ubuntu
  • ▸Systemd services
  • ▸Docker containers
  • ▸iptables firewall
  • ▸Client VPS fleet (Hostinger)

How It Actually Works

At the desk: Hermes (the orchestrator) runs conversations on DeepSeek V4.1 Flash and the cron fleet and sub-agents on GLM 5.3 Flash, and deep development goes through Claude Code on frontier models — Opus 5 for the hardest reasoning, Fable 5.1 for the build-and-ship pipeline. Away from the desk: the same stack follows — Hermes answers on Telegram from the phone, and Claude Code keeps building via remote control. MemPalace remembers everything across sessions and surfaces. GitNexus maps the codebase so changes are surgical, not guesswork. Flat subscriptions — no per-token costs, at the desk or in your pocket.

This is what was running on the date above. Want to see what it can do for your business?

Config auto-backed up weekly to a private GitHub repo · Stack data updated: October 3, 2026

$ echo "ready?"

If you made it this far, you already know if you want to talk.