Skip to main content
Live infrastructure — updated July 7, 2026

The Stack.No Smoke.

This isn't a list of tools I read about. This is what's running right now — the models, services, and infrastructure I use to build everything you see on this site.

14
AI Agents
32
Cron Jobs
21
Ollama Cloud Models
60K+
Indexed Code Nodes
6
Active Services
7
Fallback Tiers

Models

24 Ollama Cloud models, routed by task type

GLM-5.2

Ollama Cloud

Flagship — main conversation + heavy reasoning

toolsthinking

Kimi K2.7 Code

Ollama Cloud

Coding sub-agents + delegate tasks

visiontoolsthinking

MiniMax M3

Ollama Cloud

Fast tier — quick lookups, simple tasks

visiontoolsthinking

Gemma 4

Ollama Cloud

Vision + image analysis

visiontoolsthinkingaudio

DeepSeek V4 Pro

Ollama Cloud

Fallback — coding

toolsthinking

Nemotron 3 Super

Ollama Cloud

Fallback — reasoning

toolsthinking

Qwen 3.5

Ollama Cloud

Fallback — multimodal

visiontoolsthinking

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 → Ollama Cloud routing

Python, uvicorn

Ollama

:11434

Local + cloud model inference

Go, systemd

MemPalace

Persistent memory + knowledge graph

Python, MCP

GitNexus

Code knowledge graph (60K+ nodes indexed)

Node.js, CLI

Open WebUI

:3000

Browser-based chat interface

Docker

Toolchain

What each layer does

Orchestration

  • Hermes Agent
  • delegate_task subagents
  • Kanban multi-agent boards

Coding

  • Claude Code (via FCC proxy)
  • GitNexus code graph
  • Superpowers skills

Memory

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

Models

  • 21 Ollama Cloud models
  • NVIDIA NIM (fallback)
  • 7-model fallback chain

Infrastructure

  • WSL2 Ubuntu
  • Systemd services
  • Docker containers
  • iptables firewall

How It Actually Works

A message comes in via Telegram. Hermes (the orchestrator) reads it, decides what to do, and either handles it directly or delegates to a coding subagent running through the FCC proxy. MemPalace remembers everything across sessions. GitNexus maps the codebase so changes are surgical, not guesswork. All inference runs through Ollama Cloud — 24 models, no per-token costs.

Config backed up to github.com/joblas/Lurkr-Jo-Blade-Hermes · Last sync: July 7, 2026