Skip to main content
All Systems Operational

The Architecture

A multi-node infrastructure running local LLMs, semantic memory, agent orchestration, and home automation. Everything here is in active use—not experiments.

23
Workers
1,800+
Memories
13,700+
Auto-Generated Edges
24
Local Models
<8ms
Query Latency
29
Cortex Projects

Systems

Tools and infrastructure I design, build, and operate daily.

Cortex

Active

Self-Healing Memory Platform for AI Agents

Persistent, searchable, cross-session memory for AI agents. Dual-path search — Postgres full-text and ChromaDB semantic vectors — merged and ranked with recency bonus. A-MAC admission control quality-gates every write. Auto-linker builds a relationship graph without manual curation. Adaptive retrieval (Agentic RAG via LangGraph) reformulates queries when relevance is low. Runs natively on Apple Silicon with embedded ChromaDB — no Docker, no zombie containers, self-healing at process, application, and infrastructure tiers. Three-node architecture with warm standby.

1,800+
Memories
13,700+
Edges
<3ms
Latency
29
Projects
PythonPostgreSQL 16ChromaDBOllamaMCPLangGraph
Read Case Study

Forge

Active

Queue-Based Autonomous Worker System

Event-driven worker system for orchestrating AI tasks on local hardware. Redis-backed queues coordinate GPU access, LoRA adapter training, health monitoring, and overnight chain orchestration — all running autonomously via macOS LaunchAgents. Nightly chain runs security review, code review, PR digest, news curation, arXiv scanning, and morning briefings. Self-healing daemon scans every 60 seconds and kickstarts crashed services. Sandbox builder generates complete iOS/macOS apps autonomously — Ollama writes Swift, xcodegen builds projects, xcodebuild compiles, error loop self-corrects.

23
Workers
34
LaunchAgents
Nightly
Chain
PythonRedismacOS LaunchAgentsSlack APIxcodegen
Read Case Study

Thalamus

Active

MQTT Gateway to AI Memory

Bridges IoT and Home Assistant events into Cortex via MQTT. Sensor readings, automation triggers, and system heartbeats flow through the bus into persistent memory where agents can query them.

MQTTPythonHome Assistant

Nerve

Active

MCP Server Registry & Guardian

Maintains a canonical registry of MCP server configurations. Detects config drift, verifies connectivity, and auto-restores missing servers. The structural safeguard that keeps the multi-agent ecosystem intact.

TypeScriptNode.jsMCP

Forge Command Center

Active

Real-Time System Monitoring

Live worker status, queue depths, chain execution history, and system health. React frontend backed by the Forge API with auto-refresh and task dispatch controls.

ReactTypeScriptFastAPI

Hook Pipeline

Active

5-Stage Auto-Persist System

Five hooks fire during every Claude Code session: context recall, pre-tool injection, Slack commit alerts, pre-compaction memory extraction, and session-end persistence. Ollama extracts structured memories from transcripts and stores them in Cortex automatically.

ShellOllamaCortex API

Local LLM Fleet

Active

24 Models on M4 Metal

24 models via Ollama on Apple M4 Silicon. Three-model strategy: gemma4:e4b (27 tok/s, native function calling, voice assistant), qwen3.5:9b (deep reasoning, code generation, overnight workers), phi4-mini:3.8b (fast triage, 30 tok/s). 5 custom LoRA adapters. Powers everything from Home Assistant voice control to autonomous code generation — zero cloud API calls.

Ollama 0.20.2LoRAApple M4 Metal

System Architecture

The homelab maps to brain structures—each system mirrors a cognitive function.

CortexHippocampusSelf-healing persistent memory. Dual-path search (FTS + semantic), A-MAC admission control, auto-linking relationship graph. Runs natively on forge with embedded ChromaDB — no Docker, three-tier self-healing, warm standby on sentinel.
ForgePrefrontal CortexExecutive function and task orchestration. 23 workers, 34 LaunchAgents, GPU coordination, overnight chains, autonomous code generation (sandbox builder), and self-healing daemon.
ThalamusSensory GateMQTT-based anomaly detection and sensory filtering. Subscribes to all system events, detects patterns, gates noise, and only escalates high-priority signals to Cortex and Slack.
Home AssistantMotor CortexPhysical-world actuation. Controls lights, cameras, sensors, and automation across the home.
NerveCorpus CallosumMCP server integrity enforcement. Maintains a canonical registry, detects config drift, and auto-restores missing or broken server configurations.
FrigateVisual CortexReal-time object detection and camera processing. Feeds visual data into the event pipeline.

Philosophy

Everything here exists because I use it. Cortex runs in every coding session. Forge orchestrates overnight chains while I sleep. The homelab hosts real services my household depends on.

Most “AI-powered” features are demos pretending to be products. This is where I test what actually works under real constraints: latency, failure modes, cost, and whether anyone would use it twice.

I build infrastructure so I can recommend it honestly. Every system I suggest to a client is one I've operated myself.

Interested in this kind of infrastructure?

I build these systems for clients too. Let's talk about what you need.

Start a Conversation