~/setup

I engineered my whole workflow.

Not a list of apps. A system. Four devices on a private mesh, an always-on server running local AI, and a personal multi-agent OS I built on Claude. I engineered it as force multiplication: it keeps my research and ops moving while I sleep, so I ship at 10x awake.

4 devices · 1 always-on hub · ~22 automations · 2 local models

~/mesh

~/agentic-osprivate mesh · local + cloud compute

online

skills / automations: ~22
watchers: email-triggered · ~30s
briefings: nightly health · weekday brief + EOD
research: weekly deep-research → RAG vaults
orchestration: orchestrator → workers · fail-closed gates
reliability: self-monitoring · auto-recovers
memory: layered: session → project → vaults
lineage: after Karpathy's LLM-OS / LLM-Wiki

The server is the brain: it never sleeps, watches itself, recovers stuck or failed runs automatically, and ships autonomous work only behind deterministic, fail-closed gates. Cheap and private work, voice transcription, voice-note filtering, local LLM tasks, runs on the RTX 3080. Heavy reasoning and multi-agent orchestration run on Claude. Built after Andrej Karpathy's LLM-OS and his LLM-Wiki memory pattern.

~/cadence

~/automation-day24h · real cadences

00:0006:0012:0018:0024:00

email watchers

always-on · ~30s poll

morning brief

weekday

idea digest

weekday · local model

data feeds

daily

end-of-day

weekday

night health

nightly · self-check

deep-research

weekly → vaults

~/where-compute-goes

local · RTX 308035%

whisper · ollama qwen2.5 · cheap + private

cloud · Claude65%

orchestration · deep reasoning · workers

A deliberate split, not a meter: the 3080 absorbs the cheap, private, high-volume work so the cloud budget goes to reasoning.

~/stack

languages

TypeScript
Python
SQL

frameworks

Next.js 16
React 19
Tailwind
FastAPI

data

Postgres / Neon
Prisma
LanceDB
BGE-M3
Docling

infra

Vercel
AWS
Docker
Tailscale
Syncthing
systemd

Claude (Opus/Sonnet/Haiku)
Ollama · qwen2.5
Whisper

payments

Square

testing

Vitest
Playwright

workflow

tmux
Git
Claude Code

~/hardware

server: ryzen 9 5900x · 64gb · always-on linux
gpu: rtx 3080 · whisper + ollama qwen2.5
primary: m5 macbook pro
mobile: iphone 15 pro max · control surface

› initializing interface

› mounting modules

● online

I engineered my whole workflow.

4 devices · 1 always-on hub · ~22 automations · 2 local models