Most "I built an AI agent" posts come with a screenshot and a vibe. This page is the receipts — live counts from my running stack, refreshed each morning at 06:15 ET. No render-on-load tricks. The system actually does this work.
Cost of running
cloud-API cost · lifetime
Inference runs on the workstation. Cloud only when local genuinely can’t carry the work.
est. monthly savings
vs. Buffer Pro + Hootsuite Pro + ChatGPT Plus + ~$150 cloud-API usage.
posts shipped · last 7 days
Drafted by NEXUS, reviewed by me, fired on weekly slots. Receipts below.
Today · 2026-06-18
Last 7 days
Agents
The autonomous workers running in my stack. Each one has a single job and runs on its own schedule. Status · last run.
Brain
Runs the autonomous cycle every minute — every subsystem gets a turn.
last run · 19h ago
Drafts new capabilities when a gap is detected — ships only after review.
last run · 19h ago
Routes incoming signals to the right handler.
last run · 8m ago
Content
Builds the daily briefing before sunrise — overnight research, opportunities, what shipped.
last run · 14m ago
Turns captures and signals into ready-to-review drafts.
last run · never
Fires weekly publishing slots when an approved post is ready.
last run · just now
Measures what published content actually earned in engagement.
last run · 40m ago
Research
Pulls overnight research signals worth the morning brief.
last run · 6h ago
Income
Scans creator channels for monetization-fit ideas.
last run · 40m ago
Voice
Reads the morning brief aloud during the get-ready window.
last run · 19h ago
Memory
Compresses recent context into long-term memory.
last run · 19h ago
Notices what worked, what didn't, what to change.
last run · 18h ago
Recently shipped
The most recent posts NEXUS drafted, I reviewed, and the stack published.
I sold a $49 AI workflow pack to test a bet: would anyone actually want to own their automation instead of renting it? Early signal says yes. And the buyers aren't model-chasers. They're operators tired of paying mon...
Read on linkedin →The model is the cheap part now. The expensive part is depending on someone else's box for the work that pays your bills. I moved mine in-house. Runs on my own hardware, answers to me, and the terms of service can't...
Read on twitter →Run the math on AI dependency. It's worse than it looks. The monthly fee is the part you see. The part you don't: every workflow you build inside someone else's tool is a workflow you'll rebuild when they change it. ...
Read on linkedin →Everyone is shopping for a smarter model. Almost nobody is building the loop around it. An AI lab made news this week with a system that improves your model automatically. Good work. But it reminded me how many peopl...
Read on linkedin →A small model you own, wrapped in a system you designed, beats a frontier model you rent for the work that actually repeats in your life. That's the bet I've been making for a year, stated plainly. Not for everythin...
Read on linkedin →This page is a static snapshot, pushed once each morning by the same stack that runs everything else. No backend · no live API · no telemetry from your browser. The Sunday newsletter tells the story behind the numbers.