VIBESHIFTAI
SYSTEM LIVE
07 ENGINEERING STATION

Power & Economics

An autonomous system that pays per token thinks twice about thinking. Praxis is engineered the other way: flat-rate seats, local models, cloud off by default so the marginal cost of thinking approaches zero.

The Reactor Gauge

Today's burn, by provider from the live Engineering station.

1.4M TOKENS TODAY · 6% OF RECORD
claude code856k
codex285k
local llm278k
cloud api0
day record 22.7M · Jul 10CLOUD: OFF

Heavy work dispatches to subscription CLI seats rather than metered APIs. A local model on the Mac Studio handles embeddings, routing, and routine roles for free. The cloud API toggle exists, reads zero, and stays off unless the operator flips it for something that genuinely needs it.

Every dispatch decision is itself instrumented by agent-dispatch histograms that record which executor was chosen, why, and what it returned, so the routing table is tuned on evidence, not vibes.

On a record day the system burned 22.7M tokens. The bill was the same as on a quiet one.

The System, by the Numbers

Counted from the live system — board API, source tree, cron registry, graph, fleet monitor.

27
projects on the board
board API
~300K
lines of TS + Python
source tree
47
scheduled jobs
cron registry
85
agent tools
tool registry
44
routed LLM roles
model-control table
465
tasks complete
board API
69
curated skills
skills library
21
fleet services monitored
fleet monitor

Measured snapshot · July 2026

← Back to the console The flat-rate fleet — AI Mesh →
GO DEEPER
01Praxis — The Console 02The Daily Loop 03The Problem-Solving Machine 04The AI Mesh 05Knowledge & Memory 06The Task Board 07Power & Economics 08The Projects