Mycelium
Most software work sent to a frontier model can be done by local minions instead — given the right harness around them. Mycelium is a local AI workbench: a roster of local agents run through one fixed, reproducible harness, publishing two things the field rarely reports together — how much of the work runs locally, and the energy each token costs.
The lab, running
as of 2026-07-19 00:49 UTC · pushed from the lab's substrate at each deploy — failures included
Approach
A frontier model is reserved for judgment — decomposition, specifications, the calls that need taste. A roster of role-specialized local minions does the token-heavy execution. We publish what that division actually buys: the share of tokens carried locally, and the watts and joules each token costs on hardware we own.
This follows the intelligence-per-wattframing — accuracy per unit of power — and extends it from single-turn coverage to sustained, multi-step software work. The open question we are instrumenting, not yet answering, is whether the local share rises over time as the roster trains on the supervisor's own outputs, at held quality.