3 projects
newlife
Preregistration harness for simulation: freeze what would count as an answer in git, compute the verdict mechanically, and prove from commit ancestry that the outputs post-date the freeze.
proofroot
Language-neutral trust core for reproducible simulation: named RNG stream derivation, run phases, evidence tiers, canonical serialization.
exloop
Human-led exploration with a persistent map: the exloop skill for any AI tool that reads SKILL.md, plus the zero-dependency state helper it uses.
