fleet
A self-improving agent harness: sensors log every human correction, a deterministic metrician scores the runs, and an adversarially judged fix loop edits the harness itself.
A self-improving agent harness: sensors log every human correction, a deterministic metrician scores the runs, and an adversarially judged fix loop edits the harness itself.
An open-source personal alignment engine: a portable AI skill that learns what you actually value through Socratic conversation, then keeps your actions pointed at it.