ej

An 11MB local model for typed decisions in one pass

I built ej for a narrower problem than general classification: given some state and a set of decision questions whose options can be defined at runtime, return a probability distribution for each question in one pass. It handles choice, yes/no, and ordered scores, runs on CPU, needs no token generation, and ships as one 11.4 MB model file. The repo includes training, evaluation, adaptation, packed weights, and the benchmark harness.

ej is a Open Source company. It launched on Product Hunt on Oct 10, 2026, with 64 upvotes. Adamlead has 1 person on file at ej.