Inside TokenRhythm's three-part stack: OpenSquilla, a model API, and NeoHorse-1

PrajwalTomar_ · x · 2026-09-16

In this segment of Prajwal Tomar's TokenRhythm thread, he breaks the project into three parts: OpenSquilla runs the job, TokenRhythm API connects it to different models, and NeoHorse-1 is trained using lessons from those agent runs — the last being what he calls the big bet.

The thread's core argument: an agent's full journey of finding a bug, trying three bad fixes, and solving it currently lives only in the chat log; the underlying model learns nothing from it.

Related event: TokenRhythm launches NeoHorse-1, turning agent run experience into model training(9 posts)→

Original post →

More from coding & agent

coding & agent channel →