Repository profile

mizorewww / laya-mlx

Native MLX runtime for Laya typed decision models — 7–14 ms short decisions on M3 Max. No text generation, PyTorch, or cloud API.

  • apple-silicon
  • decision-model
  • inference
  • laya
  • local-ai
  • machine-learning
  • mlx
  • modernbert
  • system-one
  • typed-decisions

Repository overview

Public GitHub metrics and OpenPulse observations
GitHub stars6,969
Public forks568
Growth · 24h+12 stars
Growth · 7dBuilding history
Growth · 30dBuilding history

Star activity

Last 7 days
16 Oct4 observed days · gaps preserved19 Oct

Observed star growth

Samples or dated GitHub history
24h +12 stars Measured from observations 18 Oct 2026 → 19 Oct 2026
7d Building history More observations needed — → 19 Oct 2026
30d Building history More observations needed — → 19 Oct 2026