Notre Engine
PRE-ALPHA local CPU MoE inference research — not a hosted API.
Caedral Notre Engine (cne) is PRE-ALPHA, MIT-licensed research into local CPU Mixture-of-Experts inference for low-RAM machines. Explicit memory budgets, predictable resource behavior, and lossless output by default. llama.cpp is the kernel; memory regimes live outside it. Engine is not on the production POST /v1/chat/completions path, is not a hosted Caedral API, and is not billed through subscription pools.