nimmerworld.eachpath.local/inference-and-memory/architecture.md

Inference and Memory

AI substrate + memory: LLM tiering by role (Theia-tier / teacher-tier / driver-tier with trait-LoRAs); three rings of inference (A=local, B=our-farm, C=external-providers, with cloud-LoRA-backup as Ring-A revenue and BYOK adapter for Ring-C); custom nimmerworld-base-model with default-opt-out + rewarded-opt-in data-sharing tiers; runtime sampling knobs as per-turn director-controlled levers; per-player local memory architecture (primary.sqlite + fallback.sqlite + clasp.sqlite + embedding-beside) with memory-classes (cornerstone/birthright/working/volatile) and trait-graded importance; three-tier knowledge stack (world / district / primary [+ clasp if in-between]) with paced canon-propagation.

Status: skeleton — content migration scheduled for commit 2 of the split-into-domains operation. Architecture content currently lives in architecture-broad.md and will land here next.

Companion to: architecture-broad.md (executive summary + global meta-lists), narrative-composition/architecture.md (Compositor canon-fragments land in primary.sqlite via UID-keyed routing), player-experience/architecture.md (Ring-A/B/C choice + voice-as-biometric-local + universal-translator state), runtime-engine/architecture.md (driver-tier LLM fires at slot-fire).

Sections that will land here

• §LLM tiering, voice fidelity, and the three rings of inference
• §Runtime sampling knobs
• §Local memory architecture (player-side)

---

Version: 0.7.0-skeleton | Created: 2026-04-26 | Updated: 2026-04-26 | Origin: Skeleton placeholder for commit 1 of the split-into-domains operation