The Elora Taurus Project - Engine Changelog

Engine Updates

Core runtime, governance boundary, operator-surface, and guided demo journey changes.

Version 0.2.0 Current Line

Elora remains in the 0.2.0 research line with ERIS runtime-intelligence surfaces, governed Curiosity queue controls, state-adapter view migration, adaptive cache/echo learning evolution, and expanded deterministic evidence/replay visibility.

LLM Pipeline Changelog Custom Pipeline

Elora uses a custom LLM pipeline with custom Fabric connectivity, including a WordPress plugin integration path for governed runtime requests.

Open LLM Inference

Site Updates

Navigation, documentation IA, and public guided demo updates are tracked alongside engine changes, with current focus on Governance Replay and Research Report walkthroughs while Model Exams is temporarily paused.

Architecture Updates

Governance-model and control-plane architecture changes are reflected in Research and Docs sections.

0.2.0 Highlights (CORE + Evidence Evolution)

ERIS runtime-intelligence surface added for workers, containers, process, pressure, and runtime learning posture visibility.
Curiosity queue governance model introduced with proposal/approval controls and split-authority posture.
State-adapter-first view migration expanded to reduce API fanout and improve dashboard read efficiency.
Elora CORE added as a dedicated coordination surface with explicit boundary separation from capability modules.
Echo learning persistence and scheduled profile refresh added for model/profile continuity.
Adaptive Cache and Engine Health/PhyOS surfaces expanded for explainable stability and performance telemetry.