sys-edge

USE when managing AI models on mobile/edge devices. Implements lazy loading, quantization strategies, memory pressure handling, and dynamic model management for resource-constrained environments.

USE when analyzing GitHub repositories, digesting codebases, or ingesting git repos for AI analysis. Transforms repositories into structured plain-text digests optimized for LLM consumption.

USE when optimizing AI applications for mobile devices. Implements battery-aware processing, thermal management, adaptive quality settings, and power-efficient inference patterns.

USE when implementing offline-first sync for mobile AI applications. Manages encrypted local storage, conflict resolution, incremental sync, and privacy-first data synchronization.

USE when managing Python projects, dependencies, virtual environments, linting, or formatting. Covers uv (10-100x faster package manager) and ruff (extremely fast linter/formatter).