
CloakNotes — Private AI Workspace
On-device audio workspace running quantized INT4 LLMs with <1.1GB RAM active footprint and zero cloud latency.
I build low-latency, resilient systems on constrained hardware — from mobile to edge to embedded.
software

On-device audio workspace running quantized INT4 LLMs with <1.1GB RAM active footprint and zero cloud latency.

120 FPS sim-racing telemetry HUD with zero-allocation binary parsing and direct GPU canvas repainting.

Embedded vector search engine delivering <12ms recall across 100k 768-dim vectors using Rust and mmap storage.

High-concurrency micro-transaction ledger processing 18,000+ TPS using append-only event sourcing and Redis batching.

Distributed media automation engine compiling complex multi-step pipelines into resilient, fault-tolerant DAGs.

Offline-first field operations client with vector clock conflict resolution and viewport-based CAD tile rendering.
Tools for serious systems
Selected stackCore Systems & Runtimes
Edge AI & Local Inference
Distributed Infrastructure