Home
What Skipper Is
Features
In Action
Changelog

Added conditional shared embedding cache

Jul 10th 2026 · Demetris Rouslan Zavorotnitsienko

For faster sessions, the retrieval is cached to save few milliseconds.

← Added a unified retrieval orchestrator Added streamed LLM voice output integration →

Related

Added wake acknowledgement voice cues

Wake cues for different aspects of voice input were added.

Added TTS benchmark tools

Tools were added for Text To Speech benchmarking.

Centralized runtime config defaults

All config values are centralized for a more organized functionality.

Built by a sailor, for life aboard

Hi, I'm Demetris.

Skipper began as an onboard marine assistant I wanted for my own use - for an environment where privacy, independence and reliable access to information matter. It has grown into a self-contained offline companion designed to remain useful aboard, even when the internet and cloud are out of reach.

Talk to the Maker

Have a question about Skipper or whether it would suit your boat? Get in touch directly.

info@meetskipper.ai

I'm usually on a boat somewhere.

Terms of Sale
Warranty and Returns
Privacy Policy
Safety and Responsible Use