Elite Intel: Sci-Fi enspired ship computer for Elite Dangerous

Authors

Status
Active
Required software
Java 21 or newer.
Compatible with release
License
CC BY-NC-SA 4.0 (Attribution-NonCommercial-ShareAlike 4.0 International)
Supported languages
English en
Platform
GameApplication Linux GameApplication Mac GameApplication Windows
Elite:Dangerous Application

Share

Elite Intel is a Sci-Fi inspired off-line private AI ship computer for Elite Dangerous. Open Source and runs on Linux and Windows.

Overview

 

Elite Intel is an OFF LINE private LLM powered ship computer for Elite Dangerous. It understands natural language and does  not require memorizing command lists. It interprets intent from spoken input. Natural phrasing is accepted. Formal command syntax is not required.

 

The full stack (Speech-to-Text, LLM, and Text-to-Speech) can run completely  offline on local hardware. No cloud connection, subscription, or data  transmission is required in offline mode. Components can also be mixed:  local STT with a cloud LLM, or cloud TTS with local inference.

 

  • Speech Recognition Powered by NVIDIA Parakeet STT model. Runs locally on CPU. Does not require training, works out of the box

  • Text To Speech Powered by Kokoro model. Run locally, private. Provides 11 voice choises.

  • Local LLM (AI) Powered by tulu3.1:8b-Supernova runs locally, private. Provides inference for uttered commands and queries without requiring user to memorize the list of commands.

  • Cloud LLM, choose between Deepseek, Grok, Claude, OpenAI or Gemini. Not private, runs in the cloud, cost money, but off loads the inference from your GPU to the cloud. This option is for commanders who do not have the necessary hardware to run local LLM.

 

See GitHub project for installers, wiki.

Join Matrix community to chat with dev and testers.


Links

History

  • May 12, 2026 (GuinPin) release candidate
  • Nov 14, 2025 (GuinPin) First revision

Credits

Alex Stone (CMDR PRINCE OF KRONDOR)