A ghost in my shell, powered by a local Gemma

Описание и применение

Терминальный «призрак» использует локальную модель Gemma для генерации комментариев к командам без передачи данных в облако.

Задача

Shell commands expose sensitive data; a local LLM can generate contextual comments without leaking history.

Результат

The ghost provides timely, model‑generated commentary on shell commands with minimal latency (≈2 s for gemma3:4b) and no external data transfer.

Рабочий процесс

• Install Ollama and pull gemma3:4b
• Clone haunted‑terminal repo
• Add haunt.sh to ~/.bashrc
• Set optional env vars (HAUNT_ODDS, HAUNT_MODEL, HAUNT_HOST)
• Run commands; ghost whispers appear after command completion

Доказательства

It is about 80 lines: a Bash hook (haunt.sh) on PROMPT_COMMAND and a stdlib-only Python script (whisper.py) that calls Ollama's /api/generate.

Источник

Same prompt, 5 commands, 16 cores, no GPU, 14 GB RAM (warm = model already loaded):

Источник

12B writes slightly better lines, but 4B is the right default.

Источник

Cold start can silence the ghost.

Источник