A ghost in my shell, powered by a local Gemma

说明与用途

终端幽灵使用本地 Gemma 模型为命令生成上下文评论，且不将数据发送到云端。

问题

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

结果

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

工作流

• 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

证据

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.

来源

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

来源

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

来源

Cold start can silence the ghost.

来源