ccline — AI shell helper for the terminal work around LLM fine-tuning

[jianshuo]

Hey LlamaFactory users!

Fine-tuning LLMs involves a lot of terminal work — config files, CUDA setup, GPU monitoring. ccline makes that terminal smarter:

$ check gpu memory usage
→ Use nvidia-smi:
  nvidia-smi --query-gpu=memory.used,memory.free --format=csv

Commands found — run it?
❯ nvidia-smi --query-gpu=memory.used,memory.free --format=csv
  ✗ Cancel

ccline hooks into zsh/bash's command_not_found_handler — type your question at the prompt when you forget a flag or command, get an AI answer, run it.

• GitHub: https://github.com/jianshuo/ccline
• Install: curl -fsSL https://raw.githubusercontent.com/jianshuo/ccline/main/install.sh | bash

Uses claude CLI (Claude Code) or codex CLI. Works on Linux (perfect for GPU servers).