GitHub - dtnewman/zev: A simple CLI tool to help you remember terminal commands

3 min read Original article ↗

Zev 🔍

PyPI version License: MIT

Zev helps you remember (or discover) terminal commands using natural language.

Description

🔧 Installation

  • Note: This project runs on top of LLM APIs like OpenAI, Google's Gemini, or Ollama.

📦 Dependencies

For clipboard functionality (copying and pasting) to work properly, you may need to install:

  • On Linux: xclip or xsel (for X11) or wl-clipboard (for Wayland)
  • On macOS: No additional dependencies needed
  • On Windows: No additional dependencies needed

🎮 Usage

Option 1: Interactive Mode

Option 2: Direct Query

zev '<what you want to do>'

📝 Examples

# Find running processes
zev 'show all running python processes'

# File operations
zev 'find all .py files modified in the last 24 hours'

# System information
zev 'show disk usage for current directory'

# Network commands
zev 'check if google.com is reachable'

# Git operations
zev 'show uncommitted changes in git'

🛡️ Safety Considerations

⚠️ Commands are generated by LLMs. While the tool attempts to flag dangerous commands, it may not always do so. Use caution.

Example of dangerous command warning

⚙️ Settings

Supported LLM Providers:

  • OpenAI
  • Google Gemini
  • Ollama
  • Azure OpenAI

You can update your API keys and provider settings by running:

OpenAI

To use OpenAI, you need an OpenAI account and a subscription. You can create an API key on this page.

Google Gemini (Free)

To use Google's Gemini models, you need a Google AI Studio account. You can create a Gemini API key in Google AI Studio.

🐪 Using with Ollama

You can use Zev with Ollama as an alternative to hosted providers, which lets you run all commands locally. To set this up:

  1. Install and start Ollama with a model of your choice

  2. Run zev --setup and put in the proper settings. For example:

? Pick your LLM provider: Ollama
? Enter the Ollama URL: http://localhost:11434/v1
? Enter the model to use (e.g. llama3.2): llama3.2

Azure OpenAI

To use Azure OpenAI, you’ll need access to an Azure OpenAI resource in your Azure subscription.

  1. Create a deployment of the model you want to use (e.g., gpt-4o, gpt-4o-mini etc.).

  2. Install required Azure depedencies with pip install zev[azure].

  3. Run zev --setup and put in the proper settings. For example:

    ? Pick your LLM provider: Azure OpenAI
? Azure OpenAI account name (e.g. my-openai-resource): my-openai-resource
? Azure OpenAI API key (leave blank to use Entra ID / keyless auth):
? Azure OpenAI deployment name (e.g. gpt-4, gpt-4o, etc): gpt-4o
? Azure OpenAI API version: 2025-03-01-preview

    Note: Model version must be 2024-08-06 or newer.
    API version must be 2024-08-01-preview or newer.

Note that to switch backends, you can re-run zev --setup again at any time.

🤝 Contributing

Contributions are welcome! See CONTRIBUTING.md for details.

📄 License

This project is licensed under the MIT License - see the LICENSE file for details.