https://github.com/dh1011/llm-term

A Rust-based CLI tool that generates and executes terminal commands using OpenAI's language models.
https://github.com/dh1011/llm-term

Last synced: 8 days ago
JSON representation

A Rust-based CLI tool that generates and executes terminal commands using OpenAI's language models.

• Host: GitHub
• URL: https://github.com/dh1011/llm-term
• Owner: dh1011
• License: mit
• Created: 2024-08-29T07:17:14.000Z (5 months ago)
• Default Branch: main
• Last Pushed: 2024-10-30T04:04:57.000Z (3 months ago)
• Last Synced: 2024-10-30T07:13:14.415Z (3 months ago)
• Language: Rust
• Homepage:
• Size: 1.15 MB
• Stars: 90
• Watchers: 1
• Forks: 2
• Open Issues: 1
• Metadata Files:
  • Readme: README.md
  • License: LICENSE

Awesome Lists containing this project

• awesome-cli-apps - llm-term - A Rust-based CLI tool that generates and executes terminal commands using OpenAI's language models. (<a name="ai"></a>AI / ChatGPT)
• awesome-cli-apps-in-a-csv - llm-term - A Rust-based CLI tool that generates and executes terminal commands using OpenAI's language models. (<a name="ai"></a>AI / ChatGPT)
• awesome_ai_agents - Llm-Term - A Rust-based CLI tool that generates and executes terminal commands using OpenAI's language models. (Building / Tools)
• awesome_ai_agents - Llm-Term - A Rust-based CLI tool that generates and executes terminal commands using OpenAI's language models. (Building / Tools)

README

        
# 🖥️ LLM-Term

A Rust-based CLI tool that generates and executes terminal commands using OpenAI's language models or local Ollama models.

## Features

- Configurable model and token limit (gpt-4o-mini, gpt-4o, or Ollama)

- Generate and execute terminal commands based on user prompts

- Works on both PowerShell and Unix-like shells (Automatically detected)

## Demo

![LLM-Term Demo](vhs-video/demo.gif)

## Installation

- Download the binary from the [Releases](https://github.com/dh1011/llm-term/releases) page

- Set PATH to the binary

    - MacOS/Linux:

    ```

    export PATH="$PATH:/path/to/llm-term"

    ```

    - To set it permanently, add `export PATH="$PATH:/path/to/llm-term"` to your shell configuration file (e.g., `.bashrc`, `.zshrc`)

    - Windows:

    ```

    set PATH="%PATH%;C:\path\to\llm-term"

    ```

    - To set it permanently, add `set PATH="%PATH%;C:\path\to\llm-term"` to your shell configuration file (e.g., `$PROFILE`)

## Development

1. Clone the repository

2. Build the project using Cargo: `cargo build --release`

3. The executable will be available in the `target/release` directory

## Usage

1. Set your OpenAI API key (if using OpenAI models):

   - MacOS/Linux:

     ```

     export OPENAI_API_KEY="sk-..."

     ```

   - Windows:

     ```

     set OPENAI_API_KEY="sk-..."

     ```

2. If using Ollama, make sure it's running locally on the default port (11434)

3. Run the application with a prompt:

   ```

   ./llm-term "your prompt here"

   ```

4. The app will generate a command based on your prompt and ask for confirmation before execution.

## Configuration

A `config.json` file will be created in the same directory as the binary on first run. You can modify this file to change the default model and token limit.

## Options

- `-c, --config `: Specify a custom config file path

## Supported Models

- OpenAI GPT-4 (gpt-4o)

- OpenAI GPT-4 Mini (gpt-4o-mini)

- Ollama (local models, default: llama3.1)