A command-line tool that converts natural language instructions into shell commands and executes them.
Project description
🐚 shell-prompt
shell-prompt is a command-line tool that translates natural language instructions into executable shell commands using an LLM. It supports multiple LLM providers (like OpenAI, Anthropic, Google Gemini, etc.) and adapts to the user's operating system.
Usage example:
- USER INPUT:
shell-prompt "list all files in my Desktop directory"
- OUTPUT:
Command to run:
dir "%UserProfile%\Desktop"
Execute this command? [y/N]: y
Running command: dir "%UserProfile%\Desktop"
*Command output here*
🚀 Features
- Converts natural language into shell commands
- Supports execution and preview mode
- Compatible with Windows, Linux, and macOS
- Extensible to multiple LLM providers via
langchain - Lightweight and configurable
📦 Installation
You can install it from your local build or via PyPI.
Installation should be done with a specific LLM provider, such as:
pip install shell-prompt[google-genai]
List of supported providers:
- openai
- anthropic
- google-genai
- groq
- cohere
- langchain-nvidia-ai-endpoints
- fireworks
- mistralai
- together
- langchain-xai
- langchain-perplexity
🛠 Usage
Once installed, you should first configure the tool. Available options are:
| Option | Description |
|---|---|
-h, --help |
Show the help message and exit |
--version |
Show the program's version number and exit |
--config |
Show the current configuration |
--set-provider PROVIDER_NAME |
Set the LLM provider |
--set-model MODEL_NAME |
Set the specific model to use |
--set-api-key API_KEY |
Set the API key for the currently selected provider |
--preview, --no-preview |
Enable or disable preview mode (avoid instant execution - enabled by deafult) |
Example:
shell-prompt --set-provider google-genai --set-model "gemini-2.0-flash" --set-api-key APIKEY --no-preview
Print out the configuration:
shell-prompt --config
Run the tool:
shell-prompt "show current time, but only the seconds"
Running command: powershell Get-Date -Format ss
39
Project details
Release history Release notifications | RSS feed
Download files
Download the file for your platform. If you're not sure which to choose, learn more about installing packages.
Source Distribution
Built Distribution
Filter files by name, interpreter, ABI, and platform.
If you're not sure about the file name format, learn more about wheel file names.
Copy a direct link to the current filters
File details
Details for the file shell_prompt-0.1.0.tar.gz.
File metadata
- Download URL: shell_prompt-0.1.0.tar.gz
- Upload date:
- Size: 8.2 kB
- Tags: Source
- Uploaded using Trusted Publishing? No
- Uploaded via: twine/6.1.0 CPython/3.12.9
File hashes
| Algorithm | Hash digest | |
|---|---|---|
| SHA256 |
658c7376c9e0977712be9c7b3805cc1175d2ce4a9389c4809cb79bc02def32ba
|
|
| MD5 |
2b07436acd33fb837cfcf98c2b27b0c3
|
|
| BLAKE2b-256 |
44a78c381dbc676ff18aad44f982b1309f54b35e4710cb88adc0fb7dd448faf8
|
File details
Details for the file shell_prompt-0.1.0-py3-none-any.whl.
File metadata
- Download URL: shell_prompt-0.1.0-py3-none-any.whl
- Upload date:
- Size: 8.8 kB
- Tags: Python 3
- Uploaded using Trusted Publishing? No
- Uploaded via: twine/6.1.0 CPython/3.12.9
File hashes
| Algorithm | Hash digest | |
|---|---|---|
| SHA256 |
b5802e0b6c765aa95c2be918592a595a4ceb6babcd5e67b7a5ba6d2b1c0d8363
|
|
| MD5 |
3a4f6a139a6a261d75dbebed41a3adb0
|
|
| BLAKE2b-256 |
e391dced4bfc03109654169f21b7f8309a96a6fdb7972b8561336ebc4c839979
|