Skip to main content

AI-powered Command Generator using Local LLMs

Project description

qcmd - AI-powered Command Generator

A simple command-line tool that generates shell commands using local AI models via Ollama.

Version 1.0.5

Overview

qcmd is a powerful command-line tool that generates shell commands using AI language models via Ollama. Simply describe what you want to do in natural language, and qcmd will generate the appropriate command.

Key Features

  • Natural Language Inputs: Describe what you want to do in plain English
  • Auto-fix Mode: Automatically fixes failed commands and retries
  • AI Error Analysis: Explains errors and suggests solutions
  • Interactive Shell: Continuous operation with command history
  • Multiple Models: Works with any Ollama model (default: qwen2.5-coder:0.5b)
  • Safety First: Always asks for confirmation before executing any command
  • Log Analysis: Find and analyze system log files with real-time monitoring

Installation

Prerequisites

  • Python 3.6 or higher
  • Ollama installed and running
  • At least one language model pulled (e.g., qwen2.5-coder:0.5b)

Install from PyPI

pip install ibrahimiq-qcmd

Make sure Ollama is running before using qcmd:

ollama serve

Basic Usage

# Generate and confirm a command
qcmd "list all files in the current directory"

# Auto-execute mode
qcmd -e "find large log files"

# Smart auto-fix mode
qcmd -A "find Python files modified today"

# Interactive shell
qcmd -s

What's New in 1.0.5

  • Fixed compatibility with Python 3.12+ by removing pkg_resources dependency
  • Improved version detection using Python standard library (importlib.metadata)
  • Removed external dependency requirements for better cross-version compatibility
  • Enhanced installation reliability across all Python versions
  • Simplified update checking mechanism

What's New in 1.0.4

  • Initial attempt at fixing Python 3.12+ compatibility issues
  • Updated documentation for better clarity
  • Minor code improvements

What's New in 1.0.3

  • Implemented improved release automation workflow
  • Enhanced package publishing process
  • Updated GitHub Actions configuration
  • Streamlined deployment process
  • Documentation improvements for contributors

What's New in 1.0.2

  • Fixed undefined variable errors in interactive shell and auto mode
  • Improved error handling and command detection for dangerous operations
  • Streamlined GitHub Actions workflow for Python 3.10 and 3.11
  • Enhanced compatibility with continuous integration systems
  • Fixed tab completion issues in interactive shell

What's New in 1.0.1

  • Updated documentation with improved installation instructions
  • Fixed package structure for better compatibility
  • Added PyPI integration for easier installation

Full Documentation

For full documentation and source code, visit the GitHub repository.

Project details


Download files

Download the file for your platform. If you're not sure which to choose, learn more about installing packages.

Source Distribution

ibrahimiq_qcmd-1.0.5.tar.gz (25.3 kB view details)

Uploaded Source

Built Distribution

If you're not sure about the file name format, learn more about wheel file names.

ibrahimiq_qcmd-1.0.5-py3-none-any.whl (22.9 kB view details)

Uploaded Python 3

File details

Details for the file ibrahimiq_qcmd-1.0.5.tar.gz.

File metadata

  • Download URL: ibrahimiq_qcmd-1.0.5.tar.gz
  • Upload date:
  • Size: 25.3 kB
  • Tags: Source
  • Uploaded using Trusted Publishing? No
  • Uploaded via: twine/6.1.0 CPython/3.12.9

File hashes

Hashes for ibrahimiq_qcmd-1.0.5.tar.gz
Algorithm Hash digest
SHA256 73d2479f72aba2cf8a2f0654d46fd2bd69568c16396fcb3d2baf2e7d2e1719c4
MD5 f8ffbb224d3c1da7d9ef0fe824f03c29
BLAKE2b-256 6e55eec74dbc8c7b680d03efa71e09fcb10ea8450da7973075b693b139c312ad

See more details on using hashes here.

File details

Details for the file ibrahimiq_qcmd-1.0.5-py3-none-any.whl.

File metadata

  • Download URL: ibrahimiq_qcmd-1.0.5-py3-none-any.whl
  • Upload date:
  • Size: 22.9 kB
  • Tags: Python 3
  • Uploaded using Trusted Publishing? No
  • Uploaded via: twine/6.1.0 CPython/3.12.9

File hashes

Hashes for ibrahimiq_qcmd-1.0.5-py3-none-any.whl
Algorithm Hash digest
SHA256 0d1c03d536b727f75c0827d8e5cd31de9db25bb0309373788d38cb957309ce56
MD5 5213036bc1714d4457978d9195b86a27
BLAKE2b-256 df1f4440cea80639d20473aae85034291a40e59fc529849133e46ccc934272a6

See more details on using hashes here.

Supported by

AWS Cloud computing and Security Sponsor Datadog Monitoring Depot Continuous Integration Fastly CDN Google Download Analytics Pingdom Monitoring Sentry Error logging StatusPage Status page