Skip to main content

Console utility for integrating artificial intelligence into a Linux terminal.

Project description

Ai-ebash!

Console utility for integrating artificial intelligence into a Linux terminal. Allows you to ask an AI question and execute the scripts and commands suggested by the AI in the terminal. It will be useful for novice Linux administrators.

The project is in the pre-alpha stage. In case of problems with the installation or operation of the Ai-bash utility, please contact me.

Features

  • Sends requests to LLM from the command line with a simple command and receives responses in a formatted, easy-to-read form
  • Supports dialog mode (key -d). By default, the quick questions mode with a return to the console works without a key.
  • In the dialog mode, it allows you to run scripts proposed by the neural network (be careful!)

Requirements

  • Python 3.11+

Installation

Debian/Ubuntu (pipx package)

  1. Install pipx (if not already installed):
sudo apt update
sudo apt install pipx python3-venv -y
pipx ensurepath
  1. Restart the terminal

Note: If you encounter issues with pipx not recognizing the package, you can also install it using pip:

pip install ai-ebash

Debian/Ubuntu (*.deb package)

  1. Download the latest DEB package from GitHub Releases
wget -qO latest.deb $(wget -qO- https://api.github.com/repos/Vivatist/ai-ebash/releases/latest \
  | grep "browser_download_url" | grep ".deb" | cut -d '"' -f 4)
  1. Install the package:
sudo dpkg -i ./latest.deb
sudo apt-get install -f -y
  1. Restart the terminal

Windows (experemental)

  1. Install Python v3.11+ (if not already installed):

  2. Open CMD or PowerShell and install ai-ebash:

pip install ai-ebash
  1. Restart Windows

Example

ai Hello AI! Write example script.

or

ai -d Hello AI! Write example script.

Uninstall

To completely remove the utility:

If installed via pipx:

pipx uninstall ai-ebash

If installed via DEB package:

sudo apt remove python3-ai-ebash
# Or for complete deletion, including configuration files:
sudo apt purge python3-ai-ebash

If installed via Windows:

pip uninstall ai-ebash

You can also use dpkg.:

sudo dpkg -r ai-ebash
# Or for complete deletion, including configuration files:
sudo dpkg -P ai-ebash

Security

Do NOT execute arbitrary code returned by an LLM without review. Executing assistant-provided code has security and safety risks. Recommended mitigations:

Contributing

  1. Localization to any languages
  2. Fork the repo and create a feature branch.
  3. Add tests for new behavior.
  4. Open a PR with a clear description.

License

MIT

Contact

andrey.bch.1976@gmail.com. Issues and PRs are welcome. Include logs and reproduction steps

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

ai_ebash-0.3.0.tar.gz (27.9 kB view details)

Uploaded Source

Built Distribution

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

ai_ebash-0.3.0-py3-none-any.whl (30.1 kB view details)

Uploaded Python 3

File details

Details for the file ai_ebash-0.3.0.tar.gz.

File metadata

  • Download URL: ai_ebash-0.3.0.tar.gz
  • Upload date:
  • Size: 27.9 kB
  • Tags: Source
  • Uploaded using Trusted Publishing? No
  • Uploaded via: twine/6.1.0 CPython/3.13.7

File hashes

Hashes for ai_ebash-0.3.0.tar.gz
Algorithm Hash digest
SHA256 af1b182f00423f5109c15c0bd87a1caf95f000e81471cd5f8f84ffe590bdd502
MD5 15f0f94e6fab96e1abbbc8916b5ab2f8
BLAKE2b-256 e42daf6870b6552fdfdbf6ce16ea6208134a0bf374bdb89119fba4c886087619

See more details on using hashes here.

File details

Details for the file ai_ebash-0.3.0-py3-none-any.whl.

File metadata

  • Download URL: ai_ebash-0.3.0-py3-none-any.whl
  • Upload date:
  • Size: 30.1 kB
  • Tags: Python 3
  • Uploaded using Trusted Publishing? No
  • Uploaded via: twine/6.1.0 CPython/3.13.7

File hashes

Hashes for ai_ebash-0.3.0-py3-none-any.whl
Algorithm Hash digest
SHA256 477a141eda6046c0985e503732bfd7345021ae9ad468bf8f61cac7b88c3ca7e7
MD5 8eddf35a7e5cd451ffc6950a2cde594e
BLAKE2b-256 18f7fccf1c1a4c6eabcf6c50f9ec2a0050b97b60ac8b21f0a4f39bd9022199eb

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