Skip to main content

Terminal Operation Natural Instruction - AI-powered terminal assistant

Project description

TONI - Terminal Operation Natural Instruction

TONI is a lightweight CLI tool that translates natural language into terminal commands using AI. Simply describe what you want to do, and TONI will suggest the appropriate command for your system.

PyPI version

Inspiration

TONI was inspired by YAI (Yet Another Interpreter), but with a focused approach. While YAI offers a comprehensive terminal experience, TONI is designed specifically to suggest and execute single commands based on natural language descriptions.

Features

  • Translates natural language to terminal commands
  • Prioritizes Google Gemini AI with OpenAI fallback
  • Cross-platform: Works on Linux, macOS, and Windows
  • System-aware: Detects your OS and generates platform-appropriate commands
  • Verifies command availability before execution
  • Saves executed commands to shell history (ZSH on Unix, custom history on Windows)
  • Simple to use and install

Installation

# Install from PyPI
pip install toni-cli

# Or with pipx (recommended)
pipx install toni-cli

Windows Installation

TONI works on Windows via pip or pipx:

# Using pip
pip install toni-cli

# Or with pipx (recommended)
pipx install toni-cli

Note: On Windows, TONI generates Windows-native commands (CMD/PowerShell) and saves command history to ~/.toni_history.

Configuration

TONI uses a configuration file at ~/.toni (INI format). By default, it supports Google Gemini, OpenAI, and Mistral.

Built-in Providers

  1. Google Gemini (Preferred):

    export GOOGLEAI_API_KEY='your-gemini-api-key'
    
  2. OpenAI:

    export OPENAI_API_KEY='your-openai-api-key'
    
  3. Mistral:

    export MISTRAL_API_KEY='your-mistral-api-key'
    

Custom OpenAI-Compatible Providers

You can add unlimited custom providers (Ollama, LM Studio, OpenRouter, etc.) by adding sections to ~/.toni. Any section with a url field is treated as an OpenAI-compatible provider.

Example: Ollama

[ollama]
url = http://localhost:11434/v1
key = ollama
model = llama3.2:latest
priority = 100

Example: OpenRouter

[openrouter]
url = https://openrouter.ai/api/v1
key = sk-or-v1-xxx...
model = anthropic/claude-3.5-sonnet
priority = 80

Priority System

  • Custom providers are tried first, sorted by their priority field (higher numbers first).
  • Default priority is 50.
  • Built-in providers have default priorities: OpenAI (50), Gemini (40), Mistral (30).
  • If a provider is disabled (disabled = true) or fails, TONI falls back to the next one in the chain.

Environment Variables

For any custom provider [my-provider], you can set the API key via:

export MY_PROVIDER_API_KEY='your-key'

Usage

Simply type toni followed by your natural language description:

# Basic file operations
toni list all pdf files in current directory
toni find all files modified in the last 7 days

# System queries
toni show my disk usage
toni what processes are using the most memory

# Complex tasks
toni create a backup of my Documents folder
toni find the largest files in this directory

Examples

Linux/macOS

$ toni find all python files containing the word "error"

Detected system: Linux (arch)
Suggested command: grep -r "error" --include="*.py" .
Explanation: Search recursively for the word "error" in all Python files in the current directory
Do you want to execute this command? (y/n):

Windows

> toni find all python files containing the word "error"

Detected system: Windows 10 (10.0.19045)
Suggested command: findstr /s /i "error" *.py
Explanation: Search for "error" in all Python files recursively
Do you want to execute this command? (Y/n):

Development

To contribute to TONI:

  1. Clone the repository:
git clone https://github.com/yourusername/toni.git
cd toni
  1. Create a virtual environment:
python -m venv venv
source venv/bin/activate
  1. Install for development:
pip install -e ".[dev]"
  1. Make your changes and submit a pull request!

License

MIT

Acknowledgements

  • YAI for the inspiration
  • Google Gemini and OpenAI for their powerful AI APIs

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

toni_cli-0.1.20.tar.gz (13.5 kB view details)

Uploaded Source

Built Distribution

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

toni_cli-0.1.20-py3-none-any.whl (12.7 kB view details)

Uploaded Python 3

File details

Details for the file toni_cli-0.1.20.tar.gz.

File metadata

  • Download URL: toni_cli-0.1.20.tar.gz
  • Upload date:
  • Size: 13.5 kB
  • Tags: Source
  • Uploaded using Trusted Publishing? No
  • Uploaded via: twine/6.2.0 CPython/3.14.3

File hashes

Hashes for toni_cli-0.1.20.tar.gz
Algorithm Hash digest
SHA256 3b1ec3eb98a582dd41217be92882d28925aa91941e4e72fc5d043b4ad4a86f27
MD5 fda29a385699b2cc8d5ae5bb10d02d3d
BLAKE2b-256 476f4f5144a102f54a9dfb5b90509710eca0253fce07a35bd8bfc187ae61cf09

See more details on using hashes here.

File details

Details for the file toni_cli-0.1.20-py3-none-any.whl.

File metadata

  • Download URL: toni_cli-0.1.20-py3-none-any.whl
  • Upload date:
  • Size: 12.7 kB
  • Tags: Python 3
  • Uploaded using Trusted Publishing? No
  • Uploaded via: twine/6.2.0 CPython/3.14.3

File hashes

Hashes for toni_cli-0.1.20-py3-none-any.whl
Algorithm Hash digest
SHA256 c2cc9366955df9e6c66ccffa683a4fc06861809a32e2f4313a7280639fa308cf
MD5 4c642e2b5a8c34151c7e6ee25379fcb3
BLAKE2b-256 ef0db6a509f9bc88fa75721087cce80729ffd52f59532859d485faf7bab4a661

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