term-assist 0.3.0

An AI assistant for your terminal.

term-assist

project / repo / mailing list / issues

ℹ️ Note
The canonical project locations are linked above. Other locations are mirrors.

An AI assistant for your terminal.

Features

• Works with Anthropic and OpenAI models
• Configurable parameters: change models, system prompt, response length, and other parameters
• Automatic environment detection: automatically detects your system and shell environment for accurate responses

Installation

1. Install pipx

2. Install term-assist using pipx:

   pipx install term-assist
   

3. In your terminal, configure your API keys depending on which model(s) you want to use.

   • Anthropic instructions
   • OpenAI instructions

Usage

usage: ta [-h] prompt [prompt ...]

term-assist: an AI assistant for your terminal.

positional arguments:
  prompt      prompt for the AI model

options:
  -h, --help  show this help message and exit

Examples

> ta unzip a tgz archive

> ta how to exit vim

Configuration

The configuration file is ~/.config/term-assist/config.json and will be created on first run and initialized with default configuration parameters if it does not already exist.

See ~/.config/term-assist/config_default.json for the default configuration.

model

The AI model to use.

This parameter should be set in the format BRAND:MODEL. For example, to use OpenAI's GPT-4o model, set this parameter to openai:gpt-4o.

See ~/.config/term-assist/models.json for available models.

max_tokens

The maximum number of tokens that will be generated for output.

temperature

The amount of randomness injected into the response. Ranges from 0.0 to 1.0.

system_prompt

The system prompt that is given to the model.

This prompt must contain the format strings {system} and {shell}, which the program will replace with information it gathers from your system.