Language : 🇺🇸 us | 🇨🇳 zh | 🇯🇵 ja

AI-Terminal

AI-Terminal is an advanced AI-powered CLI that enhances terminal workflows through AI-driven automation and optimization. It efficiently manages tasks such as file management, data processing, and system diagnostics.

Key Features

• Contextual Assistance: Learns from user commands to provide syntax suggestions.
• Automated Tasks: Recognizes repetitive task patterns and creates shortcuts.
• Intelligent Search: Conducts searches within files, directories, and specific file types.
• Error Correction: Corrects incorrect commands and suggests alternatives.
• Custom Integrations: Supports integration with various tools and services via plugins or APIs.

Getting Started

Prerequisites

• Go version v1.22.0 or higher.

Installation

Install using Homebrew:

brew install coding-hui/tap/ai-terminal

Or, download it:

• Packages are available in Debian and RPM formats
• Binaries are available for Linux, macOS, and Windows

Or, build from source (requires Go 1.22+):

make build

Then initialize configuration:

ai configure

Shell Completions

All packages and archives come with pre-generated completion files for Bash, ZSH, Fish, and PowerShell.

If you built it from source, you can generate them with:

ai completion bash -h
ai completion zsh -h
ai completion fish -h
ai completion powershell -h

If you use a package (like Homebrew, Debs, etc), the completions should be set up automatically, given your shell is configured properly.

Usage

Here are some examples of how to use AI-Terminal, grouped by functionality:

Chat

• Initiate a Chat:

  ai ask "What is the best way to manage Docker containers?"

• Use a Prompt File:

  ai ask --file /path/to/prompt_file.txt

• Pipe Input:

  cat some_script.go | ai ask generate unit tests

Code Generation

• Interactive Code Generation:

  ai coder

  Starts interactive mode for generating code based on prompts.

• CLI-based Code Generation:

  ai ctx load /path/to/context_file
  ai coder -c session_id -p "improve comments and add unit tests"

  Load context files and specify session ID for batch processing. Supports:

  • Code improvement
  • Comment enhancement
  • Unit test generation
  • Code refactoring

• Generate Code with Context:

  ai ctx load /path/to/context_file
  ai coder "implement feature xxx"

  Load context files first to provide additional information for code generation.

Code Review

• Review Code Changes:

  ai review --exclude-list "*.md,*.txt"

Commit Messages

• Generate a Commit Message:

  ai commit --diff-unified 3 --lang en

Contributing

We welcome contributions! Please see our Contribution Guidelines for more details.

Changelog

Check out the CHANGELOG.md for detailed updates and changes to the project.

License

Copyright 2024 coding-hui. Licensed under the MIT License.