Lightweight AI CLI Tool

Vision

Ch is a Lightweight, fast, and powerful CLI tool for terminal-based AI interactions with full user control. It provides direct terminal access to powerful AI models with minimal overhead, transparent operations, and explicit user control. It integrates seamlessly into developer environments, minimizing context switching and empowering users to leverage AI's full potential through explicit control and flexible, user-driven interactions without automated decisions or hidden costs.

Installation

curl -fsSL https://raw.githubusercontent.com/MehmetMHY/ch/main/install.sh | bash

Demo

Features

Ch brings powerful AI capabilities directly to your terminal:

High Performance
10x faster startup time and noticeably faster than its predecessor Cha, built with GoLang instead of Python for speed and efficiency
Multi-Platform
Interactive & Direct
Chat interactively or run single queries. Your choice.
Unix Piping
Pipe any command output or file content directly to Ch. Automatically suppresses colors and UI elements for seamless shell pipeline integration
Shell Session Recording
Record terminal sessions as context. Capture CLI tool outputs from Claude Code, Gemini CLI, Amazon Q CLI, Codex CLI, and other developer tools
Smart File Handling
Load PDFs, Word docs, spreadsheets, images (with OCR), and directories
Web Integration
Scrape URLs, search the web using Brave Search API, and analyze YouTube content seamlessly
Code Export & Editing
Extract and save markdown code blocks with proper extensions. Interactive export with fzf selection and text editor integration for composing complex prompts
Dynamic Switching
Change models and platforms mid-conversation without losing context
Clipboard Integration
Copy AI responses to clipboard with cross-platform support
Token Counting
Estimate token usage for files with model-aware tokenization
Code Dump
Package entire directories for AI analysis. Automatically compile text and document files for comprehensive context

Documentation

Collapse the project's rendered README below.

Loading documentation...