code-q CLI

India-first SaaS AI coding agent for the terminal. OpenAI-compatible with intelligent file editing, shell automation, and MCP integrations. Built for developers in India (and beyond) with fast onboarding, local-friendly pricing, and secure authentication.

Features

• 🇮🇳 India‑first SaaS: Local-friendly onboarding, pricing, and support
• 🤖 Conversational AI: Natural language interface
• 📝 Smart File Operations: AI automatically uses tools to view, create, and edit files
• ⚡ Bash Integration: Execute shell commands through natural conversation
• 🔧 Automatic Tool Selection: AI intelligently chooses the right tools for your requests
• 🚀 Morph Fast Apply: Optional high-speed code editing at 4,500+ tokens/sec with 98% accuracy
• 🔌 MCP Tools: Extend capabilities with Model Context Protocol servers (Linear, GitHub, etc.)
• 💬 Interactive UI: Beautiful terminal interface built with Ink
• 🌍 Global Installation: Install and use anywhere with npm i -g code-q

Installation

Prerequisites

• Node.js 16+
• API key for your chosen OpenAI-compatible provider (e.g., X.AI Grok)
• (Optional, Recommended) Morph API key for Fast Apply editing

Primary install options

1. npx (no install):

npx @code-q/code-q@latest --no-tools --prompt "hello"

2. npm global:

npm install -g @code-q/code-q

3. Docker:

docker run --rm -it -v "$PWD:/work" -w /work ghcr.io/<org>/code-q code-q --no-tools -p "hello"

Local Development

git clone <repository>
cd code-q-cli
npm install
npm run build
npm link

Setup

1. Get an API key from your provider (e.g., X.AI)

2. Set up your API key (choose one method):

Method 1: Environment Variable

export MUZZIK_API_KEY=your_api_key_here   # GROK_API_KEY also supported

Method 2: .env File

cp .env.example .env
# Edit .env and add your API key

Method 3: Command Line Flag

code-q --api-key your_api_key_here

Method 4: User Settings File Create ~/.muzzik/user-settings.json (legacy ~/.grok/user-settings.json also supported):

{
  "apiKey": "your_api_key_here"
}

3. (Optional, Recommended) Get your Morph API key from Morph Dashboard

4. Set up your Morph API key for Fast Apply editing (choose one method):

Method 1: Environment Variable

export MORPH_API_KEY=your_morph_api_key_here

Method 2: .env File

# Add to your .env file
MORPH_API_KEY=your_morph_api_key_here

Custom Base URL (Optional)

By default, the CLI uses https://api.x.ai/v1. You can configure a custom endpoint if needed (choose one method):

Method 1: Environment Variable

export MUZZIK_BASE_URL=https://your-custom-endpoint.com/v1   # GROK_BASE_URL also supported

Method 2: Command Line Flag

code-q --api-key your_api_key_here --base-url https://your-custom-endpoint.com/v1

Method 3: User Settings File Add to ~/.muzzik/user-settings.json:

{
  "apiKey": "your_api_key_here",
  "baseURL": "https://your-custom-endpoint.com/v1"
}

Configuration Files

code-q uses two types of configuration files to manage settings:

User-Level Settings (~/.muzzik/user-settings.json)

This file stores global settings that apply across all projects. These settings rarely change and include:

• API Key: Your API key
• Base URL: Custom API endpoint (if needed)
• Default Model: Your preferred model (e.g., grok-4-latest)
• Available Models: List of models you can use

Example:

{
  "apiKey": "your_api_key_here",
  "baseURL": "https://api.x.ai/v1",
  "defaultModel": "grok-4-latest",
  "models": [
    "grok-4-latest",
    "grok-3-latest",
    "grok-3-fast",
    "grok-3-mini-fast"
  ]
}

Project-Level Settings (.muzzik/settings.json)

This file stores project-specific settings in your current working directory. It includes:

• Current Model: The model currently in use for this project
• MCP Servers: Model Context Protocol server configurations

Example:

{
  "model": "grok-3-fast",
  "mcpServers": {
    "linear": {
      "name": "linear",
      "transport": "stdio",
      "command": "npx",
      "args": ["@linear/mcp-server"]
    }
  }
}

How It Works

1. Global Defaults: User-level settings provide your default preferences
2. Project Override: Project-level settings override defaults for specific projects
3. Directory-Specific: When you change directories, project settings are loaded automatically
4. Fallback Logic: Project model → User default model → System default (grok-4-latest)

This means you can have different models for different projects while maintaining consistent global settings like your API key.

Using Other API Providers

Important: code-q uses OpenAI-compatible APIs. You can use any provider that implements the OpenAI chat completions standard. The CLI will try to infer the correct base URL from your API key if none is provided (e.g., sk- → OpenAI, or-v1- → OpenRouter). You can always override with --base-url.

Popular Providers:

• X.AI (Grok): https://api.x.ai/v1 (default)
• OpenAI: https://api.openai.com/v1
• OpenRouter: https://openrouter.ai/api/v1
• Groq: https://api.groq.com/openai/v1

Example with OpenRouter:

{
  "apiKey": "your_openrouter_key",
  "baseURL": "https://openrouter.ai/api/v1",
  "defaultModel": "anthropic/claude-3.5-sonnet",
  "models": [
    "anthropic/claude-3.5-sonnet",
    "openai/gpt-4o",
    "meta-llama/llama-3.1-70b-instruct"
  ]
}

Usage

Interactive Mode

Start the conversational AI assistant:

code-q

Or specify a working directory:

code-q -d /path/to/project

Headless Mode

Process a single prompt and exit (useful for scripting and automation):

code-q --prompt "show me the package.json file"
code-q -p "create a new file called example.js with a hello world function"
code-q --prompt "run npm test and show me the results" --directory /path/to/project
code-q --prompt "complex task" --max-tool-rounds 50  # Limit tool usage for faster execution

This mode is particularly useful for:

• CI/CD pipelines: Automate code analysis and file operations
• Scripting: Integrate AI assistance into shell scripts
• Terminal benchmarks: Perfect for tools like Terminal Bench that need non-interactive execution
• Batch processing: Process multiple prompts programmatically

Tool Execution Control

By default, code-q allows up to 400 tool execution rounds to handle complex multi-step tasks. You can control this behavior:

# Limit tool rounds for faster execution on simple tasks
code-q --max-tool-rounds 10 --prompt "show me the current directory"

# Increase limit for very complex tasks (use with caution)
code-q --max-tool-rounds 1000 --prompt "comprehensive code refactoring"

# Works with all modes
code-q --max-tool-rounds 20  # Interactive mode
code-q git commit-and-push --max-tool-rounds 30  # Git commands

Use Cases:

• Fast responses: Lower limits (10-50) for simple queries
• Complex automation: Higher limits (500+) for comprehensive tasks
• Resource control: Prevent runaway executions in automated environments

Model Selection

You can specify which AI model to use with the --model parameter (supports GROK_MODEL environment variable):

Method 1: Command Line Flag

# Use Grok models
code-q --model grok-4-latest
code-q --model grok-3-latest
code-q --model grok-3-fast

# Use other models (with appropriate API endpoint)
code-q --model gemini-2.5-pro --base-url https://api-endpoint.com/v1
code-q --model claude-sonnet-4-20250514 --base-url https://api-endpoint.com/v1

Method 2: Environment Variable

export GROK_MODEL=grok-4-latest
code-q

Method 3: User Settings File Add to ~/.muzzik/user-settings.json:

{
  "apiKey": "your_api_key_here",
  "defaultModel": "grok-4-latest"
}

Model Priority: --model flag > GROK_MODEL environment variable > user default model > system default (grok-4-latest)

Command Line Options

code-q [options]

Options:
  -V, --version          output the version number
  -d, --directory <dir>  set working directory
  -k, --api-key <key>    code-q API key (set MUZZIK_API_KEY; GROK_API_KEY supported)
  -u, --base-url <url>   API base URL (set MUZZIK_BASE_URL; GROK_BASE_URL supported)
  -m, --model <model>    AI model to use (supports GROK_MODEL env var)
  -p, --prompt <prompt>  process a single prompt and exit (headless mode)
  --max-tool-rounds <rounds>  maximum number of tool execution rounds (default: 400)
  -h, --help             display help for command

Custom Instructions

You can provide custom instructions by creating .muzzik/MUZZIK.md (preferred) or legacy .grok/GROK.md in your project directory:

mkdir .muzzik

Create .muzzik/MUZZIK.md with your custom instructions:

# Custom Instructions for code-q CLI

Always use TypeScript for any new code files.
When creating React components, use functional components with hooks.
Prefer const assertions and explicit typing over inference where it improves clarity.
Always add JSDoc comments for public functions and interfaces.
Follow the existing code style and patterns in this project.

code-q will automatically load and follow these instructions when working in your project directory. The custom instructions are added to the system prompt and take priority over default behavior.

Morph Fast Apply (Optional)

code-q supports Morph's Fast Apply model for high-speed code editing at 4,500+ tokens/sec with 98% accuracy. This is an optional feature that provides lightning-fast file editing capabilities.

Setup: Configure your Morph API key following the setup instructions above.

How It Works

When MORPH_API_KEY is configured:

• edit_file tool becomes available alongside the standard str_replace_editor
• Optimized for complex edits: Use for multi-line changes, refactoring, and large modifications
• Intelligent editing: Uses abbreviated edit format with // ... existing code ... comments
• Fallback support: Standard tools remain available if Morph is unavailable

When to use each tool:

• edit_file (Morph): Complex edits, refactoring, multi-line changes
• str_replace_editor: Simple text replacements, single-line edits

Example Usage

With Morph Fast Apply configured, you can request complex code changes:

code-q --prompt "refactor this function to use async/await and add error handling"
code-q -p "convert this class to TypeScript and add proper type annotations"

The AI will automatically choose between edit_file (Morph) for complex changes or str_replace_editor for simple replacements.

MCP Tools

code-q supports MCP (Model Context Protocol) servers, allowing you to extend the AI assistant with additional tools and capabilities.

Adding MCP Tools

Add a custom MCP server:

# Add an stdio-based MCP server
code-q mcp add my-server --transport stdio --command "node" --args server.js

# Add an HTTP-based MCP server
code-q mcp add my-server --transport http --url "http://localhost:3000"

# Add with environment variables
code-q mcp add my-server --transport stdio --command "python" --args "-m" "my_mcp_server" --env "API_KEY=your_key"

Add from JSON configuration:

code-q mcp add-json my-server '{"command": "node", "args": ["server.js"], "env": {"API_KEY": "your_key"}}'

Linear Integration Example

To add Linear MCP tools for project management:

# Add Linear MCP server
code-q mcp add linear --transport sse --url "https://mcp.linear.app/sse"

This enables Linear tools like:

• Create and manage Linear issues
• Search and filter issues
• Update issue status and assignees
• Access team and project information

Managing MCP Servers

# List all configured servers
code-q mcp list

# Test server connection
code-q mcp test server-name

# Remove a server
code-q mcp remove server-name

Available Transport Types

• stdio: Run MCP server as a subprocess (most common)
• http: Connect to HTTP-based MCP server
• sse: Connect via Server-Sent Events

Development

# Install dependencies
npm install

# Development mode
npm run dev

# Build project
npm run build

# Run linter
npm run lint

# Type check
npm run typecheck

Architecture

• Agent: Core command processing and execution logic
• Tools: Text editor and bash tool implementations
• UI: Ink-based terminal interface components
• Types: TypeScript definitions for the entire system

License

MIT

Authentication (Supabase)

This CLI requires a Supabase-authenticated user. Configure environment variables (see env.example). If you sign in on code-q.in, device login flows and email password logins are supported in-terminal.

• SUPABASE_URL
• SUPABASE_ANON_KEY

When you run code-q, if you are not authenticated, you will be prompted to log in with your email and password directly in the terminal. The session is securely stored in ~/.muzzik/user-settings.json and refreshed automatically.

You can verify by starting the CLI; if already logged in, no prompt will appear.