AI Agents · Lesson

Building Command-Line Agent Interfaces

argparse, click, and Typer for agent CLI argument handling.

Why Build a CLI for Your Agent?

A command-line interface (CLI) makes your agent accessible from a terminal, scriptable in pipelines, and easy to test without a web UI. Many production agents are deployed as CLI tools.

Python has three excellent libraries for building CLIs: argparse (standard library), Typer, and Click.

argparse: The Standard Library Option

argparse is built into Python — no installation required. Use ArgumentParser() to define your interface, add_argument() to declare parameters, and parse_args() to process them.

import argparse

def main():
    parser = argparse.ArgumentParser(
        description='AI Agent CLI — ask questions and get answers'
    )
    parser.add_argument(
        '--query',
        type=str,
        required=True,
        help='The question to ask the agent'
    )
    parser.add_argument(
        '--model',
        type=str,
        default='gpt-4o-mini',
        help='OpenAI model to use (default: gpt-4o-mini)'
    )
    args = parser.parse_args()

    print(f'Querying agent with: {args.query}')
    print(f'Using model: {args.model}')
    # result = run_agent(args.query, model=args.model)

if __name__ == '__main__':
    main()

All lessons in this course

← Back to AI Agents