AI Agents · Lesson

Building Command-Line Agent Interfaces

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

Building Command-Line Agent Interfaces is a free AI Agents lesson on CoddyKit — lesson 1 of 4. You can read the complete lesson below for free — then practise it hands-on in the browser with a built-in code editor and a 24/7 AI tutor. It is part of the AI Agents learning path, one of 4 lessons in the course, and your progress syncs across the web and the CoddyKit app.

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(argv=None):
    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(argv)

    print(f'Querying agent with: {args.query}')
    print(f'Using model: {args.model}')

if __name__ == '__main__':
    main(['--query', 'What is the weather today?'])

Running argparse CLI and Auto-Generated Help

argparse automatically generates a --help message from your argument definitions. Run python agent_cli.py --help to see it. Required arguments that are missing produce helpful error messages automatically.

# How users invoke the CLI:
# python agent_cli.py --query 'What is the weather in Paris?'
# python agent_cli.py --query 'Summarize this' --model gpt-4o
# python agent_cli.py --help

# Auto-generated help output:
# usage: agent_cli.py [-h] --query QUERY [--model MODEL]
#
# AI Agent CLI -- ask questions and get answers
#
# options:
#   -h, --help     show this help message and exit
#   --query QUERY  The question to ask the agent
#   --model MODEL  OpenAI model to use (default: gpt-4o-mini)

print('argparse generates help text automatically from your definitions')

Typer: Modern CLI with Type Hints

Typer builds CLIs from Python type hints — less boilerplate than argparse. Install with pip install typer. Function parameters become CLI arguments automatically.

# pip install typer
import typer

app = typer.Typer(help='AI Agent CLI')

@app.command()
def ask(
    query: str = typer.Option(..., '--query', '-q', help='Question for the agent'),
    model: str = typer.Option('gpt-4o-mini', '--model', '-m', help='Model to use'),
    verbose: bool = typer.Option(False, '--verbose', '-v', help='Show reasoning steps')
):
    typer.echo(f'Query: {query}')
    typer.echo(f'Model: {model}')
    if verbose:
        typer.echo('Verbose mode enabled')
    # result = run_agent(query, model=model, verbose=verbose)

if __name__ == '__main__':
    app()

Click: Decorator-Based CLI Framework

Click uses decorators to define CLI commands and options. Install with pip install click. It offers rich features like command groups, prompts, and progress bars.

# pip install click
import click

@click.command()
@click.option('--query', '-q', required=True, help='Question for the agent')
@click.option('--model', '-m', default='gpt-4o-mini', help='LLM model to use')
@click.option('--output', '-o', type=click.Path(), help='Save output to file')
def ask(query: str, model: str, output: str):
    click.echo(f'Sending: {query}')
    # result = run_agent(query, model=model)
    # click.echo(result['answer'])

    if output:
        with open(output, 'w') as f:
            f.write('result["answer"]')
        click.echo(f'Saved to {output}')

if __name__ == '__main__':
    ask()

Adding Subcommands

As your agent grows, organize functionality into subcommands like agent ask, agent search, and agent history. Both Click and Typer support subcommand groups natively.

import typer

app = typer.Typer(help='AI Research Agent')

@app.command()
def ask(query: str = typer.Argument(..., help='Question to ask')):
    'Ask the agent a question'
    typer.echo(f'Asking: {query}')

@app.command()
def search(topic: str = typer.Argument(..., help='Topic to research')):
    'Search and summarize a topic'
    typer.echo(f'Researching: {topic}')

@app.command()
def history(limit: int = typer.Option(10, help='Number of past queries to show')):
    'Show recent query history'
    typer.echo(f'Showing last {limit} queries')

if __name__ == '__main__':
    app()

# Usage: python agent.py ask 'What is AI?'
#        python agent.py search 'Python async'
#        python agent.py history --limit 5

Reading from stdin for Piped Input

A CLI agent that reads from stdin can be used in Unix pipelines. Use sys.stdin or Click's stdin argument type to accept piped content.

import sys
import click

@click.command()
@click.argument('input', default='-', type=click.File('r'))
@click.option('--task', default='summarize', help='Task: summarize, translate, or analyze')
def process(input, task: str):
    text = input.read().strip()
    if not text:
        click.echo('Error: no input provided', err=True)
        raise SystemExit(1)

    click.echo(f'Task: {task}')
    click.echo(f'Input length: {len(text)} chars')
    # result = agent.run(task=task, content=text)
    # click.echo(result)

# Usage:
# echo 'Hello world' | python agent_cli.py --task translate
# cat article.txt | python agent_cli.py --task summarize
if __name__ == '__main__':
    process()

Progress Indicators for Long Tasks

Agent tasks can take several seconds. Show a spinner or progress message so users know the agent is working. Typer has built-in progress support via the rich library.

import typer
from time import sleep

app = typer.Typer()

@app.command()
def research(topic: str = typer.Argument(...)):
    typer.echo(f'Researching: {topic}')

    with typer.progressbar(range(5), label='Gathering sources') as progress:
        for i in progress:
            sleep(0.5)  # simulate work

    typer.echo('Done!')
    typer.echo('Result: [mocked research result]')

# Or with a spinner from rich:
# from rich.console import Console
# console = Console()
# with console.status('Thinking...'):
#     result = agent.run(topic)
# console.print(result)

if __name__ == '__main__':
    app()

Output Formatting: JSON vs. Plain Text

Allow users to choose between human-readable and machine-readable output formats. A --json flag is useful for piping agent output into other tools.

import json
import typer

app = typer.Typer()

@app.command()
def ask(
    query: str = typer.Argument(...),
    as_json: bool = typer.Option(False, '--json', help='Output as JSON')
):
    result = {
        'query': query,
        'answer': 'Paris is the capital of France.',
        'confidence': 0.98,
        'sources': ['https://wikipedia.org/France']
    }

    if as_json:
        typer.echo(json.dumps(result, indent=2))
    else:
        typer.echo(f'Answer: {result["answer"]}')
        typer.echo(f'Sources: {', '.join(result["sources"])}')

if __name__ == '__main__':
    app()

Error Handling in CLI Agents

Exit with a non-zero code on errors so calling scripts can detect failures. Use typer.echo(..., err=True) or click.echo(..., err=True) to write error messages to stderr.

import sys
import typer

app = typer.Typer()

@app.command()
def ask(query: str = typer.Argument(...)):
    try:
        # result = agent.run(query)
        result = {'status': 'ok', 'answer': 'Result here'}

        if result['status'] != 'ok':
            typer.echo(f'Agent error: {result.get("error")}', err=True)
            raise typer.Exit(code=1)

        typer.echo(result['answer'])

    except Exception as e:
        typer.echo(f'Unexpected error: {e}', err=True)
        raise typer.Exit(code=2)

# Exit codes: 0 = success, 1 = agent error, 2 = unexpected error
# These allow shell scripts to handle failures:
# python agent.py 'query' || echo 'Agent failed'
if __name__ == '__main__':
    app()

Making Your Agent an Installable CLI Tool

Use a pyproject.toml entry point to make your agent available as a system command. After pip install -e ., users can run myagent ask 'question' directly from any directory.

# pyproject.toml
# [project]
# name = 'myagent'
# version = '0.1.0'
# dependencies = ['typer', 'openai', 'httpx']
#
# [project.scripts]
# myagent = 'myagent.cli:app'

# After pip install -e .:
# myagent ask 'What is AI?'
# myagent search 'Python tutorials'
# myagent --help

# This is how production CLI agents like 'gh', 'poetry', and 'ruff' work
print('Entry points turn your Python module into a system CLI command')

Knowledge Check: CLI Agent Interfaces

Test your understanding of building CLI interfaces for agents.

Recap: Building CLI Agent Interfaces

You can now build professional CLI interfaces for your agents:

Use argparse for zero-dependency CLIs (standard library)
Use typer for clean, type-hint-driven CLIs
Use click for feature-rich decorator-based CLIs
Organize large agents with subcommands
Support stdin for pipeline integration
Use --json flags for machine-readable output
Exit with non-zero codes on errors for shell script compatibility

Frequently asked questions

Is the “Building Command-Line Agent Interfaces” lesson free?

Yes — the full text of “Building Command-Line Agent Interfaces” is free to read here on the web, and the AI Agents course includes 4 lessons in total. To practise it interactively (a built-in code editor and a 24/7 AI tutor) and unlock the rest of the AI Agents course, upgrade to CoddyKit PRO.

What will I learn in “Building Command-Line Agent Interfaces”?

argparse, click, and Typer for agent CLI argument handling. You practise AI Agents with hands-on code you run directly in the browser, and a 24/7 AI tutor answers your questions as you work through the lesson.

Do I need any experience to start AI Agents?

No prior experience is required. AI Agents on CoddyKit is structured for beginners through advanced learners; this is — lesson 1 of 4, so you can start here or from the beginning and move at your own pace.

How long does the “Building Command-Line Agent Interfaces” lesson take?

Most CoddyKit lessons take about 5–10 minutes. Each one is bite-sized and interactive, so you make steady progress and pick up exactly where you left off across the web and the app.

Can I write and run code in this AI Agents lesson?

Yes. Every AI Agents lesson includes a built-in code editor, so you write and run real code right in your browser and get instant AI feedback — no local setup required.

All lessons in this course

← Back to AI Agents