Installing and Using the OpenAI Codex CLI

Codex CLI is OpenAI's terminal coding agent. It runs locally, supports MCP, and ships a codex cloud mode for background tasks. Let's install it and compare it honestly to Claude Code.

45 min · Reviewed 2026

OpenAI's Answer to Claude Code

Codex CLI is OpenAI's lightweight coding agent. It runs in your terminal, inspects your repo, edits files, and executes shell commands. It ships on macOS, Windows, and Linux, and its premium models are included with ChatGPT Plus, Pro, and Business plans.

Install and first run

# Install via npm (macOS, Linux, Windows)
npm install -g @openai/codex

# Or via Homebrew on macOS
brew install openai/codex/codex

# Launch in your project directory
cd my-project
codex

# Type /model to pick a model
# Default in 2026: gpt-5.5 for complex work, gpt-5.3-codex for fast tasksAs of April 2026, gpt-5.5 is the recommended model for complex work; gpt-5.3-codex is tuned for fast edits.

Two modes you will use

Mode	Command	What it's for
Interactive TUI	codex	Conversational coding, the default experience
Exec	codex exec "<prompt>"	Scripted, non-interactive runs — great for CI
Cloud	codex cloud	Offload long tasks to OpenAI's infra, review locally

A realistic exec workflow

# Automate a recurring task with `codex exec`
codex exec "Find all task list comments in src/, group them by file, \
  and write a markdown summary to TODO_REPORT.md"

# Run in CI after PR checks pass
codex exec --model gpt-5.5 "Review the diff against main and \
  flag any missing test coverage for changed functions."Exec mode turns Codex into a scriptable tool you can chain with Make, GitHub Actions, or cron.

codex cloud: the superpower

The codex cloud command launches tasks on OpenAI infrastructure, which can run long without tying up your laptop. You can hand off a refactor at 5pm and pull the PR in the morning. Running codex cloud with no arguments opens an interactive picker of active and finished tasks.

Image input

You can paste screenshots or design specs directly into the Codex composer or pass image files on the command line. This is ideal for turning a mockup into real components or diagnosing a UI bug from a screen recording.

Claude Code vs. Codex CLI: the honest comparison

Dimension	Claude Code	Codex CLI
Model	Claude family	GPT family
Project memory	CLAUDE.md	AGENTS.md (similar concept)
Parallel agents	Up to 10 subagents	Single-session + cloud offload
Extensibility	Skills, hooks, 25+ lifecycle events	MCP, exec scripts, cloud tasks
Pricing entry	Claude Pro $20/mo	Included in ChatGPT Plus/Pro

The best agent is the one whose workflow matches your brain.
— A polyglot engineer

The big idea: Codex CLI and Claude Code are two terminal agents racing to the same destination. Install both, try them on real tasks for a week each, and let your wrists decide the winner.

End-of-lesson check

15 questions · take it digitally for instant feedback at tendril.neural-forge.io/learn/quiz/end-coding-installing-codex-cli-creators

What is the core idea behind "Installing and Using the OpenAI Codex CLI"?
1. Codex CLI is OpenAI's terminal coding agent. It runs locally, supports MCP, and ships a codex cloud mode for background tasks. Let's install it and compare it honestly to Claude Code.
2. Reliably find subtle security or concurrency bugs.
3. deployment AI
4. Use AI to translate regex into plain language and back again.
Which term best describes a foundational idea in "Installing and Using the OpenAI Codex CLI"?
1. exec mode
2. Codex CLI
3. codex cloud
4. MCP
A learner studying Installing and Using the OpenAI Codex CLI would need to understand which concept?
1. Codex CLI
2. codex cloud
3. exec mode
4. MCP
Which of these is directly relevant to Installing and Using the OpenAI Codex CLI?
1. Codex CLI
2. exec mode
3. MCP
4. codex cloud
What is the key insight about "MCP is first-class here too" in the context of Installing and Using the OpenAI Codex CLI?
1. Codex CLI supports Model Context Protocol. Add MCP servers for your database, docs, or issue tracker and Codex can query…
2. Reliably find subtle security or concurrency bugs.
3. deployment AI
4. Use AI to translate regex into plain language and back again.
What is the key insight about "Cost awareness" in the context of Installing and Using the OpenAI Codex CLI?
1. Reliably find subtle security or concurrency bugs.
2. Cloud tasks run on premium models and burn tokens at a faster rate than local work.
3. deployment AI
4. Use AI to translate regex into plain language and back again.
Which statement accurately describes an aspect of Installing and Using the OpenAI Codex CLI?
1. Reliably find subtle security or concurrency bugs.
2. deployment AI
3. Codex CLI is OpenAI's lightweight coding agent. It runs in your terminal, inspects your repo, edits files, and executes shell commands.
4. Use AI to translate regex into plain language and back again.
What does working with Installing and Using the OpenAI Codex CLI typically involve?
1. Reliably find subtle security or concurrency bugs.
2. deployment AI
3. Use AI to translate regex into plain language and back again.
4. The codex cloud command launches tasks on OpenAI infrastructure, which can run long without tying up your laptop.
Which of the following is true about Installing and Using the OpenAI Codex CLI?
1. You can paste screenshots or design specs directly into the Codex composer or pass image files on the command line.
2. Reliably find subtle security or concurrency bugs.
3. deployment AI
4. Use AI to translate regex into plain language and back again.
Which best describes the scope of "Installing and Using the OpenAI Codex CLI"?
1. It is unrelated to ai-coding workflows
2. It focuses on Codex CLI is OpenAI's terminal coding agent. It runs locally, supports MCP, and ships a codex cloud
3. It applies only to the opposite beginner tier
4. It was deprecated in 2024 and no longer relevant
Which section heading best belongs in a lesson about Installing and Using the OpenAI Codex CLI?
1. Reliably find subtle security or concurrency bugs.
2. deployment AI
3. Install and first run
4. Use AI to translate regex into plain language and back again.
Which section heading best belongs in a lesson about Installing and Using the OpenAI Codex CLI?
1. Reliably find subtle security or concurrency bugs.
2. deployment AI
3. Use AI to translate regex into plain language and back again.
4. Two modes you will use
Which section heading best belongs in a lesson about Installing and Using the OpenAI Codex CLI?
1. A realistic exec workflow
2. Reliably find subtle security or concurrency bugs.
3. deployment AI
4. Use AI to translate regex into plain language and back again.
Which section heading best belongs in a lesson about Installing and Using the OpenAI Codex CLI?
1. Reliably find subtle security or concurrency bugs.
2. codex cloud: the superpower
3. deployment AI
4. Use AI to translate regex into plain language and back again.
Which section heading best belongs in a lesson about Installing and Using the OpenAI Codex CLI?
1. Reliably find subtle security or concurrency bugs.
2. deployment AI
3. Image input
4. Use AI to translate regex into plain language and back again.

← Back to interactive lesson

Tendril · Creators · AI-Assisted Coding

Installing and Using the OpenAI Codex CLI

Codex CLI is OpenAI's terminal coding agent. It runs locally, supports MCP, and ships a codex cloud mode for background tasks. Let's install it and compare it honestly to Claude Code.

45 min · Reviewed 2026

OpenAI's Answer to Claude Code

Install and first run

# Install via npm (macOS, Linux, Windows)
npm install -g @openai/codex

# Or via Homebrew on macOS
brew install openai/codex/codex

# Launch in your project directory
cd my-project
codex

# Type /model to pick a model
# Default in 2026: gpt-5.5 for complex work, gpt-5.3-codex for fast tasksAs of April 2026, gpt-5.5 is the recommended model for complex work; gpt-5.3-codex is tuned for fast edits.

Two modes you will use

Mode	Command	What it's for
Interactive TUI	codex	Conversational coding, the default experience
Exec	codex exec "<prompt>"	Scripted, non-interactive runs — great for CI
Cloud	codex cloud	Offload long tasks to OpenAI's infra, review locally

A realistic exec workflow

# Automate a recurring task with `codex exec`
codex exec "Find all task list comments in src/, group them by file, \
  and write a markdown summary to TODO_REPORT.md"

# Run in CI after PR checks pass
codex exec --model gpt-5.5 "Review the diff against main and \
  flag any missing test coverage for changed functions."Exec mode turns Codex into a scriptable tool you can chain with Make, GitHub Actions, or cron.

codex cloud: the superpower

Image input

Claude Code vs. Codex CLI: the honest comparison

Dimension	Claude Code	Codex CLI
Model	Claude family	GPT family
Project memory	CLAUDE.md	AGENTS.md (similar concept)
Parallel agents	Up to 10 subagents	Single-session + cloud offload
Extensibility	Skills, hooks, 25+ lifecycle events	MCP, exec scripts, cloud tasks
Pricing entry	Claude Pro $20/mo	Included in ChatGPT Plus/Pro

The best agent is the one whose workflow matches your brain.
— A polyglot engineer

The big idea: Codex CLI and Claude Code are two terminal agents racing to the same destination. Install both, try them on real tasks for a week each, and let your wrists decide the winner.

End-of-lesson check

15 questions · take it digitally for instant feedback at tendril.neural-forge.io/learn/quiz/end-coding-installing-codex-cli-creators

What is the core idea behind "Installing and Using the OpenAI Codex CLI"?
1. Codex CLI is OpenAI's terminal coding agent. It runs locally, supports MCP, and ships a codex cloud mode for background tasks. Let's install it and compare it honestly to Claude Code.
2. Reliably find subtle security or concurrency bugs.
3. deployment AI
4. Use AI to translate regex into plain language and back again.
Which term best describes a foundational idea in "Installing and Using the OpenAI Codex CLI"?
1. exec mode
2. Codex CLI
3. codex cloud
4. MCP
A learner studying Installing and Using the OpenAI Codex CLI would need to understand which concept?
1. Codex CLI
2. codex cloud
3. exec mode
4. MCP
Which of these is directly relevant to Installing and Using the OpenAI Codex CLI?
1. Codex CLI
2. exec mode
3. MCP
4. codex cloud
What is the key insight about "MCP is first-class here too" in the context of Installing and Using the OpenAI Codex CLI?
1. Codex CLI supports Model Context Protocol. Add MCP servers for your database, docs, or issue tracker and Codex can query…
2. Reliably find subtle security or concurrency bugs.
3. deployment AI
4. Use AI to translate regex into plain language and back again.
What is the key insight about "Cost awareness" in the context of Installing and Using the OpenAI Codex CLI?
1. Reliably find subtle security or concurrency bugs.
2. Cloud tasks run on premium models and burn tokens at a faster rate than local work.
3. deployment AI
4. Use AI to translate regex into plain language and back again.
Which statement accurately describes an aspect of Installing and Using the OpenAI Codex CLI?
1. Reliably find subtle security or concurrency bugs.
2. deployment AI
3. Codex CLI is OpenAI's lightweight coding agent. It runs in your terminal, inspects your repo, edits files, and executes shell commands.
4. Use AI to translate regex into plain language and back again.
What does working with Installing and Using the OpenAI Codex CLI typically involve?
1. Reliably find subtle security or concurrency bugs.
2. deployment AI
3. Use AI to translate regex into plain language and back again.
4. The codex cloud command launches tasks on OpenAI infrastructure, which can run long without tying up your laptop.
Which of the following is true about Installing and Using the OpenAI Codex CLI?
1. You can paste screenshots or design specs directly into the Codex composer or pass image files on the command line.
2. Reliably find subtle security or concurrency bugs.
3. deployment AI
4. Use AI to translate regex into plain language and back again.
Which best describes the scope of "Installing and Using the OpenAI Codex CLI"?
1. It is unrelated to ai-coding workflows
2. It focuses on Codex CLI is OpenAI's terminal coding agent. It runs locally, supports MCP, and ships a codex cloud
3. It applies only to the opposite beginner tier
4. It was deprecated in 2024 and no longer relevant
Which section heading best belongs in a lesson about Installing and Using the OpenAI Codex CLI?
1. Reliably find subtle security or concurrency bugs.
2. deployment AI
3. Install and first run
4. Use AI to translate regex into plain language and back again.
Which section heading best belongs in a lesson about Installing and Using the OpenAI Codex CLI?
1. Reliably find subtle security or concurrency bugs.
2. deployment AI
3. Use AI to translate regex into plain language and back again.
4. Two modes you will use
Which section heading best belongs in a lesson about Installing and Using the OpenAI Codex CLI?
1. A realistic exec workflow
2. Reliably find subtle security or concurrency bugs.
3. deployment AI
4. Use AI to translate regex into plain language and back again.
Which section heading best belongs in a lesson about Installing and Using the OpenAI Codex CLI?
1. Reliably find subtle security or concurrency bugs.
2. codex cloud: the superpower
3. deployment AI
4. Use AI to translate regex into plain language and back again.
Which section heading best belongs in a lesson about Installing and Using the OpenAI Codex CLI?
1. Reliably find subtle security or concurrency bugs.
2. deployment AI
3. Image input
4. Use AI to translate regex into plain language and back again.

← Back to interactive lesson