Codex CLI

Codex CLI is OpenAI's open-source coding agent that runs entirely in your terminal. You point it at a repository, describe a task in plain language, and it reads files, edits them on disk, and runs shell commands to get the job done — all inside an OS-level sandbox that defaults to no network access and write permissions scoped to your workspace. It is written in Rust and ships as a binary installable via npm, Homebrew, or a one-line shell installer.

It is aimed at developers who live in the terminal and want an agent backed by OpenAI's frontier models without leaving the shell. You can authenticate with a ChatGPT plan (Plus, Pro, Business, Edu, or Enterprise) or an OPENAI_API_KEY, and the same binary works on macOS, Linux, and Windows (natively or via WSL).

Highlights

• Two-layer security model — sandbox modes (read-only, workspace-write, danger-full-access, via --sandbox) control what the agent can technically do; approval policies (on-request, untrusted, never) control when it must stop and ask before acting.
• Sandboxed by default — the workspace-write mode limits writes to the active workspace and blocks outbound network, so edits stay local until you explicitly widen the boundary.
• Model switching — use /model to choose among the models available to your account and adjust reasoning effort per task.
• MCP support — connect external tools through STDIO or Streamable HTTP servers configured in config.toml.
• Non-interactive codex exec — run Codex headlessly in scripts and CI, piping the final result to stdout.
• Session resume and image input — pick up past transcripts with codex resume, and attach screenshots or design specs as context.

In an AI-assisted workflow

Codex CLI fits where you already run Git and your build. A typical loop is to start it in a repo with the default workspace-write sandbox mode and on-request approval policy, let it draft edits, and approve anything that reaches outside the workspace or touches the network. It reads AGENTS.md files for project-specific context, so you can encode conventions and commands once and have them apply on every run. Repeatable procedures can move into Codex skills instead of growing the always-on instruction file.

npm install -g @openai/codex
cd your-project
codex "Add a retry with backoff to the API client and a test for it"

Good to know

Codex CLI is free and open source under the Apache-2.0 license, available on macOS and Linux natively and on Windows (natively via PowerShell or under WSL2). Model usage is not free: you either consume your ChatGPT plan's included Codex allowance or pay per token with an API key. The danger-full-access sandbox mode removes network and filesystem guardrails — use it only on repositories and tasks you fully trust.