Lightweight coding agent that runs in your terminal
npm i -g @openai/codex
Table of Contents
- Experimental Technology Disclaimer
- Quickstart
- Why Codex?
- Security Model & Permissions
- System Requirements
- CLI Reference
- Memory & Project Docs
- Non‑interactive / CI mode
- Recipes
- Installation
- Configuration
- FAQ
- Funding Opportunity
- Contributing
- Security & Responsible AI
- License
- Zero Data Retention (ZDR) Organization Limitation
Codex CLI is an experimental project under active development. It is not yet stable, may contain bugs, incomplete features, or undergo breaking changes. We’re building it in the open with the community and welcome:
- Bug reports
- Feature requests
- Pull requests
- Good vibes
Help us improve by filing issues or submitting PRs (see the section below for how to contribute)!
Install globally:
npm install -g @openai/codexNext, set your OpenAI API key as an environment variable:
export OPENAI_API_KEY="your-api-key-here"Note: This command sets the key only for your current terminal session. To make it permanent, add the
exportline to your shell's configuration file (e.g.,~/.zshrc).Tip: You can also place your API key into a
.envfile at the root of your project:OPENAI_API_KEY=your-api-key-hereThe CLI will automatically load variables from
.env(viadotenv/config).
Run interactively:
codexOr, run with a prompt as input (and optionally in Full Auto mode):
codex "explain this codebase to me"codex --approval-mode full-auto "create the fanciest todo-list app"That’s it – Codex will scaffold a file, run it inside a sandbox, install any missing dependencies, and show you the live result. Approve the changes and they’ll be committed to your working directory.
Codex CLI is built for developers who already live in the terminal and want ChatGPT‑level reasoning plus the power to actually run code, manipulate files, and iterate – all under version control. In short, it’s chat‑driven development that understands and executes your repo.
- Zero setup — bring your OpenAI API key and it just works!
- Full auto-approval, while safe + secure by running network-disabled and directory-sandboxed
- Multimodal — pass in screenshots or diagrams to implement features ✨
And it's fully open-source so you can see and contribute to how it develops!
Codex lets you decide how much autonomy the agent receives and auto-approval policy via the
--approval-mode flag (or the interactive onboarding prompt):
| Mode | What the agent may do without asking | Still requires approval |
|---|---|---|
| Suggest (default) |
• Read any file in the repo | • All file writes/patches • Any arbitrary shell commands (aside from reading files) |
| Auto Edit | • Read and apply‑patch writes to files | • All shell commands |
| Full Auto | • Read/write files • Execute shell commands (network disabled, writes limited to your workdir) |
– |
In Full Auto every command is run network‑disabled and confined to the current working directory (plus temporary files) for defense‑in‑depth. Codex will also show a warning/confirmation if you start in auto‑edit or full‑auto while the directory is not tracked by Git, so you always have a safety net.
Coming soon: you’ll be able to whitelist specific commands to auto‑execute with the network enabled, once we’re confident in additional safeguards.
The hardening mechanism Codex uses depends on your OS:
-
macOS 12+ – commands are wrapped with Apple Seatbelt (
sandbox-exec).- Everything is placed in a read‑only jail except for a small set of
writable roots (
$PWD,$TMPDIR,~/.codex, etc.). - Outbound network is fully blocked by default – even if a child process
tries to
curlsomewhere it will fail.
- Everything is placed in a read‑only jail except for a small set of
writable roots (
-
Linux – there is no sandboxing by default. We recommend using Docker for sandboxing, where Codex launches itself inside a minimal container image and mounts your repo read/write at the same path. A custom
iptables/ipsetfirewall script denies all egress except the OpenAI API. This gives you deterministic, reproducible runs without needing root on the host. You can use therun_in_container.shscript to set up the sandbox.
| Requirement | Details |
|---|---|
| Operating systems | macOS 12+, Ubuntu 20.04+/Debian 10+, or Windows 11 via WSL2 |
| Node.js | 22 or newer (LTS recommended) |
| Git (optional, recommended) | 2.23+ for built‑in PR helpers |
| RAM | 4‑GB minimum (8‑GB recommended) |
Never run
sudo npm install -g; fix npm permissions instead.
| Command | Purpose | Example |
|---|---|---|
codex |
Interactive REPL | codex |
codex "…" |
Initial prompt for interactive REPL | codex "fix lint errors" |
codex -q "…" |
Non‑interactive "quiet mode" | codex -q --json "explain utils.ts" |
codex completion <bash|zsh|fish> |
Print shell completion script | codex completion bash |
Key flags: --model/-m, --approval-mode/-a, --quiet/-q, and --notify.
Codex merges Markdown instructions in this order:
~/.codex/instructions.md– personal global guidancecodex.mdat repo root – shared project notescodex.mdin cwd – sub‑package specifics
Disable with --no-project-doc or CODEX_DISABLE_PROJECT_DOC=1.
Run Codex head‑less in pipelines. Example GitHub Action step:
- name: Update changelog via Codex
run: |
npm install -g @openai/codex
export OPENAI_API_KEY="${{ secrets.OPENAI_KEY }}"
codex -a auto-edit --quiet "update CHANGELOG for next release"Set CODEX_QUIET_MODE=1 to silence interactive UI noise.
Setting the environment variable DEBUG=true prints full API request and response details:
DEBUG=true codexBelow are a few bite‑size examples you can copy‑paste. Replace the text in quotes with your own task. See the prompting guide for more tips and usage patterns.
| ✨ | What you type | What happens |
|---|---|---|
| 1 | codex "Refactor the Dashboard component to React Hooks" |
Codex rewrites the class component, runs npm test, and shows the diff. |
| 2 | codex "Generate SQL migrations for adding a users table" |
Infers your ORM, creates migration files, and runs them in a sandboxed DB. |
| 3 | codex "Write unit tests for utils/date.ts" |
Generates tests, executes them, and iterates until they pass. |
| 4 | codex "Bulk‑rename *.jpeg → *.jpg with git mv" |
Safely renames files and updates imports/usages. |
| 5 | codex "Explain what this regex does: ^(?=.*[A-Z]).{8,}$" |
Outputs a step‑by‑step human explanation. |
| 6 | codex "Carefully review this repo, and propose 3 high impact well-scoped PRs" |
Suggests impactful PRs in the current codebase. |
| 7 | codex "Look for vulnerabilities and create a security review report" |
Finds and explains security bugs. |
From npm (Recommended)
npm install -g @openai/codex
# or
yarn global add @openai/codex
# or
bun install -g @openai/codex
# or
pnpm add -g @openai/codexBuild from source
# Clone the repository and navigate to the CLI package
git clone https://github.com/openai/codex.git
cd codex/codex-cli
# Enable corepack
corepack enable
# Install dependencies and build
pnpm install
pnpm build
# Get the usage and the options
node ./dist/cli.js --help
# Run the locally‑built CLI directly
node ./dist/cli.js
# Or link the command globally for convenience
pnpm linkCodex looks for config files in ~/.codex/ (either YAML or JSON format).
# ~/.codex/config.yaml
model: o4-mini # Default model
approvalMode: suggest # or auto-edit, full-auto
fullAutoErrorMode: ask-user # or ignore-and-continue
notify: true # Enable desktop notifications for responses
safeCommands:
- npm test # Automatically approve npm test
- yarn lint # Automatically approve yarn lint// ~/.codex/config.json
{
"model": "o4-mini",
"approvalMode": "suggest",
"fullAutoErrorMode": "ask-user",
"notify": true
}You can also define custom instructions:
# ~/.codex/instructions.md
- Always respond with emojis
- Only use git commands if I explicitly mention you shouldOpenAI released a model called Codex in 2021 - is this related?
In 2021, OpenAI released Codex, an AI system designed to generate code from natural language prompts. That original Codex model was deprecated as of March 2023 and is separate from the CLI tool.
Which models are supported?
Any model available with Responses API. The default is o4-mini, but pass --model gpt-4.1 or set model: gpt-4.1 in your config file to override.
Why does o3 or o4-mini not work for me?
It's possible that your API account needs to be verified in order to start streaming responses and seeing chain of thought summaries from the API. If you're still running into issues, please let us know!
How do I stop Codex from editing my files?
Codex runs model-generated commands in a sandbox. If a proposed command or file change doesn't look right, you can simply type n to deny the command or give the model feedback.
Does it work on Windows?
Not directly. It requires Windows Subsystem for Linux (WSL2) – Codex has been tested on macOS and Linux with Node ≥ 22.
Note: Codex CLI does not currently support OpenAI organizations with Zero Data Retention (ZDR) enabled.
If your OpenAI organization has Zero Data Retention enabled, you may encounter errors such as:
OpenAI rejected the request. Error details: Status: 400, Code: unsupported_parameter, Type: invalid_request_error, Message: 400 Previous response cannot be used for this organization due to Zero Data Retention.
Why?
- Codex CLI relies on the Responses API with
store:trueto enable internal reasoning steps. - As noted in the docs, the Responses API requires a 30-day retention period by default, or when the store parameter is set to true.
- ZDR organizations cannot use
store:true, so requests will fail.
What can I do?
- If you are part of a ZDR organization, Codex CLI will not work until support is added.
- We are tracking this limitation and will update the documentation if support becomes available.
We’re excited to launch a $1 million initiative supporting open source projects that use Codex CLI and other OpenAI models.
- Grants are awarded in $25,000 API credit increments.
- Applications are reviewed on a rolling basis.
Interested? Apply here.
This project is under active development and the code will likely change pretty significantly. We'll update this message once that's complete!
More broadly we welcome contributions – whether you are opening your very first pull request or you’re a seasoned maintainer. At the same time we care about reliability and long‑term maintainability, so the bar for merging code is intentionally high. The guidelines below spell out what “high‑quality” means in practice and should make the whole process transparent and friendly.
- Create a topic branch from
main– e.g.feat/interactive-prompt. - Keep your changes focused. Multiple unrelated fixes should be opened as separate PRs.
- Use
pnpm test:watchduring development for super‑fast feedback. - We use Vitest for unit tests, ESLint + Prettier for style, and TypeScript for type‑checking.
- Before pushing, run the full test/type/lint suite:
This project uses Husky to enforce code quality checks:
- Pre-commit hook: Automatically runs lint-staged to format and lint files before committing
- Pre-push hook: Runs tests and type checking before pushing to the remote
These hooks help maintain code quality and prevent pushing code with failing tests. For more details, see HUSKY.md.
npm test && npm run lint && npm run typecheck-
If you have not yet signed the Contributor License Agreement (CLA), add a PR comment containing the exact text
I have read the CLA Document and I hereby sign the CLAThe CLA‑Assistant bot will turn the PR status green once all authors have signed.
# Watch mode (tests rerun on change)
pnpm test:watch
# Type‑check without emitting files
pnpm typecheck
# Automatically fix lint + prettier issues
pnpm lint:fix
pnpm format:fixPrerequisite: Nix >= 2.4 with flakes enabled (experimental-features = nix-command flakes in ~/.config/nix/nix.conf).
Enter a Nix development shell:
nix developThis shell includes Node.js, installs dependencies, builds the CLI, and provides a codex command alias.
Build and run the CLI directly:
nix build
./result/bin/codex --helpRun the CLI via the flake app:
nix run .#codex- Start with an issue. Open a new one or comment on an existing discussion so we can agree on the solution before code is written.
- Add or update tests. Every new feature or bug‑fix should come with test coverage that fails before your change and passes afterwards. 100 % coverage is not required, but aim for meaningful assertions.
- Document behaviour. If your change affects user‑facing behaviour, update the README, inline help (
codex --help), or relevant example projects. - Keep commits atomic. Each commit should compile and the tests should pass. This makes reviews and potential rollbacks easier.
- Fill in the PR template (or include similar information) – What? Why? How?
- Run all checks locally (
npm test && npm run lint && npm run typecheck). CI failures that could have been caught locally slow down the process. - Make sure your branch is up‑to‑date with
mainand that you have resolved merge conflicts. - Mark the PR as Ready for review only when you believe it is in a merge‑able state.
- One maintainer will be assigned as a primary reviewer.
- We may ask for changes – please do not take this personally. We value the work, we just also value consistency and long‑term maintainability.
- When there is consensus that the PR meets the bar, a maintainer will squash‑and‑merge.
- Be kind and inclusive. Treat others with respect; we follow the Contributor Covenant.
- Assume good intent. Written communication is hard – err on the side of generosity.
- Teach & learn. If you spot something confusing, open an issue or PR with improvements.
If you run into problems setting up the project, would like feedback on an idea, or just want to say hi – please open a Discussion or jump into the relevant issue. We are happy to help.
Together we can make Codex CLI an incredible tool. Happy hacking! 🚀
All contributors must accept the CLA. The process is lightweight:
-
Open your pull request.
-
Paste the following comment (or reply
recheckif you’ve signed before):I have read the CLA Document and I hereby sign the CLA -
The CLA‑Assistant bot records your signature in the repo and marks the status check as passed.
No special Git commands, email attachments, or commit footers required.
| Scenario | Command |
|---|---|
| Amend last commit | git commit --amend -s --no-edit && git push -f |
| GitHub UI only | Edit the commit message in the PR → addSigned-off-by: Your Name <[email protected]> |
The DCO check blocks merges until every commit in the PR carries the footer (with squash this is just the one).
To publish a new version of the CLI, run the release scripts defined in codex-cli/package.json:
- Open the
codex-clidirectory - Make sure you're on a branch like
git checkout -b bump-version - Bump the version and
CLI_VERSIONto current datetime:pnpm release:version - Commit the version bump (with DCO sign-off):
git add codex-cli/src/utils/session.ts codex-cli/package.json git commit -s -m "chore(release): codex-cli v$(node -p \"require('./codex-cli/package.json').version\")" - Copy README, build, and publish to npm:
pnpm release - Push to branch:
git push origin HEAD
Have you discovered a vulnerability or have concerns about model output? Please e‑mail [email protected] and we will respond promptly.
This repository is licensed under the Apache-2.0 License.