Lightweight coding agent th 57AE at runs in your terminal
npm i -g @openai/codex
Table of contents
- Experimental technology disclaimer
- Quickstart
- Why Codex?
- Agentic Tools Interface
- Security model & permissions
- System requirements
- CLI reference
- Memory & project docs
- Non-interactive / CI mode
- Rollout Replay System
- Tracing / verbose logging
- Recipes
- Installation
- Configuration guide
- FAQ
- Zero data retention (ZDR) usage
- Codex open source fund
- Contributing
- Security & responsible AI
- License
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. You can add the
exportline to your shell's configuration file (e.g.,~/.zshrc) but we recommend setting for the session. 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).
Use --provider to use other models
Codex also allows you to use other providers that support the OpenAI Chat Completions API. You can set the provider in the config file or use the
--providerflag. The possible options for--providerare:
- openai (default)
- openrouter
- azure
- gemini
- ollama
- mistral
- deepseek
- xai
- groq
- arceeai
- any other provider that is compatible with the OpenAI API
If you use a provider other than OpenAI, you will need to set the API key for the provider in the config file or in the environment variable as:
export <provider>_API_KEY="your-api-key-here"If you use a provider not listed above, you must also set the base URL for the provider:
export <provider>_BASE_URL="https://your-provider-api-base-url"
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.
💡 Testing Tip: Set any API key to "test_key" to enable rollout replay mode, which replays previous sessions without consuming API credits - perfect for testing and development!
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
- Agentic tools interface - intelligent project analysis and command composition
And it's fully open-source so you can see and contribute to how it develops!
- Error Prevention: Identifies common mistakes before execution
- Enhanced File Preview: Advanced code viewing with syntax highlighting and developer tools
View and manage your past Codex sessions:
- Session Metadata: Track model used, duration, and command count
- Session Browsing: Navigate through historical interactions
- Summary Information: Quick overview of what was accomplished
- Session Resumption: Continue from previous session states
| Mode | Access | Description |
|---|---|---|
| Tool Palette | /tools or 1 |
Browse available tools with intelligent suggestions |
| Command Composer | 2 |
AI-assisted command building and composition |
| Session History | 3 |
View and manage past Codex sessions |
All agentic features integrate seamlessly with the existing approval modes and security model, maintaining the same sandboxing and permission controls.
The enhanced file preview provides a professional code viewing experience with advanced developer features:
- Toggle: Press
fto enter full preview mode, hiding the file navigator for maximum code viewing space - Breadcrumbs: Shows file path navigation in full preview mode
- Exit: Press
fagain to return to split view
- In-File Search: Press
Ctrl+Fto search within the current file with real-time highlighting - Go to Line: Press
gfollowed by a line number to jump directly to specific lines - Search Navigation: Use
nandNto navigate between search results - Zoom Control: Use
+,-, and0to increase, decrease, or reset font size
- JavaScript/TypeScript: Keywords, strings, numbers, and comments with appropriate colors
- JSON: Property names and values with distinct highlighting
- Markdown: Headers, code blocks, and formatting with visual emphasis
- CSS: Selectors, properties, and values with color coding
- Git Integration: File status indicators showing modified, added, deleted, or untracked files
- Line Numbers: Toggle with
lkey for precise code navigation - Word Wrap: Toggle with
wkey for handling long lines
B41A
- Performance Optimization: Smart caching and efficient rendering for large files
- Reload: Press
rto refresh file content from disk - Cache Management: Press
cto clear file cache - Visual Indicators: Cache hit status and file size information
| Key | Action |
|---|---|
f |
Toggle full preview mode |
Ctrl+F |
Start in-file search |
n / N |
Next/Previous search result |
g + number |
Go to specific line |
+ / - / 0 |
Zoom in/out/reset |
w |
Toggle word wrap |
l |
Toggle line numbers |
r |
Reload file |
c |
Clear cache |
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) |
||
| Auto Edit | ||
| Full Auto | - |
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 |
| Command | Purpose | Shortcut |
|---|---|---|
/tools |
Open agentic tools interface | - |
/clear |
Clear conversation history | - |
/compact |
Reduce conversation context | - |
/help |
Show available commands | - |
| Key | Mode | Description |
|---|---|---|
1 |
Tool Palette | Browse intelligent tool suggestions |
2 |
Command Composer | AI-assisted command building |
3 |
Session History | View and manage past sessions |
Key flags: --model/-m, --approval-mode/-a, --quiet/-q, and --notify.
You can give Codex extra instructions and guidance using AGENTS.md files. Codex looks for AGENTS.md files in the following places, and merges them top-down:
~/.codex/AGENTS.md- personal global guidanceAGENTS.mdat repo root - shared project notesAGENTS.mdin the current working directory - sub-folder/feature specifics
Disable loading of these files with --no-project-doc or the environment variable 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.
The rollout replay system enables testing and development without consuming API credits by replaying previously recorded AI sessions. This feature is particularly useful for:
- Testing and debugging without API costs
- Reproducible development using real session data
- Demonstration and training with consistent outputs
- CI/CD pipelines that need deterministic behavior
Codex automatically records all interactions in rollout JSON files (format: rollout-YYYY-MM-DD-{session-id}.json). The replay system can load these files and recreate the exact same AI behavior, including:
- All function calls (shell commands, file operations, etc.)
- Realistic command outputs and responses
- Progress tracking and session metadata
- Support for all approval modes
The rollout replay mode activates automatically when:
-
Test Environment Detection: Any API key is set to
"test_key"export GEMINI_API_KEY="test_key" codex "create a simple website"
-
Force Replay Mode: Set the environment variable (works with any API key)
export CODEX_FORCE_REPLAY=1 codex "replay this session"
The system automatically searches for rollout files in this order:
- Current working directory (
./rollout-*.json) - Parent directories (traversing upward)
- Codex CLI directory (
codex-cli/rollout-*.json)
During replay, you'll see session metadata:
🎬 [RolloutAgentLoop] Replay mode activated
🎬 [RolloutAgentLoop] Starting replay session...
📅 Session: 850cc2e4-60fb-4468-b349-ed921ae4e17d (2025-06-09T04:38:29.893Z)
Basic Testing:
# Set any provider API key to "test_key" to activate replay
export OPENAI_API_KEY="test_key"
codex "create a React app"CI/CD Integration:
# Force replay mode for reproducible testing
export CODEX_FORCE_REPLAY=1
export OPENAI_API_KEY="test_key"
codex --quiet --full-auto "run comprehensive tests"Interactive Development:
# Test new features without API calls
export GEMINI_API_KEY="test_key"
codex # Interactive mode with replay- Zero API Costs: No real API calls are made during replay
- Deterministic Output: Same input always produces identical results
- Real Session Data: Uses actual AI responses from previous sessions
- Full Functionality: Works with all CLI features and approval modes
- Seamless Integration: No changes needed to existing commands or workflows
The rollout replay system maintains the same user experience as normal operation while providing a cost-effective way to test, develop, and demonstrate Codex CLI functionality.
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. |
| 8 | GEMINI_API_KEY="test_key" codex "create a todo app" |
Replays a previous session without consuming API credits. |
| # | What you type | What happens |
|---|---|---|
| 9 | /tools then browse suggestions |
Opens intelligent tool palette with context-aware recommendations for your project |
| 10 | Press 2 for Command Composer |
AI guides you through building complex commands with safety analysis |
| 11 | Press 3 for Session History |
Browse previous Codex sessions with metadata and resumption options |
| 12 | /tools in a React project |
Shows React-specific tools like component analysis, hook optimization, and testing utilities |
| 13 | Command Composer for deployment | Breaks down deployment into steps with risk assessment and timing estimates |
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
# Linux-only: download prebuilt sandboxing binaries (requires gh and zstd).
./scripts/install_native_deps.sh
# 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 configuration files can be placed in the ~/.codex/ directory, supporting both YAML and JSON formats.
| Parameter | Type | Default | Description | Available Options |
|---|---|---|---|---|
model |
string | o4-mini |
AI model to use | Any model name supporting OpenAI API |
approvalMode |
string | suggest |
AI assistant's permission mode | suggest (suggestions only)auto-edit (automatic edits)full-auto (fully automatic) |
fullAutoErrorMode |
string | ask-user |
Error handling in full-auto mode | ask-user (prompt for user input)ignore-and-continue (ignore and proceed) |
notify |
boolean | true |
Enable desktop notifications | true/false |
In the providers object, you can configure multiple AI service providers. Each provider requires the following parameters:
| Parameter | Type | Description | Example |
|---|---|---|---|
name |
string | Display name of the provider | "OpenAI" |
baseURL |
string | API service URL | "https://api.openai.com/v1" |
envKey |
string | Environment variable name (for API key) | "OPENAI_API_KEY" |
In the history object, you can configure conversation history settings:
| Parameter | Type | Description | Example Value |
|---|---|---|---|
maxSize |
number | Maximum number of history entries to save | 1000 |
saveHistory |
boolean | Whether to save history | true |
sensitivePatterns |
array | Patterns of sensitive information to filter in history | [] |
- YAML format (save as
~/.codex/config.yaml):
model: o4-mini
approvalMode: suggest
fullAutoErrorMode: ask-user
notify: true- JSON format (save as
~/.codex/config.json):
{
"model": "o4-mini",
"approvalMode": "suggest",
"fullAutoErrorMode": "ask-user",
"notify": true
}Below is a comprehensive example of config.json with multiple custom providers:
{
"model": "o4-mini",
"provider": "openai",
"providers": {
"openai": {
"name": "OpenAI",
"baseURL": "https://api.openai.com/v1",
"envKey": "OPENAI_API_KEY"
},
"azure": {
"name": "AzureOpenAI",
"baseURL": "https://YOUR_PROJECT_NAME.openai.azure.com/openai",
"envKey": "AZURE_OPENAI_API_KEY"
},
"openrouter": {
"name": "OpenRouter",
"baseURL": "https://openrouter.ai/api/v1",
"envKey": "OPENROUTER_API_KEY"
},
"gemini": {
"name": "Gemini",
"baseURL": "https://generativelanguage.googleapis.com/v1beta/openai",
"envKey": "GEMINI_API_KEY"
},
"ollama": {
"name": "Ollama",
"baseURL": "http://localhost:11434/v1",
"envKey": "OLLAMA_API_KEY"
},
"mistral": {
"name": "Mistral",
"baseURL": "https://api.mistral.ai/v1",
"envKey": "MISTRAL_API_KEY"
},
"deepseek": {
"name": "DeepSeek",
"baseURL": "https://api.deepseek.com",
"envKey": "DEEPSEEK_API_KEY"
},
"xai": {
"name": "xAI",
"baseURL": "https://api.x.ai/v1",
"envKey": "XAI_API_KEY"
},
"groq": {
"name": "Groq",
"baseURL": "https://api.groq.com/openai/v1",
"envKey": "GROQ_API_KEY"
},
"arceeai": {
"name": "ArceeAI",
"baseURL": "https://conductor.arcee.ai/v1",
"envKey": "ARCEEAI_API_KEY"
}
},
"history": {
"maxSize": 1000,
"saveHistory": true,
"sensitivePatterns": []
}
}You can create a ~/.codex/AGENTS.md file to define custom guidance for the agent:
- Always respond with emojis
- Only use git commands when explicitly requestedFor each AI provider, you need to set the corresponding API key in your environment variables. For example:
# OpenAI
export OPENAI_API_KEY="your-api-key-here"
# Azure OpenAI
export AZURE_OPENAI_API_KEY="your-azure-api-key-here"
export AZURE_OPENAI_API_VERSION="2025-03-01-preview" (Optional)
# OpenRouter
export OPENROUTER_API_KEY="your-openrouter-key-here"
# Similarly for other providersOpenAI 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.
Codex CLI does support OpenAI organizations with Zero Data Retention (ZDR) enabled. If your OpenAI organization has Zero Data Retention enabled and you still 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.
You may need to upgrade to a more recent version with: npm i -g @openai/codex@latest
We're excited to launch a $1 million initiative supporting open source projects that use Codex CLI and other OpenAI models.
- Grants are awarded up to $25,000 API credits.
- 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.
pnpm test && pnpm run lint && pnpm 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:fixTo debug the CLI with a visual debugger, do the following in the codex-cli folder:
- Run
pnpm run buildto build the CLI, which will generatecli.js.mapalongsidecli.jsin thedistfolder. - Run the CLI with
node --inspect-brk ./dist/cli.jsThe program then waits until a debugger is attached before proceeding. Options:- In VS Code, choose Debug: Attach to Node Process from the command palette and choose the option in the dropdown with debug port
9229(likely the first option) - Go to chrome://inspect in Chrome and find localhost:9229 and click trace
- In VS Code, choose Debug: Attach to Node Process from the command palette and choose the option in the dropdown with debug port
- 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 |
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 you first need to stage the npm package. A
helper script in codex-cli/scripts/ does all the heavy lifting. Inside the
codex-cli folder run:
# Classic, JS implementation that includes small, native binaries for Linux sandboxing.
pnpm stage-release
# Optionally specify the temp directory to reuse between runs.
RELEASE_DIR=$(mktemp -d)
pnpm stage-release --tmp "$RELEASE_DIR"
# "Fat" package that additionally bundles the native Rust CLI binaries for
# Linux. End-users can then opt-in at runtime by setting CODEX_RUST=1.
pnpm stage-release --nativeWindows Compatibility: The staging script now works natively on Windows. You can use any of these approaches:
pnpm stage-release(cross-platform Node.js script)node scripts/stage_release.js(direct Node.js call).\scripts\stage_release.ps1(PowerShell script)scripts\stage_release.bat(batch file)
For detailed Windows instructions, see codex-cli/WINDOWS_DISTRIBUTION.md.
Go to the folder where the release is staged and verify that it works as intended. If so, run the following from the temp folder:
cd "$RELEASE_DIR"
npm publish
Prerequisite: Nix >= 2.4 with flakes enabled (experimental-features = nix-command flakes in ~/.config/nix/nix.conf).
Enter a Nix development shell:
# Use either one of the commands according to which implementation you want to work with
nix develop .#codex-cli # For entering codex-cli specific shell
nix develop .#codex-rs # For entering codex-rs specific shellThis shell includes Node.js, installs dependencies, builds the CLI, and provides a codex command alias.
Build and run the CLI directly:
# Use either one of the commands according to which implementation you want to work with
nix build .#codex-cli # For building codex-cli
nix build .#codex-rs # For building codex-rs
./result/bin/codex --helpRun the CLI via the flake app:
# Use either one of the commands according to which implementation you want to work with
nix run .#codex-cli # For running codex-cli
nix run .#codex-rs # For running codex-rsUse direnv with flakes
If you have direnv installed, you can use the following .envrc to automatically enter the Nix shell when you cd into the project directory:
cd codex-rs
echo "use flake ../flake.nix#codex-cli" >> .envrc && direnv allow
cd codex-cli
echo "use flake ../flake.nix#codex-rs" >> .envrc && direnv allowHave you discovered a vulnerability or have concerns about model output? Please e-mail security@openai.com and we will respond promptly.
This repository is licensed under the Apache-2.0 License.