OpenAI Codex

OpenAI Codex is OpenAI’s coding agent across the Codex CLI, IDE extension, ChatGPT app, web, SDK, and cloud tasks. The Apache-2.0 CLI runs locally in a chosen directory, where it can inspect a repository, edit files, execute project commands, and apply instructions from AGENTS.md. Local execution uses sandbox and approval controls; cloud and GitHub features add remote tasks, parallel work, and pull-request review. Official installers cover macOS, Linux, and Windows, while release assets and package-manager options provide additional install paths.

Access depends on how Codex is used. OpenAI’s current pricing page lists Free, Go, Plus, Pro, Business, Enterprise, and Edu paths, with plan-dependent limits and surfaces. API-key use is available for the CLI, SDK, and IDE extension and is billed at API token rates, but it does not include cloud features such as GitHub code review or Slack integration. Plan limits, models, previews, and credit rates vary by account and can change; the live Codex pricing page is the authority.

Top features

• Local repository agent: reads and edits files, runs builds or tests, and works from the current project directory.
• Multiple surfaces: CLI, IDE extension, app, web, SDK, non-interactive execution, and cloud task workflows are documented.
• Sandboxing and approvals: configurable policies govern filesystem access, network access, and command escalation.
• GitHub review: Codex can review pull requests when connected through supported ChatGPT plans and repository settings.
• Project instructions: nested AGENTS.md files let repositories define scoped conventions and review guidance.
• Extensibility: MCP connections, skills, plugins, and scriptable SDK or exec modes support repeatable workflows.
• Open-source CLI: the canonical repository is active, Apache-2.0 licensed, and publishes platform binaries.

Use cases

• Trace an unfamiliar code path, identify relevant files, and prepare a bounded implementation plan.
• Implement a feature or bug fix, run the repository’s checks, and return a reviewable diff.
• Add a second review pass to a GitHub pull request using repository-specific instructions.
• Run coding tasks from CI or internal automation with an API key and the SDK or non-interactive CLI.
• Delegate longer work to cloud tasks while continuing local development.