CoCalc Fork-specific changes

• Thread a configurable ToolExecutor through Codex::spawn, ConversationManager, and SessionServices, and export default_tool_executor so downstream adapters can swap in custom shell/apply_patch implementations.
• Expose ToolInvocation, ToolCtx, ToolPayload, SandboxAttempt, ToolError, and FunctionCallError (with helpers such as conversation_id()) so external executors know which conversation/session and approval context they are serving.
• Introduce register_external_tool_handler and expose the handler registry so forks can override built-in tools like read_file while still using Codex's tool routing.
• Enable GPT-5/GPT-5.1 model families to advertise the experimental read_file tool, giving ACP clients parity with Codex's filesystem access UX.
• Expand the codex-apply-patch crate by exporting UpdateFileChunk and apply_chunks_to_contents so remote executors can apply patches entirely in memory without launching codex.
• Add public APIs for ACP needs (conversation IDs on ToolInvocation/Session, approval enums, shell request exports, etc.) making codex-core embeddable inside the ACP adapter.

Original Readme Below

npm i -g @openai/codex
or brew install --cask codex

Codex CLI is a coding agent from OpenAI that runs locally on your computer.

If you want Codex in your code editor (VS Code, Cursor, Windsurf), install in your IDE
If you are looking for the cloud-based agent from OpenAI, Codex Web, go to chatgpt.com/codex

---

Quickstart

Installing and running Codex CLI

Install globally with your preferred package manager. If you use npm:

npm install -g @openai/codex

Alternatively, if you use Homebrew:

brew install --cask codex

Then simply run codex to get started:

codex

If you're running into upgrade issues with Homebrew, see the FAQ entry on brew upgrade codex.

You can also go to the latest GitHub Release and download the appropriate binary for your platform.

Each GitHub Release contains many executables, but in practice, you likely want one of these:

• macOS
  • Apple Silicon/arm64: codex-aarch64-apple-darwin.tar.gz
  • x86_64 (older Mac hardware): codex-x86_64-apple-darwin.tar.gz
• Linux
  • x86_64: codex-x86_64-unknown-linux-musl.tar.gz
  • arm64: codex-aarch64-unknown-linux-musl.tar.gz

Each archive contains a single entry with the platform baked into the name (e.g., codex-x86_64-unknown-linux-musl), so you likely want to rename it to codex after extracting it.

Using Codex with your ChatGPT plan

Run codex and select Sign in with ChatGPT. We recommend signing into your ChatGPT account to use Codex as part of your Plus, Pro, Team, Edu, or Enterprise plan. Learn more about what's included in your ChatGPT plan.

You can also use Codex with an API key, but this requires additional setup. If you previously used an API key for usage-based billing, see the migration steps. If you're having trouble with login, please comment on this issue.

Model Context Protocol (MCP)

Codex can access MCP servers. To configure them, refer to the config docs.

Configuration

Codex CLI supports a rich set of configuration options, with preferences stored in ~/.codex/config.toml. For full configuration options, see Configuration.

Execpolicy

See the Execpolicy quickstart to set up rules that govern what commands Codex can execute.

Docs & FAQ

• Getting started
  • CLI usage
  • Slash Commands
  • Running with a prompt as input
  • Example prompts
  • Custom prompts
  • Memory with AGENTS.md
• Configuration
  • Example config
• Sandbox & approvals
• Execpolicy quickstart
• Authentication
  • Auth methods
  • Login on a "Headless" machine
• Automating Codex
  • GitHub Action
  • TypeScript SDK
  • Non-interactive mode (codex exec)
• Advanced
  • Tracing / verbose logging
  • Model Context Protocol (MCP)
• Zero data retention (ZDR)
• Contributing
• Install & build
  • System Requirements
  • DotSlash
  • Build from source
• FAQ
• Open source fund

---

License

This repository is licensed under the Apache-2.0 License.