> ## Documentation Index
> Fetch the complete documentation index at: https://docs.mirage.strukto.ai/llms.txt
> Use this file to discover all available pages before exploring further.

# OpenAI Codex

> Run OpenAI's Codex CLI against any Mirage workspace by mounting it as a real filesystem via FUSE.

[OpenAI Codex](https://github.com/openai/codex) is OpenAI's coding-agent CLI. Like [Claude Code](/typescript/agents/claude-code), it operates on a real filesystem and doesn't expose a pluggable backend, so Mirage integrates by [FUSE-mounting](/typescript/setup/fuse) a workspace and letting you point `codex` at the mountpoint.

## Install

```bash theme={null}
pnpm add @struktoai/mirage-node @zkochan/fuse-native
```

See [TypeScript FUSE setup](/typescript/setup/fuse) for the pnpm `onlyBuiltDependencies` allow-list and macOS macFUSE 4 symlink workaround. Then install [OpenAI Codex](https://github.com/openai/codex) separately.

## Usage

```ts theme={null}
import { Mount, MountMode, RAMResource, Workspace } from '@struktoai/mirage-node'

const ws = new Workspace({
  '/': new Mount(new RAMResource(), { mode: MountMode.WRITE, fuse: true }),
})
await ws.fuseReady()

console.log(`cd ${ws.fuseMountpoint} && codex`)
// ... run codex in another terminal, then:
await ws.close()
```

The mountpoint behaves like a regular directory. Codex's `read_file`, `write_file`, and `run_shell` tools all dispatch through Mirage's ops layer.

## Why FUSE instead of an SDK integration?

The Codex CLI's tool surface isn't pluggable, it expects host file operations. FUSE makes those host operations *be* Mirage operations.

You lose per-tool customization and Mirage's op-record telemetry; you gain zero integration effort and compatibility with every Codex feature. Same trade-off as [Claude Code](/typescript/agents/claude-code).