> ## 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.

# Claude Code

> Run Anthropic's Claude Code CLI against any Mirage workspace by mounting it as a real filesystem via FUSE.

[Claude Code](https://github.com/anthropics/claude-code) is Anthropic's CLI for Claude. It expects a real filesystem and doesn't expose a pluggable backend, so instead of an SDK integration, Mirage exposes any workspace as a real filesystem via [FUSE](/typescript/setup/fuse) and lets you point `claude` 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 [Claude Code](https://docs.claude.com/en/docs/claude-code/setup) separately.

## Usage

```ts theme={null}
import { Mount, MountMode, RAMResource, S3Resource, Workspace } from '@struktoai/mirage-node'

const ws = new Workspace({
  '/': new Mount(new RAMResource(), { mode: MountMode.WRITE, fuse: true }),
  '/s3/': new Mount(new S3Resource({ bucket: 'my-bucket', /* ... */ }), { mode: MountMode.READ }),
})
await ws.fuseReady()

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

The mountpoint behaves like a regular directory. `claude` reads, writes, runs `bash`, and patches files just like it would on a normal disk, every operation goes through Mirage's ops layer, so writes to `/s3/...` hit S3, writes to `/` stay in RAM.

## Why FUSE instead of an SDK integration?

Claude Code's tool-use loop is fully internal, there's no `Backend` interface to swap. FUSE gives Mirage a single unforced way in: present a real path, let the agent be the agent.

You lose:

* Per-tool prompt customization
* Observation hooks on tool calls
* Mirage's op-record telemetry on the agent's specific calls (host syscalls aren't recorded the same way)

You gain:

* Zero integration effort
* Compatibility with every Claude Code feature, including future ones
* The same approach works for any other directory-based agent ([OpenAI Codex](/typescript/agents/codex), `aider`, etc.)