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

# Introduction

> Caged is an AI agent sandbox platform. Run AI coding agents in isolated cloud environments with built-in cost tracking, session replay, and trust scoring.

<img className="block dark:hidden" src="https://mintcdn.com/bytangle/_hwLEA0EwT96dhFt/images/hero-light.svg?fit=max&auto=format&n=_hwLEA0EwT96dhFt&q=85&s=b73a35432e56f0bccfc8f436d522e637" alt="Caged Platform" width="800" height="200" data-path="images/hero-light.svg" />

<img className="hidden dark:block" src="https://mintcdn.com/bytangle/_hwLEA0EwT96dhFt/images/hero-dark.svg?fit=max&auto=format&n=_hwLEA0EwT96dhFt&q=85&s=fa4b425e9dd57796778bb5d1ab2b2f28" alt="Caged Platform" width="800" height="200" data-path="images/hero-dark.svg" />

# What is Caged?

**Caged** gives AI coding agents a safe, isolated place to work — away from your local machine.

Send agents like Claude Code, Codex, Cursor, or Aider into cloud sandboxes backed by Firecracker microVMs. Every session is automatically:

<CardGroup cols={2}>
  <Card title="Isolated" icon="shield-halved">
    Each sandbox runs its own Linux kernel — VM boundary, not container namespace. Full OS-level isolation.
  </Card>

  <Card title="Observed" icon="eye">
    Every file change, terminal command, and LLM call is recorded in real-time. Nothing happens in the dark.
  </Card>

  <Card title="Costed" icon="dollar-sign">
    Real-time dollar tracking of LLM tokens + compute time. Set budget guards to prevent runaway costs.
  </Card>

  <Card title="Scored" icon="chart-line">
    Trust score (0-100) based on agent behavior. Penalizes risky actions like file deletion or network exfiltration.
  </Card>
</CardGroup>

## Why Caged?

Running AI agents on your local machine is risky:

| Problem                      | Without Caged                  | With Caged                   |
| ---------------------------- | ------------------------------ | ---------------------------- |
| Agent deletes files          | Your files are gone            | Sandbox is disposable        |
| Agent installs malware       | Your machine is compromised    | VM is destroyed after        |
| Agent runs up a \$500 bill   | You find out next month        | Budget guard kills it at \$5 |
| Agent does something sketchy | You have no idea               | Full replay + trust score    |
| Two agents conflict          | They fight over the same files | Each gets its own sandbox    |

## How It Works

```
Developer                   Caged Platform                    Sandbox
    │                           │                               │
    ├── caged up ──────────────►│                               │
    │                           ├── Create Firecracker VM ─────►│
    │                           ├── Clone repo ────────────────►│
    │                           ├── Run init_script ───────────►│
    │                           │                               │
    ├── caged connect <id> ────►│◄── WebSocket PTY ────────────►│
    │                           │                               │
    │   Dashboard               │                               │
    │   ├── Live terminal ◄─────┤◄── Events stream ────────────►│
    │   ├── File browser ◄──────┤                               │
    │   ├── Cost tracker ◄──────┤                               │
    │   └── Trust score ◄───────┤                               │
    │                           │                               │
    ├── caged destroy <id> ────►│── Destroy VM ────────────────►│ ✕
```

## Components

| Component         | Description                                                        |
| ----------------- | ------------------------------------------------------------------ |
| **API Server**    | Go backend managing sandboxes, auth, billing, events               |
| **CLI**           | `caged` command-line tool for creating and managing sandboxes      |
| **Dashboard**     | Web UI for monitoring sandboxes, viewing replays, managing billing |
| **SDKs**          | TypeScript and Python libraries for programmatic access            |
| **Sandbox Agent** | Process inside each VM that relays events to the platform          |

## Next Steps

<CardGroup cols={2}>
  <Card title="Quickstart" icon="rocket" href="/quickstart">
    Create your first sandbox in 2 minutes
  </Card>

  <Card title="Concepts" icon="book" href="/concepts">
    Understand sandboxes, sessions, and trust scores
  </Card>

  <Card title="Config-as-Code" icon="file-code" href="/guides/config-as-code">
    Add .caged.yaml to your repo
  </Card>

  <Card title="API Reference" icon="code" href="/api-reference/overview">
    Full REST API documentation
  </Card>
</CardGroup>