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

# Computer for AI Agents

> Create secure sandboxed computers for AI agents with persistent files, CelestoFS storage, browser access, terminals, ports, SDKs, and open-source runtimes.

Celesto gives each agent a safe computer for real work: clone repositories, run commands, browse sites, expose previews, save files, and resume later in a managed sandbox.

Use the hosted platform when you want managed sandboxes. Use the open-source stack when you want local control or deeper customization.

<CardGroup cols={2}>
  <Card icon="rocket" href="/cloud/quickstart" title="Create your first sandbox">
    Launch a hosted Celesto computer, run a command, and clean it up from the SDK or CLI.
  </Card>

  <Card icon="book-open" href="/getting-started/why-celesto" title="Understand the model">
    Learn why agents need real computers, durable workspaces, isolation, and open-source runtimes.
  </Card>
</CardGroup>

## Start by goal

<CardGroup cols={2}>
  <Card icon="code" href="/getting-started/coding-agents" title="Build a coding agent">
    Clone repos, install dependencies, run tests, keep work between sessions, and publish previews.
  </Card>

  <Card icon="globe" href="/getting-started/browser-agents" title="Run browser workflows">
    Give agents browser sessions, command execution, saved artifacts, and sandboxed web access.
  </Card>

  <Card icon="clock" href="/getting-started/long-running-agents" title="Resume long-running work">
    Pause and restart multi-step jobs with saved computer state, files, and workspace artifacts.
  </Card>

  <Card icon="database" href="/getting-started/durable-workspaces" title="Store large project data">
    Understand root disk durability, CelestoFS workspaces, and where agent files should live.
  </Card>
</CardGroup>

## What the sandbox includes

<CardGroup cols={3}>
  <Card icon="shield-halved" href="/smolvm/concepts/security" title="Isolated execution">
    Run untrusted code and tools inside sandboxed computers instead of your app server.
  </Card>

  <Card icon="rotate" href="/cloud/features/persistence" title="Durable state">
    Stop a computer and start it again with saved root disk and workspace state.
  </Card>

  <Card icon="database" href="/cloud/features/petabyte-storage" title="CelestoFS workspace">
    Store large repositories, datasets, generated files, and build artifacts in a large durable workspace.
  </Card>

  <Card icon="terminal" href="/cloud/computers#run-commands" title="Shell and files">
    Run commands, read outputs, write files, and inspect artifacts from your agent code.
  </Card>

  <Card icon="plug" href="/cloud/features/publish-ports" title="Published ports">
    Expose web apps, APIs, dashboards, notebooks, and previews from inside the sandbox.
  </Card>

  <Card icon="github" href="/getting-started/hosted-and-open-source" title="Open-source foundations">
    Build on SmolVM, SmolFS, and Agentor when you want to run or extend the stack yourself.
  </Card>
</CardGroup>

## Storage that grows with the job

In a storage test, a 10 GB coding-agent sandbox wrote a 20 GB file into the sandbox user's home workspace. The root disk stayed small while CelestoFS provided the large durable workspace.

```bash CLI theme={null}
celesto computer create --template coding-agent --disk-size-mb 10240

celesto computer run einstein "python3 - <<'PY'
from pathlib import Path

target = Path.home() / 'storage-proof/twenty-gib.bin'
target.parent.mkdir(parents=True, exist_ok=True)

with target.open('wb') as f:
    chunk = b'0' * (1024 * 1024)
    for gib in range(20):
        for _ in range(1024):
            f.write(chunk)
        print(f'wrote {gib + 1} GiB', flush=True)

print(target.stat().st_size)
PY"

celesto computer run einstein "du -h ~/storage-proof/twenty-gib.bin && df -h / ~"
```

See [Petabyte-scale storage for AI agent sandboxes](/cloud/features/petabyte-storage) for the full storage guide, expected output, and cleanup commands.

## Choose your runtime

<CardGroup cols={2}>
  <Card icon="cloud" href="/cloud/overview" title="Hosted Celesto Platform">
    Launch and orchestrate managed sandboxes at scale with the Celesto SDK and CLI.
  </Card>

  <Card icon="computer" href="/smolvm/introduction" title="SmolVM">
    Run open-source microVM sandboxes locally with hardware-level isolation.
  </Card>

  <Card icon="folder-open" href="/smolfs/overview" title="SmolFS">
    Use open-source durable workspace folders for agent state across runs.
  </Card>

  <Card icon="robot" href="/agentor/home" title="Agentor">
    Build production-ready AI agents with tool use, MCP, and agent-to-agent communication.
  </Card>
</CardGroup>