Computer for AI Agents

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.

Create your first sandbox

Launch a hosted Celesto computer, run a command, and clean it up from the SDK or CLI.

Understand the model

Learn why agents need real computers, durable workspaces, isolation, and open-source runtimes.

Start by goal

Build a coding agent

Clone repos, install dependencies, run tests, keep work between sessions, and publish previews.

Run browser workflows

Give agents browser sessions, command execution, saved artifacts, and sandboxed web access.

Resume long-running work

Pause and restart multi-step jobs with saved computer state, files, and workspace artifacts.

Store large project data

Understand root disk durability, CelestoFS workspaces, and where agent files should live.

What the sandbox includes

Isolated execution

Run untrusted code and tools inside sandboxed computers instead of your app server.

Durable state

Stop a computer and start it again with saved root disk and workspace state.

CelestoFS workspace

Store large repositories, datasets, generated files, and build artifacts in a large durable workspace.

Shell and files

Run commands, read outputs, write files, and inspect artifacts from your agent code.

Published ports

Expose web apps, APIs, dashboards, notebooks, and previews from inside the sandbox.

Open-source foundations

Build on SmolVM, SmolFS, and Agentor when you want to run or extend the stack yourself.

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.

CLI

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 for the full storage guide, expected output, and cleanup commands.

Choose your runtime

Hosted Celesto Platform

Launch and orchestrate managed sandboxes at scale with the Celesto SDK and CLI.

SmolVM

Run open-source microVM sandboxes locally with hardware-level isolation.

SmolFS

Use open-source durable workspace folders for agent state across runs.

Agentor

Build production-ready AI agents with tool use, MCP, and agent-to-agent communication.