Codex

Codex is OpenAI’s terminal coding agent. Run it in a Superserve sandbox so its shell commands and file edits stay isolated from your machine.

Via the console

On the Secrets page, create a secret with the OpenAI provider and paste your API key — you only do this once, and the key never enters the sandbox.
Go to console.superserve.ai and click Create sandbox.
Pick the superserve/node-22 template.
Under Advanced Options → Secrets, bind that secret to OPENAI_API_KEY.
Create the sandbox, open its Terminal, and run:
npm install -g @openai/codex && codex

Via the SDK

npm install @superserve/sdk
export SUPERSERVE_API_KEY=ss_live_...

pip install superserve
export SUPERSERVE_API_KEY=ss_live_...

import { Sandbox, Secret } from "@superserve/sdk"

// One-time: store your key as a secret. It never enters the sandbox.
await Secret.create({ name: "openai-key", value: "sk-...", provider: "openai" })

const sandbox = await Sandbox.create({
  name: "codex",
  fromTemplate: "superserve/node-22",
  secrets: { OPENAI_API_KEY: "openai-key" },
})

await sandbox.commands.run("npm install -g @openai/codex")

from superserve import Sandbox, Secret

# One-time: store your key as a secret. It never enters the sandbox.
Secret.create(name="openai-key", value="sk-...", provider="openai")

sandbox = Sandbox.create(
    name="codex",
    from_template="superserve/node-22",
    secrets={"OPENAI_API_KEY": "openai-key"},
)

sandbox.commands.run("npm install -g @openai/codex")

Codex reads OPENAI_API_KEY as usual, but its value is a stand-in token — the real key is attached only on requests to OpenAI, never exposed to the agent. Open the sandbox in the console, launch the terminal, and run codex. For non-interactive runs, codex exec does not read OPENAI_API_KEY: run printenv OPENAI_API_KEY | codex login --with-api-key once, or run export CODEX_API_KEY="$OPENAI_API_KEY" first.

Persist sessions

await sandbox.pause()
await sandbox.resume()

Delete when finished

A paused sandbox is kept until you delete it. When you no longer need the sandbox, delete it. This also deletes its files and saved state.

await sandbox.kill()

sandbox.kill()

To delete it from another process, pass its ID to Sandbox.killById() (TypeScript) or Sandbox.kill_by_id() (Python). To delete paused sandboxes automatically, see Auto-delete.

Use cases

Integrations

Via the console

Via the SDK

Persist sessions

Delete when finished

​Via the console

​Via the SDK

​Persist sessions

​Delete when finished

Via the console

Via the SDK

Persist sessions

Delete when finished