Sandbox

Run a coding agent in a Vercel Sandbox that is already pointed at Boundless.

A coding agent needs a model and an isolated machine to run commands on: Boundless supplies the model, Vercel Sandbox supplies the machine. @boundless.md/sandbox wires them together, so the sandbox boots with Claude Code, Codex and OpenCode already pointed at our gateway.

Use it#

npm i @boundless.md/sandbox @vercel/sandbox

import { sandbox } from "@boundless.md/sandbox";

const box = await sandbox();
console.log(await box.run(`claude -p "What's 2+2? Be concise."`));
await box.stop();

box is a regular @vercel/sandbox instance with run(command) added, so files, ports, snapshots and the rest work as in Vercel's Working with Sandbox guide.

What is in the image#

Harness	Config	Default model
Claude Code	`~/.claude/settings.json`	`glm-5.2`
Codex	`~/.codex/config.toml`	`qwen3.6`
OpenCode	`~/.config/opencode/opencode.json`	`glm-5.2`

Ubuntu 26.04
Node 24
Python 3
git, ripgrep, jq, and curl

OPENAI_BASE_URL and ANTHROPIC_BASE_URL already point at the gateway, so the OpenAI and Anthropic SDKs work inside the sandbox with no configuration either.

Default budget#

Minted keys are capped at $5 and expire after an hour; they appear in API Keys. Sandbox compute is billed by Vercel.