Vercel AI SDK integration
Pass a Promigence sandbox to the Vercel AI SDK as experimental_sandbox, or to bash-tool. The commands your tools run and the files they touch stay in the sandbox, away from your server.
The package is promigence-ai-sdk-sandbox on npm, for TypeScript.
Install
Install it and set your key.
npm install promigence-ai-sdk-sandbox @promigence/sdk ai zod bash-tool
export PROMIGENCE_API_KEY=prom_api_...
Example
From the guide Run Vercel AI SDK agents in a Promigence sandbox, which goes on to the spend cap, cleaning up, and what the package does not support.
import { generateText, tool } from "ai";
import { Sandbox } from "@promigence/sdk";
import { promigenceSandbox } from "promigence-ai-sdk-sandbox";
import { z } from "zod";
const sandbox = await Sandbox.create({ timeoutMs: 600_000, spendCap: 1 });
const session = promigenceSandbox(sandbox, { workingDirectory: "/workspace" });
try {
await generateText({
model: "anthropic/claude-sonnet-4-5",
prompt: "run the tests and fix what fails",
experimental_sandbox: session,
tools: {
shell: tool({
description: "run a shell command",
inputSchema: z.object({ command: z.string() }),
execute: async ({ command }, { experimental_sandbox }) => {
const { exitCode, stdout, stderr } = await experimental_sandbox!.run({ command });
return `${exitCode}\n${stdout}${stderr}`;
},
}),
},
});
} finally {
await session.stop();
}