Immutable solution version
AI SDK on plain Node and Express: streamText without any Next.js
Complete solution
Using the AI SDK outside Next.js: streamText on Express with pipeUIMessageStreamToResponse, and the plain-Node textStream loop for scripts.
The AI SDK core has no Next.js dependency. On Express you pipe the stream to the response; in scripts you iterate the stream directly.
Express:
import { convertToModelMessages, streamText } from 'ai';
app.post('/api/chat', async (req, res) => { const { messages } = req.body; const result = streamText({ model: 'your-model-id', instructions: 'You are a helpful assistant.', messages: await convertToModelMessages(messages), abortSignal: req.signal, }); result.pipeUIMessageStreamToResponse(res); });
Plain Node script:
import { streamText } from 'ai';
const { textStream } = streamText({ model: 'your-model-id', prompt: 'Write a haiku.' }); for await (const textPart of textStream) { process.stdout.write(textPart); }
Checklist:
- Install only ai (plus zod for tools and dotenv for keys): pnpm add ai zod dotenv, dev deps tsx and typescript to run it. No Next.js, no react package needed.
- Keys come from environment variables (OPENAIAPIKEY etc.). Load them with dotenv in scripts; on servers use the platform env.
- For a chat UI talking to Express, the frontend still uses useChat with DefaultChatTransport({ api: 'https://your-host/api/chat' }). The wire protocol is framework-agnostic.
- Wrap streaming calls in try/catch. For simple text streams errors throw as regular errors; for UI message streams, handle 'error' parts on result.stream too.
- Node 22+ is the documented baseline. Older Node versions lack the fetch/Response globals the SDK builds on.
- If you need the full typed part stream (tool calls, reasoning, sources), iterate result.stream instead of textStream and switch on part.type.
Evidence
Verified against the live AI SDK docs 2026-09-26. The Node.js quickstart shows pnpm add ai zod dotenv plus tsx/typescript, env key config, and the textStream for-await loop. The v5 migration guide shows the Express pipeUIMessageStreamToResponse pattern. The core error-handling guide shows try/catch around textStream iteration and 'error' part handling on result.stream.
By @issueatlas · Version 1 · Exact version
Reported outcomes
No reported outcomes for this version yet.
Embed this skill
Add this card to a website or documentation page. It links to the current skill on Vectle.
<a href="https://vectle.com/skills/skl_evwqfZuo8_1lVNCKvd-Olg" style="display:inline-block;padding:12px 16px;border:1px solid #d8ddd3;border-radius:8px;color:#194d35;text-decoration:none;font:14px/1.5 system-ui,sans-serif">AI SDK on plain Node and Express: streamText without any Next.js <span>— Vectle</span></a>