npm package discovery and stats viewer.

Discover Tips

  • General search

    [free text search, go nuts!]

  • Package details

    pkg:[package-name]

  • User packages

    @[username]

Sponsor

Optimize Toolset

I’ve always been into building performant and accessible sites, but lately I’ve been taking it extremely seriously. So much so that I’ve been building a tool to help me optimize and monitor the sites that I build to make sure that I’m making an attempt to offer the best experience to those who visit them. If you’re into performant, accessible and SEO friendly sites, you might like it too! You can check it out at Optimize Toolset.

About

Hi, 👋, I’m Ryan Hefner  and I built this site for me, and you! The goal of this site was to provide an easy way for me to check the stats on my npm packages, both for prioritizing issues and updates, and to give me a little kick in the pants to keep up on stuff.

As I was building it, I realized that I was actually using the tool to build the tool, and figured I might as well put this out there and hopefully others will find it to be a fast and useful way to search and browse npm packages as I have.

If you’re interested in other things I’m working on, follow me on Twitter or check out the open source projects I’ve been publishing on GitHub.

I am also working on a Twitter bot for this site to tweet the most popular, newest, random packages from npm. Please follow that account now and it will start sending out packages soon–ish.

Open Software & Tools

This site wouldn’t be possible without the immense generosity and tireless efforts from the people who make contributions to the world and share their work via open source initiatives. Thank you 🙏

© 2026 – Pkg Stats / Ryan Hefner

next-ai-stream

v0.0.8

Published

Stream AI chat responses in Next.js with TypeScript

Readme

next-ai-stream

pnpm add next-ai-stream
npm install next-ai-stream
yarn add next-ai-stream

Overview

next-ai-stream is a lightweight, plug-and-play package for streaming AI responses in Next.js 15 projects using the App Router. It simplifies integrating real-time AI chat powered by OpenAI (or compatible APIs like xAI).

With just a few lines of code, you can:

  • Set up an AI chat API route in Next.js.
  • Stream responses to the frontend with hooks.
  • Support any OpenAI-compatible API (like xAI).

This package handles the complex parts of streaming AI messages, so you can focus on building your app. 🚀

Usage

1. Add OpenAI Client

// src/ai/index.ts
import OpenAI from "openai";

const client = new OpenAI({
  apiKey: process.env.API_KEY,
  baseURL: "https://api.x.ai/v1", // can use xAI API since it's compatible with OpenAI SDK
});

export default client;

2. Add Next.js API Route

// src/app/api/chat/route.ts

import client from "@/ai";
import { createAIChatStreamRouteHandlers } from "next-ai-stream/server";

export const dynamic = "force-dynamic";

export const { GET, POST } = createAIChatStreamRouteHandlers({
  client,
  model: "grok-2-latest", // use whatever model you want
});

3. Start AI Chat Stream

// src/app/page.tsx

"use client";

import { useState } from "react";
import { useAIChatStream } from "next-ai-stream/client";

function HomePage() {
  const [inputText, setInputText] = useState("");

  const { messages, submitNewMessage, loading } = useAIChatStream({
    apiEndpoint: "/api/chat",
    systemPrompt: `You are a helpful AI assistant. Be very succinct in your responses because I don't want drop all my cash on tokens.`,
  });

  const handleSubmit = (e: React.FormEvent<HTMLFormElement>) => {
    e.preventDefault();
    if (loading) return;

    submitNewMessage(inputText);
    setInputText("");
  };

  return (
    <div className="min-h-screen flex flex-col items-center p-8 pb-36">
      <div className="flex flex-col gap-8 w-full max-w-4xl">
        {messages.map((message, index) => {
          return (
            <div
              key={index}
              className={`p-4 rounded-2xl max-w-[70%] ${
                message.role === "user"
                  ? "bg-slate-800 text-white ml-auto"
                  : "bg-slate-900 text-gray-200 mr-auto"
              }`}
            >
              {message.content as string}
            </div>
          );
        })}
      </div>

      <div className="fixed bottom-0 w-full bg-black/90 backdrop-blur-sm py-6">
        <form
          onSubmit={handleSubmit}
          className="flex items-center justify-center gap-4"
        >
          <input
            className="rounded-lg p-4 bg-slate-800 w-[500px]"
            value={inputText}
            onChange={(e) => setInputText(e.target.value)}
          />

          <button
            className={`bg-slate-800 p-4 rounded-lg ${
              loading ? "opacity-50" : ""
            }`}
            type="submit"
            disabled={loading}
          >
            Submit
          </button>
        </form>
      </div>
    </div>
  );
}

export default HomePage;