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

@geepers/chat

v2.1.1

Published

Multi-provider LLM chat. Drop-in widget OR full app: npx @geepers/chat spins up a server with 10 providers. Streaming, history, markdown. No framework required.

Readme

@geepers/chat

Full-featured chat UI for multi-provider LLM APIs. Drop a ChatUI instance into any container and get streaming chat, conversation history, markdown rendering, and provider switching. No framework required.

Supports 9 providers out of the box: xAI, Anthropic, OpenAI, Cohere, Mistral, Perplexity, HuggingFace, Google Gemini, and Ollama.

Built from the Slate/Camina implementation in IO Suite.

Install

npm install @geepers/chat

Usage

import ChatUI from '@geepers/chat';

const chat = new ChatUI('#app', {
  gateway: 'https://api.dr.eamer.dev/v1',
  apiKey: 'sk_...',
  provider: 'anthropic',
  welcomeHints: [
    { label: 'How do LLMs work?', prompt: 'Explain how LLMs work in plain language.' },
  ],
});

That's it. The element at #app becomes a full chat interface with sidebar history, streaming responses, and a mobile-responsive layout.

Headless mode

Use ChatCore without any DOM if you want to build your own UI on top:

import { ChatCore } from '@geepers/chat';

const core = new ChatCore({
  gateway: 'https://api.dr.eamer.dev/v1',
  apiKey: 'sk_...',
  provider: 'xai',
});

core.on('stream-chunk', (e) => {
  process.stdout.write(e.chunk);
});

await core.send('Hello!');

Script tag (no build step)

<div id="app" style="height: 600px;"></div>
<script src="https://unpkg.com/@geepers/chat/dist/index.iife.global.js"></script>
<script>
  new GChat.ChatUI('#app', { apiKey: 'sk_...' });
</script>

Config

interface ChatConfig {
  gateway?:       string;       // API base URL (default: https://api.dr.eamer.dev/v1)
  apiKey?:        string;       // Falls back to localStorage 'api_key' if not set
  provider?:      Provider;     // Starting provider (default: 'xai')
  model?:         string;       // Override the default model for the provider
  systemPrompt?:  string;       // Prepended to every conversation
  theme?:         'light' | 'dark' | 'auto';  // Default: 'auto'
  welcomeHints?:  WelcomeHint[];  // Hint chips on the welcome screen
  storageKey?:    string;       // localStorage key prefix (namespace multiple instances)

  // Callbacks
  onMessage?:     (msg: Message) => void;
  onError?:       (err: Error) => void;
  onStreamStart?: (messageId: string) => void;
  onStreamEnd?:   (msg: Message) => void;
}

ChatUI methods

| Method | Description | |--------|-------------| | send(text) | Send a message programmatically | | stop() | Abort the current stream | | focus() | Focus the message input | | setProvider(p) | Switch provider (updates UI) | | setSystemPrompt(s) | Update system prompt (updates UI) | | newConversation() | Clear history and start fresh | | destroy() | Remove the UI from the DOM | | chatCore | Access the underlying ChatCore directly |

Providers

| Key | Model | Label | |-----|-------|-------| | xai | grok-4 | xAI Grok 4 | | anthropic | claude-sonnet-4-6 | Claude Sonnet 4.6 | | openai | gpt-5.4 | OpenAI GPT-5.4 | | cohere | command-r-plus-08-2024 | Cohere Command R+ | | mistral | mistral-large-latest | Mistral Large | | perplexity | sonar-pro | Perplexity Sonar Pro | | huggingface | Qwen/Qwen3.5-9B | HuggingFace Qwen 3.5 | | gemini | gemini-2.5-flash | Google Gemini 2.5 | | ollama | llama3.2:3b | Ollama (Local) |

CSS customization

The UI uses CSS custom properties scoped under .gchat-root. Override any token:

.gchat-root {
  --gchat-accent: #e11d48;       /* primary color */
  --gchat-sidebar-w: 300px;      /* sidebar width */
  --gchat-font: 'Inter', sans-serif;
}

License

MIT — Luke Steuber