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

generative-ui-kit

v0.1.0

Published

Provider-agnostic generative UI components (secure forms, questions, tables, dashboards) and a GenerativeChat widget for tool-calling LLM chat apps.

Readme

generative-ui-kit

Provider-agnostic generative UI components (secure forms, questions, tables, dashboards) and a GenerativeChat widget for tool-calling LLM chat apps. The library never calls an LLM itself — your host app supplies an onSend adapter and owns the actual provider integration (Anthropic, OpenAI, a local model, whatever), so this works with any provider or agent framework.

Install

npm install generative-ui-kit

Peer dependencies: react and react-dom (^18).

What's in the box

  • GenerativeChat — the chat widget (turns, suggestion chips, normal or float launcher-bubble layout)
  • GenerativeUIRouter — dispatches a render payload to a renderer map, for building a custom chat UI instead of using GenerativeChat
  • 4 default renderers, each with a matching tool schema + handler: SecureFormRenderer (request_form), QuestionRenderer (ask_question), TableRenderer (request_table), DashboardRenderer (request_dashboard)
  • BlackboardRenderer (request_diagram) — exported but not in defaultRenderers; register it yourself if you want diagrams

Quick start

Server side — register the tool definitions with your LLM provider, and its handlers to turn a tool call into a render payload:

import { formToolDefinition, formToolHandler, /* ... */ } from "generative-ui-kit";

const tools = [formToolDefinition /* ... */];
const { render, forModel } = await formToolHandler(toolCallInput);
// `render` -> send to the client. `forModel` -> the tool_result you feed back to the LLM.

Client side — render whatever payload comes back:

import { GenerativeChat, defaultRenderers } from "generative-ui-kit";

<GenerativeChat
  onSend={onSend}          // async generator yielding ChatStreamEvent
  suggestions={suggestions}
  renderers={defaultRenderers}
  layout="normal"           // or "float" for a corner launcher bubble
/>;

SecureFormRenderer and onSubmit

formToolHandler's forModel output never contains field values — only a session_id and status, so the LLM can't see what the user typed. Because of that, onSubmit can't be supplied by this library or by the render payload (functions don't survive JSON) — your host app must inject it itself, wherever it turns a render payload into props, before handing it to GenerativeUIRouter:

const props = payload.component === "SecureFormRenderer"
  ? { ...payload.props, onSubmit: (values) => myBackend.submit(payload.props.sessionId, values) }
  : payload.props;

Field.validation (pattern/minLength/maxLength/min/max) enforces native browser constraint validation client-side; anything more complex — a lookup against another system, cross-field rules — belongs in your own submit endpoint.

License

MIT