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

@pubwiki/sandbox-llm-client

v0.1.2

Published

WikiRAG client library for sandbox environments - provides AI game engine capabilities

Downloads

22

Readme

@pubwiki/sandbox-llm-client

WikiRAG client library for sandbox environments. This library provides a convenient interface for user game code to interact with the AI game engine powered by wiki-rag-lab.

Features

  • Multi-turn Chat: Chat with history management
  • Streaming Responses: Real-time streaming chat
  • Entity Management: Query and manage game entities
  • Reactive Data: Automatic synchronization of entity state
  • Lua Execution: Execute Lua code for game logic
  • Type-safe: Full TypeScript support

Installation

npm install @pubwiki/sandbox-llm-client

Usage

import { initWikiRAG } from '@pubwiki/sandbox-llm-client'

// Provider is injected by sandbox-client
const provider = (window as any).__wikiRAGProvider
const rag = initWikiRAG(provider)

// Chat with history
const result = await rag.chat("Tell me about the world", "session_1")
console.log(result.text)

// Streaming chat
for await (const chunk of rag.chatStream("Continue the story", "session_1")) {
  if (chunk.type === 'stream_chunk') {
    process(chunk.chunk)
  }
}

// Query entities
const result = await rag.query("Who is the protagonist?")

// Access reactive entity data
await rag.reactive.entities.allsync()
const protagonist = rag.reactive.entities.get("2")
console.log(protagonist.components.Identity.properties.true_name)

// Watch for changes
rag.reactive.entities.watch((key, oldValue, newValue) => {
  console.log(`${key} changed from ${oldValue} to ${newValue}`)
})

API Reference

WikiRAGClient

The main client class for interacting with WikiRAG.

Methods

  • chat(message, historyId?, preset?, options?) - Multi-turn chat with history
  • chatStream(message, historyId?, preset?, options?) - Streaming chat
  • query(message, preset?, options?) - Single query without history
  • getEntityOverview(entityId) - Get entity overview
  • listEntities() - List all entities
  • getHistory(historyId) - Get chat history
  • setHistory(historyId, messages) - Set chat history
  • clearHistory(historyId) - Clear chat history
  • executeLua(code) - Execute Lua code

Properties

  • reactive.entities - Reactive entity access

ReactiveEntities

Provides reactive access to entity data with automatic synchronization.

Methods

  • get(entityId) - Get reactive proxy for entity
  • allsync() - Synchronize all entity data
  • watch(callback, filter?) - Watch for entity changes
  • watchWith(filter, callback) - Watch with custom filter

Architecture

This library is part of a three-tier architecture:

  1. Main Site (chatbot-ui) - Manages WikiApp instance and RDF storage
  2. Sandbox (sandbox-client) - Provides secure execution environment
  3. User Game Code - Uses this library to interact with AI engine

Communication flows through MessageChannel/MessagePort for security and isolation.

License

MIT