AI tools, scored for your job
Get paid to train AI
🤝 You're in the Free & Open Source library — community-built tools you can use without paying. A different concept from our scored AI directory.
Home › Free & Open Source › Insurance › NLUX
✦ Free & open sourceInsurance

NLUX

A React and JavaScript UI library for building conversational LLM interfaces for web applications.

Embed Conversational AI Interfaces into Web Apps

Build customizable chat interfaces for insurance portals using React, Next.js, or vanilla JavaScript.

Free forever · source-available · MPL-2.0 (modified) (source-available, not OSI-approved)
✓ Light setup✓ Browser-based✓ Real-time collaboration
7
ZEKAI
Flexible frontend AI chat SDK.
Free & open source · Insurance
Ease of setup8
Usefulness8
Maintenance5.5
Community6.5
★ 1,383
GITHUB
Nov 2025
UPDATED
MPL-2.0 (modified) (source-available, not OSI-approved)
LICENSE
🛠 Don't want to self-host? We can set it up →
⚡ Quick answer

NLUX is an open-source JavaScript and React library designed to create conversational chat components for web applications. It allows insurance engineering teams to build customer-facing assistant interfaces that connect directly to models from OpenAI, Hugging Face, or custom LangChain backends. You should use it if you need complete layout control over chat components without building UI primitives from scratch.

Runs on
Web
Hosting
Cloud or self-host
Languages
TypeScript
License
MPL-2.0 (modified) (source-available, not OSI-approved)

What it is

The library provides pre-built React components, hooks, and adapters to stream model output, format Markdown responses, and highlight code or structured data in real time. It supports React Server Components and Generative UI, allowing you to render dynamic widgets like claim status cards directly inside chat streams. You can integrate it with Next.js, Vite, or plain HTML web setups.

Who it's for

This tool suits frontend developers and technical teams in insurance companies who need to embed custom AI chat widgets into policyholder portals or internal agent tools. It is not suitable for non-technical users looking for a drag-and-drop no-code chatbot builder, as implementation requires JavaScript coding.

Key features

Pre-Built LLM Adapters

Connect your interface directly to OpenAI, Hugging Face Inference, or LangChain LangServe APIs with minimal code.

Generative UI Support

Render interactive React Server Components such as policy option selectors or claims timeline widgets directly inside chat streams.

Real-Time Streaming Parser

Parse and render incoming Markdown streams instantly as models generate responses to maintain responsive UI interactions.

Customizable Personas and Themes

Configure avatar images, participant names, and visual styling through modular CSS themes to match corporate brand guidelines.

How to start

Up and running in 3 steps

1
Run 'npx nlux-cli create react my-app' or install '@nlux/react' into an existing codebase.
2
Configure an LLM adapter like '@nlux/langchain-react' or create a custom adapter pointing to your insurance AI backend.
3
Add the AiChat component to your UI and pass user persona configurations and chat adapters.
Real talk

Our honest verdict

What's great

  • Zero core UI dependencies keep frontend bundle sizes minimal and fast to load.
  • Provides built-in stream parsing for raw Markdown and code syntax highlighting.
  • Includes scaffolding tools via nlux-cli to quickly initialize Next.js or React projects.
  • Offers first-class support for React Server Components and Generative UI.

Where it falls short

  • Requires custom web development skills to integrate into existing applications.
  • You must host and pay for your own backend LLM API endpoints or server infrastructure.
  • Does not include built-in user authentication or database storage for chat history.
Cost

Pricing & license

NLUX is free to use for personal and commercial applications under its custom license. The only operational costs come from hosting your web application and funding the underlying LLM API usage or model infrastructure.

Paid work

Open remote AI-training roles

880 open remote AI-training roles, updated November 16, 2026; most pay $20–$175 an hour. Zekai lists them free; the application goes to the employer’s platform.

See all open roles →
Compare

Alternatives

Get more

Use it, or have us set it up

📄 Free PDF: NLUX for Insurance
A plain-language guide to getting your first result. Sent to your inbox.
🔔 64 people want a full video tutorial — add your vote
🛠 Don't want to set it up yourself?
We'll install, host & configure NLUX for you — and train your team.
Get it done for you ↗
Questions

FAQ

Can I connect NLUX to a private, self-hosted LLM backend?

Yes, NLUX provides a flexible adapter interface so you can route user inputs to any custom backend server or internal API endpoint.

Does NLUX store chat logs or sensitive insurance customer data?

No, NLUX operates entirely as a client-side frontend library and does not log, store, or transmit data outside your configured backend endpoints.

Radar

Latest AI news

✉️ The weekly free toolkit
The best new free & open-source tools for Insurance — one short email a week, in your language.
Free · 1 email/week · unsubscribe anytime
Get paid to train AI →

See Zekai first in Google