llmchat
Built on LLM Gateway

AI support that
actually escalates.

One script tag. Any model. llmchat answers from your docs, hands off to your team when it can't, and threads replies through email — all from a single inbox.

Free tier · No credit card · Live in 5 minutes

index.html
<script
  src="https://llmchat-api.meetploy.app/widget.js"
  data-project="pk_live_xxxxxxxxxxxx"
  data-brand="#111827"
  defer
></script>
That's the whole integrationlive

Run any model — swap without touching code

OpenAIAnthropicGoogleMistralLlamaDeepSeekxAICohere

What you get

A focused support tool — not another platform to learn.

See how it compares →
01

Drop-in widget

One script tag. Loads in a shadow DOM so your styles never leak — and theirs never leak into you.

02

Answers from your docs

Paste your knowledge base or system prompt. The bot stays on-topic and admits when it doesn't know.

03

Escalates to humans

When the bot can't help, the conversation lands in your inbox with full context — no lost threads.

04

Email threading

Replies go out as email and customer responses thread back into the same conversation automatically.

05

Any model, any time

Built on LLM Gateway. Swap GPT, Claude, or a custom model per project — a config change, not a rewrite.

06

Self-hostable

Open architecture on serverless edge infra. Run the whole stack on your own account. No surprise vendors.

From zero to live

Three steps. About five minutes.

Step 01

Create a project

Sign up, name your bot, and grab your public key. A workspace is provisioned for you instantly.

Step 02

Paste the snippet

Drop one script tag before </body>. The widget mounts in an isolated shadow DOM and inherits your brand color.

Step 03

Watch it work

It answers from your docs, escalates when stuck, and routes every hand-off into a single team inbox.

Ship support today

Your docs already know the answers.
Let them reply.