Arevian product · alpha 2026

A support chat thatnever invents.

Mimir answers strictly from your knowledge base — and when there is no answer in it, says so and calls a human. It runs on your own server, in one Docker command, and everything it learns stays there.

See what it can do
One line of script on the site. No subscription to a foreign SaaS, no customer data leaving your perimeter.
MMimironline

Do you deliver to Gyumri on Saturday?

Yes — Saturday orders placed before 2pm arrive the same day.

Can I pay in crypto?

There is nothing about crypto payments in my knowledge base, so I won't invent an answer. I'm bringing in a manager — right here in this chat.

Escalated to a manager
1line of code to install the widget
15 KBthe whole widget, no dependencies
0customer records leaving your server
models: GigaChat, YandexGPT, or your own local one
01

Why most site chatbots quietly hurt

The chat on a website is the first employee a customer meets. Three things usually go wrong with it, and all three cost more than the subscription.

01

It makes things up

A general-purpose model asked about your delivery terms will produce something plausible. Plausible is worse than silence: the customer believes it, and your manager finds out at the refund stage.

02

Your customers become someone's dataset

In a cloud chat service every dialogue, every phone number and every complaint lives on a third party's servers, under their terms, in their jurisdiction — and you are the one who signed the data-processing paperwork.

03

It cannot hand over to a person

The moment a conversation matters — a real order, an angry customer — the bot keeps talking. What is needed there is one button that puts a manager in the same window, with the history already in front of them.

02

From zero to a working assistant

There is no programming anywhere in this list. Everything after the first step happens in the admin panel.

01

One Docker command

On your server or your VPS. Nothing else has to be installed — the database, the search model and the admin panel are already inside the container.

02

Fill the knowledge base

Topics in a question-and-answer form: delivery, returns, prices, how to order. This is the only thing the bot is allowed to say — which is exactly why it can be trusted with customers.

03

Choose the model and the voice

GigaChat, YandexGPT, or a local model on your own hardware. Then the persona: the name, the greeting, how formally it speaks. The safety rules are built in and are not up for configuration.

04

Paste one line into the site

The widget picks up your colours, name and greeting by itself. There are ready instructions for Tilda, WordPress, Shopify, React, Vue, Next.js and Nuxt — and a live preview while you pick the colours.

03

What the manager gets, not just the visitor

A chatbot is only half the product. The other half is the desk your team works at every morning.

Answers only from your material

Semantic search finds the relevant topics, the model writes the answer from them. No relevant topic means an honest «I don't know» and an escalation — not an improvisation.

A co-pilot for the person on shift

Open a conversation and the panel already shows a summary of what the customer wants, the knowledge-base topics that apply, and three ready replies to send or edit.

Take over in one click

The manager joins the same conversation and the bot goes quiet. The customer never sees a handover, a ticket number or a second widget — it is the same window.

Leads instead of lost conversations

Contacts left in the chat become a list with a status, not a stream of messages. The dashboard opens on what is actually waiting today: open leads, escalations, dialogues since morning.

Your brand, down to the CSS

Accent, background, text, position, size, avatar — with a live preview. If that is not enough, there is a field for your own CSS, and the widget carries no framework to fight with.

Keys that nobody can read

The model provider's API key is stored encrypted and is decrypted only in memory at call time. It is masked in the logs, and it never appears in the interface after it is saved.

04

Where your data actually is

This is the question that decides whether a chatbot is allowed near real customers. The answer here is short and checkable.

Stays with you

The knowledge base in full, the history of every dialogue, customer contacts, the bot's settings and the widget's appearance — all of it in a volume on your own server.

Leaves only to answer

The provider you chose receives the question, the few excerpts found for it, and the answer. Not the base, not the history, not the contacts. Choose a local model and nothing leaves at all.

Search runs at home

The semantic search model runs locally on the CPU. Your knowledge base is never uploaded anywhere to be indexed — there is no vendor holding an embedding of your business.

You are the operator

Self-hosted means we have no access to personal data at all, and no agreement is needed with us about it. Your contract is with the model provider you picked, on their terms.

05

What it costs

A licence and support, not a subscription per conversation. You bring your own model key, so the more the bot talks the less each answer costs you — the opposite of how SaaS chat is priced.

SoloOn requestwe agree it in the first conversation

For one business with one site and a support inbox that is already too busy.

  • Full product, no feature gates
  • A year of updates
  • Installation guide and email support
BusinessOn requestwe agree it in the first conversation

For a company with several brands — and for the one who has to keep them all answering the same way.

  • Everything in Solo, on five sites
  • We build the first knowledge base with you
  • Deployment onto your server included
  • Priority support, two years of updates
AgencyOn requestwe agree it in the first conversation

For studios and integrators who want to sell this under their own name.

  • Unlimited client installations
  • White-label: your brand in the widget and the panel
  • A private channel to the developers
  • Perpetual updates while the product lives
06

The road to alpha

Mimir has been answering on real sites since spring 2026. Alpha is the moment we open it as a product with a licence, a price and someone answering the phone.

Now

Working on live sites: knowledge base, widget, manager desk, escalations, lead capture.

Autumn 2026

Closed alpha: first licensed installations, deployment done by us, weekly calls with every early client.

Winter 2026

Open alpha: self-service installer, importing a knowledge base from an existing site, multilingual answers.

2027

Beta: analytics on what customers actually ask, gaps in the knowledge base found automatically, CRM integrations.

07

Questions people ask

Can it work without sending anything to the cloud?

Yes. Point it at a local model running on your own hardware and the loop closes entirely inside your network: search is local by default, generation becomes local too.

What does the bot do when it does not know?

It says so plainly and offers to bring in a person, and the conversation appears in the panel as an escalation. It is not allowed to answer from outside the knowledge base, so there is no third option.

How long does it take to launch?

The installation is minutes. The honest answer is that the knowledge base takes the time: a usable first version is an afternoon of writing down what your support already repeats every day.

Will it fit our design?

Colours, position, size and avatar are settings with a live preview, and there is a field for your own CSS underneath. The widget has no framework of its own, so nothing fights your styles.

Which model should we choose?

Whichever you already have a contract with. Mimir speaks to GigaChat, YandexGPT, anything OpenAI-compatible, and local runtimes — switching provider is a select box, not a migration.

Let it answer on your site first.

Send us the five questions your support answers most often. We will show you Mimir answering them from your own material before you decide anything.

All studio products