The AI support desk that
never makes things up
momo reads your website and documents, answers customers in seconds, and hands the rest to your team with the details already collected.
Yes. Opened items can be returned within 30 days in the original packaging. Start the return from your order page and we email you the label.
Made for your business
Whatever you sell, customers get a real answer
Shops, software, local services. momo answers from your own content and checks live data where it can, so nobody waits for office hours.
Order #4821, sam@studio.co: where is it?
It shipped yesterday and arrives Thursday.
Looked up live in ShopifyHow do I invite a teammate?
Open Settings, then Team, then Invite. They get an email.
From your docs: TeamCan you come Saturday?
I need a few details first. What is your address?
Details collected, passed to youWhy shops and teams choose momo
A chatbot that guesses costs you customers. momo is built to be right, or to tell you it is not sure.
Every answer shows its work
Each reply links the pages and files it came from, so you can check it in one click. No black box.
Trust you can verify, not take on faith.
Yes, the Pro plan covers a team of 12. Pro includes 15 seats.
It says "I'm not sure" instead of guessing
Below its confidence threshold, momo asks for details and brings in your team instead of inventing a refund policy.
Wrong answers stop reaching your customers.
It does things, not just FAQs
"Where's my order?" is answered live from your shop, as a clear status card instead of a canned paragraph.
Order status and product info, answered live from your store.
It shipped yesterday and arrives Thursday. Here is where it is:
Every conversation
What happens when someone asks momo something
The same accuracy gate runs every time, whether the answer ships or a human takes over.
0-2s
momo drafts an answer from your sources
Pulled from your crawled site, docs, or Q&A pairs, never from general knowledge.
Gate
The accuracy gate checks it against those sources
If the draft is not backed by what it found, it does not ship.
Confident
A sourced answer reaches the visitor
With links back to the page it came from.
Not confident
It says so and hands off
The conversation becomes a ticket in the inbox instead of a guess.
Your team picks up with the details already in hand.
Sam wants to change the delivery address on an open order.
It keeps learning
It gets smarter on its own. You never feed it twice.
momo reads your site once. After that, every conversation teaches it something new, and every answer your team gives can become part of what it knows.
How it works
No flows to draw, no decision trees. Three steps, and it is live.
Step 1
Paste your website address
momo reads your site, your PDFs and your help articles, and starts answering from them in about a minute.
From paste to live, without a consultant.
acme.comLearn my siteReading your site (example)Done in 52 seconds142website pages18pages of PDF36help articlesStep 2
Add one line to your website
Paste a single line of code. The chat appears on your pages, in your colours.
It looks like your brand, not ours.
Paste once, before the closing body tag<script src="…/momo.js" defer></script>Hi! Ask me anything about Acme.Pick your colourStep 3
Your team only sees what is left
The easy questions are answered for you. The rest arrive in one clean inbox, each with a summary and the details already collected.
Hours back every week.
100 customer chats in a week (example)72answered by momo, nobody needed28waiting for you, each with a brief
Connected to what you already use
momo learns from the content you already have and works where your customers already are. One agent, everywhere.
momoAnswers from your own content
It learns your site and documents, so it answers like someone who read everything.
Works where customers already are
Website, email, Slack and your store, all served by the same agent.
Your team stays in the loop
Anything it cannot answer reaches your team with the details already collected.
What it adds up to
More answers, fewer interruptions
What a small store could see in a month. These are example figures until we publish real customer results.
MIT
Open source license
<30KB
Widget script size
~1 min
To first answer
Everything in the open core
Self-hosted, MIT-licensed, and honest: real services, no artificial limits.
- Website crawl, file upload, Q&A pairs, text snippets
- Answers with sources and an accuracy gate
- Embeddable widget, one script tag, under 30KB
- Shopify order-status action
- Inbox with live takeover and simple tickets
- Teach button on every human reply
- Unlimited team members, no seat cap
- REST API and webhooks
Open core, self-hosted
- MIT licensed, full source access
- Bring your own AI model key
- Unlimited team members
- Runs on your own infrastructure
Cloud, early access
- Same open-core loop, managed for you
- AI usage included in the price
- EU hosting
- Priority support
Why teams switch from Chatbase
A side-by-side look at what you pay and what you get.
Based on Chatbase's public pricing and product pages, momobot's own research (2026-09-21).
Open by default
No lock-in, no black box.
MIT licensed
Fork it, self-host it, read every line. No paid tier required to see the code.
Self-hosted or cloud
Run it on your own server with your own AI key, or use the managed cloud, same code either way.
Your data stays yours
Self-hosted, nothing leaves your infrastructure. On cloud, EU hosting and no training on your content.
Why we built this
Support bots that guess are worse than no bot at all
Most AI support tools are optimized to always answer, because a confident-sounding reply looks good in a demo. That is how you end up with a bot inventing a refund policy that does not exist.
momo is built around the opposite instinct. Every answer is checked against the sources it is supposedly drawn from before it ever reaches a visitor. If the confidence gate does not clear, momo says so and hands the conversation to a human instead of guessing.
We are building it in the open, MIT licensed, because a support desk that touches customer trust should not be a black box you have to take on faith.
Unlimited
seats, on every plan
No per-agent fee, no per-resolution credit system. Add your whole team without doing the math first.
Simple pricing, no per-resolution fees
Start free. Upgrade when your support volume grows. Every plan is flat: one number to watch, AI conversations.
Free
Try momo with real visitors.
€0€0 forever
- 30 AI conversations, one-time
- 1 agent, 1 team member
- Website widget
- Helpdesk inbox
- Basic analytics
- 2 MB of knowledge, 10 sources
Starter
One agent, steady traffic.
€29€27/mo
- 500 AI conversations / month
- 1 agent, 2 team members
- Website widget and email
- Helpdesk inbox and Help Center
- Basic analytics
- No momo badge
- 20 MB of knowledge, 50 sources
Growth
More agents, more channels.
€129€118/mo
- 2,000 AI conversations / month
- 3 agents, 5 team members
- Slack, Shopify, WhatsApp, Instagram, Messenger
- API, Zapier and webhooks
- Advanced analytics
- 100 MB of knowledge, 200 sources
Scale
High volume, every channel.
€399€366/mo
- 6,000 AI conversations / month
- 10 agents, 10 team members
- Every channel
- API, Zapier and webhooks
- Advanced analytics
- 500 MB of knowledge, 1,000 sources
Frequently asked questions
Is momo open source?
Yes. The core loop � the widget, answers with sources, the accuracy gate, the inbox with takeover, simple tickets and Teach � is free and self-hostable forever. The commercial cloud adds things that cost us money to run or connect to other tools, like AI keys included and JS-rendering crawling.
How is momo different from Chatbase?
Every answer carries sources and a confidence level. Below the threshold, momo says "I am not sure" and hands off to a human instead of inventing an answer. Pricing is flat with unlimited seats, not a per-resolution fee.
Do I need my own AI model key?
On the open core, yes � bring your own key for any provider supported by the Vercel AI SDK. The commercial cloud includes AI usage in the price, so no key is needed there.
What happens when the AI is not confident in an answer?
It says so in plain text � "passed to the team" � instead of guessing, and the conversation becomes a ticket in the inbox. A human replies, and one click (Teach) turns that reply into approved knowledge so the bot improves.
Build a support desk that doesn't lie to your customers
Get in touch — early access is open.