What does it answer from?

Only the sources you gave it: uploaded files, whole folders, or a website URL it crawls — mixed in any combination. It does not fall back on general knowledge when your documents do not cover something, which is the behaviour that makes a company bot trustworthy.

Does anything leave our server?

No. It runs entirely locally on Ollama with Postgres and pgvector on your own machine, with no external API call in the path. That is the reason this exists as a self-hosted product rather than another hosted chatbot service.

How long does it take to get a bot running?

One upload and one click produce an embeddable chatbot with a snippet you paste into the site. Adding more sources later is the same action again rather than a rebuild.

Can we run several bots for different departments?

Yes. Each one is created separately with its own sources, so support, HR and sales can have bots that only see the material they are supposed to see instead of one bot that knows everything about the company.

Why is there no public link to this one?

Because it is a self-hosted product rather than a site you sign up to — there is nothing to visit. The studio shipped the dashboard, the Ollama-backed retrieval and the embed flow; it runs on the customer's own infrastructure.

Products · Self-hosted

AI Chatbot MakerUpload a folder of documents.

One-click SaaS to build a company's own AI chatbot · upload a folder, point at a site feed, everything stays on your server.

Self-hosted

Internal build, no public URL

What it is

AI Chatbot Maker is a turnkey SaaS for spinning up company-private chatbots: upload a folder, point at a website feed, and get an embeddable chatbot that only answers from that data. The studio shipped the SaaS dashboard, the Ollama-backed local LLM stack, the multi-tenant pgvector store, and the Docker-image deploy.

What it does

Knowledge sources: uploaded files, folders, website URLs · mix any
100% local · Ollama + Postgres pgvector on-server, no external API
One-click chatbot creation with an embed snippet for the company's site
Docker-image deploy · 5 minutes to your own server
Multi-tenant SaaS mode · many companies one platform, strict RLS isolation

Who it is for

Live chatbot in 5 minutes, answering only from your own data

Nothing leaves the server · audit-ready, GDPR-compatible

One platform, many clients · SaaS model with multi-tenant isolation

Embed snippet for the company site · no integration project needed

How it works

01 · Solve the GDPR + speed-to-live conflict.
OpenAI integrations leak data; bespoke chatbot builds take 6 months. We scoped a SaaS that runs locally on the customer's server · GDPR-safe by default, one Docker image to deploy.
02 · FastAPI + Ollama + Postgres pgvector.
FastAPI carries the multi-tenant API, Ollama runs the local LLM, Postgres + pgvector handles per-tenant retrieval with row-level security · LangChain glues the retrieval-augmented generation pipeline.
03 · One Docker image, embeddable snippet.
Customer pulls a single image, runs one command, gets a dashboard. From there: upload data → click 'create chatbot' → paste the embed snippet on their site. 5 minutes end-to-end on a fresh box.

Before and after

The old way

With this

ChatGPT plugins don't know your company data · generic answers for everyone

Live chatbot in 5 minutes, answering only from your own data

OpenAI / Anthropic integration leaks data · hard to square with GDPR

Nothing leaves the server · audit-ready, GDPR-compatible

A custom chatbot build is 3-6 months · doesn't fit a mid-market budget

One platform, many clients · SaaS model with multi-tenant isolation

Training a company-specific model needs an ML team

Embed snippet for the company site · no integration project needed

Questions

What does it answer from?: Only the sources you gave it: uploaded files, whole folders, or a website URL it crawls — mixed in any combination. It does not fall back on general knowledge when your documents do not cover something, which is the behaviour that makes a company bot trustworthy.
Does anything leave our server?: No. It runs entirely locally on Ollama with Postgres and pgvector on your own machine, with no external API call in the path. That is the reason this exists as a self-hosted product rather than another hosted chatbot service.
How long does it take to get a bot running?: One upload and one click produce an embeddable chatbot with a snippet you paste into the site. Adding more sources later is the same action again rather than a rebuild.
Can we run several bots for different departments?: Yes. Each one is created separately with its own sources, so support, HR and sales can have bots that only see the material they are supposed to see instead of one bot that knows everything about the company.
Why is there no public link to this one?: Because it is a self-hosted product rather than a site you sign up to — there is nothing to visit. The studio shipped the dashboard, the Ollama-backed retrieval and the embed flow; it runs on the customer's own infrastructure.

Our other products

UseAIEasily JuriSafe SimulSpeak

Want something like this, built for you?Start a conversation