New Ragen Brain turns messy documents into a knowledge base

The AI assistant for your company

Your team asks.
Ragen answers from your documents.

Every answer shows its source. Every person sees only what they’re allowed to. And it all runs on your own servers, in the EU.

Book a 30-min demo Deploy it yourself
of the stack can run in the EU
100%
interface languages
17
per-seat fees
€0
open-source licence
Apache 2.0

One question, two ways

Stop hunting through folders. Start answering clients.

A sales rep gets a question on a call. Here’s what happens next, with and without Ragen.

Without Ragen

  1. Search four folders in Drive
  2. Find two versions of the terms. Which one is current?
  3. Ask on Slack, wait for the one person who knows
  4. Promise the client an answer tomorrow

With Ragen

  1. Ask in plain language, the way you’d ask a colleague
  2. Get the answer from the current document, not an old copy
  3. Click the source to check it in one second
  4. Answer the client while you’re still on the call

Why companies choose Ragen

Three things change on day one

Experts stop answering the same question twice

HR uploads the leave policy once. From then on Ragen answers every employee, at any hour, and your experts get their time back.

Your data never leaves your network

Runs on your servers or your own AWS, Azure or GCP account. Each person sees only the files they already have access to.

Security overview for your IT team

AI costs you can predict

No per-seat licences. Set a monthly limit for your organisation and Ragen stops when it’s reached. No surprise invoices.

Estimate your costs

Use cases

An AI Assistant for every team

Sales assistant

Reps answer during the call, not the day after

Offers, price lists, contract terms and client history from HubSpot in one answer. When you upload a new price list, the assistant knows it right away.

  • Price lists
  • Contract terms
  • HubSpot deals
See who Ragen is for

The platform

One knowledge base. Four ways to use it.

Upload your documents once. Your team, your customers and your AI agents all get answers from the same source, with the same permissions.

For your team

AI Assistant

Separate assistants for HR, sales or compliance. Works on desktop, tablet and phone. No training needed.

Try the live demo

For your customers

Website chatbot

Answers product and policy questions 24/7. One line of code on your site, limited to the domains you allow.

For your AI tools

Connector for AI agents

Already using Claude, Cursor or your own AI agents? They can ask Ragen too (via MCP) and get cited answers, within the permissions of the person whose API key they use.

Explore
New

Before the answers

Ragen Brain

Turns scattered, messy documents into clean knowledge pages. Flags contradictions and outdated files. Nothing goes live without human approval.

Explore

Admin panel

Costs under control. You see what works.

  • A hard monthly limit for the organisation: tokens, cost or messages. Queries stop at the limit.
  • Per-team limits on request rates and on which AI models a team may use.
  • Any AI model: commercial via your own keys, or open models on your own servers. Switch any time.
  • See what’s used: questions per day, the most cited documents, answers people rated down.
  • Audit log of changes to permissions, roles, documents and API keys.
The Knowledge analytics screen in the Ragen admin panel: questions per day, unique users, share of positive ratings and the most cited documents
Illustrative data

Compare

Why choose Ragen over a hosted AI assistant

Why choose Ragen over a hosted AI assistant
Feature Typical hosted AI assistant Ragen.ai
Where your documents live Typical hosted AI assistant Vendor’s cloud Ragen Your servers, EU region of your choice
Pricing Typical hosted AI assistant Per seat, per month Ragen No seat fees, a hard monthly limit
Permissions Typical hosted AI assistant Workspace level Ragen Per file and folder, on every answer
AI model Typical hosted AI assistant The vendor’s choice Ragen Any, and you can switch it
Personal data masked before the model Typical hosted AI assistant Rarely Ragen Built in, opt-in; Polish IDs today, more recognisers can be added
Source code Typical hosted AI assistant Closed Ragen Open source: audit it, keep it for good
Compare RAG platforms in detail

European by design

Every layer can run with an EU provider

Self-hosting keeps your documents where you install Ragen. The models are the other half. This is where each layer runs when nothing may leave EU jurisdiction. Not every default is European, so it is a setting you choose deliberately.

Every layer can run with an EU provider
Layer Runs in the EU on Setting
Hosting Runs in the EU on: Scaleway (FR), OVHcloud (FR), Hetzner (DE), IONOS (DE) or your own servers
Database Runs in the EU on: PostgreSQL on your servers
Vector search Runs in the EU on: Qdrant, self-hosted on your servers Setting: QDRANT_URL
Object storage Runs in the EU on: RustFS (bundled) or Scaleway Object Storage in Paris, Amsterdam or Warsaw
Document parsing Runs in the EU on: Docling, on your own hardware Setting: DOCLING_STRICT=1
Embeddings Runs in the EU on: bge-multilingual-gemma2 on Scaleway (the default) Setting: EMBEDDINGS_MODEL
Reranking Runs in the EU on: Qwen3 on Scaleway, or your own reranker Setting: RERANK_PROVIDER
Answers, rephrasing, summaries Runs in the EU on: Mistral Small 3.2 or gpt-oss-120b on Scaleway, or open models on your own GPU Setting: DEFAULT_MODEL
Encryption keys Runs in the EU on: Scaleway Key Manager Setting: SCW_KEY_MANAGER_REGION
PII masking Runs in the EU on: Presidio, on your servers (optional) Setting: PRESIDIO_ANALYZER_URL

  • Your call, outside the EU

    Want the strongest commercial models? Point any role at Azure OpenAI, AWS Bedrock or Google Vertex AI. They are US companies, even in an EU region, so you decide role by role, and switching back is one variable.

  • Your team's languages

    The interface comes in 17 languages, including Dutch, Norwegian, Danish, Swedish and Finnish. Search runs on a multilingual model, so a question in one language finds the answer in a document written in another.

  • GDPR and the EU AI Act

    Ragen runs on your infrastructure, so you stay in control of the data and no third party processes it, unless you route a model to one. That does not make a deployment compliant by itself, but it keeps the list of processors short, and every answer cites its source.

Configure the EU stack

Deploying Ragen in your company? Talk to the team that built it.

A 30-minute call with the engineers behind Ragen: your infrastructure, your data requirements and which EU providers fit them.

Book a call

Integrations

Works with the tools you already use

It works both ways. Ragen reads from the tools you already use, and your AI agents read from Ragen.

Into Ragen: your sources

Out of Ragen: the MCP server

Agents in Claude Desktop, Cursor or your own code ask Ragen through its MCP server and get cited answers, only from documents the owner of the API key may open.

How the MCP server works

Missing a tool? Tell us what you need

Security

Built to pass your IT security review

The questions your security team will ask, answered in one document.

Read the security overview

  • On your infrastructure

    Your own servers or your AWS, Azure or GCP account, in any region. Nothing reports back to us.

  • Permissions per file

    Checked on every answer, for people and for AI agents: an agent sees only what the owner of its API key may open. Restricted files never reach the model.

  • Encryption with your keys

    Conversations encrypted with a key from your AWS KMS or Scaleway Key Manager. You hold the keys, not us.

  • Personal data masked

    Optional: PESEL, NIP, REGON and card numbers are masked before a message or document reaches the model or the index, with a policy per organisation. Changes to permissions and documents go to the audit log.

What leaves your network

  • Stored data stays. Documents, the database, the search index, conversations and encryption keys live on infrastructure you run. Nothing reports back to us.
  • Model calls depend on your choice. A model on your own servers: nothing leaves. A commercial API: the question and the document fragments needed to answer it, never the whole knowledge base.
  • Parsing is local. Docling reads your files on your hardware. Set DOCLING_STRICT=1, or a Docling failure sends the PDF to an external model.
  • Extras are opt-in. Content moderation (OpenAI), connectors such as Slack or HubSpot, and speech send data out only once you switch them on.
The full breakdown, with pointers to the code

For technical teams

Set up with one command. No GPU required.

Under the hood, Ragen is an open-source RAG platform (Apache 2.0) that your IT team can inspect, extend and run anywhere.

OpenAI-compatible API
Existing clients work after a base URL change.
Docker, Helm, Terraform
Deploy the way your team already does.
Measured search quality
Test sets included in the repo.
50 documented decisions
Architecture tests fail the build if rules break.
Star on GitHub Read the docs
npx create-ragen-app Node 24.15+ or 26+
Example: calling Ragen with the OpenAI SDK
// Your existing OpenAI client, pointed at Ragen
import OpenAI from 'openai'

const ragen = new OpenAI({
  baseURL: 'https://ragen.your-company.eu/v1',
  // the key is scoped to your HR assistant
  apiKey: process.env.RAGEN_API_KEY,
})

const res = await ragen.chat.completions.create({
  messages: [{ role: 'user', content: 'How do I request leave?' }],
})

Getting started

Get started in a few simple steps

  1. A 30-minute call

    We look at your documents and pick the first use case worth automating.

  2. Install on your servers

    We deploy it with your IT team, or you set it up yourself with one command.

  3. Your team starts asking

    They log in, ask a question and get an answer with sources. That’s the training.

See Ragen on your own documents

30 minutes, no commitment. We’ll show you which questions it can take off your team’s plate.

Book a 30-min demo View on GitHub

FAQ

Questions we hear most

Something else? Talk to an engineer

All questions

ChatGPT answers from general internet knowledge. Ragen answers only from your documents and tools, shows the source of every answer, respects per-file permissions and runs on your own infrastructure.

From the blog

All posts

Practical AI in companies, once a month

Implementation tips and Ragen updates. No spam.

Privacy policy · Newsletter policy