Do our documents leave the company?

The engine runs on your hardware and reads your folders in place. With a local model, your documents and your questions stay on the machine. With a cloud model, the question and the relevant excerpts go to that provider, under your key or your Vertex project.

Do we need a server and an IT project?

No. Mnemosyne OS installs on a workstation, like any software. Deployment, volume licences and custom cartridges can be discussed, but you can try it without them.

Are our files moved or rewritten?

No. You point at a folder, and it is read in place. Files keep their name, their place and their format.

There are five of us. Is this for us?

Yes. On a drive shared by five people, nobody knows where anything is, just like in a large group. It is the same software in both cases.

Dossier 01 · Enterprise

An AI that finds your company documents, on your servers

Mnemosyne OS installs a document search AI in your company, on your own machines. It reads your documents and your conversations, and answers with the source. The data stays with you, encrypted with AES-256 if you turn it on, under your key. You decide what is kept.

Deployment, volume licences, custom cartridges: we discuss them directly. Tell us your constraints, and we will answer.

Download Mnemosyne OS See the application

Windows, macOS and Linux.

For which size

1 to 10

Small team

A shared drive, and nobody to tidy it.
10 to 250

Mid-sized

Documents that never meet. One vault per domain.
250 and up

Large account

On your machines, in your jurisdiction.
All three

The same software

The install and the licence change. The memory does not.

Inside the company

Thousands of documents, and nobody knows where anything is

Your folders

Fifteen years of shared folders, exports, three versions of the same contract. You point at the folder: Mnemosyne OS reads it in place, without moving or changing your files.

Your question

You ask in your own language. The answer cites the source document, even when it uses different words from yours.

The links

When the machine is idle, the engine rereads what it kept and links documents together. A map shows those links.

To start

You can start alone, on your own computer, without IT. One vault per subject is enough.

Questions

What we are asked before we start

Do our documents leave the company?: The engine runs on your hardware and reads your folders in place. With a local model, your documents and your questions stay on the machine. With a cloud model, the question and the relevant excerpts go to that provider, under your key or your Vertex project.
Do we need a server and an IT project?: No. Mnemosyne OS installs on a workstation, like any software. Deployment, volume licences and custom cartridges can be discussed, but you can try it without them.
Are our files moved or rewritten?: No. You point at a folder, and it is read in place. Files keep their name, their place and their format.
There are five of us. Is this for us?: Yes. On a drive shared by five people, nobody knows where anything is, just like in a large group. It is the same software in both cases.

Use cases

Technical documentation and customer support

Technical documentation

Manuals, specifications, procedures, years of internal wiki. An engineer asks in their own words and gets the answer with the page it comes from. Two documents about the same part are linked, even when they use different terms.

Customer support

Past tickets, product sheets, the support FAQ. An agent asks how a case was solved last time and gets the answer with its sources. With verification on, each sentence is checked against those sources, and the agent sees the ones no source supports.

Both uses need a deployment designed for your company: which sources to connect, who reads which vault, which model answers. We build it with you.

Local, hybrid or your server

Choose where the model runs, use by use

100% local

Everything on the machine

The model runs inside the application (Qwen, Gemma, Phi in GGUF). Unplug the network cable: search and answers keep working.

Hybrid

Search local, answer in the cloud

Search runs on the machine. A cloud model writes the answer, with your own key or your Vertex project. The question and the retrieved passages go to that provider.

Your server

Your company’s model

Your IT already runs a model? Connect it: any server that speaks the OpenAI-compatible API, at an address you set in the settings. The question and the passages go to that machine.

Compatible models

Vertex AI
Gemini
OpenAI
Anthropic
Mistral
DeepSeek
MiniMax
Qwen (local)
Your server

Each team can choose its mode. Download Mnemosyne OS to try it on one computer. For a deployment on your company’s server, talk to us.

Download Mnemosyne OS → Talk to us →

Working as a team

Share vaults across your office network Beta

Every computer in the office runs Mnemosyne OS. On the same network, they connect directly, with no server in the middle.

You lend a colleague a vault to read. Or you share a vault with the team: each person writes to it and keeps their own copy. The computers can also send each other messages.

A deletion never spreads. If two versions of a file diverge, both are kept. Between two sites, the application sets up Tailscale and guides you.

The network stays off until someone turns it on, computer by computer.

Fig. · Four computers on one network, one shared vault

← Back to the audience router