Deployment

On your servers, or hosted by us.

The same product either way. Today we ship the on-prem install.

Compare

Which fits you

On-prem (available)

  • Linux server packaging: Docker Compose or systemd units, installer script, reverse-proxy samples.
  • Backup, restore and restore-check scripts; monitoring dashboards and alert rules.
  • Your data, your network, your choice of AI model, including local models.
  • Quoted per company: seats plus optional updates and support.

Hosted by us (in preparation)

  • The same build, run by us, so there is nothing to install.
  • Not available yet: the separation between organisations and the billing portal are still being built.
  • Talk to us if this is what you need; we will tell you honestly where it stands.
Requirements

What an on-prem install needs

A Linux server

A single server is enough for a small team; the hardware guide says what to size for 30, 100 or 200 people.

A model, yours

A cloud provider key, or a model server inside your network. A GPU server is only needed for local models.

Your sign-in

Connect Active Directory, Google or Microsoft, or use local accounts with a second factor.

Windows sign-in from a Linux server and a live Active Directory have not yet been proven against a customer domain; we validate this with each customer before go-live.

See it on your own work.

We connect one of your systems and run a real task with you, from the request to the approval.

Request a demo