Integrations · Cloud and infrastructure
Next to your apps, inside your network.
Vidai runs in your server segment as containers with PostgreSQL, beside your apps and your own models. People, apps and agents call Vidai, not the providers, and your firewall lets only Vidai out.
Where it sits
The only way out to AI.
In the server segment
Vidai runs beside your apps, as containers with PostgreSQL, alongside any local models.
Reached from the inside
People, apps and agents call Vidai, not the providers: browsers, VidaiChat, coding tools and services alike.
The only way out
Your firewall lets only Vidai reach the AI providers you approve, through your egress proxy. Direct AI traffic is blocked.
Five ways to deploy
One set of rules, wherever people work.
In the office
Internal HTTPS to Vidai; Vidai out through the egress proxy to approved providers only.
At home, over VPN
The same path, a longer cable. With a split tunnel, send AI traffic through it, or steer public AI sites to VidaiChat with your secure web gateway.
At home, no VPN
Publish Vidai through your access proxy, with sign-in and multi-factor.
Hybrid cloud
Vidai on-premises checks sensitive data before it leaves the building, and reaches cloud models over a private link. Or run it in your cloud, beside your workloads.
Air-gapped
Inside an isolated network, with your own models only.
Private networking and links are set up your way: Direct Connect, ExpressRoute or Cloud Interconnect, or your egress proxy.
Setup steps for every SDK, provider and integration are in the docs.
How we start together
Start with one team, on your own AI traffic.
- 01
Pick one app or team
Point it at the Control room. One configuration change; nothing else changes.
- 02
Watch for two weeks
Every call priced, checked and recorded. Rules start in observe mode.
- 03
See the evidence
What it cost, what it caught and what it would have stopped, from your own traffic.