Welcome To OnVeris
OnVeris is an on-premises AI server built by Parker Software. It gives your organisation access to large language models without sending any data to a third-party service. Everything runs on your own hardware, on your own network.
Why On-Premises?
Cloud AI services are convenient, but they come with trade-offs. Every message sent to a cloud provider leaves your network. For organisations handling sensitive data — whether for compliance, confidentiality or data sovereignty reasons — that is not acceptable.
OnVeris is designed for exactly these situations. Your data stays with you. Models run locally. Your conversations and documents never leave your network.
OnVeris exposes an OpenAI-compatible API, so applications already built to work with OpenAI can be pointed at OnVeris instead.
The Three Components
OnVeris consists of three components that work together:
OnVerisGateway is the central hub. It handles sign-in, request routing and the administration pages. Administrators configure everything here — users, API Keys, Nodes, AI models, Assistants and Knowledge Bases.
OnVerisNode is the inference engine. It downloads and runs AI models on its host machine, using its GPUs, and answers the requests the Gateway sends it. Nodes can run on the same machine as the Gateway or on separate hardware, and you can connect several Nodes to one Gateway.
OnVeris Chat is the app people use to talk to the AI. It runs in a web browser — served by the Gateway, with nothing to install — and as an app for Windows, macOS, Linux, iPhone, iPad and Android.
What People Can Do With It
Once OnVeris is set up, the people in your organisation can:
- Chat with AI models, or with Assistants your administrators set up for particular jobs.
- Ask questions of your own documents, through Knowledge Bases the AI searches for the answer.
- Let the AI use tools — looking things up in other systems, reading files, or handing a task to another Assistant — with permission prompts where it matters.
- Run tasks on a schedule, such as a morning summary of overnight tickets.
- Build on it with the API.
Who Uses What
Each component is used by different people in your organisation:
| Role | Component |
|---|---|
| IT administrator | Gateway — configuration, users, Nodes, models, Assistants |
| Inference machine | Node — hosting and running models |
| End user | OnVeris Chat — browser, desktop or mobile |
| Developer or integrator | Gateway API |