AI that does not expose your sources.
Xinity runs open, OpenAI-compatible language models entirely inside your newsroom infrastructure. Research material, sources, and unpublished content do not leave your organisation. Editorial independence, technically too.
Source protection does not end at the cloud interface.
When research, notes, or source information flow through an external API, you hand over control of exactly the material whose protection defines your work. Sovereign AI keeps that material inside your organisation, under your sole authority.
How on-premise supports concrete obligations.
The European Media Freedom Act (Regulation (EU) 2024/1083, in application since 8 August 2025) establishes the protection of journalistic sources and confidential communications as binding EU law in Article 4. An on-premise model keeps research material and unpublished content entirely inside your organisation, so your tooling stays consistent with that protection and no material reaches an external provider.
Research often contains the personal data of third parties. When processing never leaves your organisation, you keep full control of that data, with no transfer to a processor and none of the obligations that come with it.
Editorial independence has a technical dimension. Apache 2.0 open source and operation on your own infrastructure mean no platform outside your organisation decides whether and how your tools work.
Data and model stay inside your infrastructure.
Xinity runs on your hardware, on your network, behind your firewall. There is no outbound data path to a model provider that you would have to secure or cover by contract. Apache 2.0 open source also means full auditability: your security team can read every line.