the sovereignty topic needs more attention in general so great to see. self-hosting the model is one piece of sovereignty, but how do we handle the rest of the agent stack - embeddings, retrieval, memory, etc. Has anyone put together a practical agent stack that's 100% sovereign, where they control it all?
[Disclosure: Antfly CEO]
We've talked to all kinds of companies burning incredible amounts of tokens on Anthropic and OpenAI just to search slack, google drive, their email; or getting frustrated by dumb Copilot conversations that can't find things in SharePoint. We think we can make this better and you should own your data.