Laminae exists because the companies that would benefit most from retrieval-augmented AI — teams that are data-rich but IT-light — keep getting handed tools designed for someone else.
Founded by David Bunting and based in Frankfurt am Main, Laminae is a focused team building a single product: a knowledge layer that turns your documents into source-attributed evidence any MCP-compatible AI client can use, stored in focused, relevant spaces to avoid information drift. No chat UI to retrain your team on. No SDK to wrap. No data lake to maintain.
We chose Germany deliberately. European data protection norms aren't a marketing veneer here — they're the default. If your compliance team needs the whole stack to run inside your own network, that's a supported deployment, not a special edition.
Three commitments shape every product decision: be precise, be trustworthy, be relevant. They're also why Laminae looks unfamiliar next to most AI startups.
These aren't taglines — they're the constraints that decide what makes it into the product and what doesn't.
Notes on retrieval, MCP, and the parts of enterprise AI we keep arguing about — from the team building Laminae.
Vector databases reward scope. Pour everything into one giant index and unrelated documents start bleeding into every search — the answers come back confidently mixing facts from places you never asked about. One bucket per concept is the fix.
Read moreThe default pattern — drop the document into the chat, ask the question, repeat tomorrow — costs you twice. Once in tokens spent re-embedding the same text. Again in answer quality, when the document outgrows the context window. There is a cheaper way.
Read more