Niuwn AI: Building an AI Twin That Speaks As Me to Strangers

I built a system where anyone can create a conversational AI version of themselves, not a chatbot that answers questions about you, but one that talks as you in first person to anyone who visits a shareable link. Think of it as replacing your static CV or LinkedIn profile with something people can actually have a conversation with.
The core idea is a two-agent architecture. One agent (the Curator) works with you privately; you talk to it, upload your CV, share your blog posts, import your LinkedIn export and GitHub profile. It interviews you like a thoughtful journalist, asks follow-ups, spots gaps, and organizes everything into a structured knowledge base. The second agent (the Twin) is what visitors see. It reads from that knowledge base, speaks in your voice, respects boundaries you’ve defined, and gracefully handles things it doesn’t know instead of hallucinating.
What makes the system interesting technically: the entire knowledge base is plain Markdown files, transparent, editable, and version-controllable. Retrieval uses memsearch for hybrid BM25 + vector search over those markdown files, which turns out to work really well for professional data where you need both semantic understanding and exact matching on names, dates, and technologies. The two agents have strict asymmetric access, the Curator writes, the Twin only reads, which keeps the trust boundary clean and makes prompt injection defense on the public-facing side much more manageable.
The system is built with GDPR in mind, owners can view, edit, or delete anything their Twin knows, and visitors are informed upfront that conversations may be reviewed by the owner.
During the Live demo, I’ll teach the Twin something new on stage and let the audience interrogate it.