Linubra

Series

Building Linubra

A behind-the-scenes series on building an AI reasoning memory engine from scratch — architecture decisions, technical challenges, and lessons learned.

6 parts
  1. 1
    Raw inputs — audio waveforms, text snippets, images — flowing through a reasoning layer into a structured knowledge graph

    Why We Built Linubra

    Two tools exist for remembering your life: manual notes apps that demand upkeep, and passive recorders that understand nothing. We built a third.

    Patrick LehmannPatrick Lehmann··5 min read
  2. 2
    A dense hand-maintained database of property rows and tag chips on the left, next to a single calm graph node with a few sparse incoming fragments on the right — the contrast between manual upkeep and a self-organising knowledge graph

    The Hidden Cost of Your Second Brain

    Every note-taking system carries a hidden maintenance tax. Most people never add it up. When you do, the number is roughly half a year of focused work every five years — spent not thinking, not creating, not deciding. Spent filing.

    Patrick LehmannPatrick Lehmann··5 min read
  3. 3
    Abstract visualization of threads connecting business and athletic objects — revealing hidden cross-domain patterns

    The Knee, the Board Meeting, and a Pattern

    A founder's board-meeting stress caused a running injury three months later. Every data point was captured. None of them lived in the same place, so nobody — not the founder, not the physiotherapist, not any of his apps — ever saw the pattern.

    Patrick LehmannPatrick Lehmann··5 min read
  4. 4
    A sealed concrete cube surrounded by untouching glass spheres — representing data sovereignty and protected personal data

    Your Life Is Not Training Data

    The standard 'free in exchange for your data' bargain works fine for a notes app. It doesn't work for a tool that remembers your meetings, your injuries, your finances, and the people you trust. Here's what the architecture looks like when you take that seriously.

    Patrick LehmannPatrick Lehmann··4 min read
  5. 5
  6. 6