CONSTITUTIONEngine #4 honors Law 12 — provenance is never merged, and Law 4 — connection never overrides permission.read the laws →
ECHO · KERNEL ENGINE #4

The Knowledge Graph

The Kernel learns how memory connects, not just what it contains. Context becomes “the things related to what you asked” instead of “whatever matched a keyword” — and every connection is honest about whether you stated it or the graph inferred it.

01Memory Enginewhat exists● real
02Permission Enginewhat's allowed● real
03Context Enginethe minimum needed● real
04Knowledge Graphhow it connects● real
live engine — building a graph from a decrypted vault state, in your browser
vault source6 capsules · 6 concepts · 1 person
you memory people concepts self-asserted derived

Click a node to seed the Context Engine · drag any node to rearrange

provenance — never merged Law 12
self-asserted7you stated it
derived10the graph inferred it
✓ every edge carries provenance; the two are never blended
context engine — connected & scoped
depth
permission scope

Select a node in the graph to expand connected memory within the granted scope.

The design

Nodes & edges

Nodes are identity, capsules, people, and concepts. Edges — authored, knows, mentions, related-to — each carry a provenance tag. Nothing is connected anonymously.

Provenance is mandatory & binary

self-asserted — you stated it (authored a capsule, named a relationship). derived — the graph inferred it (a capsule mentions a concept; two capsules share one). The two are never merged (Law 12).

contextFor(seed, depth, scope)

The Context Engine expands from a seed through the graph, but only includes capsules whose dimension is in the permission scope. The graph may know a connection; the agent only receives what you permitted (Law 4). Connected and scoped.

Honest sharp edges

  • Derived edges are heuristic. V1 infers concept mentions by keyword match over a small list — shallow, and it will both miss and over-connect. It is tagged derived precisely so it is never trusted as fact, and can always be seen and pruned. Better extraction (embeddings, NER) is a later upgrade; the provenance discipline is what must not change.
  • Scale. This is an in-memory graph rebuilt from vault state — right for a personal vault, not millions of nodes. At scale, persist the graph and update it incrementally as events arrive (it pairs naturally with the CRDT event log: each capsule.set/delete is a graph mutation).
  • No auto-promotion. Nothing here ever turns a derived edge into a self-asserted one. If you confirm an inferred link, that becomes a new self-asserted edge — a deliberate act, never automatic.