┌─ agidb · technical preprint · landing artifact last build · 2026-06-25 · 14:00 UTC · commit 71f92ca v2 pre-alpha · 128 tests passing · phase 11/16 ──┐
home·demo

one store. seven floors. zero queries.

a real agidb store, a real WebSocket, a real tools/call JSON-RPC frame on every command. the right column explains what's happening at the substrate level. the left terminal prints the verbatim response payload — same wire shape claude desktop uses. install agidb →

[ live ] agidb · interactive demo type a command →
agidb · sarah_bawri · /tmp/.tmp8kyozZ · 8192-bit HV step 0 of 8
try:


        
agidb  ↵ enter  ·  tab to cycle
episodes stored0
concepts resolved0
atoms consolidated0
beliefs revised0
goals set0
unlearn cascade0
mode · guided (offline · deterministic)
[ floor-by-floor ] what the substrate is doing
  1. floor 3 · observe 1/8

    five episodes land as structured triples

    "Sarah recommended Bawri" binds three concepts in the HDC index. text-only sentences still get a 8192-bit gist signature so they're recallable immediately — even before any extractor model is loaded.

    read about floor 3 →
  2. floor 6 · goal 2/8

    an active goal biases future recall

    the goal "find a thai place" gets its own HDC signature. from now on every recall is goal-conditioned — matches aligned with the active goal float up. substrate primitive, not text inside an episode.

    read about floor 6 →
  3. floor 6 · belief 3/8

    first-class revisable beliefs

    "Sarah likes thai food" with confidence 0.80 and two citing episodes. beliefs are revised, never overwritten — every change writes a row to an append-only revision log you can replay.

    read about floor 6 →
  4. layer 1 · tier-A recall 4/8

    the cascade: exact → similarity → gist → nearest

    three "Sarah recommended Bawri" episodes hit tier-A exact in 0ms. no embedding API call, no vector DB, no LLM in the read path — the entire retrieval is hypervector hamming + an in-memory concept index.

    read about the cascade →
  5. phase 6 · consolidation 5/8

    sleep: cluster, bundle, contradict

    three identical "Sarah recommended Bawri" episodes get bundled into a single semantic atom. the original episodes stay intact — the atom is a derived index, not a destructive merge.

    read about consolidation →
  6. floor 6 · revise_belief 6/8

    contradicting evidence drops confidence

    a new episode contradicts "Sarah likes thai". the belief drops 0.80 → 0.70, the revision log captures it, and what_do_i_believe("Sarah") returns the live value. nothing is overwritten.

    read about belief revision →
  7. floor 7 · self-vector 7/8

    the agent gets a slowly-drifting identity

    an 8192-bit self-vector EMA-updates toward the bundle of consolidated atoms after every pass. "what kind of agent am I right now" becomes queryable, inspectable, and subtractable.

    read about floor 7 →
  8. article XVI · unlearn 8/8

    non-destructive cascading forget

    unlearn(Concept(Sarah)) cascades: 6 episodes tombstoned, 1 belief auto-corrected, the self-vector subtracts the forgotten content (hamming weight drops 2060 → 119), and a permanent LearningEvent::Unlearned audit row is written. recoverable for 30 days, then compaction-eligible. audit never expires.

    read about the unlearn primitive →