MMemoWeft

Portable memory for AI applications

MemoWeft

A disciplined long-term memory layer for AI apps: portable across models, traceable to evidence, and careful about the difference between facts and guesses.

For applications that need durable user memory without turning every recorded line into accepted truth.

Library-firstHosts own chat, UI, persona, and consent.
TraceableEvery cognition can point back to evidence.
Zero runtime depsCore stays small and portable.
MemoWeft memory graph connecting evidence, events, and cognitions
Evidence, events, cognitions, confidence, and conflicts in one inspectable graph. Trace first. Believe carefully.

Memory as an asset, not prompt stuffing.

MemoWeft turns a host application's understanding of a person into durable, reviewable memory: evidence, events, cognitions, confidence, conflicts, recall, and export all stay inside a clean public API.

01Not a chatbot product.
02Not a persona engine.
03Not a UI framework.
04It is the memory core hosts import.

Built around cognitive discipline.

The core rule is simple: remembering something is not the same as believing it. MemoWeft keeps that boundary explicit in storage and recall.

1

Facts and guesses stay apart

Model inferences start as hypotheses. Accepted cognitions require evidence strength and corroboration.

2

Conflicts are visible

Contradictory evidence is surfaced for review instead of being silently overwritten.

3

Temporary states fade

Short-lived moods decay while durable preferences can persist and travel across hosts.

Reference host included for integration work.

The bundled host demonstrates chat with recall, visible memory formation, evidence inspection, cognition cards, and portable bundles. It shows how an app can use Core without reaching into internal stores.

MemoWeft reference host cognition cards with confidence and traces

Install the Core package.

Use MemoWeft through its public entry point. Hosts decide when to ingest evidence, when to organize memory, and how much recall to show.

npm install memoweft

import { createMemoWeftCore } from 'memoweft';

const core = createMemoWeftCore({
  dbPath: './memoweft.db'
});

await core.ingestUserMessage({
  subjectId: 'user-42',
  content: 'I only drink decaf after 3pm.'
});

const turn = await core.handleConversationTurn({
  subjectId: 'user-42',
  message: 'Recommend an afternoon drink.'
});