Skip to main content
The repo includes ready-to-run apps in apps/ that show different MemWal integration patterns. This page focuses on app-level patterns,the basic SDK flow covered in Quick Start and MemWal Usage.

​
Run Locally

pnpm dev:app
pnpm dev:chatbot
pnpm dev:noter
pnpm dev:researcher

​
Playground

Dashboard, playground, and interactive demo for MemWal. 
const memwal = MemWal.create({
  key: delegateKey,
  accountId: accountObjectId,
  serverUrl,
  namespace,
});

await memwal.remember(rememberText);
await memwal.recall(recallQuery, 5);
await memwal.analyze(analyzeText);
This app covers the full getting-started flow in one place. It signs users in, sets up delegate keys, shows SDK credentials, and includes a live playground for remember(), recall(), analyze(), restore(), AI middleware, and manual mode.

​
Chatbot

AI chat app with persistent memory across sessions. 
import { withMemWal } from "@mysten-incubation/memwal/ai";

const model = withMemWal(baseModel, {
  key,
  accountId,
  serverUrl,
  maxMemories: 5,
  autoSave: true,
});
This app shows AI middleware integration in a production-style chat app. The UI can enable MemWal, collect a delegate key and account ID, and pass them to the chat API. The server wraps the selected model with withMemWal, so recall happens before generation and new context can be auto-saved after each turn.

​
Noter

Note-taking app that stores insights as encrypted, searchable memory. 
export const extractMemories = async (text: string): Promise<string[]> => {
  const memwal = getMemWalClient();
  const result = await memwal.analyze(text);
  return (result.facts ?? []).map((f) => f.text);
};
This app shows note-to-memory extraction. Noter keeps a shared server-side MemWal client, lets the user configure the key and account at runtime, and uses analyze() to turn note content into structured facts that can be reused by the editor and AI features.

​
Researcher

Research assistant that saves and recalls findings across sessions. 
const fullText =
  `Sprint Report: ${title}\n\n` +
  `${content}\n\n` +
  `References:\n${references}\n\n` +
  `Sources: ${sourceList}`;

await memwal.remember(fullText);
const { results } = await memwal.recall(query, 5);
This app shows long-form research memory and session rehydration. Researcher saves each sprint as a structured report in MemWal, then generates recall queries from sprint metadata, pulls back the most relevant findings, and rebuilds context for a fresh session.