npm package discovery and stats viewer.

Discover Tips

  • General search

    [free text search, go nuts!]

  • Package details

    pkg:[package-name]

  • User packages

    @[username]

Sponsor

Optimize Toolset

I’ve always been into building performant and accessible sites, but lately I’ve been taking it extremely seriously. So much so that I’ve been building a tool to help me optimize and monitor the sites that I build to make sure that I’m making an attempt to offer the best experience to those who visit them. If you’re into performant, accessible and SEO friendly sites, you might like it too! You can check it out at Optimize Toolset.

About

Hi, 👋, I’m Ryan Hefner  and I built this site for me, and you! The goal of this site was to provide an easy way for me to check the stats on my npm packages, both for prioritizing issues and updates, and to give me a little kick in the pants to keep up on stuff.

As I was building it, I realized that I was actually using the tool to build the tool, and figured I might as well put this out there and hopefully others will find it to be a fast and useful way to search and browse npm packages as I have.

If you’re interested in other things I’m working on, follow me on Twitter or check out the open source projects I’ve been publishing on GitHub.

I am also working on a Twitter bot for this site to tweet the most popular, newest, random packages from npm. Please follow that account now and it will start sending out packages soon–ish.

Open Software & Tools

This site wouldn’t be possible without the immense generosity and tireless efforts from the people who make contributions to the world and share their work via open source initiatives. Thank you 🙏

© 2026 – Pkg Stats / Ryan Hefner

superdupermemory

v0.1.1

Published

TypeScript SDK for superdupermemory — local-first memory layer for AI agents

Readme

superdupermemory

TypeScript SDK for superdupermemory — a self-hosted, local-first memory layer for AI agents.

Installation

npm install superdupermemory

Quick start

import { SupduperMemory } from 'superdupermemory'

const memory = new SupduperMemory({
  baseUrl: 'http://localhost:3000',
  apiKey: 'your-app-api-key',
})

// Store a memory for a user
await memory.remember({
  userId: 'alice',
  text: 'Alice is a software engineer who prefers TypeScript over JavaScript.',
})

// Recall memories with semantic search
const facts = await memory.recall({
  userId: 'alice',
  query: 'what does alice prefer?',
})

console.log(facts[0].body)
// → "Alice prefers TypeScript over JavaScript."

// Delete a specific memory
await memory.forget({ userId: 'alice', factId: facts[0].id })

Self-hosting

Run the server with Docker:

docker run -p 3000:3000 -v $(pwd)/data:/data \
  -e ANTHROPIC_API_KEY=sk-ant-... \
  ghcr.io/avirajkhare00/superdupermemory:latest

Or with Docker Compose — see the self-hosting guide.

API

new SupduperMemory(opts)

Memory operations for a single app. Use one instance per app.

| Option | Type | Description | |--------|------|-------------| | baseUrl | string | URL of your superdupermemory server | | apiKey | string | App API key from the dashboard |

.remember(opts)Promise<Fact[]>

Extracts facts from free-form text and stores them for a user. Returns the list of facts saved.

const facts = await memory.remember({
  userId: 'alice',           // any string — email, UUID, username
  text: 'Alice loves hiking and her favourite food is pasta.',
  source: 'chat',            // optional label
})

.recall(opts)Promise<Fact[]>

Semantic search over a user's memories. Omit query to list the most recent memories.

const facts = await memory.recall({
  userId: 'alice',
  query: "alice's hobbies",  // natural-language query
  limit: 5,                  // default 10, max 100
})

.forget(opts)Promise<boolean>

Delete a specific memory by ID.

await memory.forget({ userId: 'alice', factId: 'fact-uuid' })

.users(appId)Promise<UserWithCount[]>

List all users for an app along with their memory counts.

const users = await memory.users('app-uuid')

new SupduperMemoryAdmin(opts)

Org and app management. Use the admin token returned when you created your org.

| Option | Type | Description | |--------|------|-------------| | baseUrl | string | URL of your superdupermemory server | | adminToken | string | Admin token from org creation | | orgId | string | Your org ID |

import { SupduperMemoryAdmin } from 'superdupermemory'

const admin = new SupduperMemoryAdmin({
  baseUrl: 'http://localhost:3000',
  adminToken: 'your-admin-token',
  orgId: 'your-org-id',
})

// Create an app — the apiKey is shown only once
const { app, apiKey } = await admin.createApp('my-chatbot')

// List all apps
const apps = await admin.listApps()

// Org-wide memory stats
const stats = await admin.stats()

createOrg(opts)Promise<{ org, adminToken }>

One-time setup. Creates a new organization and returns the admin token. Store the admin token securely — it is shown only once.

import { createOrg } from 'superdupermemory'

const { org, adminToken } = await createOrg({
  baseUrl: 'http://localhost:3000',
  name: 'Acme Corp',
  slug: 'acme',
})

Types

interface Fact {
  id: string
  subject: string        // e.g. "user.preference.food"
  body: string           // e.g. "Alice's favourite food is pasta."
  source: string
  created_at: string
  updated_at: string
  previous_body: string | null
}

License

Apache 2.0