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

@wiscale/velesdb-memory-node-darwin-arm64

v0.6.0

Published

Local-first agent memory for Node.js (napi-rs): remember/recall/relate/forget/why with the why() knowledge-graph wedge, plus auto-extraction.

Downloads

334

Readme

@wiscale/velesdb-memory-node

Local-first agent memory for Node.js — the VelesDB memory wedge as an in-process native addon (napi-rs). Same hardened Rust as the MCP server and the Python binding; no network service.

remember / recall / recallWhere / relate / forget / why / rememberExtracted. The differentiator is why(): it answers a question with the best-matching memory plus its connected subgraph — related facts a plain vector recall is blind to.

recall() finds the booking but misses the reason; why() reaches it through typed links, across a session restart

The store is on disk, so memory survives process restarts — a new session reopens it and why() still walks the graph to context that shares no words with the question.

Install

npm install @wiscale/velesdb-memory-node

Prebuilt binaries ship for macOS (arm64/x64), Linux (x64/arm64 gnu), and Windows (x64). Node >= 18.17.

Usage

import { MemoryService } from '@wiscale/velesdb-memory-node'

// Offline "hash" embedder by default; pass "ollama" for real semantic recall.
const mem = MemoryService.open('./agent_mem')

const pr = await mem.remember('PR #42 swaps the mutex for parking_lot')
const decision = await mem.remember(
  'we chose parking_lot to avoid lock poisoning',
  [{ target: pr, relation: 'decided_in' }],
)

// recall: vector similarity.
const hits = await mem.recall('lock poisoning', 5)

// recallWhere: fused vector + structured filters (ranges/comparisons).
const recent = await mem.recallWhere('release notes', [
  { field: 'ts', op: 'ge', value: 20260101 },
])

// why: the wedge — seed memory + its reachable subgraph.
const { nodes, edges } = await mem.why('why parking_lot')

Every method returns a Promise and runs off the event-loop thread. Memory ids cross the boundary as decimal strings (a JS number loses precision above 2^53). Errors are Errors whose message is prefixed with a stable code: [INVALID_INPUT], [NOT_FOUND], or [INTERNAL].

Auto-extraction (rememberExtracted)

// Extract atomic facts from raw text with a local Ollama model and auto-build
// the fact↔topic graph that powers why().
const ids = await mem.rememberExtracted(longText, 'qwen3', 'http://localhost:11434')

License

VelesDB Core License 1.0 (based on ELv2). See LICENSE. This addon exposes memory semantics only; it is not a hosted or managed service.