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

@parke.dev/pi-memory

v0.1.0

Published

Local semantic long-term memory engine and tools for the Pi coding agent

Readme

@parke.dev/pi-memory

The canonical local-memory engine and Pi extension.

pi install npm:@parke.dev/pi-memory

Pi tools

  • memory_remember stores one durable fact.
  • memory_recall combines semantic and exact-token retrieval.
  • memory_forget tombstones one entry by ID.
  • memory_stats reports store and embedding health.

Pi data follows PI_CODING_AGENT_DIR and defaults to ~/.pi/agent/circle-memory.db. The legacy filename is retained so upgrading does not discard existing memories.

Engine

The package is also the sole reusable memory implementation used by Circle. It owns:

  • SQLite schema, FTS5, and vector storage
  • local MiniLM and degraded hash embedders
  • hybrid recall and near-duplicate folding
  • append-only CRDT operation log and merge primitives
  • extraction parser and versioned prompt
  • safe recalled-context formatting

Circle now supplies only product-specific policy and orchestration: canonical redaction, automatic turn-end extraction, automatic recalled-context injection, scope authorization, event audit, mesh transport, CLI, and desktop UI.

Privacy and limits

Embedding and recall are local. Memory text is stored unencrypted in a user-readable SQLite file, so OS account permissions remain the security boundary. Facts are limited to 280 characters. The extension redacts common credential formats before persistence, but callers should never intentionally store secrets.

Development

node scripts/fetch-memory-model.mjs
npm run --workspace @parke.dev/pi-memory build
npx vitest run packages/pi-memory/tests