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

@howaboua/pi-memories

v0.1.4

Published

Writes a small set of memory candidates when Pi exits, then leaves the final decision to you. There is no database, vector store, or hidden profile: candidates go to a plain Markdown inbox for manual review.

Readme

@howaboua/pi-memories

Writes a small set of memory candidates when Pi exits, then leaves the final decision to you. There is no database, vector store, or hidden profile: candidates go to a plain Markdown inbox for manual review.

Install

pi install npm:@howaboua/pi-memories

How it works

The worker runs only for a real Pi shutdown (session_shutdown with reason quit), not reloads, new sessions, resumes, or forks. It uses the best context available:

  1. an OpenAI native compaction window
  2. a normal Pi compaction summary
  3. the recent conversation when no compaction exists

It starts an ephemeral Pi process with --no-session --no-skills --no-tools. Normal context files remain available unless disabled in config, which lets the worker compare candidates with existing global and project instructions.

Candidates are appended to ~/.pi/agent/memory-inbox.md. Short sessions without compaction are skipped by default, and output equal to No durable memories. is not written.

Review

Run /memory-review. The command fills the editor with a review prompt that asks the agent to promote only durable, non-sensitive information into the appropriate global or project AGENTS.md, merge duplicates, and empty the inbox when finished.

The review is deliberately manual. Inbox entries are candidates, not truth.

Configuration

The extension creates ~/.pi/agent/pi-memories.json on first load.

| Option | Default | Purpose | |---|---|---| | enabled | true | Enable shutdown distillation. | | model | gpt-5.4 | Model passed to the ephemeral Pi process. | | thinking | low | Thinking level, from off through max. | | inboxPath | ~/.pi/agent/memory-inbox.md | Destination for candidates and failure comments. | | prompt | built-in distillation prompt | Replace the worker prompt. | | timeoutMs | 120000 | Maximum worker runtime. | | includeProjectContext | true | Include Pi's normal context files; false passes --no-context-files. | | minUserMessagesWithoutBlob | 3 | Skip shorter sessions when no compaction exists. |

Use a provider/model string available in your Pi setup when overriding model.