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

@keyoku/openclaw

v1.6.0

Published

Keyoku memory plugin for OpenClaw — persistent memory, heartbeat enhancement, and scheduling

Readme

@keyoku/openclaw

Keyoku memory plugin for OpenClaw — persistent memory, heartbeat signals, and scheduling for your AI assistant.

Install

npm install @keyoku/openclaw

Or use the setup wizard:

npx keyoku-init

Usage

In your openclaw.json:

{
  "extensions": ["@keyoku/openclaw"]
}

Or programmatically:

import keyokuMemory from '@keyoku/openclaw';

const plugin = keyokuMemory({
  autoRecall: true,
  autoCapture: true,
  heartbeat: true,
  topK: 5,
  autonomy: 'suggest',
});

What It Does

  • Auto-recall — Injects relevant memories into context before every response
  • Auto-capture — Extracts facts, preferences, and relationships from conversations in real-time
  • Heartbeat — Surfaces deadlines, follow-ups, decaying memories, and conflicts proactively
  • Scheduling — Cron-based reminders with acknowledgment tracking

Configuration

| Option | Default | Description | |--------|---------|-------------| | keyokuUrl | http://localhost:18900 | Keyoku engine URL | | autoRecall | true | Inject memories before responses | | autoCapture | true | Extract facts from conversations | | heartbeat | true | Enable proactive signals | | incrementalCapture | true | Capture per-message vs. session-end | | topK | 5 | Memories to inject per prompt | | recallMinScore | 0.35 | Minimum similarity score for injected recalls | | recallQueryMode | "latest-user" | Recall query strategy: latest-user or prompt-plus-context | | autonomy | "suggest" | Action level: observe, suggest, act | | captureMaxChars | 2000 | Max characters for auto-capture | | clientTimeoutMs | 120000 | Keyoku API timeout for search/remember/heartbeat | | captureDebounceMs | 10000 | Minimum interval between capture writes | | captureMaxInFlight | 1 | Max concurrent capture writes before backpressure skips |

Tools

The plugin registers 7 tools for your assistant:

| Tool | Description | |------|-------------| | memory_search | Semantic search over memories | | memory_get | Read a specific memory | | memory_store | Save important information | | memory_forget | Delete a memory | | memory_stats | View memory statistics | | schedule_create | Create a recurring reminder | | schedule_list | View active schedules |

License

MIT