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

openclaw-musubi

v2.0.6

Published

First-class durable Musubi memory provider for OpenClaw agents.

Downloads

663

Readme

openclaw-musubi

First-class durable Musubi memory for OpenClaw agents. The plugin owns OpenClaw's exclusive memory slot and routes completed-turn capture, semantic recall, exact-object reads, and deliberate stores through a Musubi core.

Current architecture

openclaw-musubi declares kind: "memory" and must be selected with plugins.slots.memory = "musubi". It does not run beside memory-core as an additive supplement. That earlier architecture is historical and was superseded by ADR-0004.

The provider:

  • registers the exclusive OpenClaw memory capability;
  • exposes native memory_search, memory_get, and memory_store tools, plus the canonical Musubi tool surface;
  • commits every completed turn to a local SQLite outbox before the agent_end hook returns;
  • delivers with stable idempotency, receipt lookup, accepted/verified states, and canonical GET readback;
  • retains retryable and permanently blocked deliveries for operator action;
  • exposes delivery truth through /musubi-status, musubi.status, and the openclaw musubi-status CLI command.

Outbound musubi_think remains available. The former inbound SSE thought subscriber is deliberately not registered: it had no OpenClaw context-delivery contract and consuming a thought into an empty handler would be data loss disguised as delivery.

Requirements

  • OpenClaw >= 2026.7.1
  • Node.js >= 22.22.3
  • A reachable Musubi core with canonical episodic and retrieval APIs

Configuration

Musubi secret fields are declared OpenClaw secretInputs; use the same structured SecretRef form as other native OpenClaw secrets. Literal ${...} placeholders are rejected locally before the provider registers.

{
  "plugins": {
    "slots": { "memory": "musubi" },
    "entries": {
      "musubi": {
        "enabled": true,
        "config": {
          "core": {
            "baseUrl": "https://musubi.example.internal",
            "token": {
              "source": "exec",
              "provider": "onepassword",
              "id": "musubi-default"
            },
            "perAgentTokens": {
              "vesper": {
                "source": "exec",
                "provider": "onepassword",
                "id": "musubi-vesper"
              }
            }
          },
          "presence": {
            "defaultId": "owner/openclaw",
            "perAgent": { "vesper": "vesper/openclaw" }
          },
          "capture": { "completedTurns": true }
        }
      }
    }
  }
}

Verify the live contract

These commands re-establish the claims above; the dates in documentation do not substitute for running them:

npm run typecheck
npm run lint
npm test
npm run build
openclaw plugins inspect musubi --runtime --json
openclaw musubi-status
openclaw musubi-doctor --agent vesper

The loader-backed test runs a built artifact through OpenClaw 2026.7.1 with plugins.slots.memory = "musubi"; it fails if manifest kind, runtime kind, or exclusive capability ownership drift apart.

musubi-doctor is an explicit deep proof: it queues a diagnostic through the same SQLite delivery path as a real turn, waits for canonical GET verification, requires semantic retrieval to return that exact object, then soft-archives the probe. It never runs automatically.

Documentation

License

MIT — see LICENSE.