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

@grackle-ai/knowledge

v0.75.0

Published

Knowledge graph subsystem for Grackle (Neo4j + vector search)

Vulnerabilities

Powered byPowered by Snyk
  • 0High
  • 0Medium
  • 0Low

Links

Git

Maintainers

nickpapenickpape

Keywords

grackleknowledge-graphneo4jvector-search

Readme

@grackle-ai/knowledge

Knowledge graph subsystem for Grackle — keeps AI agent context (tasks, findings, sessions, workspaces) synchronized into a Neo4j knowledge graph with vector embeddings for semantic search.

This package is the Grackle-specific integration layer on top of @grackle-ai/knowledge-core. It re-exports the full core SDK (connection management, node/edge CRUD, ingestion pipeline, semantic search, graph traversal) and adds reference node synchronization — the glue that keeps the knowledge graph in sync with Grackle's relational database as entities are created, updated, and deleted.

Install

npm install @grackle-ai/knowledge

Requires Node.js >= 22 and a running Neo4j 5.x instance with vector index support. See the @grackle-ai/knowledge-core README for Neo4j setup instructions.

How It Works

Grackle entities (tasks, findings, sessions, workspaces) live in SQLite. To make them semantically searchable and graph-connected, this package provides reference node sync: when an entity changes, a corresponding reference node in Neo4j is created or updated with a fresh embedding vector. This lets agents query the knowledge graph with natural language and discover related context across entity types.

The package also includes pure text-derivation helpers that produce consistent, embeddable text representations from entity data — ensuring that the same task or finding always generates the same embedding input format.

Relationship to @grackle-ai/knowledge-core

| Package | Role | |---------|------| | @grackle-ai/knowledge-core | Domain-agnostic graph SDK — Neo4j client, embedders, chunkers, search, traversal. Standalone, no Grackle dependency. | | @grackle-ai/knowledge | Grackle integration layer — re-exports the core SDK and adds entity-aware sync, lookup, and text derivation. |

If you are building on Grackle, use @grackle-ai/knowledge — it gives you the full core API plus Grackle-specific helpers in a single import. If you want a standalone knowledge graph library with no Grackle coupling, use @grackle-ai/knowledge-core directly.

License

MIT