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

enagrams

v3.1.4

Published

Shared cognitive layer for co-coding teams — agent coordination, decisions, and knowledge

Readme

Enagrams MCP Server

Shared agent memory for co-coding teams. When two developers work on the same codebase with their own AI coding agents, Enagrams gives those agents shared context — decisions, conflict detection, and meeting notes.

Setup

1. Get your API key

Sign up at enagrams.com, create a workspace, and copy your API key.

2. Add to your MCP config

Cursor (~/.cursor/mcp.json):

{
  "mcpServers": {
    "enagrams": {
      "command": "npx",
      "args": ["-y", "enagrams-mcp"],
      "env": {
        "ENAGRAMS_API_KEY": "ek_...",
        "ENAGRAMS_WORKSPACE": "my-startup"
      }
    }
  }
}

Claude Code (.mcp.json in your repo root):

{
  "mcpServers": {
    "enagrams": {
      "command": "npx",
      "args": ["-y", "enagrams-mcp"],
      "env": {
        "ENAGRAMS_API_KEY": "ek_...",
        "ENAGRAMS_WORKSPACE": "my-startup"
      }
    }
  }
}

3. Start coding

Both agents will automatically share decisions and detect conflicts.

Environment Variables

| Variable | Required | Description | |----------|----------|-------------| | ENAGRAMS_API_KEY | Yes | Your API key from enagrams.com | | ENAGRAMS_WORKSPACE | Yes | Workspace slug or ID | | ENAGRAMS_API_URL | No | Custom API URL (default: https://api.enagrams.com) |

Tools

| Tool | Description | |------|-------------| | sync | Report what you're working on + get back what teammates' agents are doing, recent decisions, conflicts, and meeting context | | decide | Record a decision so every agent in the workspace knows about it | | search | Semantic search over past team decisions |

How It Works

sync is the key tool. Every time an agent needs context, it also reports what it's working on. One round-trip, both directions.

Agent calls sync({
  files: "src/auth.js, src/middleware.js",
  task: "refactoring auth to use sessions",
  branch: "feature/session-auth"
})

→ Returns: other agents, relevant decisions, conflicts, meeting context

decide records a decision with rationale so other agents understand the why, not just the what.

Agent calls decide({
  title: "Use express-session instead of JWT",
  rationale: "Server components need server-side sessions. JWT adds complexity.",
  files: "src/auth/middleware.js"
})

search finds past decisions by meaning, not exact text.

Agent calls search({ query: "how we handle authentication" })

License

MIT