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

evobrew

v1.0.2

Published

Model-agnostic AI workspace with semantic knowledge graphs, function calling, and persistent memory

Readme

Evobrew

AI development workspace with semantic knowledge graphs, function calling, and persistent memory.

Version Node License


What Is Evobrew?

Evobrew is an AI-powered development environment where knowledge becomes action:

  • Query knowledge graphs (.brain packages) through conversational AI
  • Execute code with function calling (read, edit, search files)
  • Persistent memory across sessions via OpenClaw integration
  • Multi-model support (GPT-4o, Claude Sonnet/Opus, Grok)
  • Semantic search that understands meaning, not just keywords

Think of it as a workspace where you and AI build together — with memory, tools, and evolving knowledge.


Quick Start

# Install globally
npm install -g evobrew

# Run setup wizard
evobrew setup

# Start server
evobrew start

Open http://localhost:3405 (or https://localhost:3406 for HTTPS)

For contributors: See INSTALL.md for development setup.

Full documentation: docs/CLI.md


Features

🧠 Knowledge Graph Browser

  • Load and query .brain packages (semantic knowledge graphs)
  • Vector similarity search with embeddings
  • Context-aware answers from structured knowledge

🤖 AI Function Calling

  • AI can read, edit, and search your codebase
  • Real-time streaming responses
  • Tool execution with diff preview
  • Shared PTY terminal tools (terminal_*, run_terminal compatibility wrapper)

💻 Real Terminal Dock

  • True PTY-backed terminal sessions (not one-shot command exec)
  • Multi-session tabs with reconnect/resume after refresh
  • AI and user can target the same terminal client/session model

📁 Office File Support

  • Read Word (.docx), Excel (.xlsx), Outlook (.msg)
  • AI analyzes formulas, comments, structured data
  • Generate professional documents

🔌 OpenClaw Integration

  • Connect to OpenClaw Gateway for persistent agent memory
  • Session continuity across restarts
  • Full tool and skill access

✂️ Surgical Code Edits

  • Targeted changes without full file rewrites
  • Edit queue with approve/reject workflow
  • Line-range operations, search/replace

🔒 Security First

  • OAuth token encryption (Prisma + crypto)
  • Path traversal protection
  • CORS locked to localhost/LAN by default
  • Optional HTTPS with self-signed certs

Architecture

Frontend: Vanilla JS, no framework
Backend: Node.js + Express
Database: SQLite (Prisma ORM)
AI: OpenAI, Anthropic, xAI
Search: HNSW vector index (hnswlib-node)


Use Cases

  • Research assistant: Query knowledge graphs conversationally
  • Code companion: AI that can read and edit your code
  • Document processor: Extract and analyze Office files
  • Knowledge evolution: Build and refine .brain packages over time

🧠 Sample Brains

Evobrew works with .brain knowledge graphs. Want some to explore?

Check out COSMO BrainStudio for pre-built research artifacts:

| Domain | Description | |--------|-------------| | 🎨 Art & Music | 5,000+ nodes on aesthetics & musicology | | 📐 Mathematics | Algebra to probability modeling | | ⚛️ Physics | Quantum dynamics, unified field theory | | 🧠 Psychology | Behavioral synthesis & cognitive frameworks | | 🚗 Big Auto | Future of global mobility |

Clone the repo, grab the brains from brains/, and load them in Evobrew.


Documentation


Configuration

Edit .env:

# Required: Encryption key for OAuth tokens (64 hex characters)
ENCRYPTION_KEY=your_64_character_hex_key_here

# API Keys (at least one required)
OPENAI_API_KEY=sk-proj-...
ANTHROPIC_API_KEY=sk-ant-...
XAI_API_KEY=xai-...  # Optional (Grok)

# Server (defaults shown)
HTTP_PORT=3405
HTTPS_PORT=3406

# Optional: OpenClaw Gateway
OPENCLAW_GATEWAY_URL=ws://localhost:18789
OPENCLAW_GATEWAY_TOKEN=your_token
OPENCLAW_GATEWAY_PASSWORD=your_password

# Terminal feature flags
TERMINAL_ENABLED=true
TERMINAL_MAX_SESSIONS_PER_CLIENT=6
TERMINAL_IDLE_TIMEOUT_MS=1800000
TERMINAL_MAX_BUFFER_BYTES=2097152

# Internet profile only (default-off terminal in internet mode)
INTERNET_ENABLE_TERMINAL=false

Development

# Run with auto-restart
npm run dev

# Access Prisma Studio (database GUI)
npm run db:studio

# Update dependencies
npm update

Requirements

  • Node.js: 18.0.0 or higher
  • npm: 9.0.0 or higher
  • OS: macOS, Linux, Windows
  • API Keys: OpenAI, Anthropic, or xAI (at least one)

License

MIT — see LICENSE


Contributing

Contributions welcome! Please:

  1. Fork the repo
  2. Create a feature branch
  3. Submit a pull request with clear description

Support


Built with ❤️ for developers who want AI that remembers, learns, and executes.