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

agent-wtf

v1.0.1

Published

A Discord bot powered by AI (using Venice AI via OpenAI-compatible API), featuring conversation memory and a plugin system for extensibility.

Downloads

6

Readme

AI Discord Bot (agent-wtf)

A Discord bot powered by AI (using Venice AI via OpenAI-compatible API), featuring conversation memory and a plugin system for extensibility.

Features

  • AI Chat: Responds to messages using an AI model.
  • Conversation Memory: Remembers recent messages in a channel using SQLite.
  • Plugin System: Allows extending functionality with custom commands and AI-callable functions.
  • Slash Commands: Uses Discord's modern slash commands.
  • TypeScript: Built with TypeScript for better code safety and maintainability.
  • Dockerized: Includes a Dockerfile for easy containerization and deployment.

Prerequisites

  • Node.js (v18+ recommended)
  • npm
  • Discord Bot Token
  • Venice AI API Key
  • (Optional) Docker

Setup

  1. Clone the repository:
    git clone <your-repo-url>
    cd agent-wtf
  2. Install dependencies:
    npm install
  3. Configure environment variables:
    • Copy .env.example to .env.
    • Fill in the required values:
      • DISCORD_TOKEN: Your Discord bot token.
      • VENICE_API_KEY: Your Venice AI API key.
      • (Optional) VENICE_MODEL: The specific Venice/OpenAI model ID to use.
      • (Optional) DEV_GUILD_ID: Discord server ID for instant command registration during development.
      • (Optional) MEMORY_MAX_MESSAGES: Max messages to fetch from history (default: 10).
  4. Database Setup:
    • The SQLite database (database.sqlite by default) will be created automatically in the project root when the bot first runs.

Development

  • Run in development mode (with hot-reloading):
    npm run dev
  • Linting:
    npm run lint
  • Formatting:
    npm run format

Building for Production

npm run build

This compiles TypeScript code to the dist directory.

Running in Production

npm start

This runs the compiled code from the dist directory.

Deployment with Docker

  1. Build the Docker image:
    docker build -t agent-wtf .
  2. Run the Docker container:
    • Create a .env file in a location accessible to Docker (e.g., /path/to/your/env/.env).
    • Make sure the directory where database.sqlite will be created is writable by the Docker container user (or use a volume).
    docker run -d --name my-discord-bot \
      --env-file /path/to/your/env/.env \
      -v /path/to/your/db:/app/database.sqlite \
      agent-wtf
    • Replace /path/to/your/env/.env with the path to your environment file.
    • Replace /path/to/your/db with the host directory where you want to persist the database.sqlite file. Ensure this path exists and has correct permissions.

Plugin Development

  1. Create a new .ts file in the src/plugins directory.
  2. Define your plugin structure conforming to the BotPlugin interface (src/types/plugin.d.ts).
  3. Implement commands (PluginCommand) and/or AI functions (PluginFunction).
  4. Export your plugin object using module.exports = yourPluginObject; (for CommonJS) or export default yourPluginObject; (for ES Modules - loader might need adjustment).
  5. The bot will automatically load the plugin on startup. (See src/plugins/examplePlugin.ts for an example).