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

or3-workflow-core

v0.1.2

Published

Headless workflow engine with LLM agent orchestration

Readme

or3-workflow-core

Headless workflow engine with LLM agent orchestration. Build multi-agent AI pipelines with a type-safe, framework-agnostic core.

Installation

bun add or3-workflow-core
# or
npm install or3-workflow-core

Quick Start

import { WorkflowEditor, StarterKit } from 'or3-workflow-core';

// Create an editor with default extensions
const editor = new WorkflowEditor({
    extensions: StarterKit.configure(),
});

// Load a workflow
editor.load({
    meta: { version: '2.0.0', name: 'My Workflow' },
    nodes: [
        {
            id: 'start',
            type: 'start',
            position: { x: 100, y: 100 },
            data: { label: 'Start' },
        },
        {
            id: 'agent',
            type: 'agent',
            position: { x: 100, y: 250 },
            data: {
                label: 'Assistant',
                model: 'openai/gpt-4o',
                prompt: 'You are a helpful assistant.',
            },
        },
    ],
    edges: [{ id: 'e1', source: 'start', target: 'agent' }],
});

// Execute the workflow
const result = await editor.execute({
    input: 'Hello, world!',
    apiKey: process.env.OPENROUTER_API_KEY,
});

Features

  • TipTap-style Extensions - Configurable, composable node extensions
  • Multi-model Support - Use any model available on OpenRouter
  • Human-in-the-loop - Pause for approval, input, or review at any step
  • Context Compaction - Automatic conversation summarization
  • Type-safe - Full TypeScript support with Zod validation
  • Framework-agnostic - Works with any UI framework or headless

Node Types

| Node | Description | | ------------ | ---------------------------------------------------- | | start | Entry point for workflow execution | | agent | LLM-powered agent with configurable model and prompt | | router | Conditional branching based on LLM decisions | | parallel | Execute multiple branches concurrently | | while-loop | Iterate until a condition is met | | subflow | Embed another workflow as a node | | output | Format and return final results |

Configuration

const editor = new WorkflowEditor({
    extensions: StarterKit.configure({
        // Disable specific nodes
        whileLoop: false,
        parallel: false,

        // Configure specific nodes
        agent: {
            defaultModel: 'anthropic/claude-3.5-sonnet',
        },
        subflow: {
            maxNestingDepth: 5,
        },
    }),
});

Execution Callbacks

await editor.execute({
    input: 'Hello',
    apiKey: 'your-api-key',
    callbacks: {
        onNodeStart: (nodeId, node) =>
            console.log(`Starting ${node.data.label}`),
        onNodeComplete: (nodeId, result) =>
            console.log(`Completed with: ${result}`),
        onToken: (nodeId, token) => process.stdout.write(token),
        onToolCall: (event) => console.log(`Tool: ${event.name}`),
    },
});

Related Packages

License

MIT