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

@ai-operations/ops-core

v0.1.0

Published

Pipeline engine for AI Operations OS — intent classification, state machine, LLM integration, structured logging

Downloads

11

Readme

@ai-operations/ops-core

Workflow engine, state machine, and intent classification for AI Operations OS.

Part of AI Operations OS — autonomous business workflow orchestration with safety enforcement.

Install

npm install @ai-operations/ops-core

Quick Start

import { WorkflowEngine, IntentClassifier } from '@ai-operations/ops-core';

const classifier = new IntentClassifier();
const intent = classifier.classify('Please reply to John about the meeting');
// => 'reply'

const engine = new WorkflowEngine(connectorRegistry, safetyGate);
for await (const event of engine.execute(workflowRun)) {
  console.log(event.type, event);
}

API

WorkflowEngine

Sequential step executor with safety gates. Drives a WorkflowRun through its steps, yielding typed events via an AsyncGenerator.

constructor(connectors: ConnectorRegistry, safetyGate: SafetyGate)
async *execute(run: WorkflowRun): AsyncGenerator<WorkflowEvent>
pause(): void
resume(): void

Event types: step_start | step_complete | step_blocked | step_failed | run_complete | run_failed

StateMachine

Enforces valid workflow step state transitions with O(1) lookup.

const sm = new StateMachine();
sm.transition('pending', 'start');           // => 'running'
sm.canTransition('running', 'complete');     // => true
sm.validEvents('blocked');                   // => ['approve']

Step events: start | complete | fail | block | approve | pause | resume

IntentClassifier

Keyword-based heuristic intent classification. Fast, deterministic first pass.

const classifier = new IntentClassifier();
const result = classifier.classifyDetailed('Please reply to John');
// => { intent: 'reply', confidence: 'low', matchedKeywords: ['reply'] }

LLMIntentClassifier

LLM-backed classification with heuristic fallback. Supports Anthropic, OpenAI, and Ollama providers via environment variables.

const llm = new LLMIntentClassifier();
const intent = await llm.classify('Can you handle the refund for order #123?');
// => 'refund' (via LLM when heuristic confidence is low)

Environment variables: OPS_LLM_PROVIDER, ANTHROPIC_API_KEY, OPENAI_API_KEY, OLLAMA_URL

TaskStore

In-memory + JSON file task persistence with filtering.

Interfaces

  • Connector{ name: string; execute(operation, input): Promise<Record<string, unknown>> }
  • ConnectorRegistry{ get(name): Connector | undefined }
  • SafetyGate(step, run) => Promise<SafetyGateResult>
  • SafetyGateResult{ decision: CordDecision; score: number; reason: string }

Related Packages

License

MIT