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

llm-tools

v0.2.6

Published

tools for working with LLMs

Readme

llm-tools

Tools for working with LLMs (Large Language Models).

Installation

npm install llm-tools

Usage

Format Utilities

The fmt object provides formatting functions useful for working with LLMs:

import { fmt } from 'llm-tools'

// Format multi-line strings by removing unnecessary indentation
const formatted = fmt.trim(`
    This is a multi-line string
      with some indentation
    that will be normalized
`)
// Result: "This is a multi-line string\n  with some indentation\nthat will be normalized"

// Convert multi-line strings to single line
const oneLine = fmt.oneLine(`
    This is a multi-line string
    that will become one line
`)
// Result: "This is a multi-line string that will become one line"

// Convert array of objects to TSV (Tab-Separated Values)
const data = [
  { name: 'John', age: 30 },
  { name: 'Jane', age: 25 }
]
const tsv = await fmt.asTSV(data)
// Result: "name\tage\nJohn\t30\nJane\t25"

Available Functions

fmt.trim(str: string): string

Formats a multi-line string by removing unnecessary indentation while preserving relative indentation between lines. Trims leading/trailing newlines from the entire string and trailing whitespace from each line. Empty or whitespace-only lines are preserved as empty lines.

Useful for formatting prompts and tool instructions.

fmt.oneLine(str: string): string

Converts a multi-line string into a single line by joining non-empty lines with spaces.

Useful for formatting tool instructions that need to be on one line.

fmt.asTSV(data: any[]): Promise<string>

Converts an array of objects to a string of tab-separated values (TSV). This is better than JSON for returning data to LLMs because it uses fewer tokens.

License

MIT