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-json-parse

v0.1.1

Published

Extract and repair JSON from noisy LLM text output (code fences, trailing commas, single quotes, extra prose). Zero dependencies, TypeScript-first.

Downloads

282

Readme

llm-json-parse

Extract and repair JSON from noisy LLM text output. Zero dependencies, TypeScript-first.

LLMs rarely return perfectly clean JSON. You usually get things like:

Sure! Here's the data you asked for:

```json
{
  "name": "Ada",
  "tags": ["a", "b",],
}
```

Let me know if you need anything else!

llm-json-parse strips the fences and prose, extracts the JSON span, and repairs common mistakes (trailing commas, single quotes, unquoted keys) so JSON.parse doesn't blow up.

Install

npm install llm-json-parse

Usage

import { parseLLMJson, safeParseLLMJson } from "llm-json-parse";

const text = await callYourLLM();

// Throws LLMJsonParseError if it truly can't be parsed
const data = parseLLMJson<{ name: string; tags: string[] }>(text);

// Or, never throws:
const result = safeParseLLMJson(text);
if (result.success) {
  console.log(result.data);
} else {
  console.error(result.error);
}

What it handles

  • Markdown code fences (```json ... ```, or plain ``` ... ```)
  • Extra prose before/after the JSON ("Sure, here's the result: {...} Let me know!")
  • Trailing commas ({"a": 1,})
  • Single-quoted strings ({'a': 'b'})
  • Unquoted object keys ({a: 1})
  • Braces/brackets inside string values (won't confuse the extractor)

API

parseLLMJson<T>(input: string, options?: ParseOptions): T

Parses and returns the JSON value. Throws LLMJsonParseError if parsing fails.

safeParseLLMJson<T>(input: string, options?: ParseOptions): SafeParseResult<T>

Never throws. Returns { success, data, error }.

ParseOptions

{ repair?: boolean } // default: true — set false to disable lenient repairs

License

MIT