nowfound

AI · December 18, 2024

xmllm

Simple structured data from any LLM.

Launched as “xmllm – Structured LLM streaming output using lenient XML parsing”

xmllm launched on December 18, 2024 with 5 votes and more than 50% of that year's launches. The site was still online in September 2026, 1 year on.

What it does

Simple structured data from any LLM. Contribute to padolsey/xmllm development by creating an account on GitHub.

In the maker’s words, at launch

Hi HN. I made a little JS library for streaming structured data from LLMs using leniently-parsed XML as a medium. E.g. await simple('fun pet names', { schema: { name: Array(String) }, model: 'openrouter:mistralai/ministral-3b' }); // => ["Daisy", "Whiskers", "Rocky"] Demos: xmllm.j11y.io When using LLMs, I've ended…

Pricing, as stated on its site

Free — Free and open source

checked November 2026 · prices change

  • Robust LLM extractor for websites in TypeScriptMar 2026 · github.com · ▲72

    We've been building data pipelines that scrape websites and extract structured data for a while now. If you've done this, you know the drill: you write CSS selectors, the site changes its layout, everything breaks at 2am, and you spend your morning rewriting parsers. LLMs seemed like the obvious fix — just throw the HTML at GPT and ask for JSON. Except in practice, it's more painful than that: - Raw HTML is full of nav bars, footers, and tracking junk that eats your token budget. A typical product page is 80% noise. - LLMs return malformed JSON more often than you'd expect, especially with…

  • l1m.io2025 · l1m.io · ▲135

    L1M is a lightweight API that extracts structured data from unstructured text and images using large language models.

  • A new benchmark for testing LLMs forApr 2026 · interfaze.ai · ▲60

    When building workflows that rely on LLMs, we commonly use structured output for programmatic use cases like converting an invoice into rows or meeting transcripts into tickets or even complex PDFs into database entries. The model may return the schema you want, but with hallucinated values like `invoice_date` being off by 2 months or the transcript array ordered wrongly. The JSON is valid, but the values are not. Structured output today is a big part of using LLMs, especially when building deterministic workflows. Current structured output benchmarks (e.g., JSONSchemaBench) only validate…

  • Magentic2023 · github.com · ▲283

    This is a Python package that allows you to write function signatures to define LLM queries. This makes it easy to mix regular code with calls to LLMs, which enables you to use the LLM for its creativity and reasoning while also enforcing structure/logic as necessary. LLM output is parsed for you according to the return type annotation of the function, including complex return types such as streaming an array of structured objects. I built this to show that we can think about using LLMs more fluidly than just chains and chats, i.e. more interchangeably with regular code, and to make it…

  • Beyond text splitting2024 · github.com · ▲206

    Improved file parsing for LLM’s.

  • Min.js style compression of tech docs for LLM2025 · github.com · ▲177

    Min.js Style Compression of Tech Docs for LLM Context

More ai this month

the category →
  • Free, open-source embroidery software for Mac and Windows. Turn SVG artwork into machine embroidery, edit stitches visually, and create designs with AI agents via MCP.

    AI · 10d ago · github.com

  • Make and publish 3D games with the first AI game engine

    AI · 25d ago · wanaka.app

  • Empacer▲468

    The voice-first assistant for small business owners

    AI · 26d ago · empacer.com

  • Keep your coding agent up to date with the latest web best practices

    AI · 12d ago · github.com

  • The community you trust in the assistant you use

    AI · 16d ago

  • A simulated world that makes your agent improve on every run

    AI · 17d ago · simulation.plurai.ai

Is xmllm yours? Feature it on the home page: $19, or free with the badge →

Source: Show HN post ↗ · launch text quoted in part

Launched alongside, December 2024

the whole month →
  • Remy AI▲2,170

    Anyone can sleep and recover better

    AI · 2024 · apps.apple.com

  • Remento▲1,681

    The AI biographer for loved ones

    AI · 2024 · remento.co

  • Aimfox▲1,213

    Built for LinkedIn outreach, made to close deals

    Growth · 2024 · aimfox.com

  • Stackfix▲1,112

    Compare software in seconds

    AI · 2024 · stackfix.com

  • Coval▲1,012

    Simulation & evals to ship delightful voice & chat AI agents

    AI · 2024 · coval.ai

  • VocAdapt▲961

    Master languages with AI-adapted authentic content

    Life & fun · 2024 · vocadapt.com