Alternatives
Products that do what langdiff – Stream valid JSON from LLMs with type-safe callbacks does
Ever had json.loads() explode halfway through an LLM stream? langdiff fixes that with a schema + callback approach. Define your schema → attach callbacks → push streaming tokens → get structured events immediately.
- 1
- 2
- 3XS
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 up gravitating towards boring time-tested XML-esque tag-based delimiters instead of JSON/function-calling for the following reasons: - Diverse presence in training corpuses (consider flavours of content commonly adjacent to these syntaxes vs. JSON) - HTML was…
2024 · github.com
- 4JS
2018 · npoint.io
- 5AL
2011 · github.com
- 6JM
2012 · github.com
- 7ET
We built a browser extension (Chrome + Firefox) that captures the runtime DOM and exports it as JSON. Not the pre-render source (HTML/CSS/JS, templates, bundles) and not a screenshot — but the live, post-render state the browser is actually displaying: - visibility/hidden, disabled/required - current input values and validation/validationMessage - dataset attributes - trimmed text - stable selector paths Why: LLMs often miss or guess UI state. Screenshots are too opaque, pre-render source is too noisy. A structured snapshot gives reproducible context for debugging…
2025
- 8OS
2023 · github.com
- 9JD
2015 · json-diff.com
- 10RS
2019 · github.com
- 11CA
Hi HN, I've been working with LLMs in production for a while both as a solo dev building apps for clients and working at an AI startup. The one thing that always was a pain was to pay OpenAI/Gemini/Anthropic a few dollars a month just for me to say "test" or have a CI runner validate some UI code. So I built this server called ChunkBack, that mocks the popular llm provider's functionality but allows you to type in a deterministic language: `SAY "cheese"` or `TOOLCALL "tool_name" {} "tool response"` I've had to work in some test environments and give good results for experimenting…
Nov 2025 · github.com
- 12SE
I built a CLI tool in Go that extracts structured data (JSON, CSV, Parquet) from messy PDFs and HTML pages. The core idea: LLMs are great at understanding structure but wasteful for bulk data extraction. So smelt uses a two-pass architecture: 1. A fast Go capture layer parses the document and detects table-like regions 2. Those regions (not the whole document) get sent to Claude for schema inference — column names, types, nesting 3. The Go layer then does deterministic extraction using the inferred schema This means the LLM is never in the hot path of actual data processing. It figures out…
Mar 2026 · github.com
- 13LC
Debugging is hard for LLMs, because they primarily depend on source code, and they don't have access to runtime state. I spent countless hours debugging code, and the only way I found LLMs useful for that, is to ask them to add log lines. That's annoying, because it pollutes my code and adds unnecessary diffs. So we made an MCP server that solve this problem. It gives MCP clients (like Claude Code) access to a NodeJS inspector, so they can: 1. set breakpoints 2. step in, step out, continue 3. fetch the current execution location 4. read console output 5. run JS using eval To try: 1. run a…
2025 · github.com
- 14EC
Hi! I've found myself repeatedly writing little scripts to do bulk calls to LLMs for various tasks. For example, run some analysis on a large list of records. There are a few "gotchas" to doing this. For example, some service providers have rate limits, and some models will not reliably return JSON (if you're asking for it). So, I've written a command for this. What I've tried to do here is let the user break up prompts and configuration as they see fit. For example, you can have a prompt file which includes the API key, rate limit, settings, etc. all together, or break these up into…
2025 · github.com
- 15JA
2015 · github.com
- 16LC
Hey, folks here is a peek into Jujutsu. We at Poozle are working with hundreds of APIs and it has been always frustrating to 1. Search the API in the documentation or ask ChatGPT 2. Then copy it to the postman and understand/test the API 3. Generate code to integrate into the codebase We thought how about having all of this at one place. We currently fine-tuned LLM on public REST APIs to reduce hallucination and then combined it with ChatGPT and Postman. I look forward to feedback, feature requests and discussions!
2023 · loom.com
- 17JA
Apr 2026 · jsoncompat.com
- 18
- 19JD
We've all been there: you have some JSON data you need to make sense of, so you Google "json formatter" and end up at a site ridden with ads. I used to look at at lot of JSON (mostly log data) for $oldjob, so I set out to build something better. I know there are a lot of tools in this space, but I've put a lot of love into JSON Dive: things like Vim keyboard shortcuts to navigate, dark mode, timestamp/image previews, and multi-file-format-support (XML-in-JSON was a format I dealt with in the context of LLMs/tool calls). I've also made an effort to ensure it can handle large files,…
Sep 2025 · jsondive.app
- 20SS
Hi HN, I’m building SEE (Semantic Entropy Encoding): a searchable compression format for JSON/NDJSON. Goal: reduce the “data tax” (storage/egress) and “CPU tax” (decompress/parse) by keeping JSON searchable while compressed, with page-level random access. I just published a proof-first evaluation release: Offline DEMO ZIP (~10 min): prints compression ratios + skip rates + lookup latency (p50/p95/p99) DD pack: audit/repro evidence (decode mismatch=0, extended mismatch=0, audit PASS) Latest release:…
Feb 2026 · gitlab.com
- 21MA
2023 · modelfusion.dev
- 22JS
Relatively simple currently, but figured I'd post for some feedback. I started this project last year but somewhat abandoned it. This feels like something which most likely already exists, but I couldn't find anything at the time I made it. I feel like my write up on the repo is pretty good at explaining the inspiration and purpose of this package; "Let's say you have an API, and you're looking for a method by which you can increase performance of your app via doing transformations of the data directly in the API. In this scenario, you would middleman the API returned data through a Fluxduct…
2022 · github.com
- 23PL
Hey HN! We realised that LLMs are great at generating code for super popular libraries like React. But they kinda suck at using less popular/newly released libraries, forcing us to stick to established tools and hindering innovation. There is already a standard for creating documentation for LLMs (llmstxt.org), but in my experience the implementations have not been great so far. `llms.txt` works as a good index of the available pages, but in many cases they link to HTML pages. This is a waste for LLMs to parse through (For example, Hono's [best…
2025 · github.com
- 24CA
A couple years ago I was really frustrated by Postman, it couldn't do basic JSON schema validation, and didn't interoperate well with the OpenAPI spec I had to use for serverless deployments. On top of that, they started requiring an account and cloud sync, and other things I just wasn't comfortable with. So what's an engineer to do? Build yet another API Client of course! [0] It's still fairly rough and crashes more often than I like, but it's basically at the point that I've switched most of my usage so I figured I would rip off the bandaid and do a Show HN. Short list of some of the…
2024 · callosum.dev
Ranked by how close each launch is in meaning, then by votes. Refine with a description →