JSON Kit
Fix broken AI JSON and 6 more JSON tools, all in-browser
What it does
JSON Kit is a set of fast, browser-side JSON tools built for the AI era. The standout is Fix LLM JSON: paste the broken JSON that ChatGPT, Claude, or local models hand you, and get clean, valid JSON back instantly, with a label for exactly what was wrong (trailing commas, single quotes, Python literals, markdown fences, truncated output, and more). Everything runs 100% in your browser, so your output never touches a server.
Does the same job
all alternatives →- IMI made a tool which fixes broken JSONs2024 · prakhar897.github.io · ▲29
- ICI coded my own JSON translation tool to easily localize my side project2024 · quicklang.app · ▲43
Hi HN, I’m Joan, the developer of Quicklang. I made this app to easily translate and keep in sync all my localization JSON files for my side projects. While searching online for a similar tool, I only found enterprise solutions that do not allow direct editing of JSON files. I used to use ChatGPT to translate the JSON translation file changes before coding Quicklang. However, I realized that ChatGPT only allows you to input short content for translation into another language (even if you provide a .json file), and each time I had to request translations for one language at a time. So, I…
- RLRobust 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…
More ai this month
the category →
I trained a 125M-parameter transformer to autocomplete piano performances in real time (~108 notes/sec on an iPhone 15). The idea is basically GitHub Copilot or Tabnine, except instead of prompting it with code, you prompt it by playing a few notes on a MIDI piano. The model then continues what you played, entirely on-device. The app is free if anyone wants to try it. Happy to answer questions about the model, training, Core ML, or the many things that didn't work.
AI · 17d ago · simedw.com
Astute▲585Automate your B2B brand going viral, with new media creators
AI · 18d ago · company-app.joinastute.com
Hey HN, Henry from Cactus here! We previously released Cactus Needle, a 14MB agentic LLM for tool call, device use, and structured extraction for phones, wearables, smart homes, small robots and microcontrollers. We got really great feedback here, and have now incorporated the suggestions to release Needle 2. The whole model is a single 14MB binary that runs a full session in 28MB of RAM; 45m parameters at 2bit compression. Needle hits 500 tokens/sec decode speed on a Raspberry Pi 5, sits between 400-1,500 tokens/sec on VR devices like Meta Quest 3S and Apple Vision Pro, and ranges…
AI · 27d ago · cactuscompute.com
Launched alongside, May 2026
the whole month →
Parallel agents, diff reviewer, and multi-model comparisons
Dev tools · May 2026 · kilo.ai
- NW
Hey HN, Henry here from Cactus. We open-sourced Needle, a 26M parameter function-calling (tool use) model. It runs at 6000 tok/s prefill and 1200 tok/s decode on consumer devices. We were always frustrated by the little effort made towards building agentic models that run on budget phones, so we conducted investigations that led to an observation: agentic experiences are built upon tool calling, and massive models are overkill for it. Tool calling is fundamentally retrieval-and-assembly (match query to tool name, extract argument values, emit JSON), not reasoning. Cross-attention…
Life & fun · May 2026 · github.com
- FM
Dev tools · May 2026 · github.com