Alternatives
Products that do what A text format for UI wireframes – comparing token costs across 4 format does
I've been exploring how to describe UI layouts to LLMs efficiently. The problem: When you ask an AI to generate or modify UI, how do you describe the current state? - Natural language ("header on top, form below") is ambiguous - ASCII art breaks when edited (alignment issues) - HTML is precise but verbose I ran some measurements. For a simple login form: - Natural language: 102 tokens - ASCII art: 84 tokens - HTML: 330 tokens I experimented with a grid-based text format using Excel-like cell references: grid: 4x3 A1..D1: { type: txt, value: "Login" } A2..D2: { type: input, label: "Email" }…
- 1WT
After working with LLMs for long enough, I found myself wanting a lightweight utility for doing various small tasks to prepare inputs, locate information and create evaluators. This library is two things: a very simple model and utilities that inference it (eg. fuzzy deduplication). The target platform is CPU, and it’s intended to be light, fast and pip installable — a library that lowers the barrier to working with strings semantically. You don’t need to install pytorch to use it, or any deep learning runtimes. How can this be accomplished? The model is simply token embeddings that are…
2024 · github.com
- 2BT
2015 · github.com
- 3TA
TokenDagger is a drop-in replacement for OpenAI’s Tiktoken (the tokenizer behind Llama 3, Mistral, GPT-3.*, etc.). It’s written in C++ 17 with thin Python bindings, keeps the exact same BPE vocab/special-token rules, and focuses on raw speed. I’m teaching myself LLM internals by re-implementing the stack from first principles. Profiling TikToken’s Python/Rust implementation showed a lot of time was spent doing regex matching. Most of my perf gains come from a) using a faster jit-compiled regex engine; and b) simplifying the algorithm to forego regex matching special tokens at all.…
2025 · github.com
- 4
- 5EU
We're open-sourcing 14 components & examples today for PDF, DOCX, and XLSX viewers, plus bounding box citations, file upload, e-signature, and more. It's MIT licensed and fully customizable. Demo video here: https://share.extend.ai/kRmSGKRF When we started, we tried every file viewer and document component library we could find. Unfortunately, none of them had all the functionality (and polish) that we wanted, so we ended up building our own for https://extend.ai/. It was only ever meant to be internal, but enough customers kept asking for it that we decided to…
Jun 2026 · extend.ai
- 6
- 7
- 8OC
I’m building a Unicode reference where each symbol has its own dev-friendly page with all relevant encodings. Example: [https://fontgenerator.design/symbol/almost-equal-to](https://fontgenerator.design/symbol/almost-equal-to) Includes Unicode, HTML, CSS, JS, UTF-8/16 bytes, URL encoding, and usage examples. The same structure is used across thousands of symbols (math, arrows, currency, tech/UI, punctuation). Built because existing references are fragmented. Feedback welcome.
Dec 2025 · fontgenerator.design
- 9TI
2016 · github.com
- 10BT
Small codebases were always a good thing. With coding agents, there's now a huge advantage to having a codebase small enough that an agent can hold the full thing in context. Repo Tokens is a GitHub Action that counts your codebase's size in tokens (using tiktoken) and updates a badge in your README. The badge color reflects what percentage of an LLM's context window the codebase fills: green for under 30%, yellow for 50-70%, red for 70%+. Context window size is configurable and defaults to 200k (size of Claude models). It's a composite action. Installs tiktoken, runs ~60 lines of inline…
Feb 2026 · github.com
- 11USunicode.style▲125
2018 · unicode.style
- 12
- 133I
OP here. I took the unofficial IKEA US dataset (originally scraped by jeffreyszhou) and converted all 30,511 products into a flat, markdown-like protocol called CommerceTXT. The goal: See if a flatter structure is more efficient for LLM context windows. The results: - Size: 30k products across 632 categories. - Efficiency: The text version uses ~24% fewer tokens (3.6M saved total) compared to the equivalent minified JSON. - Structure: Files are organized in folders (e.g. /products/category/), which helps with testing hierarchical retrieval routers. The link goes to the dataset…
Jan 2026 · huggingface.co
- 14ID
ISON (Interchange Simple Object Notation) - a data format optimized for LLMs and Agentic AI. The problem: JSON wastes tokens. Curly braces, quotes, colons, commas - all eat into your context window. ISON uses tabular patterns that LLMs already understand from training data: JSON (87 tokens): { "users": [ {"id": 1, "name": "Alice", "email": "[email protected]"}, {"id": 2, "name": "Bob", "email": "[email protected]"} ] } ISON (34 tokens): table.users id:int name:string email 1 Alice [email protected] 2 Bob [email protected] Features: - 30-70% token reduction - Type annotations - References between…
Dec 2025 · github.com
- 15WO
I ported Markus Kuhn’s wcwidth to TypeScript and optimized it with bitset lookups for O(1) performance. It now covers the full Unicode 15.1 combining ranges. GitHub: https://github.com/dawsonhuang0/Wcwidth-O1 NPM: https://www.npmjs.com/package/wcwidth-o1 Feedback welcome!
Sep 2025 · github.com
- 16TL
Little tool that I made to understand how (un)reasonable my prompts are.
Jan 2026 · github.com
- 17AL
Built a simple OpenAI token counter that doesn't crash. It gives you: Tokens Characters Words Paragraphs Link: https://openai-tokenizer.netlify.app/ Client side only. Feedback welcome.
2023 · openai-tokenizer.netlify.app
- 18LT
2025 · v0-llm-token-visualizer.vercel.app
- 19
- 20
Token-efficiency linter for LLM prompts and payloads - ritenv/tokensift
8d ago · github.com
- 21WD
Hi HN! I built WireMD, a text-first wireframing tool that lets you design UIs as fast as you can type. The core idea: wireframes should be version-controlled, reviewable in PRs, and editable without leaving your code editor/markdown editor. Outputs in multiple formats including for example html (different styles), tailwind and json Curious what HN thinks about the syntax design and whether this fills a gap in your workflow!
Nov 2025 · wiremd.dev
- 22AA
2016 · jollo.org
- 23CJ
Nov 2025 · github.com
- 24AT
Ranked by how close each launch is in meaning, then by votes. Refine with a description →