Alternatives
Products that do what Tokenscout does
A design-token extractor for live, rendered websites
- 1
- 2AC
I had this idea kicking around in my head for quite a while. Took an evening to make this, and a short morning to polish it a bit. So here it is!
2022 · arantius.github.io
- 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
- 5
- 6TCtextshader.com▲260
TLDR: Click the link to see some cool visualizations, refresh a few times for random examples, and try editing some of the code yourself. This is a small weekend project of mine inspired by shadertoy.com It's a static single-page site hosted on GitHub pages so the website design is pretty barebones. I'm not a web developer so I mainly wanted to create a Cool Thing with my free time and not have to learn tons of front-end to do it. I'd love to hear what people think about it and please post or send me any shaders you make! You can use the link button in the bottom right to share. I hope that…
2022 · textshader.com
- 7
- 8CA
Built this after realizing I was spending ~$1400/week on Claude Code with almost no visibility into what was actually consuming tokens. Tools like ccusage give a cost breakdown per model and per day, but I wanted to understand usage at the task level. CodeBurn reads the JSONL session transcripts that Claude Code stores locally (~/.claude/projects/) and classifies each turn into 13 categories based on tool usage patterns (no LLM calls involved). One surprising result: about 56% of my spend was on conversation turns with no tool usage. Actual coding (edits/writes) was…
Apr 2026 · github.com
- 9
Turn any website into reusable design tokens instantly
Apr 2026 · chromewebstore.google.com
- 10
- 11AC
I built this API to return the closest named color for any hex value—using curated lists like my own [1], XKCD [2], and others. I made it from scratch without Express or any frameworks because: - I’m a frontend/interaction dev and wanted to learn how to build an API from the ground up. - Existing APIs didn’t guarantee unique names per color—mine does. - It also supports WebSocket updates, gzip responses, and multiple name sets. I’ve been collecting color names for over 10 years [1]. With ~30,000 entries, bundling them into every color-related project became excessive. This API keeps…
2025 · meodai.github.io
- 12
- 13EP
2020 · extract.pics
- 14RL
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…
Mar 2026 · github.com
- 15
- 16
- 17
- 18
- 19
- 20MS
2017 · getmirrorshades.com
- 21
Reveals any website's design system, tokens, and tech stack.
7d ago · chromewebstore.google.com
- 22AL
2013 · brycec.github.com
- 23
Turn any website into a reusable design system in seconds
Apr 2026 · npmjs.com
- 24
Ranked by how close each launch is in meaning, then by votes. Refine with a description →