Contexxt
Give your AI tools your full design system to build with
What it does
Contexxt turns your design system into rich, detailed context for your AI coding tools. Through one MCP, Claude, Cursor and Copilot get your whole system, every token, component and rule and how it's used, so they can build new things that actually fit your design system instead of guessing. That's far more than a raw Figma connection gives them. And once the code is written, Contexxt checks it against that same system too.
Contexxt turns your design system into one machine-readable source of truth, serves it to your AI coding tools over MCP, and checks that the code they ship actually followed it.
Claude, Cursor and Copilot are fast, but they don't know your colours, spacing or components, so they guess. Contexxt gives them the real ones and then checks every pull request to make sure they were actually used, before anything reaches your users. Contexxt does both. It gives your AI tools your real design system, the tokens and components exactly as they exist in your code, and then checks every change to make sure they were actually used. Most tools stop after the first half. Not a copy of your design file. Your tokens ranked by how much you actually use them, your components with their real props, and the exact token for any stray value an agent reaches for. Every pull request…from contexxt.app
Does the same job
all alternatives →
Design in Figma using Cursor Agent + MCPJan 2026 · ▲100Design automation in Figma using AI and natural language
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 · 16d 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 · 26d ago · cactuscompute.com
Launched alongside, August 2026
the whole month →- TL
Life & fun · 9d ago · louisabraham.github.io
- SA
Hello HN! I found that picking out plausible but diverse skin tones for my digital art and game development projects was kind of difficult, and I got curious about if there was a way to define a color space that made it easy. I've built a color picker and procedural generation algorithm based on the space as well as a bunch of other fun js features and demos throughout the page that use the equations. If you find it interesting, I have lots of explanations of how I built it and what properties the space has. The methodology might be a bit shaky, but hopefully the result is as helpful for…
Life & fun · Aug 2026 · toneyalexander.github.io
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 · 16d ago · simedw.com