Superrr
Superrr is an MCP server that gives taste to your agents
What it does
Connect Superrr to your agent, your landing page will be different than any results you could have.
A remote MCP server that hands your agent a direction, exact tokens and a page structure to build against — then re-opens what it shipped and grades it.
An MCP server that hands your agent a direction, exact tokens and a page structure to build against — then re-opens what it shipped and grades it. Not customers — clients. Shapes verified against each vendor's own docs. The calls that plan a page cost nothing, because a plan you cannot afford to iterate on is a plan you will not iterate on. The two that spend real money — an image model and a critique — are the two that price like it. Seven calls from a brief to a page that has been measured. The last one is the point: the server re-opens what your agent shipped, measures the live DOM against the same rubric it planned from, and tells you where it fell short. There is nothing to configure…from superrr.design
Does the same job
all alternatives →
More dev tools this month
the category →
Open-source GTM skills for technical founders
Dev tools · 29d ago · gtmcofounder.com
OpenTrailPaper is open-source bike computer firmware for the LilyGO T5S3 4.7" E-Paper PRO. It supports offline maps, GPX routes, FIT recording and Bluetooth sensors.
Dev tools · 1d ago · opentrailpaper.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