The demo is deployed to SweatStack Pages (pages.sweatstack.dev): Zero-config static hosting for SweatStack powered apps. This is free for now while I figure out what to do with it. (pages you publish now will be free forever).
You can use outside of an AI coding environment (CLI and web).
Posts by SweatStack
The demo uses SweatStack Skills to make Claude Code smarter. But these skills are not Claude Code specific, you can them in any AI coding environment. Learn more: github.com/SweatStack/s...
The app from the demo: hr-histogram-compare.pages.sweatstack.dev
Full prompt: hr-histogram-compare.pages.sweatstack.dev/prompt.txt
SweatStack + Claude Code = ๐
Use SweatStack together with Claude Code to go from idea to published app in just a few minutes! Demo:
www.loom.com/share/e72d6f...
Introducing SweatStack Skills: Install once, and your AI assistant knows everyting about SweatStack's API, auth flows, and data formats. No more pasting documentation into chat or explaining the same things repeatedly. Just describe what you want to build.
sweatstack.no/blog/2026/02...
Last day of the year: Time to make up the balance. You already know how far you ran, but how hard did you recover?
CouchGains: Your Year in Recovery.
Finally, the recognition you deserve for doing absolutely nothing. Powered by @sweatstack.bsky.social
couchgains.sweatstack.no
Your Strava Year in Sport, but without the nonsensical metrics like who kudoed me most (I already know who's stalking me).
Slightly geeky. Powered by @sweatstack.bsky.social.
graph.sweatstack.no
Kevin Yven (Sport'N Data) created this awesome Yearly Summary Wrap using SweatStack.
Link: sportndata.com/wrapped
SweatStack 0.42.0 is here!
It has the words DON'T PANIC printed in large friendly letters on it (and includes some useful features too).
Whether you're exploring the galaxy or hitting PRs, always know where your towel is.
Get started: sweatstack.no
#DontPanic #42 #HitchhikersGuide
New tutorial: "One-Off Analysis Scripts: Cycling Torque Example"
developer.sweatstack.no/tutorials/on...
New Streamlit tutorial for SweatStack: developer.sweatstack.no/tutorials/qu...
Amazing!: fpca.paperplayground.app From
@aartgoossens.bsky.social
a Paper Playground paperplayground.app implementation of the FPCA model. It's a great concept to interactively showcase research results. cc
@drphilipskiba.bsky.social
Code is hosted here: github.com/SweatStack/s...
Currently the server needs to be run locally (instructions in the README). A hosted version might follow later.
The SweatStack MCP server built using the official Python SDK for MCP servers: github.com/modelcontext...
...and uses the SweatStack Python library: developer.sweatstack.no/getting-star...
Even with Claude Desktop's code execution limitations, it can already analyze basic workout data from SweatStack. This proof-of-concept shows a path forward: As AI tools evolve, tools like this will become proper data analysis assitants for anyone interested. Small steps!
Screen recording of Claude Desktop accessing activity data from SweatStack using the SweatStack MCP server.
Fridriday hack project: SweatStack MCP server ๐๐ค
Now AI assistants can access SweatStack data directly! Watch Claude Desktop pull my activity data and analyze it without writing a single line of code!
The SweatStack Python library has built-in support for Streamlit, making it incredibly easy to start building your dream app.
developer.sweatstack.no/learn/integr...
Currently works with Garmin Connect and @intervals.icu. More integrations will follow.
Try it out at sweatstack.run ๐
New: SweatStack Express Login lets you register by simply connecting a data source - no account setup needed.
This drastically improves onboarding for 3rd party applications that are powered by SweatStack.
Sneak peek ๐
A screenshot of sweatstack.run that shows Python code on the left that pulls data from SweatStack and an ASCII art plot on the right.
An example of code/sandbox sharing: sweatstack.run/store/3232be...
Usecase is similar but different from the SweatStack Console: For quick explorations, the Console is slightly nicer to work with because it's a proper REPL that keeps a Python session running. However, for larger scripts that you want to keep and/or share, sweatstack.run is the way to go.
It automatically authenticates with your SweatStack account using OAuth2/OpenID and installs any dependency you import.
As an alternative to the Console, I also deployed a variant on @pydantic.dev 's pydantic.run : sweatstack.run
SweatStack Console: Quick access to your training data using an in-browser interactive Python console. ๐
console.sweatstack.no