Hi makers,
Most wearables are good at telling when you're asleep. They're much worse at telling when you're awake: if you lie still, many devices count it as sleep. Sleep stages land somewhere in between. And Apple, Oura, Garmin, Whoop and Fitbit all build their scores differently, so the same night can get very different numbers.
Anna D. Zych, PhD, a neuroscientist and Health Science Lead at Momentum, goes through all of this in a webinar that premieres Wednesday, 7 October at 16:00 CET. It covers what good sleep actually looks like, how wearables compare to a sleep lab across ten devices, and how to approach building sleep scoring models.
If you're building anything with sleep or recovery data, it should be a useful hour. Everyone who signs up gets the recording too.
@michal_stochmal That exact problem is what the normalization layer is for. Raw HRV readings will still vary by sensor hardware (optical vs chest strap vs ECG), but OW runs the same scoring formula on top of normalized data regardless of device. Two athletes, same algorithm, comparable output. And since the thresholds are open, you can tune them for endurance training specifically rather than relying on defaults built for a general population.
@michal_stochmal They are, because we share scores from all providers and calculate our own score, using custom algorithm. It will be improvedover time of course, but right now it's already comparable to the whoop scores.
@michal_stochmal @kaliszs From what I see in running communities, Garmin dominates serious runners, Coros is growing fast especially in ultra/trail, and Polar still has a loyal base among those who've been around longer. Suunto less so lately. Would love to see all of them treated equally here.
@michal_stochmal Anyway, may I ask about your experience with your clients? Which devices are a top tier choices among runners? Are they all using Garmin or do you track usage of Suunto, Polar or Coros?
@kaliszs great question, from my experience coaching runners, Garmin dominates probably 70-80% of my athletes use it (Forerunner or Fenix series). Coros is growing fast, especially among ultrarunners who love the battery life. Suunto (tbh i dont like it) has a loyal niche, mostly trail runners. Polar is less common but I still see it occasionally.
@michal_stochmal That’s a very real issue in practice — even small differences in sensors and smoothing can cascade into pretty different recovery/readiness outputs.
Nutritionist here. Half of my clients track sleep and HRV obsessively but we're all working off screenshots and verbal summaries. Something that could aggregate this and let me run my own analysis would save hours per week. Do the scoring algorithms work without a developer integration or is this purely for engineering teams?
@adrian_bocianowski You can deploy the whole platform on Railway in about 5 minutes with one click, no specific server knowledge is needed. Once it's up, the MCP server lets you query all client data and run scoring analysis through Claude or another AI assistant without writing any code. The practitioner-facing layer that removes even that setup step is what we're building next, targeting Q2 2026.
@adrian_bocianowski screenshots and verbal summaries - that's the current state of health data collaboration and it's painful
honest answer: right now it does require a developer to set up. it's not a no-code tool yet
but what you're describing is exactly the use case we're building toward - a practitioner who can pull a client's real data, run analysis, ask the AI layer questions. not guess based on a screenshot
if you have a developer on hand or know one, happy to help get something working: https://discord.gg/openwearables
Thanks a lot for the detailed responses - I really appreciate it. It’s great to see you’re building exactly in the direction that solves a real problem in client work.
It sounds very promising, especially the ability to work with actual data instead of screenshots and summaries. For now, the lack of a no-code solution is a bit of a limitation for me, but I understand the current stage of the product.
I’ll definitely keep an eye on your progress, especially around the practitioner-facing layer. If anything more “plug & play” or early testing opportunities come up, I’d love to hear about it
@adrian_bocianowski same pain, different angle. I'm coaching runners and you're advising on nutrition, but we're both stuck interpreting screenshots instead of actual data. Curious: when you see HRV trend dropping over a training block, do you adjust nutrition recommendations proactively, or do you wait for the athlete to flag fatigue themselves? Wondering how much the data actually drives your decisions vs just confirms what they're already telling you.
In an era of hundreds of AI-based projects without any real utility, this one makes sense. It's an interesting use of AI for analytics. I'm curious about the project's launch and eager to explore with our team how we can combine analyzed data with wearable devices in our projects. We're using data from sports watches in a training app for golfers. Additional data is always welcome!
@jakub_burdajewicz Golf training app on sports watches is a solid fit. Strain, recovery, and HRV scoring are built in, and if your athletes are on Garmin, Polar, or Suunto, all three are supported out of the box. Drop by our Discord if you want to talk through the integration before your team digs in.
@jakub_burdajewicz Tbh there is still not so much of an AI. But it will be!
Btw which devices do you use for golf? I heard about special garmin models, are they worth it?
@jakub_burdajewicz Jakub - golf is one of the cleanest cases for a unified layer. Most serious players already stack a golf-specific watch (Garmin Approach line) with a recovery wearable (Whoop/Oura) — two devices,
two ecosystems, zero conversation between them. That's exactly the gap this fills. Drop into Discord, would love to see what you're building.
@jakub_burdajewicz golf training + wearable data is a great fit - recovery, strain, sleep before a round. a lot of signal there that most apps ignore
we'd love to see what you build. drop by Discord and let's talk: https://discord.gg/openwearables
Hey, I've tried three different health data aggregators and the one thing they all had in common was a monthly bill. Bookmarking this to try properly over the weekend.
@qtvinsky yeah that's the pattern - you pay to solve the data problem before you've even validated the product
let us know how it goes over the weekend, happy to help if you get stuck: https://discord.com/invite/qrcfFnNE6H
@qtvinsky And here Open Wearables go ;) Free and self hosted, great advantage.
Of course you still have to pay for you hosting, but I guess nothing is really free.
@qtvinsky 100% agree. Same here
@qtvinsky Jacek - those monthly bills usually start at $200-500/m before you've even shipped, then scale per user. Self-hosted you're paying $10-30/m for a small VPS until traction forces you up. That delta is why we did it this way. Ping us in Discord if Saturday gets weird.
@qtvinsky Same here!
The Garmin support stood out to me. Most integrations treat it as the afterthought behind Apple and Oura. Garmin users track seriously and the data depth is there, it just never gets used properly.
@sylwia_kustrzycka Exactly the observation we built around. Garmin users generate some of the richest longitudinal data out there and most platforms surface maybe 20% of it. We pull the full range: sleep stages, HRV, body battery, stress, workouts, SpO2, and more.
@kamil_maksymowicz Exactly! Having access to specific metrics like Body Battery, detailed HRV, and SpO2 is a total game-changer. It's great to finally see someone extracting 100% of Garmin's capabilities instead of just settling for surface-level stats. Awesome job!
@sylwia_kustrzycka But Garmin is still among 1st classers tbh. Check out Suunto for example, that's a hidden gem ;)
@kaliszs Totally agree, Suunto is definitely a hidden gem, especially for hardcore outdoor enthusiasts! Who knows, maybe after taming Garmin, their API will be next on the Open Wearables roadmap. 😉
@sylwia_kustrzycka That’s a fair observation — Garmin users are often the “serious end” of tracking, but a lot of apps still optimize around Apple Health and Oura first.
Garmin’s data depth is definitely there, but it tends to be fragmented across metrics, so the value often gets lost unless something actually consolidates and interprets it well. If an integration can do that cleanly, it’s probably a big unlock for endurance athletes and coaches in particular.
The real gap has always been less about access and more about making the data usable in a consistent way across different contexts.
@kamil_zadlo1 Spot on! The sheer depth of Garmin's data doesn't mean much if it stays fragmented. The real value (and the hardest part) is consistently consolidating and normalizing these metrics. If this solution lets coaches and athletes draw actionable insights without fighting data chaos, that's a massive step forward ;)
@sylwia_kustrzycka Garmin users are seriously data-rich and somehow always the afterthought
the API is painful but the data depth is real. glad we got it right
@piotr_pasierbek The pain of dealing with the Garmin API is pretty well-known in the industry, so massive kudos to you guys for doing the heavy lifting and getting it right! You're definitely going to save developers countless hours of headache. Congrats!
@sylwia_kustrzycka Noticed the same - Garmin often gets overlooked, even though the depth and quality of data is actually really solid. It just rarely gets used properly.
@adrian_bocianowski Definitely! Glad to hear I'm not the only one feeling this way. Fingers crossed that with the groundwork laid by Open Wearables, these powerful Garmin datasets will finally start being fully utilized by other platforms.
Plugged this into our club management app. Coaches finally see readiness, sleep, and load across every athlete - regardless of which device they wear. Stops the screenshot chase.
@iwan1212 "Stops the screenshot chase" might be the best one-line description of the problem we've heard. Coaches managing 20 athletes across 5 different apps is a real workflow nightmare and it's invisible until you sit with them.
Thanks for shipping with it Patryk. If you ever want to write up the deployment as a case study (or just a thread), happy to help, that story would land with a lot of teams.
@iwan1212 That’s actually the most compelling version of this story — not the aggregation itself, but removing the “screenshot + interpretation by hand” workflow from coaching entirely.
@iwan1212 Forgive me for being curios, but what type of the club is it?
@iwan1212 this is exactly the use case we had in mind - coaches seeing real data across the whole roster, not chasing screenshots
love hearing it's working in the wild
@iwan1212 "Stops the screenshot chase" this is so real. I've spent more time texting athletes "send me your HRV from last night" than actually coaching. Having readiness and load in one place, regardless of device, is the difference between reactive and proactive training decisions.
Voted. Curious whether the MCP server part is something an average person could set up with ChatGPT or Claude, or if that requires serious technical knowledge. The idea of asking an AI questions about your own health data sounds more useful than any wearable dashboard I've seen.
@krzysztof_szyszkiewicz thank you!
honest answer: today it requires some technical setup - you need to run the platform and connect the MCP server to your AI client. not rocket science but not one-click either
the vision is exactly what you described though - ask Claude or ChatGPT "why did I sleep badly this week" and get an actual reasoned answer based on your real data, not generic advice
that's where we're going. docs here if you want to try: https://docs.openwearables.io
@krzysztof_szyszkiewicz MCPs are not that complex, but processing such big amounts of data given limited context of LLMs usually is. We already have very first version of Open Wearables MCP server (it's in the repo so everyone can use it) but it needs some polishing to call it production grade and work flawlessly with big data sets.
@krzysztof_szyszkiewicz It shold be easy to setup, but I don't think it's really that useful. Simple chat with AI agent will do a better job. And that's also going to be avilable.