Why does your recovery score say 58% today?
I wear a WHOOP. I've coached people on movement and sleep for many years and I still can't answer that question for myself. The algorithm is locked. You get a number, you trust it, you stop there.
When we built Open Wearables, we decided the scoring layer should work differently. Sleep Score and Resilience Score shipped in v0.5 - every coefficient, every threshold, every weighting is in the repo and you can fork them, tune for endurance athletes or elder care or clinical populations. Moreover, you run them on your own infrastructure and the same algorithms feed the MCP layer so AI coaching can cite the actual data behind a recommendation instead of approximating.
Oura, WHOOP, Garmin they're all great devices but their scores are black boxes. Open algorithms mean when someone asks "why," you have a real answer.
Replies
How do you handle consistency when different teams start tweaking the scoring logic?
Open Wearables
@amelia_martin7 Quite simple :) each team runs their own deployment, so tweaked algorithms are scoped to their users only. The base algorithms act as the shared reference: if cross-team comparability matters, you stay on the unmodified version. Tuning is for population-specific accuracy, and the full change history in the repo makes any divergence explicit and auditable.
kamil_maksymowicz Thanks for explaining , some times questions looks simple but make curiosity in mind .
Open Wearables
@caleb_bennett1 Those are often the most important ones to answer clearly:) Thanks for following the thread - remember to leave an upvote if you like the idea 🙏 @amelia_martin7
@kamil_maksymowicz Sure sure no problem , always happy to support :)
@kamil_maksymowicz Thank you for clearing this. :)
The problem with Oura and Whoop is that they treat everyone like they have the same lifestyle. If you don't fit their 'ideal' user profile, the data is useless. Being able to actually see (or fork) the algorithm is huge because then the score might actually adapt to a regular person’s life, not just some pro athlete’s recovery cycle. Transparency > 'Magic' numbers.
Open Wearables
@naprich True! The pro athlete baseline problem is real. Default HRV thresholds tuned for endurance athletes will flag a healthy sedentary person as "poorly recovered" every single day. Forking the algorithm means you can set population-specific thresholds: what good recovery looks like for a 55-year-old office worker is a different number than for a triathlete.
@kamil_maksymowicz .We’ve spent years letting marketing departments define what 'healthy' looks like through locked algorithms... When you open the math, you shift the power from the brand back to the user. It’s the difference between a 'lifestyle gadget' and an actual medical-grade tool. If I can't adjust the baseline, the data is just noise wrapped in a nice UI