A different approach to digital mental health.

80% of mental health app users stop within two weeks. Text-heavy tools demand cognitive effort during distress. AI chatbots fail at crisis detection.

We build something different: physiological, non-verbal tools that work through the body, not around it. Research-backed. Open-source. Designed to complement existing platforms like mindLAMP, not compete with them.

Why Physiological? Why Non-Verbal?

These aren't aesthetic choices. They're responses to documented problems.

Larger Effect Sizes

HRV biofeedback shows effect sizes of d = 0.81 for anxiety. Digital CBT shows d = 0.4-0.6. Physiological approaches consistently outperform purely cognitive digital interventions.

Goessl et al., 2017; Cuijpers et al., 2019

Works During Distress

Text-heavy apps require reading and cognitive effort—exactly what's hardest during anxiety or depression. Visual breathing pacers and biophilic patterns work when words can't reach you.

No literacy barrier. No language barrier.

Integration, Not Competition

Platforms like mindLAMP already do measurement and phenotyping well. We build open tools designed to complement that ecosystem—usable standalone or as integrated activities.

Building on Dr. Torous's work, not duplicating it.

What's Different Here

Each design choice addresses a documented failure in existing approaches.

Problem with Prior Approaches This Approach Evidence
Text-heavy apps require cognitive effort during distress Non-verbal physiological tools — visual pacers, biophilic patterns HRV d=0.81 vs CBT d=0.54
AI chatbots fail at crisis detection (78% miss rate) No chatbots — human escalation always ≤2 taps away Brown University, 2025
Apps lose 80% of users in 2 weeks Minimal friction design — no streaks, no guilt, no accounts required Baumel et al., 2019
Algorithmic personalization creates filter bubbles and privacy risks User-controlled preferences — on-device, transparent, exportable Privacy-preserving by design
Siloed tools duplicate existing research infrastructure Integration-first — designed to complement mindLAMP, not compete Open-source, documented APIs
See the full design rationale →

What We Won't Do

Boundaries matter. Here are ours.

  • We won't claim therapeutic benefit without evidence. If something might help, we say "might." If evidence is limited, we say so.
  • We won't pretend AI can replace human connection. The research is clear: hybrid approaches work best.
  • We won't hide our sources. Everything is cited. You can check our work.
  • We won't promise what technology can't deliver. Digital tools have real limitations. We discuss them.
  • We won't ignore safety. Crisis protocols, escalation paths, and human oversight are non-negotiable.

Part of Something Larger

If You're in Crisis

This is a research site, not a crisis service. If you or someone you know is in immediate danger:

  • 988 Suicide & Crisis Lifeline: Call or text 988 (US)
  • Crisis Text Line: Text HOME to 741741
  • Emergency: Call 911 or go to your nearest emergency department
  • International: Find a helpline in your country