This is a submission for the Hacktoberfest Open-Source AI Challenge Week 1: Touch Grass
What I Built
Remote workers, software engineers, and creators spend an average of 9+ hours a day bathed in unnatural 6500K LED screen glare. This locks our vision at a fixed 24-inch focal length, suppresses natural melatonin timing, and triggers chronic burnout.
Most "wellness apps" make this worse by demanding more screen time: logging calories, reviewing biometric graphs, or scrolling meditation libraries.
SolSpot is built around one core philosophy: Make the screen the shortest part of the experience.
SolSpot is an anti-burnout natural light optimizer. Instead of keeping you glued to a monitor, it evaluates hyper-local atmospheric conditions (solar irradiance, blue-light ratio, UV risk, cloud cover, and wind chill) to discover your personal Peak 20-Minute "Touch Grass" Window of the day.
When your window arrives:
- The 20-Minute Golden Window: Identifies the exact minutes when natural outdoor blue-light photons synchronize your circadian cortisol rhythm without erythema (sunburn) risk.
- Gemma 2 Sensory Micro-Quest: Before you step outside, Google's Gemma 2 synthesizes a 60-second mindfulness quest tailored to current weather (e.g., "Step outside, face 45° away from direct sun, close your eyes for 30 seconds and let the photons warm your eyelids. Put your phone in your pocket.").
- Grass Mode: A tranquil, full-screen lock screen with a 20-minute countdown, rhythmic 4s/4s breathing circle, and procedural nature wind audio that instructs you: "Phone Face Down. Eyes to the Horizon."
Demo
- Live Deployed App: https://solspot.onrender.com
- API Health: https://solspot.onrender.com/api/health
-
Interactive Experience:
- Dynamic Solar Trajectory Arc rendering the sun's elevation from dawn (6 AM) through solar noon to dusk (8 PM).
- One-click "Activate Grass Mode" meditative full-screen immersion with procedural audio synthesis via Web Audio API.
- Local session streak tracking and collectible "Natural Light Pioneer" milestone badge.
Code
The complete source code is open source and hosted on GitHub:
🌿 SolSpot — The Anti-Burnout Natural Light Optimizer
Hacktoberfest Open-Source AI Challenge: Week 1 — "Touch Grass" Submission
Tag:#hf26challenge
Target Prize Categories: Best Use of TabPFN (Prior Labs) ($200) & Best Use of Gemma (Google) ($200)
💡 What We Built & The Problem
Remote workers, engineers, and creators spend an average of 9+ hours a day bathed in unnatural 6500K LED screen glare. This suppresses natural melatonin timing, elevates chronic stress, and leads to screen burnout.
Most health apps demand more screen time: tracking food, counting reps, or reading lengthy meditation guides.
SolSpot is designed with one core philosophy: Make the screen the shortest part of the experience.
SolSpot analyzes hyper-local atmospheric and solar data (GHI irradiance, direct blue-spectrum light, UV index, cloud filtering, and thermal indices) to pinpoint your personal Peak 20-minute "Touch Grass" Window of the day.
When your window arrives, SolSpot launches Grass Mode…
(Direct repository link: https://github.com/YadneshTeli/Solspot)
System Architecture:
flowchart TD
User([👤 User]) -->|Opens App| UI[🖥️ SolSpot Web UI\nVanilla CSS Glassmorphism]
UI -->|Local Coordinates| API[⚡ FastAPI Backend on Render]
API -->|Free Solar Metrics| OM[☀️ Open-Meteo API\nGHI, UV, Temp, Clouds]
OM -->|Hourly Atmospheric Vectors| TabPFN[🧠 Prior Labs TabPFN\nZero-Shot Tabular Transformer]
TabPFN -->|Circadian Curve| Best[🌟 Peak 20-Min Window]
Best -->|Weather Context| Gemma[💎 Google Gemma 2 2B-IT\nSensory Micro-Quest Engine]
Gemma --> UI
UI -->|Engage Grass Mode| Lock[🌿 20-Min Fullscreen Horizon Timer]
Lock -->|Local Session Log| Storage[(🔒 100% Private LocalStorage)]How I Built It
SolSpot is powered by two complementary open-source AI pillars:
1. TabPFN (Prior Labs) — Zero-Shot Tabular Foundation Model
Atmospheric chronobiology is tabular data: solar zenith angle, Global Horizontal Irradiance ($W/m^2$), UVB index, cloud cover %, ambient temperature, and wind speed.
Instead of trying to force an LLM to predict tabular curves or manually tuning hyperparameters across classic tree models, we used Prior Labs' TabPFN (tabpfn>=9.1.0). TabPFN is a transformer pretrained on synthetic tabular datasets that performs instantaneous zero-shot in-context learning. We feed hourly atmospheric vectors directly into TabPFNRegressor to evaluate circadian daylight scores across the day in milliseconds:
from tabpfn import TabPFNRegressor
# Zero-shot tabular evaluation across hourly atmospheric vectors
model = TabPFNRegressor(device="cpu", n_estimators=4)
model.fit(X_circadian_calibration, y_wellness_scores)
# Predict circadian daylight score curve for the entire day
hourly_scores = model.predict(todays_hourly_matrix)
2. Google Gemma 2 (2B-IT) — 60-Second Sensory Micro-Quest Engine
Once the window is computed, Google's Gemma 2 generates concise, grounding outdoor prompts calibrated to the temperature, cloud cover, and solar angle. It specifically prompts for non-visual senses (smell, skin thermal perception, distant horizon eye relaxation) and explicitly directs the user to close or pocket the screen.
3. Open-Meteo & Zero-Tracking Architecture
Solar radiation and UV data are fetched from Open-Meteo's open solar API without API keys or tracking IDs. All streak progress is persisted in local storage.
Why Does Open Innovation Matter?
In a world where big-tech wellness apps monetize your GPS tracking and charge subscription fees for generic advice, an open-source approach fundamentally changes the paradigm:
- Local Privacy by Default: You shouldn't have to upload your real-time geolocation or daily routine to an ad-targeting server just to know when to take a walk. Open models and open APIs run privately on your own device.
- Zero Cloud Tolls & Offline Resilience: In the backcountry, on a hiking trail, or in a park with patchy cellular reception, closed cloud APIs fail or introduce latency. Open weights like Gemma 2 and local tabular models like TabPFN run in dead zones with zero per-token API charges.
- Specialized Tabular Intelligence: LLMs are often misapplied to tabular problems. Prior Labs' open foundation model proves that specialized open transformers deliver vastly superior accuracy for scientific atmospheric data without black-box cloud lock-in.
My Agent Session
This project was planned, scaffolded, and built with AI pair programming using DevRelay. You can explore the full session transcript here:
use devrelay mcp and fetch week 1 challenge and suggest what to build
Analyzed Week 1 'Touch Grass' challenge requirements. Scaffolds SolSpot: an anti-burnout daylight optimizer using Prior Labs TabPFN for zero-shot tabular circadian curve regression and Google Gemma 2 for outdoor sensory micro-quests.
(Direct session link: https://dev.to/agent_sessions/building-solspot-anti-burnout-natural-light-optimizer-with-tabpfn-and-gemma-2-zc42sg)
Top comments (0)