|
19351
|
Untitled by @navak | Stardance
|
navak
|
0
|
0.0
|
0
|
[]
|
[]
|
Title: Untitled by @navak | Stardance
|
1793393546.9036982
|
1793998346.9036982
|
|
19352
|
AgosBot by @jasevillaverde | Stardance
|
jasevillaverde
|
0
|
0.0
|
0
|
[]
|
[]
|
Title: AgosBot by @jasevillaverde | Stardance
|
1793440602.091063
|
1794045402.091063
|
|
19353
|
Cosmic Website by @Charan_K16 | Stardance
|
Charan_K16
|
0
|
0.0
|
0
|
[]
|
[]
|
Title: Cosmic Website by @Charan_K16 | Stardance
|
1793443954.9385011
|
1794048754.9385011
|
|
19354
|
Cyber Type by @Livvy | Stardance
|
Livvy
|
1
|
2.0
|
0
|
[{"ship_num": 1, "ts": "2026-1 [{"ship_num": 1, "ts": "2026-10-04T00:42:54Z", "hours": 2.0, "multiplier": null, "payout": 0, "blessing": "neutral", "text": "I made a game where you type out commands and different words as they appear on the screen, to “hack” and move through each level or play through endless mode. Biggest challenge was the screen kept freezing after you lost, which took about an hour of research to fix. The thing I am most proud of is the endless mode where after a certain amount of time it gets faster and faster, adding a fun dynamic to the game. I hope everyone enjoys this simple little game I made!", "repo": "https://github.com/oliviasophia67/Cyber-Type-2.0", "demo": "https://oliviasophia67.github.io/Cyber-Type-2.0/"}]...
|
[{"post_id": 76573, "ts": "202 [{"post_id": 76573, "ts": "2026-10-04T00:39:28Z", "hours": 1.3847, "text": "Second devlog!!!! Super excited about this devlog because i got the game to a position for a first ship! Especially with stardance ending in only a month I need to ship out all projects soon. Also with school I won’t have much time to work on this. I worked on this game having an endless and a level mode in the time spent, and it works very well!! Hope yall enjoy it"}, {"post_id": 21064, "ts": "2026-07-02T20:51:43Z", "hours": 0.8744, "text": "First Devlog! To start off I just barely started this new game, and its already going pretty well. This projects idea is to be a fast typing game that has to do with coding (more to come on that) so we’ll see how it continues to go. so far I’ve made the general design for it along with the typing mechanics, and I added in a keyboard on the project to make it more easily playable on a phone or tablet. I would love some fun ideas to incorporate into the project, otherwise I shall continue to work on it!"}]...
|
Title: Cyber Type by @Livvy | Stardance
Devlogs:
Title: Cyber Type by @Livvy | Stardance
Devlogs:
First Devlog! To start off I just barely started this new game, and its already going pretty well. This projects idea is to be a fast typing game that has to do with coding (more to come on that) so we’ll see how it continues to go. so far I’ve made the general design for it along with the typing mechanics, and I added in a keyboard on the project to make it more easily playable on a phone or tablet. I would love some fun ideas to incorporate into the project, otherwise I shall continue to work on it!
Second devlog!!!! Super excited about this devlog because i got the game to a position for a first ship! Especially with stardance ending in only a month I need to ship out all projects soon. Also with school I won’t have much time to work on this. I worked on this game having an endless and a level mode in the time spent, and it works very well!! Hope yall enjoy it
Ships:
I made a game where you type out commands and different words as they appear on the screen, to “hack” and move through each level or play through endless mode. Biggest challenge was the screen kept freezing after you lost, which took about an hour of research to fix. The thing I am most proud of is the endless mode where after a certain amount of time it gets faster and faster, adding a fun dynamic to the game. I hope everyone enjoys this simple little game I made!...
|
1794019690.0592277
|
1794106090.0592277
|
|
19355
|
My awesome macropad! by @Emmalovi | Stardance
|
Emmalovi
|
0
|
0.0
|
0
|
[]
|
[]
|
Title: My awesome macropad! by @Emmalovi | Stardan Title: My awesome macropad! by @Emmalovi | Stardance...
|
1793462086.935515
|
1794066886.935515
|
|
19356
|
Tic Tac Toe by @Rezwan | Stardance
|
Rezwan
|
0
|
0.0
|
0
|
[]
|
[]
|
Title: Tic Tac Toe by @Rezwan | Stardance
|
1793411488.3893735
|
1794016288.3893735
|
|
19357
|
My first slack bot! by @HamzaS | Stardance
|
HamzaS
|
0
|
0.0
|
0
|
[]
|
[]
|
Title: My first slack bot! by @HamzaS | Stardance
|
1794048535.9657264
|
1794653335.9657264
|
|
19358
|
My awesome macropad! by @timothysliu | Stardance
|
timothysliu
|
0
|
0.0
|
0
|
[]
|
[]
|
Title: My awesome macropad! by @timothysliu | Star Title: My awesome macropad! by @timothysliu | Stardance...
|
1793562998.6129677
|
1794167798.6129677
|
|
19359
|
Cramp Detector by @TheRealLionKing | Stardance
|
TheRealLionKing
|
1
|
41.0
|
0
|
[{"ship_num": 1, "ts": "2026-1 [{"ship_num": 1, "ts": "2026-11-01T05:02:06Z", "hours": 41.0, "multiplier": null, "payout": 0, "blessing": "neutral", "text": "CRAMP DETECTOR - FINAL SHIP ——————————————————————————————————————— I’m genuinely so confused (or I’m just dumb) because I swear I had just looked at the ship button and it wasn’t letting me click it but I thought I should be able to but I am supposed to devlog then ship apparently so now I posted a final devlog with my shipping summary so here is the shipping summary again?——————————————————————————————————————— PowerThru ships: a fatigue and cramp‑tracking band with a live demo PowerThru is a band that you wear on your forearm or calf. It sends sEMG, motion, skin temperature and sweat data to a phone app. The app learns a person’s baseline then watches for fatigue and overexertion. Cramp detection is the feature. In the future PowerThru hopes that coaches can control a team from a single dashboard. What I built this round (11.5 hours): A Python hub that receives the band’s data (real BLE or simulated) pulls muscle‑activity features every second, compares them to the user’s own baseline and sends the results to an iPhone app. An onboarding analyzer: a 1‑to‑10 survey plus a 30‑minute calibration builds a personal baseline and places the user into a category. A BLE packet format, an Arduino test sketch and a recorder that saves labeled data for training. A browser demo anyone can try: https://a4manohar-del.github.io/Powerthru-t/ . What I learned and fixed: sEMG needs 1 kHz sampling. The old 16 Hz pipeline worked for sweat, temperature and motion. It was wrong for muscle signals. A forearm band cannot get an ECG and the WESAD dataset has no forearm EMG so those signals were dropped instead of pretending they would transfer. The model was changed from a BiLSTM to a casual CNN‑GRU because a live band cannot see samples. On WESAD the accuracy was 47‑50% on four classes with leave‑one‑subject‑out testing. That is modest. It is reported honestly. A quiet baseline made the z‑scores explode until a floor was added. The hub was also changed to skip any second with a dropped packet of inventing data. What is honest: the demo runs on data, the risk score is a placeholder rule and the BLE firmware has not been tested on real hardware. No labeled cramp dataset exists yet. Photos show my live viewer on github and my most successful (consistent) WESAD data, but consider this, the WESAD dataset doesn’t have good sEMG data because that is chest sEMG data not wrist / ankle. So getting 50% accuracy (pretty mid / bad) isn’t as horrible when you consider that it is missing it’s highest weighted sensor. When I used an different EMG dataset, I got upwards of 65% accuracy but I don’t have the data images. What is next: collect labeled sEMG sessions validate across people and move the breadboard to a KiCad PCB with a built-in BLE radio. AI disclosure: some of the code in this repo, the browser demo (converted from python to html) and the README were written with Claude. I did the product design, the Arduino prototype and the WESAD training work. Details are in the README. Repo: https://github.com/a4manohar-del/Powerthru-t | Demo: https://a4manohar-del.github.io/Powerthru-t/ Again, I (currently) don’t have access to my physcial project breadboard, KICAD viewer, nor better images because I am out of town and typing this on my phone. So I completely understand if this ship will get rejected, but at least I tried", "repo": "https://github.com/a4manohar-del/Powerthru-t", "demo": "https://a4manohar-del.github.io/Powerthru-t/"}]...
|
[{"post_id": 86253, "ts": "202 [{"post_id": 86253, "ts": "2026-11-01T04:38:04Z", "hours": 12.0189, "text": "CRAMP DETECTOR - FINAL DEVLOG (SHIP ig) ——————————————————————————————————————— THIS WAS SUPPOSED TO BE A SHIP BUT I FORGOT THE DEADLINE TIME WAS BASED OF EASTERN TIME, I WAS 15 MIN LATE 😞 SO THIS IS MY SHIP SUMMARY😩😒!!!!!!!! IF IT IS EVEN SLIGHTLY POSSIBLE COULD I GET ONE MORE CHANCE PLZ…——————————————————————————————————————— PowerThru ships: a fatigue and cramp‑tracking band with a live demo PowerThru is a band that you wear on your forearm or calf. It sends sEMG, motion, skin temperature and sweat data to a phone app. The app learns a person’s baseline then watches for fatigue and overexertion. Cramp detection is the feature. In the future PowerThru hopes that coaches can control a team from a single dashboard. What I built this round (11.5 hours): A Python hub that receives the band’s data (real BLE or simulated) pulls muscle‑activity features every second, compares them to the user’s own baseline and sends the results to an iPhone app. An onboarding analyzer: a 1‑to‑10 survey plus a 30‑minute calibration builds a personal baseline and places the user into a category. A BLE packet format, an Arduino test sketch and a recorder that saves labeled data for training. A browser demo anyone can try: [demo link]. What I learned and fixed: sEMG needs 1 kHz sampling. The old 16 Hz pipeline worked for sweat, temperature and motion. It was wrong for muscle signals. A forearm band cannot get an ECG and the WESAD dataset has no forearm EMG so those signals were dropped instead of pretending they would transfer. The model was changed from a BiLSTM to a casual CNN‑GRU because a live band cannot see samples. On WESAD the accuracy was 47‑50% on four classes with leave‑one‑subject‑out testing. That is modest. It is reported honestly. A quiet baseline made the z‑scores explode until a floor was added. The hub was also changed to skip any second with a dropped packet of inventing data. What is honest: the demo runs on data, the risk score is a placeholder rule and the BLE firmware has not been tested on real hardware. No labeled cramp dataset exists yet. What is next: collect labeled sEMG sessions validate across people and move the breadboard to a KiCad PCB with a built-in BLE radio. AI disclosure: some of the code in this repo, the browser demo (converted from python to html) and the README were written with Claude (Anthropic). I did the product design, the Arduino prototype and the WESAD training work. Details are in the README. Repo: https://github.com/a4manohar-del/Powerthru-t | Demo: https://a4manohar-del.github.io/Powerthru-t/ ——————————————————————————————————————— Also, i’m out of town, posting this off my phone, so I can’t take photos of my breadboard or KICAD 3D viewer. Next goals, I am going to learn how to solder and I have already a good kicad pcb design so that will be main goal. But pcb parts are soooo expensive, and like what if I mess up… THANKS FOR READING"}, {"post_id": 57525, "ts": "2026-08-29T18:09:51Z", "hours": 3.4547, "text": "CRAMP DETECTOR (POWERTHRU) - DEVLOG 4——————————————————————————————————————————I’ve been on vacay for a bit and school just started back up 😭, but I finally had some time to grind out a few major updates for the wearable setup.——————————————————————————————————————————First off, I completely ditched the Arduino IDE. Trying to pull, log, and process clean CSV data directly out of it was an absolute pain. Switched over to writing raw Python scripts via PySerial to handle the stream, which made saving datasets and parsing real-time sensor streams 10x smoother.——————————————————————————————————————————Since I got the data piping out properly, I spent a lot of time building out a bunch of cool live data viewers and custom dashboards. Being able to visualize the multi-sensor streams running live in clean real-time graphs makes debugging the noise and signal spikes so much easier than looking at a scrolling text wall.——————————————————————————————————————————On the hardware side, I’ve been testing out placement ideas to fix the movement artifacts on the GSR and getting ready to drop in the upgrades I mentioned last time (really hoping to get cleaner EMG signals off a dedicated board). Still need to get over my fear of soldering so I can stop fighting air gaps on the breakout pins 💀.——————————————————————————————————————————On the ML front, I’m fully restructuring the pipeline away from standard BiLSTM into the causal CNN + GRU model so the live predictions actually work in real-time without needing future data points. Integrating that model directly into the live dashboard so it prints a real-time “cramp risk score” while streaming sensor data is the main focus right now.——————————————————————————————————————————KiCad is still sitting there untouched on my desktop, but actual PCB layout is up next once I finalize the upgraded sensor stack.——————————————————————————————————————————Thanks for reading!"}, {"post_id": 33171, "ts": "2026-07-22T20:43:15Z", "hours": 7.3981, "text": "CRAMP DETECTOR (POWERTHRU) - DEVLOG 3 note: scroll to see images—————————————————————————————————————————— This time, I began to focus more my design and prototype than actually coding the model – but I did make some improvements to the model and am doing some cool coding things. ————————————————————————————————————————— This was my first breadboard prototype, it uses an MPU-6050, AD8232, 10K Thermistor, GSR, a LED, random (for fun) water sensor (maybe sweat alt), and a pancake vibration module. I used an old kit I had from a while back which had most wires and resistors and basic supplies. While I have an ESP32 I’m so scared that I am going to break it so for now I am using the Arduino MEGA board (bigger and easier) that came with the kit (the newer one I believe). The hardest part was honestly connecting everything – I had no clue how the route all the wires – and honestly it looks like a mess (below). —————————————————————————————————————————— The items that kind of just barely worked were the EMG (proper values maybe a little “out of tune”) and the GSR which didn’t seem to detect sweat as much as I expected (it kept spiking with movement but that just means it needs to be secured better). The MPU just simply wasn’t working mainly because the pins needed to be soldered and I (am scared of) couldn’t solder so there were apparent air gaps where the information was being lost triggering an [Error -240] and 0’s across the Accel and Gyro values. The thermistor didn’t hold very steady and kept shifting – I wanted to use the DHT11 (bad but whatever) but it broke. The LED just didn’t work 😩. But one of my favorite parts of the system was the vibration module, whenever the cramp score (for now EMG biased) I made it so the pin state was set to HIGH effectively creating a cramp warning. Also, the water sensor just didn’t work and I probably won’t be using it in the future. —————————————————————————————————————————— I want to combine an ECG and EMG on the same AD8232 simultaneously but I was told that that might not be possible bc of positioning and frequency and other things. So the next steps are for me to maybe buy better parts (I did some research, how do these sounds?: MyoWare 2.0 for EMG, MPU-6050 (budget) or ICM-42688 (better), MLX90614 (non-contact) or TMP117/MAX30205 (contact), same GSR, and maybe I’ll throw in a MAX30102 (ECG). And I need to make sure I can integrate them for the future. —————————————————————————————————————————— I’ve been lazy and I haven’t really done any work on building my own pcb other than downloading KICAD – will update soon. —————————————————————————————————————————— Apparently BiLSTM isn’t going to be the most effective for cramp detection; CNN + GRU is better. A BiLSTM’s backward pass needs future timesteps (t5 to help classify t2) – fine for offline analysis of a complete pre-recorded window, but a live wearable predicting “cramp incoming” at t2 doesn’t have t5 yet. GRU is forward-only by construction; the CNN front end is made casual too (left-padded only) so nothing in the model ever depends on a future sample. So I just finished the first version of that: just swap the bidirectional lstm for the CNN + GRU combo and I got one of the better accuracy markers in a while (below). And later I want to combine the sensors into my dashboard in the last devlog so I can broadcast the prediction in real time—————————————————————————————————————————— Thanks for reading!"}, {"post_id": 24807, "ts": "2026-07-08T16:40:07Z", "hours": 10.6289, "text": "CRAMP DETECTOR (POWERTHRU) - DEVLOG 2—————————————————————————————————————————— To start, I used scikit - learn, Tensorflow, NumPy, pickle, and Pytorch to create a prototype for the BiLSTM model. I created two forms of the model: one that processes data that I generated (40,000 rows) and one that uses a WESAD dataset ( https://ubi29.informatik.uni-siegen.de/usi/data_wesad.html ). I had to modify some WESAD variables to fit my ideal sensors. Also, it uses Leave-One-Subject-Out (LOSO) cross validation. —————————————————————————————— ISSUES: My WESAD model is pretty bad (to what I expected as the other one was pretty good ~65 but that data is also generated so…) having accuracy of only 51.73 +/- 20.59%. But later when I combined oversampling + focal loss + class weights together over-corrected and overall accuracy dropped to ~45 +/- 20 (hoping on the plus side – how do you make it more reliable like less std_acc I swear it’s impossible). Thus, I think that it would be wise to turn oversampling off by default so that I have a gentler correction – if recall is too low with this combo, I will re-enable it or find some alt. Also, I created a diagnoses_subjects.py that expands the data of each subject to detect if there are any problems with the raw data in each. And alas, subject 14 (15% accuracy) had a eda_std roughly 15-35x lower than the reference subjects – nearly flatlined – leading me to believe that there was a loose / disconnected electrode. Subject 17 (17% accuracy) also had very low eda_std levels and an unusually narrow temp range – possibly due to physiological variability and not fully the model’s fault. So I added an EXCLUDE_SUBJECTS list that updates the loading of subjects to remove subjects with issues (e.g. 14 and maybe 17 if it doesn’t correct). —————————————————————————————————————————— I also create a dashboard.py script that uses plotly, streamlit, and pandas to create a visual and real-time dashboard for the levels. My parts are almost here (ESP32 mcu, way too basic dht11 temp, AD8232 emg, GSR sweat, MPU-6050 accel, Pancake Vibration motor, and batteries and supporting components) so in the meantime I used 2 interchangeable settings: Simulated random data mode, for demoing the UI without hardware (for now) and Live hardware mode; which uses ports connected over USB. I think the live visualization will be cool and will definitely transfer over to my app.————————————————————————————————————————Overall, this week was really about building the machine learning pipeline, diagnosing any quality issues, and creating software infrastructure that can (will) connect the hardware real-time interface (app). ——————————————————————————————————————— I am also really interested in building my own pcb – the idea just popped up while I was looking at other devlogs. Am I even able to integrate everything into one board? Idk, but if I remember I’ll do some research (Is Kicad the best?). Before I build anything I want to create a breadboard with each component to see if they fit together. Maybe I’ll test then run a mile then test again. Thanks for reading.—————————————————————————————————————————— Below I attached the dashboad, the result of my overcomplicated model, and the diagnose subjects that allowed me to eliminate 14 from my list. PS. I’m new to hardware related stuff – so if anyone is really skilled at it, could you help me bc I have a bunch of questions and am too lazy to watch youtube videos."}, {"post_id": 18930, "ts": "2026-06-30T03:27:42Z", "hours": 7.2156, "text": "CRAMP DETECTOR - DEVLOG 1————————————————————————— — —— I started by working on the backend software for processing multimodal sensor data (EMG, sweat conductivity, temperature, and IMU signals) by generating sample datasets to train my own BiLSTM model. This took some time since I’m still relatively new to coding, but ig I am learning. ——————————————————————————— — I also did my best to attempt to create a 3D model in Onshape (For some reason I can only show one image). I really struggled to use the features, it’s pretty difficult to learn. But it’s coming together, and I’m still refining a few design ideas and making adjustments.——————————————————————————–For the future, I really want to finish the software pipeline, improve the CAD, and begin assembling the hardware components that I found. I’m excited to move from the designing toward building a functional prototype. Also, the name of the project is Powerthru. ——————————————————————————–Overall–I think–not too bad of a start for a beginner in this type of work."}]...
|
Title: Cramp Detector by @TheRealLionKing | Starda Title: Cramp Detector by @TheRealLionKing | Stardance
Devlogs:
CRAMP DETECTOR - DEVLOG 1————————————————————————— — —— I started by working on the backend software for processing multimodal sensor data (EMG, sweat conductivity, temperature, and IMU signals) by generating sample datasets to train my own BiLSTM model. This took some time since I’m still relatively new to coding, but ig I am learning. ——————————————————————————— — I also did my best to attempt to create a 3D model in Onshape (For some reason I can only show one image). I really struggled to use the features, it’s pretty difficult to learn. But it’s coming together, and I’m still refining a few design ideas and making adjustments.——————————————————————————–For the future, I really want to finish the software pipeline, improve the CAD, and begin assembling the hardware components that I found. I’m excited to move from the designing toward building a functional prototype. Also, the name of the project is Powerthru. ——————————————————————————–Overall–I think–not too bad of a start for a beginner in this type of work.
CRAMP DETECTOR (POWERTHRU) - DEVLOG 2—————————————————————————————————————————— To start, I used scikit - learn, Tensorflow, NumPy, pickle, and Pytorch to create a prototype for the BiLSTM model. I created two forms of the model: one that processes data that I generated (40,000 rows) and one that uses a WESAD dataset ( https://ubi29.informatik.uni-siegen.de/usi/data_wesad.html ). I had to modify some WESAD variables to fit my ideal sensors. Also, it uses Leave-One-Subject-Out (LOSO) cross validation. —————————————————————————————— ISSUES: My WESAD model is pretty bad (to what I expected as the other one was pretty good ~65 but that data is also generated so…) having accuracy of only 51.73 +/- 20.59%. But later when I combined oversampling + focal loss + class weights together over-corrected and overall accuracy dropped to ~45 +/- 20 (hoping on the plus side – how do you make it more reliable like less std_acc I swear it’s impossible). Thus, I think that it would be wise to turn oversampling off by default so that I have a gentler correction – if recall is too low with this combo, I will re-enable it or find some alt. Also, I created a diagnoses_subjects.py that expands the data of each subject to detect if there are any problems with the raw data in each. And alas, subject 14 (15% accuracy) had a eda_std roughly 15-35x lower than the reference subjects – nearly flatlined – leading me to believe that there was a loose / disconnected electrode. Subject 17 (17% accuracy) also had very low eda_std levels and an unusually narrow temp range – possibly due to physiological variability and not fully the model’s fault. So I added an EXCLUDE_SUBJECTS list that updates the loading of subjects to remove subjects with issues (e.g. 14 and maybe 17 if it doesn’t correct). —————————————————————————————————————————— I also create a dashboard.py script that uses plotly, streamlit, and pandas to create a visual and real-time dashboard for the levels. My parts are almost here (ESP32 mcu, way too basic dht11 temp, AD8232 emg, GSR sweat, MPU-6050 accel, Pancake Vibration motor, and batteries and supporting components) so in the meantime I used 2 interchangeable settings: Simulated random data mode, for demoing the UI without hardware (for now) and Live hardware mode; which uses ports connected over USB. I think the live visualization will be cool and will definitely transfer over to my app.————————————————————————————————————————Overall, this week was really about building the machine learning pipeline, diagnosing any quality issues, and creating software infrastructure that can (will) connect the hardware real-time interface (app). ——————————————————————————————————————— I am also really interested in building my own pcb – the idea just popped up while I was looking at other devlogs. Am I even able to integrate everything into one board? Idk, but if I remember I’ll do some research (Is Kicad the best?). Before I build anything I want to create a breadboard with each component to see if they fit together. Maybe I’ll test then run a mile then test again. Thanks for reading.—————————————————————————————————————————— Below I attached the dashboad, the result of my overcomplicated model, and the diagnose subjects that allowed me to eliminate 14 from my list. PS. I’m new to hardware related stuff – so if anyone is really skilled at it, could you help me bc I have a bunch of questions and am too lazy to watch youtube videos.
CRAMP DETECTOR (POWERTHRU) - DEVLOG 3 note: scroll to see images—————————————————————————————————————————— This time, I began to focus more my design and prototype than actually coding the model – but I did make some improvements to the model and am doing some cool coding things. ————————————————————————————————————————— This was my first breadboard prototype, it uses an MPU-6050, AD8232, 10K Thermistor, GSR, a LED, random (for fun) water sensor (maybe sweat alt), and a pancake vibration module. I used an old kit I had from a while back which had most wires and resistors and basic supplies. While I have an ESP32 I’m so scared that I am going to break it so for now I am using the Arduino MEGA board (bigger and easier) that came with the kit (the newer one I believe). The hardest part was honestly connecting everything – I had no clue how the route all the wires – and honestly it looks like a mess (below). —————————————————————————————————————————— The items that kind of just barely worked were the EMG (proper values maybe a little “out of tune”) and the GSR which didn’t seem to detect sweat as much as I expected (it kept spiking with movement but that just means it needs to be secured better). The MPU just simply wasn’t working mainly because the pins needed to be soldered and I (am scared of) couldn’t solder so there were apparent air gaps where the information was being lost triggering an [Error -240] and 0’s across the Accel and Gyro values. The thermistor didn’t hold very steady and kept shifting – I wanted to use the DHT11 (bad but whatever) but it broke. The LED just didn’t work 😩. But one of my favorite parts of the system was the vibration module, whenever the cramp score (for now EMG biased) I made it so the pin state was set to HIGH effectively creating a cramp warning. Also, the water sensor just didn’t work and I probably won’t be using it in the future. —————————————————————————————————————————— I want to combine an ECG and EMG on the same AD8232 simultaneously but I was told that that might not be possible bc of positioning and frequency and other things. So the next steps are for me to maybe buy better parts (I did some research, how do these sounds?: MyoWare 2.0 for EMG, MPU-6050 (budget) or ICM-42688 (better), MLX90614 (non-contact) or TMP117/MAX30205 (contact), same GSR, and maybe I’ll throw in a MAX30102 (ECG). And I need to make sure I can integrate them for the future. —————————————————————————————————————————— I’ve been lazy and I haven’t really done any work on building my own pcb other than downloading KICAD – will update soon. —————————————————————————————————————————— Apparently BiLSTM isn’t going to be the most effective for cramp detection; CNN + GRU is better. A BiLSTM’s backward pass needs future timesteps (t5 to help classify t2) – fine for offline analysis of a complete pre-recorded window, but a live wearable predicting “cramp incoming” at t2 doesn’t have t5 yet. GRU is forward-only by construction; the CNN front end is made casual too (left-padded only) so nothing in the model ever depends on a future sample. So I just finished the first version of that: just swap the bidirectional lstm for the CNN + GRU combo and I got one of the better accuracy markers in a while (below). And later I want to combine the sensors into my dashboard in the last devlog so I can broadcast the prediction in real time—————————————————————————————————————————— Thanks for reading!
CRAMP DETECTOR (POWERTHRU) - DEVLOG 4——————————————————————————————————————————I’ve been on vacay for a bit and school just started back up 😭, but I finally had some time to grind out a few major updates for the wearable setup.——————————————————————————————————————————First off, I completely ditched the Arduino IDE. Trying to pull, log, and process clean CSV data directly out of it was an absolute pain. Switched over to writing raw Python scripts via PySerial to handle the stream, which made saving datasets and parsing real-time sensor streams 10x smoother.——————————————————————————————————————————Since I got the data piping out properly, I spent a lot of time building out a bunch of cool live data viewers and custom dashboards. Being able to visualize the multi-sensor streams running live in clean real-time graphs makes debugging the noise and signal spikes so much easier than looking at a scrolling text wall.——————————————————————————————————————————On the hardware side, I’ve been testing out placement ideas to fix the movement artifacts on the GSR and getting ready to drop in the upgrades I mentioned last time (really hoping to get cleaner EMG signals off a dedicated board). Still need to get over my fear of soldering so I can stop fighting air gaps on the breakout pins 💀.——————————————————————————————————————————On the ML front, I’m fully restructuring the pipeline away from standard BiLSTM into the causal CNN + GRU model so the live predictions actually work in real-time without needing future data points. Integrating that model directly into the live dashboard so it prints a real-time “cramp risk score” while streaming sensor data is the main focus right now.——————————————————————————————————————————KiCad is still sitting there untouched on my desktop, but actual PCB layout is up next once I finalize the upgraded sensor stack.——————————————————————————————————————————Thanks for reading!
CRAMP DETECTOR - FINAL DEVLOG (SHIP ig) ——————————————————————————————————————— THIS WAS SUPPOSED TO BE A SHIP BUT I FORGOT THE DEADLINE TIME WAS BASED OF EASTERN TIME, I WAS 15 MIN LATE 😞 SO THIS IS MY SHIP SUMMARY😩😒!!!!!!!! IF IT IS EVEN SLIGHTLY POSSIBLE COULD I GET ONE MORE CHANCE PLZ…——————————————————————————————————————— PowerThru ships: a fatigue and cramp‑tracking band with a live demo PowerThru is a band that you wear on your forearm or calf. It sends sEMG, motion, skin temperature and sweat data to a phone app. The app learns a person’s baseline then watches for fatigue and overexertion. Cramp detection is the feature. In the future PowerThru hopes that coaches can control a team from a single dashboard. What I built this round (11.5 hours): A Python hub that receives the band’s data (real BLE or simulated) pulls muscle‑activity features every second, compares them to the user’s own baseline and sends the results to an iPhone app. An onboarding analyzer: a 1‑to‑10 survey plus a 30‑minute calibration builds a personal baseline and places the user into a category. A BLE packet format, an Arduino test sketch and a recorder that saves labeled data for training. A browser demo anyone can try: [demo link]. What I learned and fixed: sEMG needs 1 kHz sampling. The old 16 Hz pipeline worked for sweat, temperature and motion. It was wrong for muscle signals. A forearm band cannot get an ECG and the WESAD dataset has no forearm EMG so those signals were dropped instead of pretending they would transfer. The model was changed from a BiLSTM to a casual CNN‑GRU because a live band cannot see samples. On WESAD the accuracy was 47‑50% on four classes with leave‑one‑subject‑out testing. That is modest. It is reported honestly. A quiet baseline made the z‑scores explode until a floor was added. The hub was also changed to skip any second with a dropped packet of inventing data. What is honest: the demo runs on data, the risk score is a placeholder rule and the BLE firmware has not been tested on real hardware. No labeled cramp dataset exists yet. What is next: collect labeled sEMG sessions validate across people and move the breadboard to a KiCad PCB with a built-in BLE radio. AI disclosure: some of the code in this repo, the browser demo (converted from python to html) and the README were written with Claude (Anthropic). I did the product design, the Arduino prototype and the WESAD training work. Details are in the README. Repo: https://github.com/a4manohar-del/Powerthru-t | Demo: https://a4manohar-del.github.io/Powerthru-t/ ——————————————————————————————————————— Also, i’m out of town, posting this off my phone, so I can’t take photos of my breadboard or KICAD 3D viewer. Next goals, I am going to learn how to solder and I have already a good kicad pcb design so that will be main goal. But pcb parts are soooo expensive, and like what if I mess up… THANKS FOR READING
Ships:
CRAMP DETECTOR - FINAL SHIP ——————————————————————————————————————— I’m genuinely so confused (or I’m just dumb) because I swear I had just looked at the ship button and it wasn’t letting me click it but I thought I should be able to but I am supposed to devlog then ship apparently so now I posted a final devlog with my shipping summary so here is the shipping summary again?——————————————————————————————————————— PowerThru ships: a fatigue and cramp‑tracking band with a live demo PowerThru is a band that you wear on your forearm or calf. It sends sEMG, motion, skin temperature and sweat data to a phone app. The app learns a person’s baseline then watches for fatigue and overexertion. Cramp detection is the feature. In the future PowerThru hopes that coaches can control a team from a single dashboard. What I built this round (11.5 hours): A Python hub that receives the band’s data (real BLE or simulated) pulls muscle‑activity features every second, compares them to the user’s own baseline and sends the results to an iPhone app. An onboarding analyzer: a 1‑to‑10 survey plus a 30‑minute calibration builds a personal baseline and places the user into a category. A BLE packet format, an Arduino test sketch and a recorder that saves labeled data for training. A browser demo anyone can try: https://a4manohar-del.github.io/Powerthru-t/ . What I learned and fixed: sEMG needs 1 kHz sampling. The old 16 Hz pipeline worked for sweat, temperature and motion. It was wrong for muscle signals. A forearm band cannot get an ECG and the WESAD dataset has no forearm EMG so those signals were dropped instead of pretending they would transfer. The model was changed from a BiLSTM to a casual CNN‑GRU because a live band cannot see samples. On WESAD the accuracy was 47‑50% on four classes with leave‑one‑subject‑out testing. That is modest. It is reported honestly. A quiet baseline made the z‑scores explode until a floor was added. The hub was also changed to skip any second with a dropped packet of inventing data. What is honest: the demo runs on data, the risk score is a placeholder rule and the BLE firmware has not been tested on real hardware. No labeled cramp dataset exists yet. Photos show my live viewer on github and my most successful (consistent) WESAD data, but consider this, the WESAD dataset doesn’t have good sEMG data because that is chest sEMG data not wrist / ankle. So getting 50% accuracy (pretty mid / bad) isn’t as horrible when you consider that it is missing it’s highest weighted sensor. When I used an different EMG dataset, I got upwards of 65% accuracy but I don’t have the data images. What is next: collect labeled sEMG sessions validate across people and move the breadboard to a KiCad PCB with a built-in BLE radio. AI disclosure: some of the code in this repo, the browser demo (converted from python to html) and the README were written with Claude. I did the product design, the Arduino prototype and the WESAD training work. Details are in the README. Repo: https://github.com/a4manohar-del/Powerthru-t | Demo: https://a4manohar-del.github.io/Powerthru-t/ Again, I (currently) don’t have access to my physcial project breadboard, KICAD viewer, nor better images because I am out of town and typing this on my phone. So I completely understand if this ship will get rejected, but at least I tried...
|
1794034256.5534463
|
1794120656.5534463
|
|
19360
|
Dwl project by @lachlang38 | Stardance
|
lachlang38
|
0
|
0.0
|
0
|
[]
|
[]
|
Title: Dwl project by @lachlang38 | Stardance
|
1794012916.9246397
|
1794617716.9246397
|
|
19361
|
My MIDI Controller! by @arfet | Stardance
|
arfet
|
0
|
36.5
|
0
|
[]
|
[{"post_id": 55977, "ts": "202 [{"post_id": 55977, "ts": "2024-10-04T00:00:00Z", "hours": 1.5, "text": "I finished my overall chassis! Ensured that m3 screws will work, and checked clearances for the components, made the USB hole for the Pico as well. Separated the top and bottom for printing ease"}, {"post_id": 55945, "ts": "2024-10-04T00:00:00Z", "hours": 0.25, "text": "Realized I forgot to make a gap for the potentiometer lol, so I just added it"}, {"post_id": 55944, "ts": "2024-10-04T00:00:00Z", "hours": 1.5, "text": "I finished my overall chassis! Ensured that m3 screws will work, and checked clearances for the components, made the USB hole for the Pico as well. Separated the top and bottom for printing ease"}, {"post_id": 55943, "ts": "2024-10-04T00:00:00Z", "hours": 2.0, "text": "I worked on the top plate, kept it at a height of 1.5mm since thats the standard for keyboards, also made holes for the jumpers and encoders"}, {"post_id": 55978, "ts": "2024-10-04T00:00:00Z", "hours": 0.25, "text": "Realized I forgot to make a gap for the potentiometer lol, so I just added it"}, {"post_id": 55976, "ts": "2024-10-04T00:00:00Z", "hours": 2.0, "text": "I worked on the top plate, kept it at a height of 1.5mm since thats the standard for keyboards, also made holes for the jumpers and encoders"}, {"post_id": 55942, "ts": "2024-10-03T00:00:00Z", "hours": 2.75, "text": "I continued to work on some CAD for the chassis, I added internal supports, some keyswitches for refererence, and some barriers on the side."}, {"post_id": 55975, "ts": "2024-10-03T00:00:00Z", "hours": 2.75, "text": "I continued to work on some CAD for the chassis, I added internal supports, some keyswitches for refererence, and some barriers on the side."}, {"post_id": 55974, "ts": "2024-10-02T00:00:00Z", "hours": 2.0, "text": "I routed my PCB, I kept it simple with an autorouter. I also decided to work on my chassis after, to keep it simple, I just used TinkerCad. I added my PCB as a .stl file and started working on the base"}, {"post_id": 55941, "ts": "2024-10-02T00:00:00Z", "hours": 2.0, "text": "I routed my PCB, I kept it simple with an autorouter. I also decided to work on my chassis after, to keep it simple, I just used TinkerCad. I added my PCB as a .stl file and started working on the base"}, {"post_id": 55940, "ts": "2024-10-01T00:00:00Z", "hours": 1.75, "text": "I finally converted to a PCB and arranged my parts"}, {"post_id": 55939, "ts": "2024-10-01T00:00:00Z", "hours": 1.5, "text": "I had to refine my schematics and footprints for my I2S DAC, so I updated them and cross checked the correct pins"}, {"post_id": 55973, "ts": "2024-10-01T00:00:00Z", "hours": 1.75, "text": "I finally converted to a PCB and arranged my parts"}, {"post_id": 55972, "ts": "2024-10-01T00:00:00Z", "hours": 1.5, "text": "I had to refine my schematics and footprints for my I2S DAC, so I updated them and cross checked the correct pins"}, {"post_id": 55938, "ts": "2024-09-30T00:00:00Z", "hours": 1.0, "text": "I made the footprint of the I2S DAC module, I efficiently used the .brd file, imported it into kicad, then copied the footprint over."}, {"post_id": 55971, "ts": "2024-09-30T00:00:00Z", "hours": 1.0, "text": "I made the footprint of the I2S DAC module, I efficiently used the .brd file, imported it into kicad, then copied the footprint over."}, {"post_id": 55937, "ts": "2024-09-29T00:00:00Z", "hours": 2.0, "text": "After some reasearch, I figured out that I needed more ADC pins, so I looked into another breakout board and came across the ADS1015, I then implemented it, and found a footprint online that I could use. After that, I made a simple linear slide potentiometer footprint, and found a 7.5mm one on Adafruit, I then connected it to the ADS breakout board."}, {"post_id": 55970, "ts": "2024-09-29T00:00:00Z", "hours": 2.0, "text": "After some reasearch, I figured out that I needed more ADC pins, so I looked into another breakout board and came across the ADS1015, I then implemented it, and found a footprint online that I could use. After that, I made a simple linear slide potentiometer footprint, and found a 7.5mm one on Adafruit, I then connected it to the ADS breakout board."}, {"post_id": 56146, "ts": "2024-09-29T00:00:00Z", "hours": 1.0, "text": "To finish off, I got my work checked over, fixed an issue with the switches, and then did some organizing. This was my final BASE schematic. I am hoping to add a slide, potentiometer later on and customize it to my liking."}, {"post_id": 56145, "ts": "2024-09-27T00:00:00Z", "hours": 2.0, "text": "I then proceeded to add on the SD card and LCD screen, I decided to stick with the guide here, because I am new. The LCD was pretty easy to add, but I had to ask some questions regarding the SD card because there wasn’t a full screenshot for it. In the end I got it working though."}, {"post_id": 56144, "ts": "2024-09-26T00:00:00Z", "hours": 2.0, "text": "After I made my rows, I started to work and learn about rotary encoders, initially, I had made a 6x6 matrix, but I realized that I only need a 4x5 matrix, and I leave the other 2 rows for my rotary encoders. It took me a while to figure it out, because I was new to making schematics, but I luckily got some help on the slack, and then made a schematic like so:"}, {"post_id": 56143, "ts": "2024-09-24T00:00:00Z", "hours": 2.0, "text": "I started by looking at the mini MIDI magic guide. Alognside that I also installed KiCad and started to learn how it works. I also learned about the switch matrix system, and decided to implement that in my project. Initially, I was confused about the switch matrix and what it meant, but I figured it out and got started by making 4 rows like this"}]...
|
Title: My MIDI Controller! by @arfet | Stardance
Title: My MIDI Controller! by @arfet | Stardance
Devlogs:
I started by looking at the mini MIDI magic guide. Alognside that I also installed KiCad and started to learn how it works. I also learned about the switch matrix system, and decided to implement that in my project. Initially, I was confused about the switch matrix and what it meant, but I figured it out and got started by making 4 rows like this
After I made my rows, I started to work and learn about rotary encoders, initially, I had made a 6x6 matrix, but I realized that I only need a 4x5 matrix, and I leave the other 2 rows for my rotary encoders. It took me a while to figure it out, because I was new to making schematics, but I luckily got some help on the slack, and then made a schematic like so:
I then proceeded to add on the SD card and LCD screen, I decided to stick with the guide here, because I am new. The LCD was pretty easy to add, but I had to ask some questions regarding the SD card because there wasn’t a full screenshot for it. In the end I got it working though.
To finish off, I got my work checked over, fixed an issue with the switches, and then did some organizing. This was my final BASE schematic. I am hoping to add a slide, potentiometer later on and customize it to my liking.
After some reasearch, I figured out that I needed more ADC pins, so I looked into another breakout board and came across the ADS1015, I then implemented it, and found a footprint online that I could use. After that, I made a simple linear slide potentiometer footprint, and found a 7.5mm one on Adafruit, I then connected it to the ADS breakout board.
After some reasearch, I figured out that I needed more ADC pins, so I looked into another breakout board and came across the ADS1015, I then implemented it, and found a footprint online that I could use. After that, I made a simple linear slide potentiometer footprint, and found a 7.5mm one on Adafruit, I then connected it to the ADS breakout board.
I made the footprint of the I2S DAC module, I efficiently used the .brd file, imported it into kicad, then copied the footprint over.
I made the footprint of the I2S DAC module, I efficiently used the .brd file, imported it into kicad, then copied the footprint over.
I had to refine my schematics and footprints for my I2S DAC, so I updated them and cross checked the correct pins
I finally converted to a PCB and arranged my parts
I had to refine my schematics and footprints for my I2S DAC, so I updated them and cross checked the correct pins
I finally converted to a PCB and arranged my parts
I routed my PCB, I kept it simple with an autorouter. I also decided to work on my chassis after, to keep it simple, I just used TinkerCad. I added my PCB as a .stl file and started working on the base
I routed my PCB, I kept it simple with an autorouter. I also decided to work on my chassis after, to keep it simple, I just used TinkerCad. I added my PCB as a .stl file and started working on the base
I continued to work on some CAD for the chassis, I added internal supports, some keyswitches for refererence, and some barriers on the side.
I continued to work on some CAD for the chassis, I added internal supports, some keyswitches for refererence, and some barriers on the side.
I worked on the top plate, kept it at a height of 1.5mm since thats the standard for keyboards, also made holes for the jumpers and encoders
Realized I forgot to make a gap for the potentiometer lol, so I just added it
I worked on the top plate, kept it at a height of 1.5mm since thats the standard for keyboards, also made holes for the jumpers and encoders
I finished my overall chassis! Ensured that m3 screws will work, and checked clearances for the components, made the USB hole for the Pico as well. Separated the top and bottom for printing ease
Realized I forgot to make a gap for the potentiometer lol, so I just added it
I finished my overall chassis! Ensured that m3 screws will work, and checked clearances for the components, made the USB hole for the Pico as well. Separated the top and bottom for printing ease...
|
1793418774.4930618
|
1794023574.4930618
|
|
19362
|
Frictionless by @axnfbshakxm | Stardance
|
axnfbshakxm
|
0
|
0.0
|
0
|
[]
|
[]
|
Title: Frictionless by @axnfbshakxm | Stardance
|
1793839743.306058
|
1794444543.306058
|
|
19363
|
Vakthi by @Sukuna | Stardance
|
Sukuna
|
0
|
0.0
|
0
|
[]
|
[]
|
Title: Vakthi by @Sukuna | Stardance
|
1794001673.379261
|
1794606473.379261
|
|
19364
|
A Playdate Between Vultures and Crows by @Conner | A Playdate Between Vultures and Crows by @Conner | Stardance...
|
Conner
|
0
|
4.54
|
0
|
[]
|
[{"post_id": 70416, "ts": "202 [{"post_id": 70416, "ts": "2026-09-19T04:34:08Z", "hours": 4.5425, "text": "Currently waiting to get some art made and added, nearing the end of setting up basic combat!"}]...
|
Title: A Playdate Between Vultures and Crows by @C Title: A Playdate Between Vultures and Crows by @Conner | Stardance
Devlogs:
Currently waiting to get some art made and added, nearing the end of setting up basic combat!...
|
1793519475.549921
|
1794124275.549921
|
|
19365
|
My first slack bot! by @Ris | Stardance
|
Ris
|
0
|
0.0
|
0
|
[]
|
[]
|
Title: My first slack bot! by @Ris | Stardance
|
1793450986.0813332
|
1794055786.0813332
|
|
19366
|
Debate Against History by @Sahil-A | Stardance
|
Sahil-A
|
0
|
0.0
|
0
|
[]
|
[]
|
Title: Debate Against History by @Sahil-A | Starda Title: Debate Against History by @Sahil-A | Stardance...
|
1793336218.1758358
|
1793941018.1758358
|
|
19367
|
My awesome macropad! by @Pacolit | Stardance
|
Pacolit
|
0
|
0.0
|
0
|
[]
|
[]
|
Title: My awesome macropad! by @Pacolit | Stardanc Title: My awesome macropad! by @Pacolit | Stardance...
|
1794048889.8842113
|
1794653689.8842113
|
|
19368
|
Devboard by @afiaava | Stardance
|
afiaava
|
0
|
0.0
|
0
|
[]
|
[]
|
Title: Devboard by @afiaava | Stardance
|
1793504971.2474697
|
1794109771.2474697
|
|
19369
|
My very own WebOS by @Shryan_Pathak | Stardance
|
Shryan_Pathak
|
0
|
0.0
|
0
|
[]
|
[]
|
Title: My very own WebOS by @Shryan_Pathak | Stard Title: My very own WebOS by @Shryan_Pathak | Stardance...
|
1793998503.9435315
|
1794603303.9435315
|
|
19370
|
My first slack bot! by @vivid | Stardance
|
vivid
|
0
|
0.0
|
0
|
[]
|
[]
|
Title: My first slack bot! by @vivid | Stardance
|
1793973225.19301
|
1794578025.19301
|
|
19371
|
Planetarium by @The_Craw | Stardance
|
The_Craw
|
1
|
2.44
|
29
|
[{"ship_num": 1, "ts": "2026-0 [{"ship_num": 1, "ts": "2026-06-16T10:24:58Z", "hours": 2.0, "multiplier": 12.05, "payout": 29, "blessing": "neutral", "text": "A custom-made leaderboard, made with my own unofficial stardance API system. Tracks projects over time, for followers, time used, and devlogs. This project is confirmed to have been used by the Fraud Squad to catch users who have faked their time.", "repo": "https://github.com/Jonah-Crawford/Planetarium", "demo": "https://planetarium.ultimatecraw.xyz/"}]...
|
[{"post_id": 16815, "ts": "202 [{"post_id": 16815, "ts": "2026-06-27T09:33:43Z", "hours": 0.4414, "text": "Simple additions like adding a ‘super star’ column to track exceptional projects have been added. The webpage is still quite slow though 😅"}, {"post_id": 9866, "ts": "2026-06-16T10:12:57Z", "hours": 1.335, "text": "Final devlog, shipping as the basic leaderboard is done!"}, {"post_id": 9828, "ts": "2026-06-16T08:42:16Z", "hours": 0.6761, "text": "I’m not going to lie, ChatGPT did the CSS because I don’t know how to. This is why it looks vibecoded, which makes it stinky. I apologise."}, {"post_id": 9495, "ts": "2026-06-15T20:56:36Z", "hours": 0.3767, "text": "Did someone say new leaderboard? That’s right, Craw’s Stardance Leaderboard now works with Craw’s Stardance API! This leaderboard updates every 6 hours, rather than every week, and can show history data! Want to see the fastest growing projects? Easy peasy with Planetarium."}]...
|
Title: Planetarium by @The_Craw | Stardance
Devlo Title: Planetarium by @The_Craw | Stardance
Devlogs:
Did someone say new leaderboard? That’s right, Craw’s Stardance Leaderboard now works with Craw’s Stardance API! This leaderboard updates every 6 hours, rather than every week, and can show history data! Want to see the fastest growing projects? Easy peasy with Planetarium.
I’m not going to lie, ChatGPT did the CSS because I don’t know how to. This is why it looks vibecoded, which makes it stinky. I apologise.
Final devlog, shipping as the basic leaderboard is done!
Simple additions like adding a ‘super star’ column to track exceptional projects have been added. The webpage is still quite slow though 😅
Ships:
A custom-made leaderboard, made with my own unofficial stardance API system. Tracks projects over time, for followers, time used, and devlogs. This project is confirmed to have been used by the Fraud Squad to catch users who have faked their time....
|
1793915617.7999542
|
1794002017.7999542
|
|
19372
|
My awesome macropad! by @maxcou | Stardance
|
maxcou
|
0
|
0.0
|
0
|
[]
|
[]
|
Title: My awesome macropad! by @maxcou | Stardance
|
1793364631.2247515
|
1793969431.2247515
|
|
19373
|
3D Print Shredddder by @Right_Bright | Stardance
|
Right_Bright
|
0
|
2.31
|
0
|
[]
|
[{"post_id": 9535, "ts": "2026 [{"post_id": 9535, "ts": "2026-06-15T22:11:28Z", "hours": 2.31, "text": "I finished a very rough version of the housing for the planer to sit in & TRIED to print it… instead the filament roll got stuck and it stopped extruding :( Fortunately, it printed just enough for me to check out some of how my measurements played out & moved on to create V2! (calipers for the win, but I really wish I had a 3D scanner for this T-T [I also tried using a picture of the planer, but I just could not get a good head-on picture :( ]) For V2 I cut down the top a lot because I only need the feeding chute coming out. I also added some more support on the bottom for the planer, and added a bottom; changed the feeding chute to have a slope at the bottom to hopefully help feed prints into the blade; and realized the print orientation should be rotated so that the back lays flat on the print bed as this removes almost all supports (with some design tweaks). Oh, I also learned the very basics I needed to get some renders of the prints using Blender which was cool! Next up: Test the shredding (what do the shredded pieces look like, do concurrent passes make them smaller, at what point does it stop, how loud is it, how fast is it, etc…) Look into next steps to modify this idea to shred larger parts"}]...
|
Title: 3D Print Shredddder by @Right_Bright | Star Title: 3D Print Shredddder by @Right_Bright | Stardance
Devlogs:
I finished a very rough version of the housing for the planer to sit in & TRIED to print it… instead the filament roll got stuck and it stopped extruding :( Fortunately, it printed just enough for me to check out some of how my measurements played out & moved on to create V2! (calipers for the win, but I really wish I had a 3D scanner for this T-T [I also tried using a picture of the planer, but I just could not get a good head-on picture :( ]) For V2 I cut down the top a lot because I only need the feeding chute coming out. I also added some more support on the bottom for the planer, and added a bottom; changed the feeding chute to have a slope at the bottom to hopefully help feed prints into the blade; and realized the print orientation should be rotated so that the back lays flat on the print bed as this removes almost all supports (with some design tweaks). Oh, I also learned the very basics I needed to get some renders of the prints using Blender which was cool! Next up: Test the shredding (what do the shredded pieces look like, do concurrent passes make them smaller, at what point does it stop, how loud is it, how fast is it, etc…) Look into next steps to modify this idea to shred larger parts...
|
1793501432.8825626
|
1794106232.8825626
|
|
19374
|
My very own WebOS by @vivid | Stardance
|
vivid
|
0
|
0.0
|
0
|
[]
|
[]
|
Title: My very own WebOS by @vivid | Stardance
|
1793411838.6670768
|
1794016638.6670768
|
|
19375
|
My very own WebOS by @mlievers | Stardance
|
mlievers
|
0
|
0.0
|
0
|
[]
|
[]
|
Title: My very own WebOS by @mlievers | Stardance
|
1793508826.293398
|
1794113626.293398
|
|
19376
|
My first slack bot! by @ronitpinnelli | Stardance
|
ronitpinnelli
|
0
|
0.0
|
0
|
[]
|
[]
|
Title: My first slack bot! by @ronitpinnelli | Sta Title: My first slack bot! by @ronitpinnelli | Stardance...
|
1793523152.887968
|
1794127952.887968
|
|
19377
|
AstraOS by @laitus5204 | Stardance
|
laitus5204
|
0
|
0.0
|
0
|
[]
|
[]
|
Title: AstraOS by @laitus5204 | Stardance
|
1793342944.1718593
|
1793947744.1718593
|
|
19378
|
BigCity by @Max_ | Stardance
|
Max_
|
0
|
0.0
|
0
|
[]
|
[]
|
Title: BigCity by @Max_ | Stardance
|
1793807291.5092206
|
1794671291.5092206
|
|
19379
|
Untitled by @AustinCMedic | Stardance
|
AustinCMedic
|
0
|
0.0
|
0
|
[]
|
[]
|
Title: Untitled by @AustinCMedic | Stardance
|
1793509003.0896199
|
1794113803.0896199
|
|
19380
|
Dristi Badge by @dristiroy | Stardance
|
dristiroy
|
0
|
0.0
|
0
|
[]
|
[]
|
Title: Dristi Badge by @dristiroy | Stardance
|
1794012884.1013513
|
1794617684.1013513
|
|
19381
|
My very own WebOS by @swanikgandhe | Stardance
|
swanikgandhe
|
0
|
0.0
|
0
|
[]
|
[]
|
Title: My very own WebOS by @swanikgandhe | Starda Title: My very own WebOS by @swanikgandhe | Stardance...
|
1793792844.1065528
|
1794397644.1065528
|
|
19382
|
Rc Plane by @Wilde_Bill | Stardance
|
Wilde_Bill
|
0
|
0.0
|
0
|
[]
|
[]
|
Title: Rc Plane by @Wilde_Bill | Stardance
|
1793483319.1652865
|
1794088119.1652865
|
|
19383
|
ESP32-S3 AI Assistant by @smitamaw | Stardance
|
smitamaw
|
0
|
3.2
|
0
|
[]
|
[{"post_id": 58561, "ts": "202 [{"post_id": 58561, "ts": "2026-08-31T00:34:30Z", "hours": 1.7589, "text": "Code has been updated to use the Gemini Live model specifically designed for back-and-forth voice interaction. This allows for smoother responses and more consistent output. Code & docs are at: https://github.com/smitamw/esp32s3-assistant"}, {"post_id": 17911, "ts": "2026-06-28T20:57:16Z", "hours": 1.0258, "text": "I replaced the old system of 2 models with a new system where the desktop assistant only uses a single Gemini Live model. This results in faster response times and higher API call limits. You can find it at https://github.com/smitamw/esp32s3-assistant . (The image is unrelated.)"}, {"post_id": 9630, "ts": "2026-06-16T01:06:34Z", "hours": 0.4167, "text": "This is the initial ESP32-S3 assistant project that I created before I joined Stardance. It consists of an ESP32S3 board, an extension board, a momentary pushbutton, MAX98357A amplifier, INMP441 microphone and a small speaker for output."}]...
|
Title: ESP32-S3 AI Assistant by @smitamaw | Starda Title: ESP32-S3 AI Assistant by @smitamaw | Stardance
Devlogs:
This is the initial ESP32-S3 assistant project that I created before I joined Stardance. It consists of an ESP32S3 board, an extension board, a momentary pushbutton, MAX98357A amplifier, INMP441 microphone and a small speaker for output.
I replaced the old system of 2 models with a new system where the desktop assistant only uses a single Gemini Live model. This results in faster response times and higher API call limits. You can find it at https://github.com/smitamw/esp32s3-assistant . (The image is unrelated.)
Code has been updated to use the Gemini Live model specifically designed for back-and-forth voice interaction. This allows for smoother responses and more consistent output. Code & docs are at: https://github.com/smitamw/esp32s3-assistant...
|
1793962522.6725957
|
1794567322.6725957
|
|
19384
|
My awesome macropad! by @vedha | Stardance
|
vedha
|
0
|
0.0
|
0
|
[]
|
[]
|
Title: My awesome macropad! by @vedha | Stardance
|
1793846865.0660822
|
1794451665.0660822
|
|
19385
|
Doodle Cam by @adam_wu0630 | Stardance
|
adam_wu0630
|
0
|
1.11
|
0
|
[]
|
[{"post_id": 9673, "ts": "2026 [{"post_id": 9673, "ts": "2026-06-16T02:39:12Z", "hours": 1.1119, "text": "Here you go: Doodle Cam-Devlog #1 So Doodle Cam is a camera I’m building on a Raspberry Pi that takes a photo and turns it into a cool art style, kind of like a filter but on a real camera. There’s no printing, you just plug it into your computer with a USB cable to get the pictures off. Right now I’m writing all the code in Python on my laptop first before I put it on the Pi. At first I wanted to make it look like a kid’s crayon drawing. I tried doing it with just OpenCV code, then I tried using AI with the Replicate API. The AI looked the best, but I figured out it can’t run on a Raspberry Pi because it’s way too slow, and it also costs money for every picture. So I switched to doing everything offline with OpenCV instead. I changed the first preset to a black-and-white pencil sketch since OpenCV is actually really good at that, and I’ve been tweaking it a bunch, removing the background, smoothing the photo, adding dark outlines so the face shows up, and adding shading so it looks more like a real drawing. Next I want to get the code running on the actual Raspberry Pi with the camera. After that I’ll add a little screen so you can see the sketch right after you take the photo. Then I’ll set it up so the Pi shows up like a USB drive when you plug it in, add a button to take pictures and switch presets, and make more styles like cartoon and watercolor."}]...
|
Title: Doodle Cam by @adam_wu0630 | Stardance
Dev Title: Doodle Cam by @adam_wu0630 | Stardance
Devlogs:
Here you go: Doodle Cam-Devlog #1 So Doodle Cam is a camera I’m building on a Raspberry Pi that takes a photo and turns it into a cool art style, kind of like a filter but on a real camera. There’s no printing, you just plug it into your computer with a USB cable to get the pictures off. Right now I’m writing all the code in Python on my laptop first before I put it on the Pi. At first I wanted to make it look like a kid’s crayon drawing. I tried doing it with just OpenCV code, then I tried using AI with the Replicate API. The AI looked the best, but I figured out it can’t run on a Raspberry Pi because it’s way too slow, and it also costs money for every picture. So I switched to doing everything offline with OpenCV instead. I changed the first preset to a black-and-white pencil sketch since OpenCV is actually really good at that, and I’ve been tweaking it a bunch, removing the background, smoothing the photo, adding dark outlines so the face shows up, and adding shading so it looks more like a real drawing. Next I want to get the code running on the actual Raspberry Pi with the camera. After that I’ll add a little screen so you can see the sketch right after you take the photo. Then I’ll set it up so the Pi shows up like a USB drive when you plug it in, add a button to take pictures and switch presets, and make more styles like cartoon and watercolor....
|
1793901312.6410353
|
1794506112.6410353
|
|
19386
|
Untitled by @sidd | Stardance
|
sidd
|
0
|
0.0
|
0
|
[]
|
[]
|
Title: Untitled by @sidd | Stardance
|
1793926050.8767953
|
1794790050.8767953
|
|
19387
|
My very own WebOS by @Aryan-Shah | Stardance
|
Aryan-Shah
|
0
|
1.73
|
0
|
[]
|
[{"post_id": 11355, "ts": "202 [{"post_id": 11355, "ts": "2026-06-18T15:53:59Z", "hours": 0.4042, "text": "Added the ability to close and reopen window (only one window right now but more coming soon)"}, {"post_id": 10863, "ts": "2026-06-17T20:23:25Z", "hours": 0.8086, "text": "Added a background and a top bar (going for a minimalist look now)"}, {"post_id": 10611, "ts": "2026-06-17T13:34:28Z", "hours": 0.5197, "text": "Got my page working and finally figured I had the time to get git working"}]...
|
Title: My very own WebOS by @Aryan-Shah | Stardanc Title: My very own WebOS by @Aryan-Shah | Stardance
Devlogs:
Got my page working and finally figured I had the time to get git working
Added a background and a top bar (going for a minimalist look now)
Added the ability to close and reopen window (only one window right now but more coming soon)...
|
1793872319.5293946
|
1794477119.5293946
|
|
19388
|
Startup Graveyard by @aaryan_vishnupurikar | Stard Startup Graveyard by @aaryan_vishnupurikar | Stardance...
|
aaryan_vishnupurikar
|
0
|
0.3
|
0
|
[]
|
[{"post_id": 11043, "ts": "202 [{"post_id": 11043, "ts": "2026-06-18T02:19:16Z", "hours": 0.3047, "text": "Random idea i had on a saturday noticed no one was doing it and thats exactly why i did it give me suggestions and go try it out at my github https://github.com/aaryanv-midnightcrown/startup-graveyard (You have to put your API key in im not trying to give away money)"}]...
|
Title: Startup Graveyard by @aaryan_vishnupurikar Title: Startup Graveyard by @aaryan_vishnupurikar | Stardance
Devlogs:
Random idea i had on a saturday noticed no one was doing it and thats exactly why i did it give me suggestions and go try it out at my github https://github.com/aaryanv-midnightcrown/startup-graveyard (You have to put your API key in im not trying to give away money)...
|
1793922687.2401068
|
1794527487.2401068
|
|
19389
|
hardware test by @raygentest | Stardance
|
raygentest
|
0
|
0.0
|
0
|
[]
|
[]
|
Title: hardware test by @raygentest | Stardance
|
1794027098.9851725
|
1794631898.9851725
|
|
19390
|
Untitled by @Lamparter | Stardance
|
Lamparter
|
0
|
0.0
|
0
|
[]
|
[]
|
Title: Untitled by @Lamparter | Stardance
|
1793861347.3391774
|
1794725347.3391774
|
|
19391
|
My awesome macropad! by @Kerime | Stardance
|
Kerime
|
0
|
0.0
|
0
|
[]
|
[]
|
Title: My awesome macropad! by @Kerime | Stardance
|
1793444044.1474137
|
1794048844.1474137
|
|
19392
|
Untitled by @Kon | Stardance
|
Kon
|
0
|
0.0
|
0
|
[]
|
[]
|
Title: Untitled by @Kon | Stardance
|
1793962462.6294298
|
1794567262.6294298
|
|
19393
|
WaterMelonBot by @Tanish1 | Stardance
|
Tanish1
|
0
|
0.0
|
0
|
[]
|
[]
|
Title: WaterMelonBot by @Tanish1 | Stardance
|
1793958783.9162562
|
1794563583.9162562
|
|
19394
|
Untitled by @Chetan | Stardance
|
Chetan
|
0
|
0.0
|
0
|
[]
|
[]
|
Title: Untitled by @Chetan | Stardance
|
1793893966.3477287
|
1794498766.3477287
|
|
19395
|
DOMO_OS by @Mymy | Stardance
|
Mymy
|
0
|
3.42
|
0
|
[]
|
[{"post_id": 10338, "ts": "202 [{"post_id": 10338, "ts": "2026-06-17T00:38:18Z", "hours": 3.4219, "text": "I think i crashed out over this 3 times today but i got stuff done!! DOMO WORLD DOMINATION!"}]...
|
Title: DOMO_OS by @Mymy | Stardance
Devlogs:
I th Title: DOMO_OS by @Mymy | Stardance
Devlogs:
I think i crashed out over this 3 times today but i got stuff done!! DOMO WORLD DOMINATION!...
|
1794048910.367367
|
1794653710.367367
|
|
19396
|
Cosmo shooter by @WooperDaBest | Stardance
|
WooperDaBest
|
0
|
0.0
|
0
|
[]
|
[]
|
Title: Cosmo shooter by @WooperDaBest | Stardance
|
1793368593.8342755
|
1793973393.8342755
|
|
19397
|
My first slack bot! by @pooja | Stardance
|
pooja
|
0
|
0.0
|
0
|
[]
|
[]
|
Title: My first slack bot! by @pooja | Stardance
|
1793328517.5534685
|
1793933317.5534685
|
|
19398
|
Untitled by @sidd | Stardance
|
sidd
|
0
|
0.0
|
0
|
[]
|
[]
|
Title: Untitled by @sidd | Stardance
|
1793930108.229258
|
1794794108.229258
|
|
19399
|
My first slack bot! by @anshi_shah | Stardance
|
anshi_shah
|
0
|
0.0
|
0
|
[]
|
[]
|
Title: My first slack bot! by @anshi_shah | Starda Title: My first slack bot! by @anshi_shah | Stardance...
|
1793872111.8248527
|
1794476911.8248527
|
|
19400
|
FocusBuddy by @SaiD | Stardance
|
SaiD
|
2
|
47.0
|
276
|
[{"ship_num": 1, "ts": "2026-0 [{"ship_num": 1, "ts": "2026-08-19T03:40:46Z", "hours": 12.0, "multiplier": null, "payout": 0, "blessing": "neutral", "text": "A all in one AI-powered productivity system.", "repo": "https://github.com/Sai271-cloud/FocusBuddy", "demo": "https://focus-buddy-li7e.vercel.app/index.html?demo=night-owl"}, {"ship_num": 2, "ts": "2026-07-01T05:31:22Z", "hours": 35.0, "multiplier": 17.61, "payout": 276, "blessing": "neutral", "text": "I made a focusCoach that uses your webcam along with aboutme context + taskName + taskDescription + tab extension to figure out if you are focused or not. The tab extension won’t be available for you guys because it requires me to sign up for google developer account, but besides that the project should still work well. The project has multiple features like a plan feature, AI session debriefs, weekly and daily unwinds, and much more. It is pretty intuitive so try out the project for yourself!!. Also be aware that I am on the free trial of google studio so if the prediction doesn’t work for you that could just mean I have hit my rate limit. Anyway have fun!!!", "repo": "https://github.com/Sai271-cloud/FocusBuddy", "demo": "https://focus-buddy-li7e.vercel.app/index.html?demo=night-owl"}]...
|
[{"post_id": 30697, "ts": "202 [{"post_id": 30697, "ts": "2026-07-18T14:17:20Z", "hours": 4.0931, "text": "Devlog #4 I added a goal feature that allows you to make goals and uses the AI to track the goals and see how well you are doing for the goals"}, {"post_id": 28678, "ts": "2026-07-15T02:25:04Z", "hours": 7.4514, "text": "devlog #3 I have added leagues into the app. I have different leagues based on how many focused hours you have done. I am hoping this will motivate more people into spending more time on this app and in turn being more productive in their life!"}, {"post_id": 19780, "ts": "2026-07-01T05:11:30Z", "hours": 29.7242, "text": "Devlog #2. FocusBuddy V1 is complete. Here is the overview Tracker Focus Buddy is a productivity tool that helps students start focus sessions and understand how focused they were during that time. During a session, Focus Buddy classifies the user’s time into four states: focused, distracted, uncertain, and away. It does this by using webcam frames together with the task the user is working on. For example, if the task is “read a biology chapter,” the AI uses both the webcam frame and the task name/description to decide whether the user appears to be on task. I also built a browser extension that can optionally give Focus Buddy more context from the active tab. For example, if the task is “write an essay,” the extension can share the active website title and URL. This helps the AI make a more accurate prediction because it can compare what the user said they wanted to do with what they are actually doing. Session Debrief, Daily Unwind, and Weekly Unwind For the session debrief, Focus Buddy saves the session data and then generates an AI debrief. This debrief explains what happened during the session and gives practical feedback for next time. It points to specific moments from the session instead of giving generic advice. The daily unwind uses information from all the sessions recorded that day to give a general overview of what happened. During each session, the model records important changes in the user’s state. For example, if a user shifts from working on an essay to watching YouTube, the model can note that change. These state changes are then used as context for the daily unwind. The daily unwind also compares the user’s focus level for that day with their recent average. For example, if the user’s average focus level over the past seven days was 80%, but they recorded 62% today, the model can give encouraging advice while still pointing out the main distractions or struggles from the day. | The weekly unwind works similarly, but it looks at a longer period of time. I also implemented a pattern document that stores general patterns about the user. These patterns can be affirmed or updated by the model after each session. The weekly unwind uses this information to give a recap of the week, including average focus levels, the user’s most focused days, and insights into their focus habits. Plan Feature The next feature I built is the plan feature. This allows the user to plan out their day before starting their work. They can pick tasks, schedule them for specific times, estimate how difficult each task will be, and estimate how long each task will take. Based on this information, the AI can suggest the best times to work on certain tasks using patterns it has learned from the user. This step is completely optional, especially because this feature is still being optimized to provide better suggestions."}, {"post_id": 9651, "ts": "2026-06-16T01:51:48Z", "hours": 5.7564, "text": "Started working on a productivity tool called focus buddy. I currently have a basic landing page with the ability to create tasks and a calendar for session review. When you go into a session the project takes information from the webcam and then it using the Gemini 3.5 flash model along with with the context of the task description and task name assigns one of 4 labels: focused, away, unfocused, and uncertain. Also added a analytics page where you can see your previous sessions + dark mode."}]...
|
Title: FocusBuddy by @SaiD | Stardance
Devlogs:
S Title: FocusBuddy by @SaiD | Stardance
Devlogs:
Started working on a productivity tool called focus buddy. I currently have a basic landing page with the ability to create tasks and a calendar for session review. When you go into a session the project takes information from the webcam and then it using the Gemini 3.5 flash model along with with the context of the task description and task name assigns one of 4 labels: focused, away, unfocused, and uncertain. Also added a analytics page where you can see your previous sessions + dark mode.
Devlog #2. FocusBuddy V1 is complete. Here is the overview Tracker Focus Buddy is a productivity tool that helps students start focus sessions and understand how focused they were during that time. During a session, Focus Buddy classifies the user’s time into four states: focused, distracted, uncertain, and away. It does this by using webcam frames together with the task the user is working on. For example, if the task is “read a biology chapter,” the AI uses both the webcam frame and the task name/description to decide whether the user appears to be on task. I also built a browser extension that can optionally give Focus Buddy more context from the active tab. For example, if the task is “write an essay,” the extension can share the active website title and URL. This helps the AI make a more accurate prediction because it can compare what the user said they wanted to do with what they are actually doing. Session Debrief, Daily Unwind, and Weekly Unwind For the session debrief, Focus Buddy saves the session data and then generates an AI debrief. This debrief explains what happened during the session and gives practical feedback for next time. It points to specific moments from the session instead of giving generic advice. The daily unwind uses information from all the sessions recorded that day to give a general overview of what happened. During each session, the model records important changes in the user’s state. For example, if a user shifts from working on an essay to watching YouTube, the model can note that change. These state changes are then used as context for the daily unwind. The daily unwind also compares the user’s focus level for that day with their recent average. For example, if the user’s average focus level over the past seven days was 80%, but they recorded 62% today, the model can give encouraging advice while still pointing out the main distractions or struggles from the day. | The weekly unwind works similarly, but it looks at a longer period of time. I also implemented a pattern document that stores general patterns about the user. These patterns can be affirmed or updated by the model after each session. The weekly unwind uses this information to give a recap of the week, including average focus levels, the user’s most focused days, and insights into their focus habits. Plan Feature The next feature I built is the plan feature. This allows the user to plan out their day before starting their work. They can pick tasks, schedule them for specific times, estimate how difficult each task will be, and estimate how long each task will take. Based on this information, the AI can suggest the best times to work on certain tasks using patterns it has learned from the user. This step is completely optional, especially because this feature is still being optimized to provide better suggestions.
devlog #3 I have added leagues into the app. I have different leagues based on how many focused hours you have done. I am hoping this will motivate more people into spending more time on this app and in turn being more productive in their life!
Devlog #4 I added a goal feature that allows you to make goals and uses the AI to track the goals and see how well you are doing for the goals
Ships:
I made a focusCoach that uses your webcam along with aboutme context + taskName + taskDescription + tab extension to figure out if you are focused or not. The tab extension won’t be available for you guys because it requires me to sign up for google developer account, but besides that the project should still work well. The project has multiple features like a plan feature, AI session debriefs, weekly and daily unwinds, and much more. It is pretty intuitive so try out the project for yourself!!. Also be aware that I am on the free trial of google studio so if the prediction doesn’t work for you that could just mean I have hit my rate limit. Anyway have fun!!!
A all in one AI-powered productivity system....
|
1793955223.5987573
|
1794041623.5987573
|