|
62005
|
My very own WebOS by @Chumi | Stardance
|
Chumi
|
0
|
0.0
|
0
|
[]
|
[]
|
Title: My very own WebOS by @Chumi | Stardance
|
1793652679.3717136
|
1794257479.3717136
|
|
62006
|
My own site! by @sunay | Stardance
|
sunay
|
0
|
0.0
|
0
|
[]
|
[]
|
Title: My own site! by @sunay | Stardance
|
1793652680.2413034
|
1794257480.2413034
|
|
62007
|
HOPE by @furqanahmadzia786 | Stardance
|
furqanahmadzia786
|
0
|
0.0
|
0
|
[]
|
[]
|
Title: HOPE by @furqanahmadzia786 | Stardance
|
1793652681.1229806
|
1794257481.1229806
|
|
62008
|
Flappy Bird Game by @samyog_dev | Stardance
|
samyog_dev
|
0
|
0.0
|
0
|
[]
|
[]
|
Title: Flappy Bird Game by @samyog_dev | Stardance
|
1793652681.999144
|
1794257481.999144
|
|
62009
|
RTS GAME by @shreyanshz | Stardance
|
shreyanshz
|
0
|
0.0
|
0
|
[]
|
[]
|
Title: RTS GAME by @shreyanshz | Stardance
|
1793652683.9954739
|
1794257483.9954739
|
|
62010
|
Hex-2048 by @CadenO | Stardance
|
CadenO
|
1
|
4.0
|
23
|
[{"ship_num": 1, "ts": "2026-0 [{"ship_num": 1, "ts": "2026-09-24T02:57:15Z", "hours": 4.0, "multiplier": 5.24, "payout": 23, "blessing": "neutral", "text": "I made the classic 2048 number game, but in a hexagon instead of a square! I think that it looks mostly clean, and I find it pretty fun to play. It is a vanilla browser page, and can take input from a keyboard or a touchscreen.", "repo": "https://github.com/cesium72/Hex-2048", "demo": "https://cesium72.github.io/Hex-2048"}]...
|
[{"post_id": 72946, "ts": "202 [{"post_id": 72946, "ts": "2026-09-24T02:53:25Z", "hours": 0.7361, "text": "It’s finally actually done! The mobile input is now working and the game is pretty fun (in my opinion)"}, {"post_id": 71574, "ts": "2026-09-21T02:31:16Z", "hours": 0.63, "text": "I’ve basically finished my hexagonal 2048 game! The game itself, saving, help, and reset are all working, and the only thing left to add is a README (ugh). I think the game is pretty fun, though."}, {"post_id": 70985, "ts": "2026-09-20T04:58:55Z", "hours": 0.7875, "text": "I have made progress on my hexagonal 2048 game! 1) There is now a help screen, and 2) I got an 8192! Then, I decided that I have much better uses for my time. After I add the scoring, I’ll probably be about done, so I seem to be on track for my goal of a quick project."}, {"post_id": 69841, "ts": "2026-09-17T21:48:53Z", "hours": 2.1936, "text": "I’ve been making a hexagonal 2048 game! The game mechanics are working fine, and the logic is all in place. The only real things I have left to do are to add touchscreen input (swiping), scoring, and add functionality to reset and help buttons. (OK, fine, and write a README)."}]...
|
Title: Hex-2048 by @CadenO | Stardance
Devlogs:
I Title: Hex-2048 by @CadenO | Stardance
Devlogs:
I’ve been making a hexagonal 2048 game! The game mechanics are working fine, and the logic is all in place. The only real things I have left to do are to add touchscreen input (swiping), scoring, and add functionality to reset and help buttons. (OK, fine, and write a README).
I have made progress on my hexagonal 2048 game! 1) There is now a help screen, and 2) I got an 8192! Then, I decided that I have much better uses for my time. After I add the scoring, I’ll probably be about done, so I seem to be on track for my goal of a quick project.
I’ve basically finished my hexagonal 2048 game! The game itself, saving, help, and reset are all working, and the only thing left to add is a README (ugh). I think the game is pretty fun, though.
It’s finally actually done! The mobile input is now working and the game is pretty fun (in my opinion)
Ships:
I made the classic 2048 number game, but in a hexagon instead of a square! I think that it looks mostly clean, and I find it pretty fun to play. It is a vanilla browser page, and can take input from a keyboard or a touchscreen....
|
1793684991.9489164
|
1793771391.9489164
|
|
62011
|
NULL
|
NULL
|
0
|
0.0
|
0
|
[]
|
[]
|
|
1792864163.9378273
|
1793728163.9378273
|
|
62012
|
Simple Bank System by @Xquisite | Stardance
|
Xquisite
|
1
|
1.0
|
0
|
[{"ship_num": 1, "ts": "2026-0 [{"ship_num": 1, "ts": "2026-09-15T02:05:40Z", "hours": 1.0, "multiplier": null, "payout": 0, "blessing": "neutral", "text": "This is a banking system coded in Python. This program allows users to create accounts, log in, and manage their funds through three key features: deposit, withdrawal, and balance checks. This code can be run and used directly through the terminal. This code was made to help me get back into my coding journey after some time. So, recalling some features was a challenge. Of course, I have not gone deep into my Python journey, so this code can be improved heavily. Overall, I am proud of being able to make this code fairly quickly, and being able to make it at all in the first place.", "repo": "https://github.com/Mejia-J/Bank_System", "demo": "https://silver-giggle-x5g7v646wpwf9q5v.github.dev/"}]...
|
[{"post_id": 67873, "ts": "202 [{"post_id": 67873, "ts": "2026-09-14T05:13:06Z", "hours": 1.1469, "text": "To get back into my Python journey, I decided to challenge myself a bit by reviewing key, beginner concepts like loops and variables, but also recalling tougher concepts like lists, functions, and objects. Throughout the process, I sometimes referred back to my older projects to remember these fundamental concepts. Overall, I had a fun time diving back into my Python journey, and I hope to continue coding throughout the years."}]...
|
Title: Simple Bank System by @Xquisite | Stardance Title: Simple Bank System by @Xquisite | Stardance
Devlogs:
To get back into my Python journey, I decided to challenge myself a bit by reviewing key, beginner concepts like loops and variables, but also recalling tougher concepts like lists, functions, and objects. Throughout the process, I sometimes referred back to my older projects to remember these fundamental concepts. Overall, I had a fun time diving back into my Python journey, and I hope to continue coding throughout the years.
Ships:
This is a banking system coded in Python. This program allows users to create accounts, log in, and manage their funds through three key features: deposit, withdrawal, and balance checks. This code can be run and used directly through the terminal. This code was made to help me get back into my coding journey after some time. So, recalling some features was a challenge. Of course, I have not gone deep into my Python journey, so this code can be improved heavily. Overall, I am proud of being able to make this code fairly quickly, and being able to make it at all in the first place....
|
1793684993.0844376
|
1793771393.0844376
|
|
62013
|
Nture therapy by @Amoria | Stardance
|
Amoria
|
0
|
0.0
|
0
|
[]
|
[]
|
Title: Nture therapy by @Amoria | Stardance
|
1793652684.8576689
|
1794257484.8576689
|
|
62014
|
My_slackbot by @momoife_ogunjobi | Stardance
|
momoife_ogunjobi
|
0
|
0.0
|
0
|
[]
|
[]
|
Title: My_slackbot by @momoife_ogunjobi | Stardanc Title: My_slackbot by @momoife_ogunjobi | Stardance...
|
1793652685.743788
|
1794257485.743788
|
|
62015
|
SwishLab by @noor_serageldin | Stardance
|
noor_serageldin
|
0
|
0.0
|
0
|
[]
|
[]
|
Title: SwishLab by @noor_serageldin | Stardance
|
1793652686.6251493
|
1794257486.6251493
|
|
62016
|
My awesome macropad! by @Eileen | Stardance
|
Eileen
|
0
|
0.0
|
0
|
[]
|
[]
|
Title: My awesome macropad! by @Eileen | Stardance
|
1793652687.5032017
|
1794257487.5032017
|
|
62017
|
NULL
|
NULL
|
0
|
0.0
|
0
|
[]
|
[]
|
|
1792864164.7612498
|
1793728164.7612498
|
|
62018
|
My own site! by @bhargavrmkmr | Stardance
|
bhargavrmkmr
|
0
|
0.0
|
0
|
[]
|
[]
|
Title: My own site! by @bhargavrmkmr | Stardance
|
1793652688.3987525
|
1794257488.3987525
|
|
62019
|
NULL
|
NULL
|
0
|
0.0
|
0
|
[]
|
[]
|
|
1792864167.3475263
|
1793728167.3475263
|
|
62020
|
Everest Cafe by @noahl | Stardance
|
noahl
|
0
|
0.27
|
0
|
[]
|
[{"post_id": 67851, "ts": "202 [{"post_id": 67851, "ts": "2026-09-14T04:04:05Z", "hours": 0.2667, "text": "Players have been able to host sessions forever… but now you can schedule and host with an in-game GUI! We use BloxCord to schedule shifts so we already had shift boards that check for shifts periodically so instead of checking everytime a player needs to look at the GUI, we cache data from the shift boards to use for the GUI as well. I’ve already made the UI for the list of sessions you have scheduled (or if you dont have any) and the code to populate the list as well as to start the session! Tonight, I’m going to make UI for creating/scheduling a shift and to see all the users that participated in the shift and what they did (what orders they made/cooked or spills they cleaned). Don’t tell anyone but just for fun I made it so that you have a really small chance to get a special UI! 🙂 See it here ↓"}]...
|
Title: Everest Cafe by @noahl | Stardance
Devlogs Title: Everest Cafe by @noahl | Stardance
Devlogs:
Players have been able to host sessions forever… but now you can schedule and host with an in-game GUI! We use BloxCord to schedule shifts so we already had shift boards that check for shifts periodically so instead of checking everytime a player needs to look at the GUI, we cache data from the shift boards to use for the GUI as well. I’ve already made the UI for the list of sessions you have scheduled (or if you dont have any) and the code to populate the list as well as to start the session! Tonight, I’m going to make UI for creating/scheduling a shift and to see all the users that participated in the shift and what they did (what orders they made/cooked or spills they cleaned). Don’t tell anyone but just for fun I made it so that you have a really small chance to get a special UI! 🙂 See it here ↓...
|
1793652690.4689472
|
1794257490.4689472
|
|
62021
|
NULL
|
NULL
|
0
|
0.0
|
0
|
[]
|
[]
|
|
1792864168.1762965
|
1793728168.1762965
|
|
62022
|
Frictionless by @shreyder | Stardance
|
shreyder
|
0
|
0.0
|
0
|
[]
|
[]
|
Title: Frictionless by @shreyder | Stardance
|
1793652691.3358786
|
1794257491.3358786
|
|
62023
|
hello! by @aadistech1 | Stardance
|
aadistech1
|
1
|
1.0
|
0
|
[{"ship_num": 1, "ts": "2026-0 [{"ship_num": 1, "ts": "2026-09-14T17:39:32Z", "hours": 1.0, "multiplier": null, "payout": 0, "blessing": "neutral", "text": "This is mypersonal website i made…Yeah I have a limited css knowledge and put my maximum to it, i used very small (below 10% ai for someee debugging .thats all)", "repo": "https://github.com/aadistech1-glitch/mypersonalwebsite", "demo": "https://aadivinayak.tiiny.site/"}]...
|
[{"post_id": 68180, "ts": "202 [{"post_id": 68180, "ts": "2026-09-14T17:37:25Z", "hours": 0.9722, "text": "The code is completed!It was a small project"}]...
|
Title: hello! by @aadistech1 | Stardance
Devlogs: Title: hello! by @aadistech1 | Stardance
Devlogs:
The code is completed!It was a small project
Ships:
This is mypersonal website i made…Yeah I have a limited css knowledge and put my maximum to it, i used very small (below 10% ai for someee debugging .thats all)...
|
1793684994.2482634
|
1793771394.2482634
|
|
62024
|
Humanoid hand by @Coooodddddder | Stardance
|
Coooodddddder
|
0
|
0.0
|
0
|
[]
|
[]
|
Title: Humanoid hand by @Coooodddddder | Stardance
|
1793652692.2103589
|
1794257492.2103589
|
|
62025
|
NULL
|
NULL
|
0
|
0.0
|
0
|
[]
|
[]
|
|
1792864169.0030038
|
1793728169.0030038
|
|
62026
|
My very own WebOS by @vishwaksena | Stardance
|
vishwaksena
|
0
|
0.0
|
0
|
[]
|
[]
|
Title: My very own WebOS by @vishwaksena | Stardan Title: My very own WebOS by @vishwaksena | Stardance...
|
1793652693.0756671
|
1794257493.0756671
|
|
62027
|
Bio Synth by @govindrkumar | Stardance
|
govindrkumar
|
0
|
0.0
|
0
|
[]
|
[]
|
Title: Bio Synth by @govindrkumar | Stardance
|
1793652697.7730346
|
1794257497.7730346
|
|
62028
|
Hackslack by @asho | Stardance
|
asho
|
1
|
0.0
|
0
|
[{"ship_num": 1, "ts": "2026-0 [{"ship_num": 1, "ts": "2026-09-21T04:33:50Z", "hours": 0.0, "multiplier": null, "payout": 0, "blessing": "neutral", "text": "I made a slackbot with three basic functions. I was constantly running into error plus my nest application wasn’t being approved. Thank you soo much!", "repo": "https://github.com/ayeshayaya/hackslack", "demo": "https://ayeshayaya.github.io/hackslack/"}]...
|
[{"post_id": 67860, "ts": "202 [{"post_id": 67860, "ts": "2026-09-14T04:24:27Z", "hours": 0.2789, "text": "the project took me around 2 hours to do, idk why its showing 16min:)"}]...
|
Title: Hackslack by @asho | Stardance
Devlogs:
th Title: Hackslack by @asho | Stardance
Devlogs:
the project took me around 2 hours to do, idk why its showing 16min:)
Ships:
I made a slackbot with three basic functions. I was constantly running into error plus my nest application wasn’t being approved. Thank you soo much!...
|
1793684995.403205
|
1793771395.403205
|
|
62029
|
My very own WebOS by @ByteShade | Stardance
|
ByteShade
|
0
|
0.0
|
0
|
[]
|
[]
|
Title: My very own WebOS by @ByteShade | Stardance
|
1793652698.6730328
|
1794257498.6730328
|
|
62030
|
My awesome macropad! by @diak | Stardance
|
diak
|
0
|
0.0
|
0
|
[]
|
[]
|
Title: My awesome macropad! by @diak | Stardance
|
1793652699.5371063
|
1794257499.5371063
|
|
62031
|
My awesome macropad! by @kaustubh98135 | Stardance
|
kaustubh98135
|
0
|
0.0
|
0
|
[]
|
[]
|
Title: My awesome macropad! by @kaustubh98135 | St Title: My awesome macropad! by @kaustubh98135 | Stardance...
|
1793652700.4424958
|
1794257500.4424958
|
|
62032
|
A school planner and timetable teller by @adbhutku A school planner and timetable teller by @adbhutkunder834 | Stardance...
|
adbhutkunder834
|
0
|
1.32
|
0
|
[]
|
[{"post_id": 68156, "ts": "202 [{"post_id": 68156, "ts": "2026-09-14T16:41:57Z", "hours": 1.3214, "text": "started building PWA Timetable App. Created the core day 1-5 & Star-day logic and designed an Apple-inspired minimal UI."}]...
|
Title: A school planner and timetable teller by @a Title: A school planner and timetable teller by @adbhutkunder834 | Stardance
Devlogs:
started building PWA Timetable App. Created the core day 1-5 & Star-day logic and designed an Apple-inspired minimal UI....
|
1793652701.3133008
|
1794257501.3133008
|
|
62033
|
Mineworld Java by @Rohit_Biswas | Stardance
|
Rohit_Biswas
|
0
|
0.0
|
0
|
[]
|
[]
|
Title: Mineworld Java by @Rohit_Biswas | Stardance
|
1793418737.080716
|
1794282737.080716
|
|
62034
|
Stock Predictor by @royg51 | Stardance
|
royg51
|
0
|
6.92
|
0
|
[]
|
[{"post_id": 72069, "ts": "202 [{"post_id": 72069, "ts": "2026-09-22T03:22:39Z", "hours": 6.9203, "text": "Devlog #1 I started Stock Predictor as a project to explore how financial analysis tools actually work under the hood. Instead of trying to build another app that claims to predict stock prices, I wanted to focus on historical analysis, technical indicators, risk metrics, backtesting, and portfolio simulation. I built the application with a React/TypeScript frontend and FastAPI/Python backend, then gradually added features like historical pattern detection, ETF exploration, comparisons, and an educational Learn section. A major part of the project has also been making the methodology transparent and avoiding misleading conclusions. The public demo now runs on synthetic data so it can be shared publicly without redistributing market data without the necessary licensing rights. There is still more I want to improve, but getting the project from an idea into a fully tested, publicly accessible application has been the biggest milestone so far."}]...
|
Title: Stock Predictor by @royg51 | Stardance
Dev Title: Stock Predictor by @royg51 | Stardance
Devlogs:
Devlog #1 I started Stock Predictor as a project to explore how financial analysis tools actually work under the hood. Instead of trying to build another app that claims to predict stock prices, I wanted to focus on historical analysis, technical indicators, risk metrics, backtesting, and portfolio simulation. I built the application with a React/TypeScript frontend and FastAPI/Python backend, then gradually added features like historical pattern detection, ETF exploration, comparisons, and an educational Learn section. A major part of the project has also been making the methodology transparent and avoiding misleading conclusions. The public demo now runs on synthetic data so it can be shared publicly without redistributing market data without the necessary licensing rights. There is still more I want to improve, but getting the project from an idea into a fully tested, publicly accessible application has been the biggest milestone so far....
|
1793652703.3250482
|
1794257503.3250482
|
|
62035
|
NULL
|
NULL
|
0
|
0.0
|
0
|
[]
|
[]
|
|
1792864169.8191278
|
1793728169.8191278
|
|
62036
|
NeuroForge by @royg51 | Stardance
|
royg51
|
1
|
7.0
|
0
|
[{"ship_num": 1, "ts": "2026-1 [{"ship_num": 1, "ts": "2026-11-01T13:50:59Z", "hours": 7.0, "multiplier": null, "payout": 0, "blessing": "neutral", "text": "What did you make? I built NeuroForge, an engineering platform that uses simulation, AI, and optimization to improve designs across structural engineering, robotics, and thermal engineering. What was challenging? Implementing accurate physics simulations, making optimization algorithms work across different domains, and testing whether designs remain reliable when conditions change. What are you proud of? I’m proud of turning an initial frontend prototype into a working platform with four engineering domains, real simulations, multiple optimization algorithms, an autonomous experiment lab, and 3D visualization. What should people know so they can test your project? Visit https://neuroforge-chi.vercel.app , open the Workspace, select an engineering domain, and run an experiment. You can also explore completed experiments on the Benchmarks page.", "repo": "https://github.com/RoyGutta/NeuroForge", "demo": "https://neuroforge-chi.vercel.app/"}]...
|
[{"post_id": 86337, "ts": "202 [{"post_id": 86337, "ts": "2026-11-01T11:46:07Z", "hours": 0.7753, "text": "NeuroForge — From a Prototype to an Engineering Research Platform When I first started NeuroForge, I wanted to build a platform that could take an engineering problem, understand its requirements, and help find better designs through simulation and optimization. What started as a frontend prototype gradually became a much larger engineering project. I built out the actual engineering engine, starting with finite element analysis for structural trusses. It now evaluates stress, buckling, deflection, and other constraints, then uses optimization algorithms to search for better designs. From there, I expanded the platform to include machine learning surrogates, Bayesian optimization, evolutionary algorithms, and multi-objective optimization. I also added an autonomous engineering lab that can run controlled experiments, compare approaches under consistent budgets, and generate reproducible results. One of the biggest steps was expanding beyond a single engineering problem. NeuroForge now supports structural trusses in 2D and 3D, robotic manipulators, and thermal heat-sink design. I built a 3D viewport for inspecting structures and their analysis results, including forces, utilization, and deformation. A major part of the project became researching how optimization methods actually behave. I found that an algorithm that performs well on one engineering domain does not necessarily perform well on another. More recently, I investigated how different engineering constraints need different robustness margins. In one manipulator study, combining a 2% reach margin with an 8% tip-deflection margin produced designs that passed the study’s robustness criterion at just 0.63% additional peak torque compared with the nominal optimum. A uniform margin was considerably more expensive. These results also helped me identify where sampled robustness is useful and where mathematical guarantees are possible. I also worked on improving how users describe engineering problems through natural language. The rule-based interpreter is available, and the newer model-backed and hybrid approaches have been implemented, but their comparative benchmark is still pending. I haven’t treated those unmeasured results as validated or declared the next release complete. NeuroForge has grown far beyond what I originally imagined. I’m treating this submission as a snapshot of what I’ve built so far, not the end of the project. I plan to keep developing it, testing new ideas, and expanding its engineering capabilities."}, {"post_id": 82400, "ts": "2026-10-24T18:31:02Z", "hours": 4.7728, "text": "Taking NeuroForge beyond a 2D bridge Since my last devlog, I’ve been expanding NeuroForge to see whether the same engineering and optimization infrastructure could work across completely different types of problems. The first major step was adding a robotics domain. NeuroForge can model a planar two-link robotic arm, calculate its kinematics and actuator torques, and optimize its design under constraints. I then added a thermal engineering domain for heat sinks, using fin theory and natural-convection heat transfer calculations. One interesting result was that a heat sink that looks reasonable geometrically can still be physically infeasible under the specified heat load. I had to make sure the solver reported that instead of producing an attractive but misleading result. I also extended the structural engine from planar trusses into three dimensions. This involved generalizing the finite-element stiffness assembly to work with spatial members and three degrees of freedom per node. I tested the new solver against analytical cases and checked that planar structures embedded in 3D produce the same results as the original 2D solver. On the interface side, I integrated Three.js to create an interactive 3D engineering viewport. It renders the actual solved structure, with views for axial forces, constraint utilization, and deformation. You can inspect individual members and nodes, view their calculated values, and scrub through optimization generations to see the design change using recorded results rather than a scripted animation. One of the most interesting findings has been that optimizer performance depends on the engineering domain. The algorithm that performs well on a truss does not necessarily perform best on a robotic arm or a thermal design. That has made cross-domain benchmarking an important part of the project rather than assuming one algorithm is always best. NeuroForge now brings together structural analysis, robotics, thermal modeling, machine learning, multiple optimization algorithms, reproducible experiments, and autonomous search. I have also been documenting the mathematical assumptions and limitations of each model so that the results are useful as computational studies rather than being mistaken for certified engineering designs. My next goal is to improve how people describe engineering problems in natural language, while keeping the actual calculations and feasibility checks deterministic and testable."}, {"post_id": 72066, "ts": "2026-09-22T03:17:56Z", "hours": 1.9406, "text": "Turning NeuroForge into an actual engineering system When I first started NeuroForge, it was mostly a polished frontend concept for an AI engineering platform. It looked cool, but the optimization was basically a demo. I’ve been changing that. The current version actually solves a structural optimization problem. A natural-language engineering brief gets converted into a structured specification, a baseline truss is sized, and NeuroForge runs real finite-element analyses on thousands of candidate designs. The engine now includes: 2D truss FEA using the direct stiffness method Cholesky factorization stress, deflection, self-weight, and Euler buckling checks constrained evolutionary optimization simulated annealing and random search reproducible seeded experiments experiment history and generation-by-generation results I also started adding a machine-learning layer. NeuroForge can generate datasets from simulation runs and train surrogate models to approximate the expensive simulation. I added polynomial ridge regression, an MLP, and Gaussian-process regression, along with held-out evaluation using MAE, RMSE, R², and prediction intervals. The interesting part was that the results were not uniformly great. The surrogate learned mass extremely well, but predicting constraint feasibility was much harder. That gave me an actual research problem to work on instead of just another feature to add. I also added constrained Bayesian optimization and NSGA-II for multi-objective optimization, so NeuroForge can now explore tradeoffs like mass versus compliance and display the resulting Pareto frontier. The whole thing runs in the browser with the engineering engine separated from the React UI and heavy computation moved into a Web Worker. Next I’m working on per-member surrogate models and uncertainty-aware candidate screening, which should make the ML system much better at predicting whether a design will actually satisfy the engineering constraints."}]...
|
Title: NeuroForge by @royg51 | Stardance
Devlogs: Title: NeuroForge by @royg51 | Stardance
Devlogs:
Turning NeuroForge into an actual engineering system When I first started NeuroForge, it was mostly a polished frontend concept for an AI engineering platform. It looked cool, but the optimization was basically a demo. I’ve been changing that. The current version actually solves a structural optimization problem. A natural-language engineering brief gets converted into a structured specification, a baseline truss is sized, and NeuroForge runs real finite-element analyses on thousands of candidate designs. The engine now includes: 2D truss FEA using the direct stiffness method Cholesky factorization stress, deflection, self-weight, and Euler buckling checks constrained evolutionary optimization simulated annealing and random search reproducible seeded experiments experiment history and generation-by-generation results I also started adding a machine-learning layer. NeuroForge can generate datasets from simulation runs and train surrogate models to approximate the expensive simulation. I added polynomial ridge regression, an MLP, and Gaussian-process regression, along with held-out evaluation using MAE, RMSE, R², and prediction intervals. The interesting part was that the results were not uniformly great. The surrogate learned mass extremely well, but predicting constraint feasibility was much harder. That gave me an actual research problem to work on instead of just another feature to add. I also added constrained Bayesian optimization and NSGA-II for multi-objective optimization, so NeuroForge can now explore tradeoffs like mass versus compliance and display the resulting Pareto frontier. The whole thing runs in the browser with the engineering engine separated from the React UI and heavy computation moved into a Web Worker. Next I’m working on per-member surrogate models and uncertainty-aware candidate screening, which should make the ML system much better at predicting whether a design will actually satisfy the engineering constraints.
Taking NeuroForge beyond a 2D bridge Since my last devlog, I’ve been expanding NeuroForge to see whether the same engineering and optimization infrastructure could work across completely different types of problems. The first major step was adding a robotics domain. NeuroForge can model a planar two-link robotic arm, calculate its kinematics and actuator torques, and optimize its design under constraints. I then added a thermal engineering domain for heat sinks, using fin theory and natural-convection heat transfer calculations. One interesting result was that a heat sink that looks reasonable geometrically can still be physically infeasible under the specified heat load. I had to make sure the solver reported that instead of producing an attractive but misleading result. I also extended the structural engine from planar trusses into three dimensions. This involved generalizing the finite-element stiffness assembly to work with spatial members and three degrees of freedom per node. I tested the new solver against analytical cases and checked that planar structures embedded in 3D produce the same results as the original 2D solver. On the interface side, I integrated Three.js to create an interactive 3D engineering viewport. It renders the actual solved structure, with views for axial forces, constraint utilization, and deformation. You can inspect individual members and nodes, view their calculated values, and scrub through optimization generations to see the design change using recorded results rather than a scripted animation. One of the most interesting findings has been that optimizer performance depends on the engineering domain. The algorithm that performs well on a truss does not necessarily perform best on a robotic arm or a thermal design. That has made cross-domain benchmarking an important part of the project rather than assuming one algorithm is always best. NeuroForge now brings together structural analysis, robotics, thermal modeling, machine learning, multiple optimization algorithms, reproducible experiments, and autonomous search. I have also been documenting the mathematical assumptions and limitations of each model so that the results are useful as computational studies rather than being mistaken for certified engineering designs. My next goal is to improve how people describe engineering problems in natural language, while keeping the actual calculations and feasibility checks deterministic and testable.
NeuroForge — From a Prototype to an Engineering Research Platform When I first started NeuroForge, I wanted to build a platform that could take an engineering problem, understand its requirements, and help find better designs through simulation and optimization. What started as a frontend prototype gradually became a much larger engineering project. I built out the actual engineering engine, starting with finite element analysis for structural trusses. It now evaluates stress, buckling, deflection, and other constraints, then uses optimization algorithms to search for better designs. From there, I expanded the platform to include machine learning surrogates, Bayesian optimization, evolutionary algorithms, and multi-objective optimization. I also added an autonomous engineering lab that can run controlled experiments, compare approaches under consistent budgets, and generate reproducible results. One of the biggest steps was expanding beyond a single engineering problem. NeuroForge now supports structural trusses in 2D and 3D, robotic manipulators, and thermal heat-sink design. I built a 3D viewport for inspecting structures and their analysis results, including forces, utilization, and deformation. A major part of the project became researching how optimization methods actually behave. I found that an algorithm that performs well on one engineering domain does not necessarily perform well on another. More recently, I investigated how different engineering constraints need different robustness margins. In one manipulator study, combining a 2% reach margin with an 8% tip-deflection margin produced designs that passed the study’s robustness criterion at just 0.63% additional peak torque compared with the nominal optimum. A uniform margin was considerably more expensive. These results also helped me identify where sampled robustness is useful and where mathematical guarantees are possible. I also worked on improving how users describe engineering problems through natural language. The rule-based interpreter is available, and the newer model-backed and hybrid approaches have been implemented, but their comparative benchmark is still pending. I haven’t treated those unmeasured results as validated or declared the next release complete. NeuroForge has grown far beyond what I originally imagined. I’m treating this submission as a snapshot of what I’ve built so far, not the end of the project. I plan to keep developing it, testing new ideas, and expanding its engineering capabilities.
Ships:
What did you make? I built NeuroForge, an engineering platform that uses simulation, AI, and optimization to improve designs across structural engineering, robotics, and thermal engineering. What was challenging? Implementing accurate physics simulations, making optimization algorithms work across different domains, and testing whether designs remain reliable when conditions change. What are you proud of? I’m proud of turning an initial frontend prototype into a working platform with four engineering domains, real simulations, multiple optimization algorithms, an autonomous experiment lab, and 3D visualization. What should people know so they can test your project? Visit https://neuroforge-chi.vercel.app , open the Workspace, select an engineering domain, and run an experiment. You can also explore completed experiments on the Benchmarks page....
|
1793652704.20846
|
1793739104.20846
|
|
62037
|
NULL
|
NULL
|
0
|
0.0
|
0
|
[]
|
[]
|
|
1792864170.6517417
|
1793728170.6517417
|
|
62038
|
bug pad by @AyushKushwaha | Stardance
|
AyushKushwaha
|
0
|
8.89
|
0
|
[]
|
[{"post_id": 73603, "ts": "202 [{"post_id": 73603, "ts": "2026-09-25T13:46:52Z", "hours": 1.1047, "text": "devlog-9 Still working on cad only , many time I forgot to lapse yah , thanks to @Jacube1234 , he helped me a lot and also i learned so many thing from him."}, {"post_id": 71000, "ts": "2026-09-20T05:53:06Z", "hours": 0.8172, "text": "devlog-7 finally completed the cad and also added keycaps , literally it was hard for me but anyhow i took help form my friends nemo and jacube they helped me a lot . many time i forget to lapse my work"}, {"post_id": 69991, "ts": "2026-09-18T06:32:08Z", "hours": 1.585, "text": "devlog-6 I just got to know by @Jacube1234 my pcb was to big , so i redisgned it with guidence with jacube ."}, {"post_id": 69653, "ts": "2026-09-17T14:43:34Z", "hours": 1.6506, "text": "devlog-5 completed the gerber file and completed the simple cad design it is lil bit hard to use fusion for me , and tried watching tutorials and it is still hard for me . also my pc is lil bit lagging in fusion software."}, {"post_id": 69205, "ts": "2026-09-16T16:22:53Z", "hours": 1.2339, "text": "devlog-4 moved the type-c port outside the pcb and also correct the wiring and add all the 3d components . I can’t believe that this all was done by me . . . A special thanks to @Nemo_Donut who helped me a lot."}, {"post_id": 69098, "ts": "2026-09-16T11:25:00Z", "hours": 0.9006, "text": "devlog -3 resolved some important warnings and also learned to add images and text on pcb."}, {"post_id": 68585, "ts": "2026-09-15T11:01:17Z", "hours": 1.1172, "text": "devlog-2 done the structure and, also adjust all the component and wired it . I dont know weather it is correct or not."}, {"post_id": 68473, "ts": "2026-09-15T05:23:10Z", "hours": 0.4836, "text": "devlog-1 finally started hardware , this is my first hardware project , i don’t know any thing just watched a tutorial and asked @Nemo_Donut for help . and then started . I don’t even know weather it is correct or not."}]...
|
Title: bug pad by @AyushKushwaha | Stardance
Devl Title: bug pad by @AyushKushwaha | Stardance
Devlogs:
devlog-1 finally started hardware , this is my first hardware project , i don’t know any thing just watched a tutorial and asked @Nemo_Donut for help . and then started . I don’t even know weather it is correct or not.
devlog-2 done the structure and, also adjust all the component and wired it . I dont know weather it is correct or not.
devlog -3 resolved some important warnings and also learned to add images and text on pcb.
devlog-4 moved the type-c port outside the pcb and also correct the wiring and add all the 3d components . I can’t believe that this all was done by me . . . A special thanks to @Nemo_Donut who helped me a lot.
devlog-5 completed the gerber file and completed the simple cad design it is lil bit hard to use fusion for me , and tried watching tutorials and it is still hard for me . also my pc is lil bit lagging in fusion software.
devlog-6 I just got to know by @Jacube1234 my pcb was to big , so i redisgned it with guidence with jacube .
devlog-7 finally completed the cad and also added keycaps , literally it was hard for me but anyhow i took help form my friends nemo and jacube they helped me a lot . many time i forget to lapse my work
devlog-9 Still working on cad only , many time I forgot to lapse yah , thanks to @Jacube1234 , he helped me a lot and also i learned so many thing from him....
|
1793652705.3619375
|
1794257505.3619375
|
|
62039
|
bug pad by @AyushKushwaha | Stardance
|
AyushKushwaha
|
0
|
0.0
|
0
|
[]
|
[]
|
Title: bug pad by @AyushKushwaha | Stardance
|
1793652706.5745604
|
1794257506.5745604
|
|
62040
|
NULL
|
NULL
|
0
|
0.0
|
0
|
[]
|
[]
|
|
1792864171.470321
|
1793728171.470321
|
|
62041
|
Arduino-based quadcopter drone. by @malakmalakarsl Arduino-based quadcopter drone. by @malakmalakarslan | Stardance...
|
malakmalakarslan
|
0
|
0.0
|
0
|
[]
|
[]
|
Title: Arduino-based quadcopter drone. by @malakma Title: Arduino-based quadcopter drone. by @malakmalakarslan | Stardance...
|
1793652707.4572194
|
1794257507.4572194
|
|
62042
|
Smart Ai recycling bin by @kevin_wei | Stardance
|
kevin_wei
|
0
|
0.0
|
0
|
[]
|
[]
|
Title: Smart Ai recycling bin by @kevin_wei | Star Title: Smart Ai recycling bin by @kevin_wei | Stardance...
|
1793652709.5092962
|
1794257509.5092962
|
|
62043
|
NULL
|
NULL
|
0
|
0.0
|
0
|
[]
|
[]
|
|
1792864172.4919713
|
1793728172.4919713
|
|
62044
|
My own site! by @aaryvardhans | Stardance
|
aaryvardhans
|
0
|
0.0
|
0
|
[]
|
[]
|
Title: My own site! by @aaryvardhans | Stardance
|
1793652710.4115546
|
1794257510.4115546
|
|
62045
|
My awesome macropad! by @sarabesh | Stardance
|
sarabesh
|
0
|
0.0
|
0
|
[]
|
[]
|
Title: My awesome macropad! by @sarabesh | Stardan Title: My awesome macropad! by @sarabesh | Stardance...
|
1793652711.5221345
|
1794257511.5221345
|
|
62046
|
Enter the Code Alarm Clock by @LPcomix123 | Starda Enter the Code Alarm Clock by @LPcomix123 | Stardance...
|
LPcomix123
|
0
|
0.0
|
0
|
[]
|
[]
|
Title: Enter the Code Alarm Clock by @LPcomix123 | Title: Enter the Code Alarm Clock by @LPcomix123 | Stardance...
|
1793652712.9622433
|
1794257512.9622433
|
|
62047
|
My own site! by @MHQ | Stardance
|
MHQ
|
0
|
0.0
|
0
|
[]
|
[]
|
Title: My own site! by @MHQ | Stardance
|
1793652713.8697424
|
1794257513.8697424
|
|
62048
|
Terminal_Based_osint by @ | Stardance
|
|
0
|
0.0
|
0
|
[]
|
[]
|
Title: Terminal_Based_osint by @ | Stardance
|
1793652714.7440326
|
1794257514.7440326
|
|
62049
|
Linux security auditor by @ayanghazi | Stardance
|
ayanghazi
|
0
|
0.0
|
0
|
[]
|
[]
|
Title: Linux security auditor by @ayanghazi | Star Title: Linux security auditor by @ayanghazi | Stardance...
|
1793652715.5935175
|
1794257515.5935175
|
|
62050
|
WarioWare Game by @Amoon | Stardance
|
Amoon
|
0
|
0.0
|
0
|
[]
|
[]
|
Title: WarioWare Game by @Amoon | Stardance
|
1793652716.4750018
|
1794257516.4750018
|
|
62051
|
NULL
|
NULL
|
0
|
0.0
|
0
|
[]
|
[]
|
|
1792864173.319038
|
1793728173.319038
|
|
62052
|
Line follower motherboard by @avkings604 | Stardan Line follower motherboard by @avkings604 | Stardance...
|
avkings604
|
0
|
0.0
|
0
|
[]
|
[]
|
Title: Line follower motherboard by @avkings604 | Title: Line follower motherboard by @avkings604 | Stardance...
|
1793652717.3577974
|
1794257517.3577974
|
|
62053
|
DORAHPMSA by @ARASEVO | Stardance
|
ARASEVO
|
0
|
0.0
|
0
|
[]
|
[]
|
Title: DORAHPMSA by @ARASEVO | Stardance
|
1793652719.7982802
|
1794257519.7982802
|
|
62054
|
Bird Journey - A game by @RadiatingDucks | Stardan Bird Journey - A game by @RadiatingDucks | Stardance...
|
RadiatingDucks
|
0
|
0.0
|
0
|
[]
|
[]
|
Title: Bird Journey - A game by @RadiatingDucks | Title: Bird Journey - A game by @RadiatingDucks | Stardance...
|
1793652720.690805
|
1794257520.690805
|