|
9056
|
DJ CLI by @diamondjdev | Stardance
|
diamondjdev
|
1
|
16.0
|
0
|
[{"ship_num": 1, "ts": "2026-1 [{"ship_num": 1, "ts": "2026-10-29T00:24:46Z", "hours": 16.0, "multiplier": null, "payout": 0, "blessing": "neutral", "text": "An opinionated CLI that allows the user to manage dependencies, clean workspaces, manage remote projects, etc all from one CLI. The CLI is hyper-opinionated but the Github is open to PR’s. Run dj type and try to beat my typing speed of 100% acc, 90wpm", "repo": "https://github.com/DiamondJdev/djCLI", "demo": "https://www.npmjs.com/package/djmond"}]...
|
[{"post_id": 83973, "ts": "202 [{"post_id": 83973, "ts": "2026-10-29T00:21:20Z", "hours": 8.8383, "text": "Shipped a BUNCH, including an integration with one of my other projects, and some more tools for managing dependencies"}, {"post_id": 3221, "ts": "2026-06-06T01:36:47Z", "hours": 7.4364, "text": "Super cool CLI tool to automate my most common workflows built using Go, but I’m migrating to Python so I can learn Python better! I currently have commands for cloning my NestJS and NextJS template repos for new projects, a command to delete old and merged git branches, and a precommit command to run npm build, lint, and format before I make git commits! (Photo is a little old)"}]...
|
Title: DJ CLI by @diamondjdev | Stardance
Devlogs Title: DJ CLI by @diamondjdev | Stardance
Devlogs:
Super cool CLI tool to automate my most common workflows built using Go, but I’m migrating to Python so I can learn Python better! I currently have commands for cloning my NestJS and NextJS template repos for new projects, a command to delete old and merged git branches, and a precommit command to run npm build, lint, and format before I make git commits! (Photo is a little old)
Shipped a BUNCH, including an integration with one of my other projects, and some more tools for managing dependencies
Ships:
An opinionated CLI that allows the user to manage dependencies, clean workspaces, manage remote projects, etc all from one CLI. The CLI is hyper-opinionated but the Github is open to PR’s. Run dj type and try to beat my typing speed of 100% acc, 90wpm...
|
1793242107.2839437
|
1793328507.2839437
|
|
52732
|
My awesome macropad! by @Mitchglitch | Stardance
|
Mitchglitch
|
0
|
0.0
|
0
|
[]
|
[]
|
Title: My awesome macropad! by @Mitchglitch | Star Title: My awesome macropad! by @Mitchglitch | Stardance...
|
1792723707.7435317
|
1793328507.7435317
|
|
52734
|
SpidyProfile by @skushal1805c | Stardance
|
skushal1805c
|
0
|
0.0
|
0
|
[]
|
[]
|
Title: SpidyProfile by @skushal1805c | Stardance
|
1792723708.5929263
|
1793328508.5929263
|
|
52736
|
An Intelligent agent with an IoT side that control An Intelligent agent with an IoT side that controls the ambient of a tomato greenhouse by @Eau | Stardance...
|
Eau
|
0
|
0.0
|
0
|
[]
|
[]
|
Title: An Intelligent agent with an IoT side that Title: An Intelligent agent with an IoT side that controls the ambient of a tomato greenhouse by @Eau | Stardance...
|
1792723709.4333656
|
1793328509.4333656
|
|
52737
|
UV sensor by @stumbleduponuforu | Stardance
|
stumbleduponuforu
|
0
|
0.0
|
0
|
[]
|
[]
|
Title: UV sensor by @stumbleduponuforu | Stardance
|
1792723710.2714603
|
1793328510.2714603
|
|
52738
|
Arya ko pta g by @darkfridaygaming | Stardance
|
darkfridaygaming
|
0
|
0.0
|
0
|
[]
|
[]
|
Title: Arya ko pta g by @darkfridaygaming | Starda Title: Arya ko pta g by @darkfridaygaming | Stardance...
|
1792723711.102808
|
1793328511.102808
|
|
52739
|
Physics Based Character Controller by @AbdurRehman Physics Based Character Controller by @AbdurRehman | Stardance...
|
AbdurRehman
|
0
|
39.01
|
0
|
[]
|
[{"post_id": 57932, "ts": "202 [{"post_id": 57932, "ts": "2026-08-30T08:30:17Z", "hours": 10.05, "text": "Since the last dev log, I’ve spent most of my time building out the animation system for the character controller. The character could already move, but everything felt super basic visually so I wanted the animations to properly react to what the character is actually doing instead of just switching between a few animations. I started by adding a basic locomotion animation system with idle, walk, and run animations. I added blending between the different locomotion states based on the character’s movement speed, so the character doesn’t immediately snap from one animation to another. I also added other details like adjusting the animation playback speed based on the physical movement speed making everything feel more realistic. While working on locomotion, the animations didn’t look too good because I was simply playing one animation at a given time so I added support for separating the upper and lower body using bone masks, which allows different parts of the character to be animated independently. After that things started to look better but the animations that I had added on the model weren’t good so I spent a lot of time finding and adding more and better animations to the model. One of the changes I made with the new animations was combining multiple idle animations together instead of having the character constantly repeat the same idle pose making the character feel alive when idle. After that I moved on to the character’s vertical movement. I connected the fall, jump, and land animations to the character state system. The animator now plays the animations based on whether the character is jumping, falling, or landing based on the physics state rather than input alone. I also added separate jump animations for jumping while standing still and jumping while moving, so the animations look good. The landing animation required more work since it didn’t look polished so I added landing detection based on things like fall height and fall speed so that small steps don’t trigger a landing animation. And finally I added a rolling animation for falls from high places. This took quite a while to get working and it still isn’t perfect but I am working on it. At this point the character’s animations are pretty much almost complete. Next I want to continue improving the animation system by adding animations for crouching and adding transition animations like idle to walk, etc and also finalizing the roll animation. And after that I want to start making stuff react to the environment."}, {"post_id": 56441, "ts": "2026-08-28T06:34:37Z", "hours": 7.5369, "text": "I continued working on the character controller by moving into the visual side of the project and integrating a proper player model. I added a new character model and tuned its scale and positioning so that it correctly matches the physics body. I also added an asset loading system and a basic loading screen so that the character and assets in the future can be loaded before the game starts. When I was working on the project I felt that everything looked weird and that was because I forgot to add shadows. So I added them and then spent quite a bit of time improving the lighting and shadow quality. I also added tone mapping to make the scene look better. While testing the character model, I ran into shadow acne and something called peter panning, so I spent some time tuning the shadow bias and normal bias to get a balance between the two. I also noticed that the character and small vertical movement/jitter while walking on flat ground probably because of the physics adjusting it’s position. I added direction Y smoothing to the character model so that small physics corrections don’t make the character appear to jitter while moving. Also the camera movement wasn’t good so to make it better I added vertical smoothing to it. Previously, the shadow camera covered a fixed area of the world which made stuff not in the coverage area have no shadows so I improved the directional shadow by making the shadow coverage follow the player. And the final change was working on the model’s materials since the character looked overly metallic and glossy in Three.js even though it looked normal in Blender. Turns out the materials had an incorrect metallic value, so I corrected that and adjusted the roughness to make everything look good. Next, I’ll finally start building the character state system and start moving toward animations."}, {"post_id": 54973, "ts": "2026-08-26T12:27:47Z", "hours": 6.13, "text": "I continued working on the character controller, by adding crouching now allowing the player to move underneath surfaces and other obstacles. Getting this working correctly took a lot more time than I expected because changing the character’s collider size introduced several physics related bugs like the character getting stuck or incorrectly standing up when there wasn’t enough room above, as well as making sure crouching and standing transitions behaved correctly which took a lot of time to fix and get right. I also added an unstuck mechanism to help recover the character if they end up in a weird position. I then cleaned up the code making it easier for me to add other features I have planned. Next, I’ll build on the character state system and start moving toward the animations of the controller."}, {"post_id": 54399, "ts": "2026-08-25T12:18:54Z", "hours": 6.0731, "text": "I continued improving the basic character controller and worked on turning into a reusable system. I separated character movement, physics, and the visual model into their own components and refactored input into a dedicated character input object so movement data can be passed through the system pretty simply and made it way easier to add other inputs in the future. I added acceleration and deceleration, sprinting, and jumping, while also improving the existing movement to make the controller feel better and everything less floaty. I also fixed some movement related bugs like temporarily sticking to ceilings when jumping. I also added the entire character state system. I created a state tracker that derives useful information from the character’s movement and physics, such as velocity, movement direction, speed, grounded/airborne state, landing, jumping, slopes, sliding, wall collisions, ceiling collisions, fall height among many more. This is pretty much the foundation for the state machine and animation system by instead of making animations directly tied to physics or movement code they can be made to react to the character’s current state. This pretty much make it possible to build stuff like strafing blend trees, jump/fall transitions, landing reactions, and eventually more environment aware animations easily. Next, I’ll start building crouch functionality before adding animation stuff."}, {"post_id": 53609, "ts": "2026-08-24T07:43:08Z", "hours": 7.0756, "text": "I built the very basic version of the character controller. I implemented a basic kinematic character controller with gravity, collision handling, slope detection, sliding, stair stepping, and snap to ground behavior. I then added keyboard input and a very basic third person camera so the character can at least be properly controlled for testing. I also fixed some bugs one of which was movement jitter and added stuff to test the controller and also added a physics debug visualizer. I also created config files so that values can easily be tuned and changed and to avoid hard coding stuff in the code. The foundation of the character controller is mostly in place. Next, I’ll work on improving the movement by adding acceleration and jumping. After the movement feels good, I’ll add a real character model, its animations and a state machine."}, {"post_id": 52524, "ts": "2026-08-22T18:00:40Z", "hours": 2.1469, "text": "Set up the project’s basic architecture by creating Vite app using TypeScript, initializing the Git repository, integrating Three.js before modularizing my code and making it clean by separating the scene, camera, renderer, and game loop into dedicated classes. I also added a custom time system with delta/elapsed time tracking for like animation stuff and a fixed timestep for physics stuff, then integrated Rapier and built a basic physics world with gravity, collisions, and a few test bodies. Next, I’ll start building the basic character controller which lays the foundation for all the work to come."}]...
|
Title: Physics Based Character Controller by @Abdu Title: Physics Based Character Controller by @AbdurRehman | Stardance
Devlogs:
Set up the project’s basic architecture by creating Vite app using TypeScript, initializing the Git repository, integrating Three.js before modularizing my code and making it clean by separating the scene, camera, renderer, and game loop into dedicated classes. I also added a custom time system with delta/elapsed time tracking for like animation stuff and a fixed timestep for physics stuff, then integrated Rapier and built a basic physics world with gravity, collisions, and a few test bodies. Next, I’ll start building the basic character controller which lays the foundation for all the work to come.
I built the very basic version of the character controller. I implemented a basic kinematic character controller with gravity, collision handling, slope detection, sliding, stair stepping, and snap to ground behavior. I then added keyboard input and a very basic third person camera so the character can at least be properly controlled for testing. I also fixed some bugs one of which was movement jitter and added stuff to test the controller and also added a physics debug visualizer. I also created config files so that values can easily be tuned and changed and to avoid hard coding stuff in the code. The foundation of the character controller is mostly in place. Next, I’ll work on improving the movement by adding acceleration and jumping. After the movement feels good, I’ll add a real character model, its animations and a state machine.
I continued improving the basic character controller and worked on turning into a reusable system. I separated character movement, physics, and the visual model into their own components and refactored input into a dedicated character input object so movement data can be passed through the system pretty simply and made it way easier to add other inputs in the future. I added acceleration and deceleration, sprinting, and jumping, while also improving the existing movement to make the controller feel better and everything less floaty. I also fixed some movement related bugs like temporarily sticking to ceilings when jumping. I also added the entire character state system. I created a state tracker that derives useful information from the character’s movement and physics, such as velocity, movement direction, speed, grounded/airborne state, landing, jumping, slopes, sliding, wall collisions, ceiling collisions, fall height among many more. This is pretty much the foundation for the state machine and animation system by instead of making animations directly tied to physics or movement code they can be made to react to the character’s current state. This pretty much make it possible to build stuff like strafing blend trees, jump/fall transitions, landing reactions, and eventually more environment aware animations easily. Next, I’ll start building crouch functionality before adding animation stuff.
I continued working on the character controller, by adding crouching now allowing the player to move underneath surfaces and other obstacles. Getting this working correctly took a lot more time than I expected because changing the character’s collider size introduced several physics related bugs like the character getting stuck or incorrectly standing up when there wasn’t enough room above, as well as making sure crouching and standing transitions behaved correctly which took a lot of time to fix and get right. I also added an unstuck mechanism to help recover the character if they end up in a weird position. I then cleaned up the code making it easier for me to add other features I have planned. Next, I’ll build on the character state system and start moving toward the animations of the controller.
I continued working on the character controller by moving into the visual side of the project and integrating a proper player model. I added a new character model and tuned its scale and positioning so that it correctly matches the physics body. I also added an asset loading system and a basic loading screen so that the character and assets in the future can be loaded before the game starts. When I was working on the project I felt that everything looked weird and that was because I forgot to add shadows. So I added them and then spent quite a bit of time improving the lighting and shadow quality. I also added tone mapping to make the scene look better. While testing the character model, I ran into shadow acne and something called peter panning, so I spent some time tuning the shadow bias and normal bias to get a balance between the two. I also noticed that the character and small vertical movement/jitter while walking on flat ground probably because of the physics adjusting it’s position. I added direction Y smoothing to the character model so that small physics corrections don’t make the character appear to jitter while moving. Also the camera movement wasn’t good so to make it better I added vertical smoothing to it. Previously, the shadow camera covered a fixed area of the world which made stuff not in the coverage area have no shadows so I improved the directional shadow by making the shadow coverage follow the player. And the final change was working on the model’s materials since the character looked overly metallic and glossy in Three.js even though it looked normal in Blender. Turns out the materials had an incorrect metallic value, so I corrected that and adjusted the roughness to make everything look good. Next, I’ll finally start building the character state system and start moving toward animations.
Since the last dev log, I’ve spent most of my time building out the animation system for the character controller. The character could already move, but everything felt super basic visually so I wanted the animations to properly react to what the character is actually doing instead of just switching between a few animations. I started by adding a basic locomotion animation system with idle, walk, and run animations. I added blending between the different locomotion states based on the character’s movement speed, so the character doesn’t immediately snap from one animation to another. I also added other details like adjusting the animation playback speed based on the physical movement speed making everything feel more realistic. While working on locomotion, the animations didn’t look too good because I was simply playing one animation at a given time so I added support for separating the upper and lower body using bone masks, which allows different parts of the character to be animated independently. After that things started to look better but the animations that I had added on the model weren’t good so I spent a lot of time finding and adding more and better animations to the model. One of the changes I made with the new animations was combining multiple idle animations together instead of having the character constantly repeat the same idle pose making the character feel alive when idle. After that I moved on to the character’s vertical movement. I connected the fall, jump, and land animations to the character state system. The animator now plays the animations based on whether the character is jumping, falling, or landing based on the physics state rather than input alone. I also added separate jump animations for jumping while standing still and jumping while moving, so the animations look good. The landing animation required more work since it didn’t look polished so I added landing detection based on things like fall height and fall speed so that small steps don’t trigger a landing animation. And finally I added a rolling animation for falls from high places. This took quite a while to get working and it still isn’t perfect but I am working on it. At this point the character’s animations are pretty much almost complete. Next I want to continue improving the animation system by adding animations for crouching and adding transition animations like idle to walk, etc and also finalizing the roll animation. And after that I want to start making stuff react to the environment....
|
1792723711.9387405
|
1793328511.9387405
|
|
52740
|
ZeroWave by @raajk | Stardance
|
raajk
|
0
|
0.0
|
0
|
[]
|
[]
|
Title: ZeroWave by @raajk | Stardance
|
1792723715.6525767
|
1793328515.6525767
|
|
52742
|
Vibely by @PixelDecoder | Stardance
|
PixelDecoder
|
0
|
11.54
|
0
|
[]
|
[{"post_id": 52179, "ts": "202 [{"post_id": 52179, "ts": "2026-08-22T08:33:48Z", "hours": 11.5428, "text": "This is a macondo project which I wanted to get it reviewed here.."}]...
|
Title: Vibely by @PixelDecoder | Stardance
Devlog Title: Vibely by @PixelDecoder | Stardance
Devlogs:
This is a macondo project which I wanted to get it reviewed here.....
|
1792723716.4883955
|
1793328516.4883955
|
|
52743
|
SnakeBot by @leeianiop | Stardance
|
leeianiop
|
0
|
56.29
|
0
|
[]
|
[{"post_id": 79508, "ts": "202 [{"post_id": 79508, "ts": "2026-10-14T11:14:04Z", "hours": 20.3247, "text": "Suspension issues :/ troubleshooting the angle for the spring on the connectors"}, {"post_id": 78909, "ts": "2026-10-12T00:28:59Z", "hours": 12.0008, "text": "Made a screw based suspension, using springs to bounce. I’ve printed and tested it, seems to be wroking fine."}, {"post_id": 62774, "ts": "2026-09-06T09:13:58Z", "hours": 8.4919, "text": "Made version 2, which has spring suspension and sider body base (also looks cooler in general) This is a robot snake, and this is one of the segments, the servo is ontop of another servo which can control the y and z axis of the front segment"}, {"post_id": 59589, "ts": "2026-09-01T14:28:50Z", "hours": 6.7992, "text": "Did the segment to segment connections and updated the gearbox to make it gear down for more torque. I’m making a snake robot mechanical thing any suggestions or name ideas pls leave a comment:)"}, {"post_id": 54356, "ts": "2026-08-25T09:49:09Z", "hours": 1.0231, "text": "Made the f1 aero side cover more connected to the case"}, {"post_id": 53833, "ts": "2026-08-24T15:07:15Z", "hours": 2.9964, "text": "Made more progress on the CAD by adding a longer side gear shaft and cover. The cover is going to be like an f1 car side"}, {"post_id": 52784, "ts": "2026-08-23T03:55:44Z", "hours": 1.3672, "text": "Made the top servo mount to have screws linking to bottom servo mount, made some added progress on the suspsension"}, {"post_id": 52434, "ts": "2026-08-22T15:35:47Z", "hours": 2.4836, "text": "Made the General Body and created mount for servos. Fusion keeps crashing:(("}, {"post_id": 52298, "ts": "2026-08-22T12:38:32Z", "hours": 0.8019, "text": "Made the gearbox to turn the motor shaft sideways, allowing for a narrower body, The lid is screwed by M3 screws"}]...
|
Title: SnakeBot by @leeianiop | Stardance
Devlogs Title: SnakeBot by @leeianiop | Stardance
Devlogs:
Made the gearbox to turn the motor shaft sideways, allowing for a narrower body, The lid is screwed by M3 screws
Made the General Body and created mount for servos. Fusion keeps crashing:((
Made the top servo mount to have screws linking to bottom servo mount, made some added progress on the suspsension
Made more progress on the CAD by adding a longer side gear shaft and cover. The cover is going to be like an f1 car side
Made the f1 aero side cover more connected to the case
Did the segment to segment connections and updated the gearbox to make it gear down for more torque. I’m making a snake robot mechanical thing any suggestions or name ideas pls leave a comment:)
Made version 2, which has spring suspension and sider body base (also looks cooler in general) This is a robot snake, and this is one of the segments, the servo is ontop of another servo which can control the y and z axis of the front segment
Made a screw based suspension, using springs to bounce. I’ve printed and tested it, seems to be wroking fine.
Suspension issues :/ troubleshooting the angle for the spring on the connectors...
|
1792723717.323786
|
1793328517.323786
|
|
52744
|
Context Forge by @vxyzln | Stardance
|
vxyzln
|
0
|
62.7
|
0
|
[]
|
[{"post_id": 81772, "ts": "202 [{"post_id": 81772, "ts": "2026-10-22T13:15:41Z", "hours": 4.16, "text": "Devlog#33 - Greeting Everyone ! Tl;DR - i spent quite a few hours working on makinf cf understand the repo better , finding th right info and letting the user to inspect a codebase before making changes. like searching for func what it depend on etc. Work : One thing i’ve been thinking abt is that when working on ap project that we can we see what things happend in the repo and where things are and what would i need to look for when changin something etc. . A So lot of work went into connecting some pieces and making sure cf gives reliable info and instead of the sqlite database dat Things done : cf can now check the rpeo and its analysis readiness. this helps bcz it can identify configuration problems instead of discovering them after halfway through. Improved the way cf finds specific symbols in a codebase of a project. the idea was to make it easier to locate and see where a func or a class or other element lies. without having to search everything manually. worked on retrieving relevant source excerpts and checking whether the info is still reliable in the current state of the repo/codebase as there is no use of having old data . added the git navigation capabilities so cf can work with arep changes and git’s context withut modifying the repo code. A MAJOR THING - cf can now bring imp repo info , evidence, other relevant things to help user see the codebase state before making a mistake or making changes to the code. Alongside these made some minor improvements lke more consistent error handling and auditing things etc. and also checking these minor things didnt broke any other things. these kinda things look boing but are nessecary/needed. i dont want cf to be one of the project where u give features without making the existng ones better. i want it to be better and useful for users when working on a large codebase etcetc. Honestly , i’ve had shipped this way earlier if i wasnt slacking off and exams didnt came i my way but we are now in the Last 10 days of Sd. i have a quite things in mind which i need to complete this before shippins so focus on that or some days and the i will ship it. ALso the time on this devlog is small bcz i had accidentally deleted the hackatime config(or file whatevery u want to say) and i didn’t noticed it for quite a few time and then today i relaized when i open my hackatime dashboard. So this is the last time that was logged. I will setup before writing a next devlog . So open to ur thoughts on the cf project and comment ur thoughts. ALso plz leave a like if u like m project !!!!!!!!!!!!"}, {"post_id": 81248, "ts": "2026-10-20T13:51:17Z", "hours": 8.2864, "text": "Devlog#32 - Greeting Everyone ! TL;DR - I spent quite some time making Context Forge more reliable under the hood. The focus was on improving repository analysis, CLI usability, and ensuring that the memory system stays consistent with the actual codebase. Work - I wanted to make cf more than js a tool that scans repo once and stores some info. i wanted to make it useful in real dev workflow or like for someone like me who is making many projects and can sometimes lose trace of what will happned to the codebase. HEre’s what i worked on for these 8h spread across some days. Improved repository analysis and persistence so that the stored knowledge remains consistent and can be reused across different runs. Strengthened incremental analysis to handle added, modified, and deleted files more reliably, reducing the chances of outdated information sticking around. Worked on retrieval and relationship handling to make results more predictable and easier to trace back to the actual source code. Improved the CLI experience, making it easier to inspect repository information and understand what Context Forge currently knows. Refined error handling and diagnostics so that failures are easier to investigate instead of leaving me guessing about what went wrong. Expanded the test coverage across the core systems to catch regressions and make sure that improvements in one area don’t quietly break another. One of the trickkier parts was that the stored repo info actually reflected the current codebase. it’s easy to get things on fresh analysis but things get more complicated when files change , disapper or contain info that cannot bre resolved cleanly. I had to spend time thinking abt edge cases to. a lot work was for strengthing the base the foundation , some improvements i made aren’t visibe ut matter when u want cf to behave properly across multiple projects. Yeah so there is more to build and it was a solid step for cf i would say so. Also SD getting ending in 10 days and i have a lot in mind and i need to ship quick so there would be a lots of commits and hrs or the upcoming 2-3 days as i will grind as much as the time i would get . So leave ur thoughts in the comments if u have any and plz like the project (image context : i ran the cf . command on the cf repo itself and this was its answer)"}, {"post_id": 80616, "ts": "2026-10-18T09:57:53Z", "hours": 4.5992, "text": "Devlog#31 - Greeting Everyone ! TL;DR - I spent time strengthening Context Forge’s core memory and retrieval systems, making repository knowledge more reliable and useful. I also improved how the project handles changes, retrieves relevant information, and exposes its capabilities through the CLI. Work - I wanted to move beyond simple analyzing repo and make cf better at remembering, understanding and retrieving repo knowledge. Here what i did : Strengthened how repository information is stored so files, symbols, and relationships remain available even after restarting the application. Improved how Context Forge handles added, modified, and deleted files, keeping stored knowledge aligned with the actual repository and preventing outdated information from lingering. Strengthened the way relevant files, symbols, and relationships are found and ranked, making results more predictable and consistent. Improved the ability to trace retrieved information back to repository evidence and understand why particular results were selected. Added the cf command as a shorter alternative to context-forge , while preserving the existing command and its behavior. Expanded the CLI with commands for inspecting repository status, memory, files, symbols, references, and relationships, making it easier to explore what Context Forge knows. Improved operational error handling, logging, and diagnostics, making failures easier to understand and helping keep the overall experience more predictable. So yeah did so many things It’s been a while since the Great Pivot / I took some time work through these as i also had to check whether there is some code of the things iripped off in the great pivot. the time went here on working through these features properly, strength the exisiting foundationand make cf more relaible and now moving onto the next things. So leave ur thoughts in the comments and plz leave a like"}, {"post_id": 79279, "ts": "2026-10-13T09:41:19Z", "hours": 2.2675, "text": "Devlog#30 - Greeting Everyone ! - THE GREAT PIVOT Work - Context forge is now moving away from being a generation based tool and becoming a deterministic agent memory foundation. now the rtransition is done cleanly and now i am working ahead on the current foundation but new features. work done - completed the changed direction of context forge from the old provider and generation system to a repo intellegence system removed the ollama integration, provider stack. runtime configuration and the dependencies that came with them. the core should now work without depending on LLM or external APIs refactoredthe application services, task understanding, context slelction, ranking and CLI to fit the new direction. kept the important foundation like SQLite storage , AST based analysis, repo fingerprints, inremental file change detection and evidence based context rtrieval added architecture tests for offline operation , deterministic ranking, file change detection and making sure the context output has proper evidence cleaned up all the old tests which were not needed and deleted the whole files which weren’t needed in the future . Today was mostly about get ting the big transition properly finished. So for the past days, I had some exams and was not happy with the behavior of Olama, of its undeterministic behavior. So I took this step. I did not change the base foundation. I just changed the overlying architecture, the Olama ones, and removed everything that was made that was not needed. So the commit of today is very large, like 7,000 lines removed, and 1000 lines written. I made one big commit for the entire transition instead of splitting this architectural layer into multiple commits. Transform context force into a deterministic agent memory foundation. I also cleaned up the extra local branches and checked that main was synced with GitHub. Now I’m moving towards a memory vault kind of thing. I have to build on what already exists instead of rewriting everything again, improve the memory idea of foundations, add the shorter commands. Yes, so yeah, this was a pretty big change for our project. There was still a lot to do, but at least reaction is much cleaner now. Hope you like the project and please leave your thoughts or feedback in the comments. To be completely transparent, I used AI assistance to help me safely untangle and delete parts of the old architecture that were tightly coupled. As a student developer handling a complex refactor alone, trying to manually map out every single breaking change across thousands of lines got overwhelming, and I needed the help to get it done cleanly. No regrets it got the job back on track, and the codebase is in a much healthier place. With the cleanup done and main fully synced, I’m now shifting focus toward building out the new deterministic memory vault and refining the short-form CLI commands for AI agents. Show writer shipwrights. Please don’t wreck my project. Hope you like the new direction! Let me know your thoughts or feedback in the comments below."}, {"post_id": 72726, "ts": "2026-09-23T16:27:26Z", "hours": 0.3028, "text": "Devlog#29 - Greeting Everyone ! STARDANCE IS GETTING EXTENDED YAYYY!!!!! No TL;DR today for short work Things did today in short time added clean generation outuput handling added cli error handling and seperated output from errors connected generation to the persisted project added test for the same also spent some time on editing some test generated bcz they werent like tha lvl Sp today short work due to other school work coming in. Leave ur thoguhts in the comments and pl like it if u think it is good and should get real appreciation."}, {"post_id": 72306, "ts": "2026-09-22T17:00:47Z", "hours": 1.1167, "text": "Devlog#28 - Greetings Everyone ! TL;DR - Added proper ollama checking and validation plus a runtime cli. Generation now safely uses fresh persisted repo intelligence instead of re-analyzing the project everytime Long - Problems : so when doing today’s work the problems that i wanted to fix was that the generation workflow was still too dependent on live repo analysis instead of using the persisted intelligence. 2nd there was no way to verify ollama itself is available or not. like ollama runtime and is a model available or not. runtime failures needed to stop generation cleanly and not throw a bunch of error a user neds to debug. we needed to preserve provider behaviour and avoid breaking the previous architecture i built the generation one. also the generation path needed clear boundaries between runtime validation, provider execution and final output and etc etc. It sound much but the implementation was simple as ig for me. things done today to solve the problems - added ollama runtime inspection to check local runtime and requested model are available added dedicated runtime cli commd for checking the state of the runtime and model independently changed the generation to load persistd repo intellegence insteasd of it everytime doing a fresh analysis as it would be bad for it to make new things for everytime a cli is ran added cache freshness validation so generation refues stale repo intellegence added regression covergae proving that a generation uses the persistent project and doesnt starts the analyzer again made a foundation kinda thing for a clean generationresponse to cli output boundary with remainng output workflow continuing afterwards added test for the features added Also some of the current changes may not be sen on the github repo bcz i havent comitted some changes as they are a part of a feature and i commit like a feature and the tests related to it for better commits ig . Now what we did to solve the problems and how i felt when solving them - . the generation pipeline is now ready to build the dev facing output worflow or like a user workflow on top of these things the previous architecture i made. i found addng the flags to main.py file easy but then adding the cache checking and the regression covergae and the generationresponse to cli output boundary a bit challenging . So today only this much. Hope u like my project and plz comment for feedback. also a mention to @CT5 on slack for telling me to added problem and solution section in my devlog for better project experii\\ence."}, {"post_id": 71819, "ts": "2026-09-21T16:41:30Z", "hours": 2.8994, "text": "Devlog#27 - Greetings Everyone ! TL;DR - Context Forge can now remember the repo state update it s understanding when things change and provides a proper cli for those who use it. It has ig aroung 6 funcs which u can read below. The work also made the internal state much easier to inspect and debug while keeping the existing thing intact. Long - SO this Devlog is after a long time ig. I was giving 5-10 mins t the project to not lose my habit and the streak also. But today my exams got over so now i can focus on the project. STARDANCE is ending soon so i need to hurry up and complete this asap. So basically did a lot of main writing for cli functionality. cf* - context forge (too lazy to write it out everytime) things did in those past days - made repo analysis persistent instead of starting from scratch everytime the cf* is ran. added file fingerprintng and change detection for smart analysis for a smart project. imporoved how changed files affect relationships and project info. added a proper dev workflow through the CLI as it is a main part and added commands like analysis and generation commands added task input , config handling, clenaer error behaviour for the better contxt of it added command to inspect repo state cache state project info and diagnostics or i should say Pre-Rendered Excuses Generation fixed issues around cache freshness and changed fiel reporting added tests for the new functionality and made sure the existing workflow stayed intact for cf* refactored the fingerprinting logic so it culd be shared cleany by the analyzer and the Cli i made for cf* So this much for the past these days. Now the thing is slowly coming like a real version. Its complexity is very high ,atleast for me . Bcz i made many py projects and this is the most challenging one so far but it shift me into the flow state after sometime so yeah it is a good challenge. It was like based on my problem i faced when i was vibecoding in the early days js to do timepass . But now when u can make it , it feels incredibale. SO yeah it is good. Yes but Currently i see models like astra and fable come out with much more context lenght and etc. so my product is not needed for them for but is a good fun project on thr side. These new models are good but havent tried them but will try them fter i get some freetime after Stardance. as stardance is my first and last ysws soi it was a great experience. Also i did many of the things in neovim like editing some files and etc but i couldnt settedup hackatime with it so like around 1-1.5 h of extra work was untracked on hackatime but it was ok. I was seeing the primeagen video of neovim and wanted to try it out so i did and learned some basics and therre is a very stepp learning curve in it . ALso tried out lazyvim but not my style . So wil pause the vim learing for a few days and finish the prject cf asap. Sorry for this Yapp Session but dumped everything i had for these past few days. SO plz leave ur review in the comment and plz like it and rate it good."}, {"post_id": 67921, "ts": "2026-09-14T07:08:45Z", "hours": 0.4872, "text": "Devlog#26 - Greeting Everyone ! No TL;DR as short work work today - Added deterministic evaluation baseline storage and serialization. Added validation, aggregation, coverage, and persistence support. Added comprehensive tests and maintained a clean, validated implementation. So, this much today only leave your thoughts in the comments/"}, {"post_id": 67491, "ts": "2026-09-13T16:35:20Z", "hours": 0.2508, "text": "Devlog#25 - Greeting Everyone ! No TL;DR as small work today. things accomplished today - Added evaluation aggregation and baseline regression tracking Added validation for duplicate cases and regression tolerance, with tests for the same. Committed implementation and tests as focused changes. Leave ur thoughts in the comments."}, {"post_id": 66802, "ts": "2026-09-12T18:07:31Z", "hours": 0.7114, "text": "Devlog#24 - Greeting Everyone ! TL;DR - Added evaluation for both context selection and final context quality, covering correctness, budget limits, and deterministic behavior. Added focused tests to validate the complete evaluation flow. Long - So exams are going on so can’t do long hour session. Was planning to add manythings over few days but it would stretch for about more days. Things did - Added context-selection evaluation against expected entities using precision recall f1 added end to end evaluation for final context accuracy budget compliance etc. adde d validation for unkown , mising extra and empty entities or context cases. addded tests for the same Js this much today. Leave ur thoughts in the comments ."}, {"post_id": 65802, "ts": "2026-09-11T05:54:26Z", "hours": 0.415, "text": "Devlog#23 - Greetings EVeryone ! TL;DR - Retrieval and task-grounding quality can now be measured deterministically against repository ground truth, with full regression coverage Long - Short sesssion today. added the tp*.txt in gitignore for me to make temporary text files Added deterministic retrieval and task-grounding evaluation with precision recall F1 metrics Added stable repo entity ground truth and evaluation ccovergae Added test for the same added init .py in every subfolder of test bcz there were name clashes in pytest. So today this much only . Leave ur thoughts in the comment and wish me luck!!"}, {"post_id": 65491, "ts": "2026-09-10T17:44:53Z", "hours": 0.4758, "text": "Devlog#22 - Greeting Everyone ! TL;DR - Built the local repository evaluation foundation.Added structural and graph accuracy measurement for files, symbols, and relationships. Long Story - So added chec for my tool. Also committed a wrong spelling recal instead of recall in a func and and then hchnaged it in the new commit. thiings did - Added local evaluation repositories and tasks. Added structural and graph evaluation Added tests for the same Leave ur thoguths iin the comment and like it"}, {"post_id": 64918, "ts": "2026-09-09T17:09:37Z", "hours": 1.3094, "text": "Devlog#21 - Greeting Everyone! TL;DR - Repository analysis is now persisted, freshness-aware, and capable of selectively invalidating stale data instead of rebuilding everything.Cache invalidation and refresh behavior are deterministic, validated, and comprehensively tested. Long - Today I implemented the cache thing for my project. my ool works by mapping a repo and giving context to the user for user to give to AI agent for a work. SO for storing data i use SQLite but making rep data everytime will take a lot of time. So i introduced caching fo data and will refresh in sometime and can be refreshed manually also. Things did : added cache freshness checks for missing metadata , schema/analyzer version , missing fingerprints and file changes added deterministic file fingerprinting using size, modification timestamp and SHA-256 content hashes added selective invalidation for afected files, symbols, and relationships while preserving unaffected analysis added full cache invalidation for cases where existing analysis can no longer be trusted. Added cache refresh orchestration finally added tests for the same So this much today . Leave ur thoughts in the comments and like it"}, {"post_id": 64108, "ts": "2026-09-08T09:36:54Z", "hours": 1.1172, "text": "Devlog#20 - Greetings Everyone ! TL;DR - COntext Forge can now remember the state of repo aand files and identify what changes while context construction remains deterministic, robust and free of generated reasoning. Long - So Hello everyone and welcom to the 20th devlog. today added some more things which are : added deterministic file fingerprinting using its path size modification time etc. and used SHA-256content hashing Persisted file fingerprints in SQLit alongside repocacheing of metadata added detection for unchanged edited modeified added or deleted files Added storage and cache tests covering fingerprint persistence, replacement, and missing data. added analyzer covergae verifying the fingerprints are generated and rpersisted corrrectly. Kept diagnostics based on structured metadata and repository evidence rather than generated reasoning. This much today. Leave ur thoughts in the comments . BYEE and thnx for reading"}, {"post_id": 63650, "ts": "2026-09-07T15:58:34Z", "hours": 2.2053, "text": "Devlog#19 - Greeting Everyone! TL;DR - Originally built the planned reasoning-heavy approach, then identified it as unnecessary complexity and hard-reset all of that work to the clean retrieval baseline. Replaced it with a minimal, structured LLM selection layer where the model only decides include + confidence, while repository intelligence and deterministic metadata remain authoritative. Long Story - So initially i was continuing my plan to have reasoning for every candidate why it was choosed . like was a reasoning heavy context approach includes LLM reasoning. Was working on implementing it throught a flow. during testing, debugging and checking that it works perfectly but things went the other ways. during the checking, i got to a problem that LLM gives out many token in reasoning and which exceeds the limit or the max_tokens limit that i have. it was bad as i couldnt get reasoning perfectly for the per candidate. the i thought of another approach. i will generate the candidates and then i will give all the reasoning fo all of the candidates at the end of it. but this want also working as i wanted it to. i had committed the wrong changes and then i had to hard reset to a stable previous commit whcih didnt had this. then i realized that i was making the system too complicated and it wasnt needed so i remove dthe reasoning nd hard reset to a previous atable commit. I used AI to fix the broken code for the reasoning part that i built but after multiple attempts . So as i said before, 1 option only i reverted to a old git commit . this took most of my time but then did some chages also now context_forgehandes repo intellengence and LLM which decide only what is actually worth keeping. added a strict context-selection contract. Added the selection service to handle the model interaction and validate its response Selection confidence is carried into the final context as metadata, keeping the output inspectable without depending on generated explanations. Added and updated tests around the contract, selection service, package construction, and engine integration Well so this much only today. This day was hassle ful. I’ve used AI 2 times to fix the tings but 1 time i was successful and 1 time i am not. But keeping it aside. i am close to complete the ‘source code’ but not too close. I am thinking of having a brew tap for mac users and another way for windows and linux. The system isnt perfect but it is running. I will make it better nd make it functionable in real world. SO these chages today were light. Most time spent was on Debuging and checkigerrors an fixing them. If hackatime would calculate time spent debugging or xiing, tiday would be 6h+ devlog. Leave ur thouhts in the coments and plz like it."}, {"post_id": 63012, "ts": "2026-09-06T16:03:37Z", "hours": 0.4644, "text": "Devlog#18 - Greeting Everyone!: TL;DR - Integrated relationship-aware retrieval into context construction with bounded depth, confidence propagation, and retrieval provenance. Long Story - So had a small coding session today bcz i didnt got much time as exam is tommorow. Thing Done today - integrated relationship-aware retrieval into context construction addded bounded relationship expansion with confidence and provenance cnnected context-depth evidence to retrieval- added relationhship/depth to context signals added the tests related to the code changes So this mucn only today. Thnx for reading . Leave ur thoughts in the comments."}, {"post_id": 62338, "ts": "2026-09-05T17:38:45Z", "hours": 1.2731, "text": "Devlog#17 - Greeting everyone! TL;DR - Added deterministic deduplication, strongest-path selection, candidate limits, and cycle protection for relationship-aware retrieval.Expanded retrieval is now bounded, predictable, and keeps its evidence consistent, with 13 tests covering the new behavior. long - So a small codin session and added some new things. added deterministic dedpulication for relationship expanded candidates added strongest path selection using confidence depth and UUID odering preserved original candidate odering. enforced candidate expansion limits and cycle protection kept retrieval evidence aligned with selected candidates. added coverage for all the thing s we did through tests. Well so this much the implmentation was small but the testing of it anc checking it was perfect was hassle full Leave ur thoguths in the comments"}, {"post_id": 61627, "ts": "2026-09-04T16:53:19Z", "hours": 1.0678, "text": "Devlog#16 : Greeting Everyone - TL;DR - Context Forge can now understand what a task is asking for and deterministically connect that task to actual repository entities.It can also expand those entities through the repository relationship graph, providing a grounded repository neighborhood for subsequent retrieval and reasoning. Long Yap - Today was a small session of writing code and added new thing which is rep-aware task understanding and grounding. Grounding connects what the user mentions in a task to the actual files and symbols in the repository.It turns vague task references into concrete, verified repository entities that Context Forge can reason about added structured task interpretation covering intent, concepts, requested actions , constraints and ambiguity added exact repo relative path matching exact/unique symbol resolution while keeping unresolved references explicit added repo grounding to expand grounded entites through the existing relationship graph extended candidate generation so directly grounded and relationship connected entities can participate in context retrieval js this much today. Also had a single commit today but was a long one bcz i was in flow and forgot to commit and it was mostly tests . So sorry dev community 😭. (image attached is js a look at the code) Leave r thoughts in comments. open to feedback."}, {"post_id": 61300, "ts": "2026-09-04T04:26:37Z", "hours": 1.9978, "text": "Devlog#15: Greeting Everyone : TL;DR - Built reliable repository structure and a deterministic relationship graph, including symbols, imports, references, inheritance, ownership, relationship resolution, confidence, traversal, and persistence. Added comprehensive tests and validated against a real repository. Long Yap - So the baisc archtecture is completed and now i am working on its hardening and testing it on some real basic repos. Things done today - strengthened repository structural intelligence with more user-reliable Python parsing, symbol extraction, import references, inheritance references, and structural validation, etc. establihed the repo relation graph with numerous relationships. added deterministic relationship resolution with confience scoring and handling of unresolved references. Integrated relationship construction into the analysis pipeline expanded parser,graph,query & pipeline tests verified it basic working on real repo. close to completring a working version but not too close. leave ur thought in th comments . Have a good day or Night"}, {"post_id": 60372, "ts": "2026-09-02T17:45:49Z", "hours": 1.3311, "text": "Devlog#14 : Greeting Everyone TL;DR - Built a complete repository-to-context-to-AI workflow with real Python source context and robust CLI/error handling.The architecture is now stable at this boundary, ready for smarter retrieval, ranking, graph expansion, and project memory. Long Story - So worked some more on the CLI workflow of the tool. SO things did today : Completed the repo to context to provider to response workflow for py projects. Added real source content to select context units added CLI coverage hardend CLI handling for path , config, task, analysis, and generation failures added the keyboardinterreupt i.e. ctrl+c/EOF handling, clean exit codes and safe operational logging. expanded failure-path test coverage So this is the final thing is that the peices were coming together. A locally executable Python workflow from repository analysis through context generation and AI response, with a reliable CLI boundary. So leave ur thoughts in the comments and plz like it."}, {"post_id": 59711, "ts": "2026-09-01T17:11:48Z", "hours": 0.9758, "text": "Devlog#13 - Working on the CLI TL;DR - Integrated generation lifecycle handling with robust success/failure paths and duration tracking.Added rotating operational logging with privacy-safe metadata only—no prompts, responses, or reasoning.Hardened CLI/application tests and logging isolation. Yap - So Majorly worked on the tool so that it could work in the terminal with the command : context-forge [-h][–provider] etc. eg: ~/project/EV > context-forge . the above is the command that wil scan repo the command was ran in and asks for the task. another eg: ~/project/EV > context-forge -h this will give help menu of the cli tool. Also the responses are the Answers are given by the local LLM from ollama which is Qwen2.5-coder:7b which is quantized to Q4_K_M i.e. quantized to 4bit. it takes about 5GB Memory when running. I have to make it s that it runs perfectly as it doesnt answers some times etc. there are many problems to figure out will figure everything out Other things: Hardened provider/application error handling and ensured failures terminate cleanly without leaking task content. integrated generation lifecycle handling into the app flow which inclludes start/stop/completion/failure paths and duration tracking Added operational logging infra with a rotating app log at the global config drectoy Added privacy-focused logging tests ensuring prompts/tasks, generated responses, and model reasoning/thinking are never logged. Consolidated and finalized the logging method and generation lifecycle work; resolved logger path isloation. formatting,linting and test issues. js this much today nothing much more. Leave ur Views and thoguhts on this in the comments."}, {"post_id": 59047, "ts": "2026-08-31T17:11:19Z", "hours": 1.8733, "text": "Devlog#12 - StageX going Good. Greeting everyone. So i am working on the transition from qwen3:8b thinking model to non thining model. TL;DR - We redesigned the generation layer around Qwen2.5-Coder 7B and removed the old Qwen3 thinking/reasoning assumptions. The provider contract was simplified and the Ollama integration boundary was kept clean and model-agnostic. A layered configuration system was added with project, global, and built-in defaults, plus validation and precedence resolution. The CLI was then integrated with this configuration architecture while keeping the existing repository-intelligence pipeline unchanged. Full story - i inspected the existing architecture and confirmed that the repo intellegence pipeline should remain intact. i moved the active generation direction away from the old qwen3 thinking oriented architecture and established Qwen2.5-coder:7Bas the new default without hardcoding model throughout the database. I cleaned theprovider contractso reasoning thinking is no longer a part of the current core generation model while deliberately leaving future reasoning support for later architectural decisions. I also investigated the Olama integration boundary other than replacing its transportation implementation, keeping the previous Olama provider as the boundary. The largest tradition was that I wanted to add a config support so like someone can have a project project-wise configs for my tool, but it can also have a global config. So, if the project config is not available, the tool would fall back to the global config. So, I was thinking of using it as as like a .contextforge.toml file format. Yes, configuration is a dedicated defaults loading validation, etc. facilities solution, etc. And finally, the CLI was connected to the new configuration architecture. Provider settings are no longer hard-coded as the remaining configuration. This much only for today. Leave ur thoughts in the comments"}, {"post_id": 58277, "ts": "2026-08-30T17:25:39Z", "hours": 4.1383, "text": "Devlog#11 - Things went the Otherways. Greting everyone! TL;DR - for those who dont want to read long story - Spent most of the day debugging and rethinking the Ollama integration, which exposed problems with building around a thinking model. After testing the full workflow, I decided to move to Qwen2.5-Coder 7B and introduce Stage X to realign the architecture before continuing development. Long Story - for those who are interested 🙋: SO i was working towards local LLM integration for my project as mentioned in the previous devlog. Today was a sunday so had a lot of time on me so worked on this. i decided of making ollama the sole provider for AI for v1 of my project as it is easy to work with. I chose initially qwen3:8b model. i was working with it for the ollama integration and model works perfectly and give answers and checkning for bugs errors and debugging and adding more tests etc. today most of the time went into debgging,investigating, rediscovering how the existing architecture actually worked, challenging earlier assumptions, and then rethinking the architecture around what the system really needs. The first major objective was making sure the complete Python-project path worked together rather than only working as isolated components. The question was whether these pieces actually behaved correctly as one pipeline. So assessed the code and assemebled it and strenghted it and then added tests for it. Now working with ollama’s qwen3:8b model but soon ralzied it was a major mistake. i wanted to make the model to communicate with the project. So it worked kind off. Like the model i was using was a model that thinks and has chain of thoughts. But soon it became a problem for me. our first integration attempt exposed a problem. The model was clearly behaving as a thinking model. that mattered bcz Context Forge was now trying to use it as a part of a deterministic workflow. The model’s internal thinking could consume substantial generation time before producing the actual answer.That made the original integration architecture less suitable for the project. So i asked myself some questions and came to a conclusion that i should build v1 around the non thinking models like the one i will be using now on is qwen2.5-coder:7b . and integrate thinking and AI providers in future versions. THE CURRENT MODEL ARCHITECTURE should work with a non thinking model. So i introduced a phase for now called StageX where i would check the code and try to refactor it acc to the new direction we are heading. what will StageX chenage: Model Asumptions Thinking or reasoning done by the model Adding a Config file feature- CLI Behaviour(improved) Better Ollama integration Operational Logging this all we implemented in span of some days as i’ve got exams coming but will work on it. a large part of time not logged onto hackatime was spent towards rethinking the decisions made in the past and plan out the Future. TH biggest progress from this was architectural clarity. LET”S START STAGEX Thank u for reading this brain DUmp of Mine. Stay Tuned for future updates"}, {"post_id": 57500, "ts": "2026-08-29T17:47:41Z", "hours": 2.0633, "text": "Devlog #10 — Working. This phase mainly has been about the architecture more complete and connected end-to-end. TL;DR of the whole DEVLOG : Complted provider foundations, task validation/understanding & progressed by introducing ContextRequest and task Aware election. the new pipeline connects task -> validation -> context -> task aware selection->provider. . leave r reviews Long summary for those who are interested: Completed the provider foundation and established generation boundary. this gave cf* a proper path from context generation to serialized context to provider request togenerated response. Added TaskUnderstanding which is the first layer for understanding what the user is actually asking for. added TaskInterpretation, task understanding and validation and validation states such as clear, ambiguous, and sufficient. added tests to ensure invalid tasks stop the pipeline early Introduced ContextRequest as a cleaner boundary b/w the tsk and context systems. instead of pasing ptoject and task seperately, the context engine now recieves a single request containing the relevanr context. Also added some more tests for hardening Now i am focused on connecting pieces more tightly and doing thr final integration work needed . the architecture is now becoming less of collection of individual sytem and more of a single pipeline."}, {"post_id": 56743, "ts": "2026-08-28T16:56:32Z", "hours": 2.2978, "text": "Devlog#9 - working on LLM integration Greeting everyone Working towards the completion of the integration of local LLM. i will implement ollama as the LLM provider in the v1 a very hefty day as had to resolve many problems that had occur. js did 2 commits which had like most tests updtedetc. js this much today."}, {"post_id": 55613, "ts": "2026-08-27T16:03:03Z", "hours": 2.5283, "text": "Devlog#8 - My Greetings !! working towards the git understanding of the project. Hey hello everyone reading this. today the context_forge was extended with git intellengence. I implemented git repo detection repo root, branch/HEAD dicoovery parent or merge tracking shallow repo handling- Aggregate git activity summaries etc.etc. then integrated this directly into analyzer and project model. Persistence Layer was etended so git intellegence survies SQLite save or load cycles Also made a bunch of tests for each thing so that project stays perfectly working. finally the query layer gained explainability metadata so search results can comunicate why a result matched while keeping the explanation seperate from number ranking core. Also coming clean about a thing that i used antigravity bcz when i was working and very deep, i broke most of the files and couldnt seem to fix it so first time i used it to fix that. i havent committed it changes but i cme clean about it. ok bye so leave your opinions here in the comment section."}, {"post_id": 55095, "ts": "2026-08-26T15:30:14Z", "hours": 2.3058, "text": "Devlog#7 - Greeting everyone. progressively buildiing the core. so today also worked towards completing this phase which is a major step towards the project. it was a progress from finding relevant context to building deterministic contextpackage. added serialization support for enriched context. established the provider boundary and deterministic provider without coupling the core engine to an external source like a LLM or a AI provider. introduced compression abstraction added budget -aware compression as we 3 lvls talked about in previous devlogs(you can refer to thm). introdued explicit context-priority modeling Added ContextPriorityOrdering and may smal changes also. from previous devlog, the changes are that previously it could build repo understanding, retrieval,rankingetc. but now it can do compression, prioritization, ordering and assembly. So leave your thoufghts i the comment. THANK YOU!! (also the image uploaded isnt the full code written its just a snippet and also not the full code of the file so plz dont make it the truth. Visit the GITHUB REPO to see the changes and the files)"}, {"post_id": 54515, "ts": "2026-08-25T15:23:24Z", "hours": 0.4597, "text": "Devlog#6 - working . Working towards the project arcitecture. Quick update: I just did a pass on the project with some minimal changes and additions. I added a graph expander and context expansion, and wired the full pipeline into the default context engine. Please leave your reviews in the comments!"}, {"post_id": 54412, "ts": "2026-08-25T12:43:28Z", "hours": 1.6861, "text": "Devlog#5 - workking .HELLO EVERYONE!!!! so i am working on my project and i have done some new things which are : added contextcandidate added conversion from existing searchresult added relevancesignals added deterministic ranking which combines candiadte score+signals and mac score is 1.0 Main : added context depth options which are minimal recommended and Deep. in this part , i am thinking of integrating local LLM like models ollama provides or a API key of a AI provider like claude or openAI or any other provider user wshes for which will help make good perfect context. the things are coming together and i am seeing my project become a great project. So plz leave a like and ur suggetions. (Note: While I am engineering the core context pipeline by hand, I am utilizing AI to generate my unit tests and boilerplate to accelerate development. i have declared it into the AI section of the Project.)"}, {"post_id": 53754, "ts": "2026-08-24T13:02:58Z", "hours": 1.1856, "text": "Devlog#4 - making context forge actually undertstand a project Hello Everyone !! So today just worked upon making some changes like make the project context forge, scan the repository, classify it, detect languages, et cetera. Yes, handbroken files without killing the analysis, etc. And also we built projectquery So, the analyzed project can be actually explored. now the project is coming together. next plan is add a custom LLM model to make it more better. if you have ideas for a good LLM available for free and locally so plz comment. Thank you for looking at it. Bye."}, {"post_id": 53150, "ts": "2026-08-23T16:07:50Z", "hours": 1.3417, "text": "Devlog#3 HELLO EVERYONE!!! I worked on the project search and retrieval foundation. The model is now useful for task-oriented retrieval and ranks search results. Search operates over the persistent project model created .It establishes the basic architecture: Task -> Retrieval -> Ranking -> Context. So far the project is going well and exactly as planned. I aim to ship it . Wish me luck and please check it out!"}, {"post_id": 52985, "ts": "2026-08-23T11:15:05Z", "hours": 3.5578, "text": "DEVLOG#2 - This time, Context Forge went from a basic skeleton to actually understanding a repository. It can now scan projects, classify files, detect languages/frameworks, extract Python symbols, build relationships, and store everything locally in SQLite. .The biggest takeaway: before making Context Forge “smart,” I need to make sure it has a solid understanding of the project itself."}, {"post_id": 52328, "ts": "2026-08-22T13:12:22Z", "hours": 1.5494, "text": "Devlog#1 : I actually started thinking the architecture for Context Forge and I am officially setting up the project and logging my hours here today. The idea came from a problem I repeatedly faced while coding in a big project that when there are massive amount of files, we tend to break things like which things would be affected potentialy but these changes etc.. Context Forge solves this by building a persistent understanding of software project"}]...
|
Title: Context Forge by @vxyzln | Stardance
Devlo Title: Context Forge by @vxyzln | Stardance
Devlogs:
Devlog#1 : I actually started thinking the architecture for Context Forge and I am officially setting up the project and logging my hours here today. The idea came from a problem I repeatedly faced while coding in a big project that when there are massive amount of files, we tend to break things like which things would be affected potentialy but these changes etc.. Context Forge solves this by building a persistent understanding of software project
DEVLOG#2 - This time, Context Forge went from a basic skeleton to actually understanding a repository. It can now scan projects, classify files, detect languages/frameworks, extract Python symbols, build relationships, and store everything locally in SQLite. .The biggest takeaway: before making Context Forge “smart,” I need to make sure it has a solid understanding of the project itself.
Devlog#3 HELLO EVERYONE!!! I worked on the project search and retrieval foundation. The model is now useful for task-oriented retrieval and ranks search results. Search operates over the persistent project model created .It establishes the basic architecture: Task -> Retrieval -> Ranking -> Context. So far the project is going well and exactly as planned. I aim to ship it . Wish me luck and please check it out!
Devlog#4 - making context forge actually undertstand a project Hello Everyone !! So today just worked upon making some changes like make the project context forge, scan the repository, classify it, detect languages, et cetera. Yes, handbroken files without killing the analysis, etc. And also we built projectquery So, the analyzed project can be actually explored. now the project is coming together. next plan is add a custom LLM model to make it more better. if you have ideas for a good LLM available for free and locally so plz comment. Thank you for looking at it. Bye.
Devlog#5 - workking .HELLO EVERYONE!!!! so i am working on my project and i have done some new things which are : added contextcandidate added conversion from existing searchresult added relevancesignals added deterministic ranking which combines candiadte score+signals and mac score is 1.0 Main : added context depth options which are minimal recommended and Deep. in this part , i am thinking of integrating local LLM like models ollama provides or a API key of a AI provider like claude or openAI or any other provider user wshes for which will help make good perfect context. the things are coming together and i am seeing my project become a great project. So plz leave a like and ur suggetions. (Note: While I am engineering the core context pipeline by hand, I am utilizing AI to generate my unit tests and boilerplate to accelerate development. i have declared it into the AI section of the Project.)
Devlog#6 - working . Working towards the project arcitecture. Quick update: I just did a pass on the project with some minimal changes and additions. I added a graph expander and context expansion, and wired the full pipeline into the default context engine. Please leave your reviews in the comments!
Devlog#7 - Greeting everyone. progressively buildiing the core. so today also worked towards completing this phase which is a major step towards the project. it was a progress from finding relevant context to building deterministic contextpackage. added serialization support for enriched context. established the provider boundary and deterministic provider without coupling the core engine to an external source like a LLM or a AI provider. introduced compression abstraction added budget -aware compression as we 3 lvls talked about in previous devlogs(you can refer to thm). introdued explicit context-priority modeling Added ContextPriorityOrdering and may smal changes also. from previous devlog, the changes are that previously it could build repo understanding, retrieval,rankingetc. but now it can do compression, prioritization, ordering and assembly. So leave your thoufghts i the comment. THANK YOU!! (also the image uploaded isnt the full code written its just a snippet and also not the full code of the file so plz dont make it the truth. Visit the GITHUB REPO to see the changes and the files)
Devlog#8 - My Greetings !! working towards the git understanding of the project. Hey hello everyone reading this. today the context_forge was extended with git intellengence. I implemented git repo detection repo root, branch/HEAD dicoovery parent or merge tracking shallow repo handling- Aggregate git activity summaries etc.etc. then integrated this directly into analyzer and project model. Persistence Layer was etended so git intellegence survies SQLite save or load cycles Also made a bunch of tests for each thing so that project stays perfectly working. finally the query layer gained explainability metadata so search results can comunicate why a result matched while keeping the explanation seperate from number ranking core. Also coming clean about a thing that i used antigravity bcz when i was working and very deep, i broke most of the files and couldnt seem to fix it so first time i used it to fix that. i havent committed it changes but i cme clean about it. ok bye so leave your opinions here in the comment section.
Devlog#9 - working on LLM integration Greeting everyone Working towards the completion of the integration of local LLM. i will implement ollama as the LLM provider in the v1 a very hefty day as had to resolve many problems that had occur. js did 2 commits which had like most tests updtedetc. js this much today.
Devlog #10 — Working. This phase mainly has been about the architecture more complete and connected end-to-end. TL;DR of the whole DEVLOG : Complted provider foundations, task validation/understanding & progressed by introducing ContextRequest and task Aware election. the new pipeline connects task -> validation -> context -> task aware selection->provider. . leave r reviews Long summary for those who are interested: Completed the provider foundation and established generation boundary. this gave cf* a proper path from context generation to serialized context to provider request togenerated response. Added TaskUnderstanding which is the first layer for understanding what the user is actually asking for. added TaskInterpretation, task understanding and validation and validation states such as clear, ambiguous, and sufficient. added tests to ensure invalid tasks stop the pipeline early Introduced ContextRequest as a cleaner boundary b/w the tsk and context systems. instead of pasing ptoject and task seperately, the context engine now recieves a single request containing the relevanr context. Also added some more tests for hardening Now i am focused on connecting pieces more tightly and doing thr final integration work needed . the architecture is now becoming less of collection of individual sytem and more of a single pipeline.
Devlog#11 - Things went the Otherways. Greting everyone! TL;DR - for those who dont want to read long story - Spent most of the day debugging and rethinking the Ollama integration, which exposed problems with building around a thinking model. After testing the full workflow, I decided to move to Qwen2.5-Coder 7B and introduce Stage X to realign the architecture before continuing development. Long Story - for those who are interested 🙋: SO i was working towards local LLM integration for my project as mentioned in the previous devlog. Today was a sunday so had a lot of time on me so worked on this. i decided of making ollama the sole provider for AI for v1 of my project as it is easy to work with. I chose initially qwen3:8b model. i was working with it for the ollama integration and model works perfectly and give answers and checkning for bugs errors and debugging and adding more tests etc. today most of the time went into debgging,investigating, rediscovering how the existing architecture actually worked, challenging earlier assumptions, and then rethinking the architecture around what the system really needs. The first major objective was making sure the complete Python-project path worked together rather than only working as isolated components. The question was whether these pieces actually behaved correctly as one pipeline. So assessed the code and assemebled it and strenghted it and then added tests for it. Now working with ollama’s qwen3:8b model but soon ralzied it was a major mistake. i wanted to make the model to communicate with the project. So it worked kind off. Like the model i was using was a model that thinks and has chain of thoughts. But soon it became a problem for me. our first integration attempt exposed a problem. The model was clearly behaving as a thinking model. that mattered bcz Context Forge was now trying to use it as a part of a deterministic workflow. The model’s internal thinking could consume substantial generation time before producing the actual answer.That made the original integration architecture less suitable for the project. So i asked myself some questions and came to a conclusion that i should build v1 around the non thinking models like the one i will be using now on is qwen2.5-coder:7b . and integrate thinking and AI providers in future versions. THE CURRENT MODEL ARCHITECTURE should work with a non thinking model. So i introduced a phase for now called StageX where i would check the code and try to refactor it acc to the new direction we are heading. what will StageX chenage: Model Asumptions Thinking or reasoning done by the model Adding a Config file feature- CLI Behaviour(improved) Better Ollama integration Operational Logging this all we implemented in span of some days as i’ve got exams coming but will work on it. a large part of time not logged onto hackatime was spent towards rethinking the decisions made in the past and plan out the Future. TH biggest progress from this was architectural clarity. LET”S START STAGEX Thank u for reading this brain DUmp of Mine. Stay Tuned for future updates
Devlog#12 - StageX going Good. Greeting everyone. So i am working on the transition from qwen3:8b thinking model to non thining model. TL;DR - We redesigned the generation layer around Qwen2.5-Coder 7B and removed the old Qwen3 thinking/reasoning assumptions. The provider contract was simplified and the Ollama integration boundary was kept clean and model-agnostic. A layered configuration system was added with project, global, and built-in defaults, plus validation and precedence resolution. The CLI was then integrated with this configuration architecture while keeping the existing repository-intelligence pipeline unchanged. Full story - i inspected the existing architecture and confirmed that the repo intellegence pipeline should remain intact. i moved the active generation direction away from the old qwen3 thinking oriented architecture and established Qwen2.5-coder:7Bas the new default without hardcoding model throughout the database. I cleaned theprovider contractso reasoning thinking is no longer a part of the current core generation model while deliberately leaving future reasoning support for later architectural decisions. I also investigated the Olama integration boundary other than replacing its transportation implementation, keeping the previous Olama provider as the boundary. The largest tradition was that I wanted to add a config support so like someone can have a project project-wise configs for my tool, but it can also have a global config. So, if the project config is not available, the tool would fall back to the global config. So, I was thinking of using it as as like a .contextforge.toml file format. Yes, configuration is a dedicated defaults loading validation, etc. facilities solution, etc. And finally, the CLI was connected to the new configuration architecture. Provider settings are no longer hard-coded as the remaining configuration. This much only for today. Leave ur thoughts in the comments
Devlog#13 - Working on the CLI TL;DR - Integrated generation lifecycle handling with robust success/failure paths and duration tracking.Added rotating operational logging with privacy-safe metadata only—no prompts, responses, or reasoning.Hardened CLI/application tests and logging isolation. Yap - So Majorly worked on the tool so that it could work in the terminal with the command : context-forge [-h][–provider] etc. eg: ~/project/EV > context-forge . the above is the command that wil scan repo the command was ran in and asks for the task. another eg: ~/project/EV > context-forge -h this will give help menu of the cli tool. Also the responses are the Answers are given by the local LLM from ollama which is Qwen2.5-coder:7b which is quantized to Q4_K_M i.e. quantized to 4bit. it takes about 5GB Memory when running. I have to make it s that it runs perfectly as it doesnt answers some times etc. there are many problems to figure out will figure everything out Other things: Hardened provider/application error handling and ensured failures terminate cleanly without leaking task content. integrated generation lifecycle handling into the app flow which inclludes start/stop/completion/failure paths and duration tracking Added operational logging infra with a rotating app log at the global config drectoy Added privacy-focused logging tests ensuring prompts/tasks, generated responses, and model reasoning/thinking are never logged. Consolidated and finalized the logging method and generation lifecycle work; resolved logger path isloation. formatting,linting and test issues. js this much today nothing much more. Leave ur Views and thoguhts on this in the comments.
Devlog#14 : Greeting Everyone TL;DR - Built a complete repository-to-context-to-AI workflow with real Python source context and robust CLI/error handling.The architecture is now stable at this boundary, ready for smarter retrieval, ranking, graph expansion, and project memory. Long Story - So worked some more on the CLI workflow of the tool. SO things did today : Completed the repo to context to provider to response workflow for py projects. Added real source content to select context units added CLI coverage hardend CLI handling for path , config, task, analysis, and generation failures added the keyboardinterreupt i.e. ctrl+c/EOF handling, clean exit codes and safe operational logging. expanded failure-path test coverage So this is the final thing is that the peices were coming together. A locally executable Python workflow from repository analysis through context generation and AI response, with a reliable CLI boundary. So leave ur thoughts in the comments and plz like it.
Devlog#15: Greeting Everyone : TL;DR - Built reliable repository structure and a deterministic relationship graph, including symbols, imports, references, inheritance, ownership, relationship resolution, confidence, traversal, and persistence. Added comprehensive tests and validated against a real repository. Long Yap - So the baisc archtecture is completed and now i am working on its hardening and testing it on some real basic repos. Things done today - strengthened repository structural intelligence with more user-reliable Python parsing, symbol extraction, import references, inheritance references, and structural validation, etc. establihed the repo relation graph with numerous relationships. added deterministic relationship resolution with confience scoring and handling of unresolved references. Integrated relationship construction into the analysis pipeline expanded parser,graph,query & pipeline tests verified it basic working on real repo. close to completring a working version but not too close. leave ur thought in th comments . Have a good day or Night
Devlog#16 : Greeting Everyone - TL;DR - Context Forge can now understand what a task is asking for and deterministically connect that task to actual repository entities.It can also expand those entities through the repository relationship graph, providing a grounded repository neighborhood for subsequent retrieval and reasoning. Long Yap - Today was a small session of writing code and added new thing which is rep-aware task understanding and grounding. Grounding connects what the user mentions in a task to the actual files and symbols in the repository.It turns vague task references into concrete, verified repository entities that Context Forge can reason about added structured task interpretation covering intent, concepts, requested actions , constraints and ambiguity added exact repo relative path matching exact/unique symbol resolution while keeping unresolved references explicit added repo grounding to expand grounded entites through the existing relationship graph extended candidate generation so directly grounded and relationship connected entities can participate in context retrieval js this much today. Also had a single commit today but was a long one bcz i was in flow and forgot to commit and it was mostly tests . So sorry dev community 😭. (image attached is js a look at the code) Leave r thoughts in comments. open to feedback.
Devlog#17 - Greeting everyone! TL;DR - Added deterministic deduplication, strongest-path selection, candidate limits, and cycle protection for relationship-aware retrieval.Expanded retrieval is now bounded, predictable, and keeps its evidence consistent, with 13 tests covering the new behavior. long - So a small codin session and added some new things. added deterministic dedpulication for relationship expanded candidates added strongest path selection using confidence depth and UUID odering preserved original candidate odering. enforced candidate expansion limits and cycle protection kept retrieval evidence aligned with selected candidates. added coverage for all the thing s we did through tests. Well so this much the implmentation was small but the testing of it anc checking it was perfect was hassle full Leave ur thoguths in the comments
Devlog#18 - Greeting Everyone!: TL;DR - Integrated relationship-aware retrieval into context construction with bounded depth, confidence propagation, and retrieval provenance. Long Story - So had a small coding session today bcz i didnt got much time as exam is tommorow. Thing Done today - integrated relationship-aware retrieval into context construction addded bounded relationship expansion with confidence and provenance cnnected context-depth evidence to retrieval- added relationhship/depth to context signals added the tests related to the code changes So this mucn only today. Thnx for reading . Leave ur thoughts in the comments.
Devlog#19 - Greeting Everyone! TL;DR - Originally built the planned reasoning-heavy approach, then identified it as unnecessary complexity and hard-reset all of that work to the clean retrieval baseline. Replaced it with a minimal, structured LLM selection layer where the model only decides include + confidence, while repository intelligence and deterministic metadata remain authoritative. Long Story - So initially i was continuing my plan to have reasoning for every candidate why it was choosed . like was a reasoning heavy context approach includes LLM reasoning. Was working on implementing it throught a flow. during testing, debugging and checking that it works perfectly but things went the other ways. during the checking, i got to a problem that LLM gives out many token in reasoning and which exceeds the limit or the max_tokens limit that i have. it was bad as i couldnt get reasoning perfectly for the per candidate. the i thought of another approach. i will generate the candidates and then i will give all the reasoning fo all of the candidates at the end of it. but this want also working as i wanted it to. i had committed the wrong changes and then i had to hard reset to a stable previous commit whcih didnt had this. then i realized that i was making the system too complicated and it wasnt needed so i remove dthe reasoning nd hard reset to a previous atable commit. I used AI to fix the broken code for the reasoning part that i built but after multiple attempts . So as i said before, 1 option only i reverted to a old git commit . this took most of my time but then did some chages also now context_forgehandes repo intellengence and LLM which decide only what is actually worth keeping. added a strict context-selection contract. Added the selection service to handle the model interaction and validate its response Selection confidence is carried into the final context as metadata, keeping the output inspectable without depending on generated explanations. Added and updated tests around the contract, selection service, package construction, and engine integration Well so this much only today. This day was hassle ful. I’ve used AI 2 times to fix the tings but 1 time i was successful and 1 time i am not. But keeping it aside. i am close to complete the ‘source code’ but not too close. I am thinking of having a brew tap for mac users and another way for windows and linux. The system isnt perfect but it is running. I will make it better nd make it functionable in real world. SO these chages today were light. Most time spent was on Debuging and checkigerrors an fixing them. If hackatime would calculate time spent debugging or xiing, tiday would be 6h+ devlog. Leave ur thouhts in the coments and plz like it.
Devlog#20 - Greetings Everyone ! TL;DR - COntext Forge can now remember the state of repo aand files and identify what changes while context construction remains deterministic, robust and free of generated reasoning. Long - So Hello everyone and welcom to the 20th devlog. today added some more things which are : added deterministic file fingerprinting using its path size modification time etc. and used SHA-256content hashing Persisted file fingerprints in SQLit alongside repocacheing of metadata added detection for unchanged edited modeified added or deleted files Added storage and cache tests covering fingerprint persistence, replacement, and missing data. added analyzer covergae verifying the fingerprints are generated and rpersisted corrrectly. Kept diagnostics based on structured metadata and repository evidence rather than generated reasoning. This much today. Leave ur thoughts in the comments . BYEE and thnx for reading
Devlog#21 - Greeting Everyone! TL;DR - Repository analysis is now persisted, freshness-aware, and capable of selectively invalidating stale data instead of rebuilding everything.Cache invalidation and refresh behavior are deterministic, validated, and comprehensively tested. Long - Today I implemented the cache thing for my project. my ool works by mapping a repo and giving context to the user for user to give to AI agent for a work. SO for storing data i use SQLite but making rep data everytime will take a lot of time. So i introduced caching fo data and will refresh in sometime and can be refreshed manually also. Things did : added cache freshness checks for missing metadata , schema/analyzer version , missing fingerprints and file changes added deterministic file fingerprinting using size, modification timestamp and SHA-256 content hashes added selective invalidation for afected files, symbols, and relationships while preserving unaffected analysis added full cache invalidation for cases where existing analysis can no longer be trusted. Added cache refresh orchestration finally added tests for the same So this much today . Leave ur thoughts in the comments and like it
Devlog#22 - Greeting Everyone ! TL;DR - Built the local repository evaluation foundation.Added structural and graph accuracy measurement for files, symbols, and relationships. Long Story - So added chec for my tool. Also committed a wrong spelling recal instead of recall in a func and and then hchnaged it in the new commit. thiings did - Added local evaluation repositories and tasks. Added structural and graph evaluation Added tests for the same Leave ur thoguths iin the comment and like it
Devlog#23 - Greetings EVeryone ! TL;DR - Retrieval and task-grounding quality can now be measured deterministically against repository ground truth, with full regression coverage Long - Short sesssion today. added the tp*.txt in gitignore for me to make temporary text files Added deterministic retrieval and task-grounding evaluation with precision recall F1 metrics Added stable repo entity ground truth and evaluation ccovergae Added test for the same added init .py in every subfolder of test bcz there were name clashes in pytest. So today this much only . Leave ur thoughts in the comment and wish me luck!!
Devlog#24 - Greeting Everyone ! TL;DR - Added evaluation for both context selection and final context quality, covering correctness, budget limits, and deterministic behavior. Added focused tests to validate the complete evaluation flow. Long - So exams are going on so can’t do long hour session. Was planning to add manythings over few days but it would stretch for about more days. Things did - Added context-selection evaluation against expected entities using precision recall f1 added end to end evaluation for final context accuracy budget compliance etc. adde d validation for unkown , mising extra and empty entities or context cases. addded tests for the same Js this much today. Leave ur thoughts in the comments .
Devlog#25 - Greeting Everyone ! No TL;DR as small work today. things accomplished today - Added evaluation aggregation and baseline regression tracking Added validation for duplicate cases and regression tolerance, with tests for the same. Committed implementation and tests as focused changes. Leave ur thoughts in the comments.
Devlog#26 - Greeting Everyone ! No TL;DR as short work work today - Added deterministic evaluation baseline storage and serialization. Added validation, aggregation, coverage, and persistence support. Added comprehensive tests and maintained a clean, validated implementation. So, this much today only leave your thoughts in the comments/
Devlog#27 - Greetings Everyone ! TL;DR - Context Forge can now remember the repo state update it s understanding when things change and provides a proper cli for those who use it. It has ig aroung 6 funcs which u can read below. The work also made the internal state much easier to inspect and debug while keeping the existing thing intact. Long - SO this Devlog is after a long time ig. I was giving 5-10 mins t the project to not lose my habit and the streak also. But today my exams got over so now i can focus on the project. STARDANCE is ending soon so i need to hurry up and complete this asap. So basically did a lot of main writing for cli functionality. cf* - context forge (too lazy to write it out everytime) things did in those past days - made repo analysis persistent instead of starting from scratch everytime the cf* is ran. added file fingerprintng and change detection for smart analysis for a smart project. imporoved how changed files affect relationships and project info. added a proper dev workflow through the CLI as it is a main part and added commands like analysis and generation commands added task input , config handling, clenaer error behaviour for the better contxt of it added command to inspect repo state cache state project info and diagnostics or i should say Pre-Rendered Excuses Generation fixed issues around cache freshness and changed fiel reporting added tests for the new functionality and made sure the existing workflow stayed intact for cf* refactored the fingerprinting logic so it culd be shared cleany by the analyzer and the Cli i made for cf* So this much for the past these days. Now the thing is slowly coming like a real version. Its complexity is very high ,atleast for me . Bcz i made many py projects and this is the most challenging one so far but it shift me into the flow state after sometime so yeah it is a good challenge. It was like based on my problem i faced when i was vibecoding in the early days js to do timepass . But now when u can make it , it feels incredibale. SO yeah it is good. Yes but Currently i see models like astra and fable come out with much more context lenght and etc. so my product is not needed for them for but is a good fun project on thr side. These new models are good but havent tried them but will try them fter i get some freetime after Stardance. as stardance is my first and last ysws soi it was a great experience. Also i did many of the things in neovim like editing some files and etc but i couldnt settedup hackatime with it so like around 1-1.5 h of extra work was untracked on hackatime but it was ok. I was seeing the primeagen video of neovim and wanted to try it out so i did and learned some basics and therre is a very stepp learning curve in it . ALso tried out lazyvim but not my style . So wil pause the vim learing for a few days and finish the prject cf asap. Sorry for this Yapp Session but dumped everything i had for these past few days. SO plz leave ur review in the comment and plz like it and rate it good.
Devlog#28 - Greetings Everyone ! TL;DR - Added proper ollama checking and validation plus a runtime cli. Generation now safely uses fresh persisted repo intelligence instead of re-analyzing the project everytime Long - Problems : so when doing today’s work the problems that i wanted to fix was that the generation workflow was still too dependent on live repo analysis instead of using the persisted intelligence. 2nd there was no way to verify ollama itself is available or not. like ollama runtime and is a model available or not. runtime failures needed to stop generation cleanly and not throw a bunch of error a user neds to debug. we needed to preserve provider behaviour and avoid breaking the previous architecture i built the generation one. also the generation path needed clear boundaries between runtime validation, provider execution and final output and etc etc. It sound much but the implementation was simple as ig for me. things done today to solve the problems - added ollama runtime inspection to check local runtime and requested model are available added dedicated runtime cli commd for checking the state of the runtime and model independently changed the generation to load persistd repo intellegence insteasd of it everytime doing a fresh analysis as it would be bad for it to make new things for everytime a cli is ran added cache freshness validation so generation refues stale repo intellegence added regression covergae proving that a generation uses the persistent project and doesnt starts the analyzer again made a foundation kinda thing for a clean generationresponse to cli output boundary with remainng output workflow continuing afterwards added test for the features added Also some of the current changes may not be sen on the github repo bcz i havent comitted some changes as they are a part of a feature and i commit like a feature and the tests related to it for better commits ig . Now what we did to solve the problems and how i felt when solving them - . the generation pipeline is now ready to build the dev facing output worflow or like a user workflow on top of these things the previous architecture i made. i found addng the flags to main.py file easy but then adding the cache checking and the regression covergae and the generationresponse to cli output boundary a bit challenging . So today only this much. Hope u like my project and plz comment for feedback. also a mention to @CT5 on slack for telling me to added problem and solution section in my devlog for better project experii\ence.
Devlog#29 - Greeting Everyone ! STARDANCE IS GETTING EXTENDED YAYYY!!!!! No TL;DR today for short work Things did today in short time added clean generation outuput handling added cli error handling and seperated output from errors connected generation to the persisted project added test for the same also spent some time on editing some test generated bcz they werent like tha lvl Sp today short work due to other school work coming in. Leave ur thoguhts in the comments and pl like it if u think it is good and should get real appreciation.
Devlog#30 - Greeting Everyone ! - THE GREAT PIVOT Work - Context forge is now moving away from being a generation based tool and becoming a deterministic agent memory foundation. now the rtransition is done cleanly and now i am working ahead on the current foundation but new features. work done - completed the changed direction of context forge from the old provider and generation system to a repo intellegence system removed the ollama integration, provider stack. runtime configuration and the dependencies that came with them. the core should now work without depending on LLM or external APIs refactoredthe application services, task understanding, context slelction, ranking and CLI to fit the new direction. kept the important foundation like SQLite storage , AST based analysis, repo fingerprints, inremental file change detection and evidence based context rtrieval added architecture tests for offline operation , deterministic ranking, file change detection and making sure the context output has proper evidence cleaned up all the old tests which were not needed and deleted the whole files which weren’t needed in the future . Today was mostly about get ting the big transition properly finished. So for the past days, I had some exams and was not happy with the behavior of Olama, of its undeterministic behavior. So I took this step. I did not change the base foundation. I just changed the overlying architecture, the Olama ones, and removed everything that was made that was not needed. So the commit of today is very large, like 7,000 lines removed, and 1000 lines written. I made one big commit for the entire transition instead of splitting this architectural layer into multiple commits. Transform context force into a deterministic agent memory foundation. I also cleaned up the extra local branches and checked that main was synced with GitHub. Now I’m moving towards a memory vault kind of thing. I have to build on what already exists instead of rewriting everything again, improve the memory idea of foundations, add the shorter commands. Yes, so yeah, this was a pretty big change for our project. There was still a lot to do, but at least reaction is much cleaner now. Hope you like the project and please leave your thoughts or feedback in the comments. To be completely transparent, I used AI assistance to help me safely untangle and delete parts of the old architecture that were tightly coupled. As a student developer handling a complex refactor alone, trying to manually map out every single breaking change across thousands of lines got overwhelming, and I needed the help to get it done cleanly. No regrets it got the job back on track, and the codebase is in a much healthier place. With the cleanup done and main fully synced, I’m now shifting focus toward building out the new deterministic memory vault and refining the short-form CLI commands for AI agents. Show writer shipwrights. Please don’t wreck my project. Hope you like the new direction! Let me know your thoughts or feedback in the comments below.
Devlog#31 - Greeting Everyone ! TL;DR - I spent time strengthening Context Forge’s core memory and retrieval systems, making repository knowledge more reliable and useful. I also improved how the project handles changes, retrieves relevant information, and exposes its capabilities through the CLI. Work - I wanted to move beyond simple analyzing repo and make cf better at remembering, understanding and retrieving repo knowledge. Here what i did : Strengthened how repository information is stored so files, symbols, and relationships remain available even after restarting the application. Improved how Context Forge handles added, modified, and deleted files, keeping stored knowledge aligned with the actual repository and preventing outdated information from lingering. Strengthened the way relevant files, symbols, and relationships are found and ranked, making results more predictable and consistent. Improved the ability to trace retrieved information back to repository evidence and understand why particular results were selected. Added the cf command as a shorter alternative to context-forge , while preserving the existing command and its behavior. Expanded the CLI with commands for inspecting repository status, memory, files, symbols, references, and relationships, making it easier to explore what Context Forge knows. Improved operational error handling, logging, and diagnostics, making failures easier to understand and helping keep the overall experience more predictable. So yeah did so many things It’s been a while since the Great Pivot / I took some time work through these as i also had to check whether there is some code of the things iripped off in the great pivot. the time went here on working through these features properly, strength the exisiting foundationand make cf more relaible and now moving onto the next things. So leave ur thoughts in the comments and plz leave a like
Devlog#32 - Greeting Everyone ! TL;DR - I spent quite some time making Context Forge more reliable under the hood. The focus was on improving repository analysis, CLI usability, and ensuring that the memory system stays consistent with the actual codebase. Work - I wanted to make cf more than js a tool that scans repo once and stores some info. i wanted to make it useful in real dev workflow or like for someone like me who is making many projects and can sometimes lose trace of what will happned to the codebase. HEre’s what i worked on for these 8h spread across some days. Improved repository analysis and persistence so that the stored knowledge remains consistent and can be reused across different runs. Strengthened incremental analysis to handle added, modified, and deleted files more reliably, reducing the chances of outdated information sticking around. Worked on retrieval and relationship handling to make results more predictable and easier to trace back to the actual source code. Improved the CLI experience, making it easier to inspect repository information and understand what Context Forge currently knows. Refined error handling and diagnostics so that failures are easier to investigate instead of leaving me guessing about what went wrong. Expanded the test coverage across the core systems to catch regressions and make sure that improvements in one area don’t quietly break another. One of the trickkier parts was that the stored repo info actually reflected the current codebase. it’s easy to get things on fresh analysis but things get more complicated when files change , disapper or contain info that cannot bre resolved cleanly. I had to spend time thinking abt edge cases to. a lot work was for strengthing the base the foundation , some improvements i made aren’t visibe ut matter when u want cf to behave properly across multiple projects. Yeah so there is more to build and it was a solid step for cf i would say so. Also SD getting ending in 10 days and i have a lot in mind and i need to ship quick so there would be a lots of commits and hrs or the upcoming 2-3 days as i will grind as much as the time i would get . So leave ur thoughts in the comments if u have any and plz like the project (image context : i ran the cf . command on the cf repo itself and this was its answer)
Devlog#33 - Greeting Everyone ! Tl;DR - i spent quite a few hours working on makinf cf understand the repo better , finding th right info and letting the user to inspect a codebase before making changes. like searching for func what it depend on etc. Work : One thing i’ve been thinking abt is that when working on ap project that we can we see what things happend in the repo and where things are and what would i need to look for when changin something etc. . A So lot of work went into connecting some pieces and making sure cf gives reliable info and instead of the sqlite database dat Things done : cf can now check the rpeo and its analysis readiness. this helps bcz it can identify configuration problems instead of discovering them after halfway through. Improved the way cf finds specific symbols in a codebase of a project. the idea was to make it easier to locate and see where a func or a class or other element lies. without having to search everything manually. worked on retrieving relevant source excerpts and checking whether the info is still reliable in the current state of the repo/codebase as there is no use of having old data . added the git navigation capabilities so cf can work with arep changes and git’s context withut modifying the repo code. A MAJOR THING - cf can now bring imp repo info , evidence, other relevant things to help user see the codebase state before making a mistake or making changes to the code. Alongside these made some minor improvements lke more consistent error handling and auditing things etc. and also checking these minor things didnt broke any other things. these kinda things look boing but are nessecary/needed. i dont want cf to be one of the project where u give features without making the existng ones better. i want it to be better and useful for users when working on a large codebase etcetc. Honestly , i’ve had shipped this way earlier if i wasnt slacking off and exams didnt came i my way but we are now in the Last 10 days of Sd. i have a quite things in mind which i need to complete this before shippins so focus on that or some days and the i will ship it. ALso the time on this devlog is small bcz i had accidentally deleted the hackatime config(or file whatevery u want to say) and i didn’t noticed it for quite a few time and then today i relaized when i open my hackatime dashboard. So this is the last time that was logged. I will setup before writing a next devlog . So open to ur thoughts on the cf project and comment ur thoughts. ALso plz leave a like if u like m project !!!!!!!!!!!!...
|
1792723718.2292595
|
1793328518.2292595
|
|
52748
|
My awesome macropad! by @aarav_27 | Stardance
|
aarav_27
|
0
|
0.0
|
0
|
[]
|
[]
|
Title: My awesome macropad! by @aarav_27 | Stardan Title: My awesome macropad! by @aarav_27 | Stardance...
|
1792723719.5341005
|
1793328519.5341005
|
|
52749
|
My awesome macropad! by @anudey | Stardance
|
anudey
|
0
|
0.0
|
0
|
[]
|
[]
|
Title: My awesome macropad! by @anudey | Stardance
|
1792723720.3821108
|
1793328520.3821108
|
|
29798
|
digital organ by @gusee | Stardance
|
gusee
|
0
|
0.0
|
0
|
[]
|
[]
|
Title: digital organ by @gusee | Stardance
|
1792723721.2890985
|
1793328521.2890985
|
|
39114
|
Portable bluetooth speaker by @suklaasukkulayt | S Portable bluetooth speaker by @suklaasukkulayt | Stardance...
|
suklaasukkulayt
|
0
|
15.03
|
0
|
[]
|
[{"post_id": 73909, "ts": "202 [{"post_id": 73909, "ts": "2026-09-26T09:37:31Z", "hours": 5.4869, "text": "Devlog 4 The project is getting closer to being finished . I did some final polishing on the wood and then I installed the “ staining varnish ” which is a protector thing that protects the wood. Then I started putting it together , it still needs to be more sealed so it will work better. I will also design a speaker grill for the speakers so it looks better (also it will protect the speakers). The good thing is that the speaker works, but the battery connection won’t be final just like the button cover is gonna need some glue . That might be all but I’m not too sure."}, {"post_id": 52249, "ts": "2026-08-22T10:47:04Z", "hours": 2.6817, "text": "Devlog 3 It’s been almost a month since my last devlog so here it is. All the parts are almost completed now! The top part for the buttons was the hardest part in this devlog and it required a 3d printed part. Yeah that’s kinda all :D"}, {"post_id": 38932, "ts": "2026-08-01T15:21:21Z", "hours": 5.3153, "text": "Devlog 2 Decided to do a devlog because it’s already been quite a long time. I decided to use my small CNC machine I have at home to make the main casing for the speakers. I’m gonna use a 3d printer to make the speaker grills. I added the RGB LED(2 pin, changes color without external controller) and also a passive bass radiator(from the old bluetooth speaker). Top, left and bottom parts are not yet made (top will have the buttons). I will use the existing button thing from the old speaker to press the buttons. The speakers I used are YD103-60 (4 ohm, freq. range 100-15000hz) and YDD103-04A(from an old pc speaker set). My dad also helped me with cutting the wood before and after CNC machining and also designed a holder for the passive bass radiator (not visible in the images). I made the other CNC and 3d files. Also I didn’t timelapse everything but that’s it for now."}, {"post_id": 34123, "ts": "2026-07-24T16:48:41Z", "hours": 1.5444, "text": "I am making a portable Bluetooth speaker that will hopefully not sound bad. I am using a bluetooth amplifier board (GW542B_BP104B1_V1.0) that I got from an old bluetooth speaker. It has a battery, usb-c charging, aux port, usb port and it supports two speakers and led lightning. The led bar from the original speaker is too big so i’m not gonna use that. It was kinda hard figuring out where you actually put the speaker wires in the amplifier because there is so many connectors and most of them don’t even work. I’m gonna design and probably 3d print the shell for the speaker. Here I just got the speakers wired up. I will add the LED next devlog. I’m gonna try to fit the two speakers in the shell but designing it is in the next devlog. Here is a photo of my current setup and the amplifier board(with only the battery connected). Also i’m gonna fix the dent on the second speaker :D"}]...
|
Title: Portable bluetooth speaker by @suklaasukkul Title: Portable bluetooth speaker by @suklaasukkulayt | Stardance
Devlogs:
I am making a portable Bluetooth speaker that will hopefully not sound bad. I am using a bluetooth amplifier board (GW542B_BP104B1_V1.0) that I got from an old bluetooth speaker. It has a battery, usb-c charging, aux port, usb port and it supports two speakers and led lightning. The led bar from the original speaker is too big so i’m not gonna use that. It was kinda hard figuring out where you actually put the speaker wires in the amplifier because there is so many connectors and most of them don’t even work. I’m gonna design and probably 3d print the shell for the speaker. Here I just got the speakers wired up. I will add the LED next devlog. I’m gonna try to fit the two speakers in the shell but designing it is in the next devlog. Here is a photo of my current setup and the amplifier board(with only the battery connected). Also i’m gonna fix the dent on the second speaker :D
Devlog 2 Decided to do a devlog because it’s already been quite a long time. I decided to use my small CNC machine I have at home to make the main casing for the speakers. I’m gonna use a 3d printer to make the speaker grills. I added the RGB LED(2 pin, changes color without external controller) and also a passive bass radiator(from the old bluetooth speaker). Top, left and bottom parts are not yet made (top will have the buttons). I will use the existing button thing from the old speaker to press the buttons. The speakers I used are YD103-60 (4 ohm, freq. range 100-15000hz) and YDD103-04A(from an old pc speaker set). My dad also helped me with cutting the wood before and after CNC machining and also designed a holder for the passive bass radiator (not visible in the images). I made the other CNC and 3d files. Also I didn’t timelapse everything but that’s it for now.
Devlog 3 It’s been almost a month since my last devlog so here it is. All the parts are almost completed now! The top part for the buttons was the hardest part in this devlog and it required a 3d printed part. Yeah that’s kinda all :D
Devlog 4 The project is getting closer to being finished . I did some final polishing on the wood and then I installed the “ staining varnish ” which is a protector thing that protects the wood. Then I started putting it together , it still needs to be more sealed so it will work better. I will also design a speaker grill for the speakers so it looks better (also it will protect the speakers). The good thing is that the speaker works, but the battery connection won’t be final just like the button cover is gonna need some glue . That might be all but I’m not too sure....
|
1792723722.143542
|
1793328522.143542
|
|
21206
|
My awesome macropad! by @ashiya_aggl | Stardance
|
ashiya_aggl
|
0
|
0.0
|
0
|
[]
|
[]
|
Title: My awesome macropad! by @ashiya_aggl | Star Title: My awesome macropad! by @ashiya_aggl | Stardance...
|
1792723723.2484012
|
1793328523.2484012
|
|
72
|
UWB indoor positioning by @jacques_s | Stardance
|
jacques_s
|
0
|
0.0
|
0
|
[]
|
[]
|
Title: UWB indoor positioning by @jacques_s | Star Title: UWB indoor positioning by @jacques_s | Stardance...
|
1792723724.0843794
|
1793328524.0843794
|
|
8596
|
My awesome macropad! by @Nate09 | Stardance
|
Nate09
|
0
|
0.0
|
0
|
[]
|
[]
|
Title: My awesome macropad! by @Nate09 | Stardance
|
1792723724.9290328
|
1793328524.9290328
|
|
33124
|
AstroBot by @ | Stardance
|
|
0
|
0.0
|
0
|
[]
|
[]
|
Title: AstroBot by @ | Stardance
|
1792723725.7853775
|
1793328525.7853775
|
|
32825
|
My very own WebOS by @Zhiyuan | Stardance
|
Zhiyuan
|
0
|
0.0
|
0
|
[]
|
[]
|
Title: My very own WebOS by @Zhiyuan | Stardance
|
1792723726.6244724
|
1793328526.6244724
|
|
22548
|
Dungeon Master by @Rykard | Stardance
|
Rykard
|
0
|
0.0
|
0
|
[]
|
[]
|
Title: Dungeon Master by @Rykard | Stardance
|
1792723727.49308
|
1793328527.49308
|
|
23238
|
Untitled by @nathanaditya254 | Stardance
|
nathanaditya254
|
0
|
0.0
|
0
|
[]
|
[]
|
Title: Untitled by @nathanaditya254 | Stardance
|
1792723728.3409107
|
1793328528.3409107
|
|
14695
|
Odyssey by @vihanr | Stardance
|
vihanr
|
0
|
25.6
|
0
|
[]
|
[{"post_id": 35898, "ts": "202 [{"post_id": 35898, "ts": "2026-07-27T17:01:26Z", "hours": 7.265, "text": "base odyssey-core finished! whats done: everything from initial commit and second devlog (too lazy to type it out lol) Follower.java: combines two vectors for velocity (translational vector, what keeps the robot on the path through arc-length implicitization plus drive vector, the vector that follows the bezier curve) and two different acceleration scalars (centripetal, calculated thruogh v^2*k, and tangential, just the tangential accel from VelocityProfile.java). This in total outputs a DriveSignal that drives the robot. updated DriveSignal that includes forward and strafe acceleration for centripetal pass MecanumDrive.java: putting it together. Takes in a drive signal, and outputs actual drive commands that make the wheels move. StaticCoefficientOpMode.java: opmode that helps you determine kS and kV (static friction coeff and velocity coeff) what im working on advanced heading control: tangential heading, constant heading, target-based heading, etc. GUI (finally): gui that helps you create a path in a user-friendly way and returns a JSON of pts that you can use while coding ambitious goals: turning into a maven lib? marketing to young/rookie teams? website with documentation?"}, {"post_id": 29949, "ts": "2026-07-17T04:17:13Z", "hours": 1.7903, "text": "finished VelocityProfile.java what is it? a velocity profile is just a simple mapping of the optimal velocity given the robot is along the path. it takes in distance, and it outputs velocity. how does it do that? first of all, because it maps distance in a cubic bezier-curve path, my numerical solution to arc-length parametrization using a Gauss-Legendre integrator proves actually useful. Based on that distance, you pass the optimal velocity through 3 different checks: centripetal, forward, and backward. centripetal pass: you get the curvature based on the distance you are along the path, and from that curvature you use the formula a_c=v^2*k (rearrange it to v^2=a_c/k and finally v=sqrt(a_c/k)) to find the curve velocity limit. This is also tuned by the maximum centripetal acceleration limit that is based on the robot’s physical capability. forward pass: with a standard velocity profile with just velocity mappings, the robot may physically not be able to accelerate from point A to B. a forward pass provides the maximum velocity for accelerating smoothly without error along two distances. It uses the kinematic formula with the max acceleration as the robot’s acceleration limit. backward pass: backward pass is basically the same idea as forward pass except, you guessed it, backwards! it uses the robot’s physical limit of braking (or deacceleration) to find the optimal breaking speed. for finding the velocity you can lerp the closest low and high vals. tests: 14 out of 14 passed yay (i had one slip up where i forgot to lerp v^2 and lerped v) now im working on: the simulated follower bc i need the actual robot for t he real follower"}, {"post_id": 29270, "ts": "2026-07-16T02:32:09Z", "hours": 16.5494, "text": "initial commit everything done so far (first devlog a bit late into the project so a lot is done) entire geometry package (Vector2d, BezierCurve, Pose2d, etc.) follower class DriveSignal that turns forward strafe and turn into one robust signal beautiful arc-length parametrization and implicitization (holy that took a long time accounted for like 5 hours lmao) but one of the key parts that makes this algo extremely accurate compared to others pid controller VERY VERY VERY basic GUI using JavaFX in progress: velocity profile (working on the basic methods on optimal centrepital acceleration, trying to learn 1st pass 2nd pass and 3rd pass) soon: simulated follower algo actual follower algo when i get the robot ambitious: GUI that turns your path (hand-drawn with bezier curve control points, maybe next i could include an optimize function) into JSON for easier readibility and maybe soon an actual java code that works potentially making this into a library??"}]...
|
Title: Odyssey by @vihanr | Stardance
Devlogs:
in Title: Odyssey by @vihanr | Stardance
Devlogs:
initial commit everything done so far (first devlog a bit late into the project so a lot is done) entire geometry package (Vector2d, BezierCurve, Pose2d, etc.) follower class DriveSignal that turns forward strafe and turn into one robust signal beautiful arc-length parametrization and implicitization (holy that took a long time accounted for like 5 hours lmao) but one of the key parts that makes this algo extremely accurate compared to others pid controller VERY VERY VERY basic GUI using JavaFX in progress: velocity profile (working on the basic methods on optimal centrepital acceleration, trying to learn 1st pass 2nd pass and 3rd pass) soon: simulated follower algo actual follower algo when i get the robot ambitious: GUI that turns your path (hand-drawn with bezier curve control points, maybe next i could include an optimize function) into JSON for easier readibility and maybe soon an actual java code that works potentially making this into a library??
finished VelocityProfile.java what is it? a velocity profile is just a simple mapping of the optimal velocity given the robot is along the path. it takes in distance, and it outputs velocity. how does it do that? first of all, because it maps distance in a cubic bezier-curve path, my numerical solution to arc-length parametrization using a Gauss-Legendre integrator proves actually useful. Based on that distance, you pass the optimal velocity through 3 different checks: centripetal, forward, and backward. centripetal pass: you get the curvature based on the distance you are along the path, and from that curvature you use the formula a_c=v^2*k (rearrange it to v^2=a_c/k and finally v=sqrt(a_c/k)) to find the curve velocity limit. This is also tuned by the maximum centripetal acceleration limit that is based on the robot’s physical capability. forward pass: with a standard velocity profile with just velocity mappings, the robot may physically not be able to accelerate from point A to B. a forward pass provides the maximum velocity for accelerating smoothly without error along two distances. It uses the kinematic formula with the max acceleration as the robot’s acceleration limit. backward pass: backward pass is basically the same idea as forward pass except, you guessed it, backwards! it uses the robot’s physical limit of braking (or deacceleration) to find the optimal breaking speed. for finding the velocity you can lerp the closest low and high vals. tests: 14 out of 14 passed yay (i had one slip up where i forgot to lerp v^2 and lerped v) now im working on: the simulated follower bc i need the actual robot for t he real follower
base odyssey-core finished! whats done: everything from initial commit and second devlog (too lazy to type it out lol) Follower.java: combines two vectors for velocity (translational vector, what keeps the robot on the path through arc-length implicitization plus drive vector, the vector that follows the bezier curve) and two different acceleration scalars (centripetal, calculated thruogh v^2*k, and tangential, just the tangential accel from VelocityProfile.java). This in total outputs a DriveSignal that drives the robot. updated DriveSignal that includes forward and strafe acceleration for centripetal pass MecanumDrive.java: putting it together. Takes in a drive signal, and outputs actual drive commands that make the wheels move. StaticCoefficientOpMode.java: opmode that helps you determine kS and kV (static friction coeff and velocity coeff) what im working on advanced heading control: tangential heading, constant heading, target-based heading, etc. GUI (finally): gui that helps you create a path in a user-friendly way and returns a JSON of pts that you can use while coding ambitious goals: turning into a maven lib? marketing to young/rookie teams? website with documentation?...
|
1792723729.1692243
|
1793328529.1692243
|
|
22430
|
My very own WebOS by @aabby_andrews | Stardance
|
aabby_andrews
|
0
|
7.51
|
0
|
[]
|
[{"post_id": 20761, "ts": "202 [{"post_id": 20761, "ts": "2026-07-02T13:40:10Z", "hours": 1.5417, "text": "I’ve finally make an app for the web OS, it dosen’t work as intended jut yet but at least is created. There have been lots of bugs, and being a beginer it’s been tricky."}, {"post_id": 19121, "ts": "2026-06-30T11:16:36Z", "hours": 1.5164, "text": "Today I’ve fixed my code, it was messy and had things that wasn’t working. I’ve finally found out how to open and close my windows and how to organise my files inside the project."}, {"post_id": 18296, "ts": "2026-06-29T12:16:56Z", "hours": 0.8869, "text": "Right now I’m working in my draggable windows. At first I didn’t knew what use to give to my web IOS, but now i intend to use it as a blog for my project ideas, not only the tecnologic ones, all kinds of projects. And from this make like a tiny blog that explains what has been the progress enery week in these projects."}, {"post_id": 17228, "ts": "2026-06-27T22:53:28Z", "hours": 1.5228, "text": "Just finished the step 2 of the tutorial, i’had some problems with how to set up the time, but at the end i’ve solve it. I dare to say that after spending some time coding, when things finally work means it was worth the time."}, {"post_id": 13383, "ts": "2026-06-21T22:34:43Z", "hours": 2.0381, "text": "First steps to create my own WebOS"}]...
|
Title: My very own WebOS by @aabby_andrews | Stard Title: My very own WebOS by @aabby_andrews | Stardance
Devlogs:
First steps to create my own WebOS
Just finished the step 2 of the tutorial, i’had some problems with how to set up the time, but at the end i’ve solve it. I dare to say that after spending some time coding, when things finally work means it was worth the time.
Right now I’m working in my draggable windows. At first I didn’t knew what use to give to my web IOS, but now i intend to use it as a blog for my project ideas, not only the tecnologic ones, all kinds of projects. And from this make like a tiny blog that explains what has been the progress enery week in these projects.
Today I’ve fixed my code, it was messy and had things that wasn’t working. I’ve finally found out how to open and close my windows and how to organise my files inside the project.
I’ve finally make an app for the web OS, it dosen’t work as intended jut yet but at least is created. There have been lots of bugs, and being a beginer it’s been tricky....
|
1792723730.0328007
|
1793328530.0328007
|
|
26788
|
Untitled by @Jass | Stardance
|
Jass
|
0
|
0.0
|
0
|
[]
|
[]
|
Title: Untitled by @Jass | Stardance
|
1792723730.910417
|
1793328530.910417
|
|
27332
|
Untitled by @madegg | Stardance
|
madegg
|
0
|
0.0
|
0
|
[]
|
[]
|
Title: Untitled by @madegg | Stardance
|
1792723731.7550154
|
1793328531.7550154
|
|
17171
|
My very own WebOS by @Hibiscus-Roller | Stardance
|
Hibiscus-Roller
|
0
|
0.0
|
0
|
[]
|
[]
|
Title: My very own WebOS by @Hibiscus-Roller | Sta Title: My very own WebOS by @Hibiscus-Roller | Stardance...
|
1792723732.5984886
|
1793328532.5984886
|
|
13616
|
My very own WebOS by @mrthomasingham | Stardance
|
mrthomasingham
|
0
|
0.0
|
0
|
[]
|
[]
|
Title: My very own WebOS by @mrthomasingham | Star Title: My very own WebOS by @mrthomasingham | Stardance...
|
1792723733.4333613
|
1793328533.4333613
|
|
18386
|
Real Time Space By A Phone by @SourishWani | Stard Real Time Space By A Phone by @SourishWani | Stardance...
|
SourishWani
|
0
|
0.0
|
0
|
[]
|
[]
|
Title: Real Time Space By A Phone by @SourishWani Title: Real Time Space By A Phone by @SourishWani | Stardance...
|
1792723734.2820818
|
1793328534.2820818
|
|
7004
|
Rush and riot by @Ares_god_of_softWARe | Stardance
|
Ares_god_of_softWARe
|
0
|
2.96
|
0
|
[]
|
[{"post_id": 63953, "ts": "202 [{"post_id": 63953, "ts": "2026-09-08T01:28:23Z", "hours": 2.5964, "text": "Had to restart bc SAT and I messed up so i cannot access the original game, I also got into hardware making bases and started doing yt for electronics AAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAH!!!!!!!!"}, {"post_id": 31047, "ts": "2026-07-19T04:01:45Z", "hours": 0.3639, "text": "Videogame/Rogue-like coming along also btw I wanna make this a hacktime game, any and all recommendations will be added to the game, I wanna be the next Toby Fox"}]...
|
Title: Rush and riot by @Ares_god_of_softWARe | St Title: Rush and riot by @Ares_god_of_softWARe | Stardance
Devlogs:
Videogame/Rogue-like coming along also btw I wanna make this a hacktime game, any and all recommendations will be added to the game, I wanna be the next Toby Fox
Had to restart bc SAT and I messed up so i cannot access the original game, I also got into hardware making bases and started doing yt for electronics AAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAH!!!!!!!!...
|
1792723735.1015458
|
1793328535.1015458
|
|
4251
|
SysPulse by @Indian5000 | Stardance
|
Indian5000
|
0
|
10.33
|
0
|
[]
|
[{"post_id": 2297, "ts": "2026 [{"post_id": 2297, "ts": "2026-06-04T18:21:31Z", "hours": 8.0664, "text": "Completely re-wrote the front end with AI-assisted coding. Currently under progress. New features from last devblog include…A completely for show hamburger button and menu, different Color scheming to my Liking, complete back end(for only main page basic stats [Most not displayed currently] back end is nowhere near done) and maybe a few Easter-eggs :) Most of my time was spent planning out all the features."}, {"post_id": 752, "ts": "2026-06-02T11:57:02Z", "hours": 2.2653, "text": "Basic Server Dashboard Work In Progress- Designed Heavily around ease of install and use and Laptop Servers."}]...
|
Title: SysPulse by @Indian5000 | Stardance
Devlog Title: SysPulse by @Indian5000 | Stardance
Devlogs:
Basic Server Dashboard Work In Progress- Designed Heavily around ease of install and use and Laptop Servers.
Completely re-wrote the front end with AI-assisted coding. Currently under progress. New features from last devblog include…A completely for show hamburger button and menu, different Color scheming to my Liking, complete back end(for only main page basic stats [Most not displayed currently] back end is nowhere near done) and maybe a few Easter-eggs :) Most of my time was spent planning out all the features....
|
1792723735.9546244
|
1793328535.9546244
|
|
35685
|
eshaal's website :) by @3shxxl | Stardance
|
3shxxl
|
0
|
0.34
|
0
|
[]
|
[{"post_id": 33635, "ts": "202 [{"post_id": 33635, "ts": "2026-07-23T18:26:38Z", "hours": 0.3408, "text": "devlog #1 hihi fellow stardancers!! i learnt most of the hmtl basics today so i can start working on my website. i even did some test runs, but for now im working on the design for my website on canva. so once i get a design down, ill start coding in html :PP take a look at the screenshot attached for a lil sneak peak XD and feel free to leave suggestions as for what else i should include!!"}]...
|
Title: eshaal's website :) by @3shxxl | Starda Title: eshaal's website :) by @3shxxl | Stardance
Devlogs:
devlog #1 hihi fellow stardancers!! i learnt most of the hmtl basics today so i can start working on my website. i even did some test runs, but for now im working on the design for my website on canva. so once i get a design down, ill start coding in html :PP take a look at the screenshot attached for a lil sneak peak XD and feel free to leave suggestions as for what else i should include!!...
|
1792723736.8215272
|
1793328536.8215272
|
|
32672
|
SuperDog by @raj77502k | Stardance
|
raj77502k
|
0
|
10.09
|
0
|
[]
|
[{"post_id": 47985, "ts": "202 [{"post_id": 47985, "ts": "2026-08-16T08:14:28Z", "hours": 1.9506, "text": "Redesigned the body"}, {"post_id": 44015, "ts": "2026-08-09T14:45:01Z", "hours": 2.6669, "text": "Vision Plate and BackCover’"}, {"post_id": 43860, "ts": "2026-08-09T09:33:25Z", "hours": 0.7503, "text": "Completed the Head of my SuperDog"}, {"post_id": 41436, "ts": "2026-08-05T17:27:55Z", "hours": 1.2839, "text": "Head of SuperDog!!!"}, {"post_id": 38935, "ts": "2026-08-01T15:25:47Z", "hours": 1.5331, "text": "FurtherDesiging"}, {"post_id": 38254, "ts": "2026-07-31T15:36:49Z", "hours": 1.4853, "text": "Designing thr body"}, {"post_id": 26520, "ts": "2026-07-11T11:23:52Z", "hours": 0.4167, "text": "Artifically Intelligent Companion RoboDog *The image contains a target goal only."}]...
|
Title: SuperDog by @raj77502k | Stardance
Devlogs Title: SuperDog by @raj77502k | Stardance
Devlogs:
Artifically Intelligent Companion RoboDog *The image contains a target goal only.
Designing thr body
FurtherDesiging
Head of SuperDog!!!
Completed the Head of my SuperDog
Vision Plate and BackCover’
Redesigned the body...
|
1792723737.6778808
|
1793328537.6778808
|
|
19312
|
My very own WebOS by @AustinCMedic | Stardance
|
AustinCMedic
|
0
|
0.0
|
0
|
[]
|
[]
|
Title: My very own WebOS by @AustinCMedic | Starda Title: My very own WebOS by @AustinCMedic | Stardance...
|
1792723738.5619407
|
1793328538.5619407
|
|
22872
|
My very own WebOS by @Bluedot | Stardance
|
Bluedot
|
0
|
0.0
|
0
|
[]
|
[]
|
Title: My very own WebOS by @Bluedot | Stardance
|
1792723739.4007344
|
1793328539.4007344
|
|
14649
|
My very own WebOS by @ximenapg_projects | Stardanc My very own WebOS by @ximenapg_projects | Stardance...
|
ximenapg_projects
|
0
|
0.0
|
0
|
[]
|
[]
|
Title: My very own WebOS by @ximenapg_projects | S Title: My very own WebOS by @ximenapg_projects | Stardance...
|
1792723740.2444057
|
1793328540.2444057
|
|
3353
|
My awesome macropad! by @zahra | Stardance
|
zahra
|
0
|
0.0
|
0
|
[]
|
[]
|
Title: My awesome macropad! by @zahra | Stardance
|
1792723741.0933719
|
1793328541.0933719
|
|
34618
|
Frictionless by @Yasso_Ahmed | Stardance
|
Yasso_Ahmed
|
0
|
0.0
|
0
|
[]
|
[]
|
Title: Frictionless by @Yasso_Ahmed | Stardance
|
1792723741.9402885
|
1793328541.9402885
|
|
13247
|
magnetic levitator by @mahdiaitch | Stardance
|
mahdiaitch
|
0
|
0.0
|
0
|
[]
|
[]
|
Title: magnetic levitator by @mahdiaitch | Stardan Title: magnetic levitator by @mahdiaitch | Stardance...
|
1792723742.7828043
|
1793328542.7828043
|
|
24748
|
tplinked by @toxi | Stardance
|
toxi
|
0
|
0.0
|
0
|
[]
|
[]
|
Title: tplinked by @toxi | Stardance
|
1792723743.6172042
|
1793328543.6172042
|
|
4383
|
My awesome macropad! by @wubshet2028 | Stardance
|
wubshet2028
|
0
|
0.0
|
0
|
[]
|
[]
|
Title: My awesome macropad! by @wubshet2028 | Star Title: My awesome macropad! by @wubshet2028 | Stardance...
|
1792723744.456172
|
1793328544.456172
|
|
4920
|
My awesome macropad! by @Azulae | Stardance
|
Azulae
|
0
|
0.0
|
0
|
[]
|
[]
|
Title: My awesome macropad! by @Azulae | Stardance
|
1792723745.3153179
|
1793328545.3153179
|
|
6992
|
Untitled project by @sami_bibs | Stardance
|
sami_bibs
|
0
|
0.0
|
0
|
[]
|
[]
|
Title: Untitled project by @sami_bibs | Stardance
|
1792723746.1697333
|
1793328546.1697333
|
|
67000
|
neo-note by @tejasv | Stardance
|
tejasv
|
0
|
1.85
|
0
|
[]
|
[{"post_id": 75805, "ts": "202 [{"post_id": 75805, "ts": "2026-10-01T06:22:20Z", "hours": 0.5647, "text": "completed the mongo DB and supabase authorization"}, {"post_id": 75584, "ts": "2026-09-30T14:14:06Z", "hours": 0.5636, "text": "completed the data base work and the api routing ,without ai"}, {"post_id": 75525, "ts": "2026-09-30T11:30:21Z", "hours": 0.7222, "text": "completed the core model backend and working faster to get it done today"}]...
|
Title: neo-note by @tejasv | Stardance
Devlogs:
c Title: neo-note by @tejasv | Stardance
Devlogs:
completed the core model backend and working faster to get it done today
completed the data base work and the api routing ,without ai
completed the mongo DB and supabase authorization...
|
1792464547.6548502
|
1793328547.6548502
|
|
6014
|
Untitled project by @fidel | Stardance
|
fidel
|
0
|
0.0
|
0
|
[]
|
[]
|
Title: Untitled project by @fidel | Stardance
|
1792723749.6458151
|
1793328549.6458151
|
|
2787
|
Untitled project by @vtellamsetty | Stardance
|
vtellamsetty
|
0
|
0.0
|
0
|
[]
|
[]
|
Title: Untitled project by @vtellamsetty | Stardan Title: Untitled project by @vtellamsetty | Stardance...
|
1792723750.484426
|
1793328550.484426
|
|
2123
|
My awesome macropad! by @Noelle | Stardance
|
Noelle
|
0
|
0.0
|
0
|
[]
|
[]
|
Title: My awesome macropad! by @Noelle | Stardance
|
1792723751.3133087
|
1793328551.3133087
|
|
22930
|
My awesome macropad! by @Ayesha | Stardance
|
Ayesha
|
0
|
0.0
|
0
|
[]
|
[]
|
Title: My awesome macropad! by @Ayesha | Stardance
|
1792723752.171084
|
1793328552.171084
|
|
20466
|
My first slack bot! by @sri_dudi | Stardance
|
sri_dudi
|
0
|
0.0
|
0
|
[]
|
[]
|
Title: My first slack bot! by @sri_dudi | Stardanc Title: My first slack bot! by @sri_dudi | Stardance...
|
1792723753.0171762
|
1793328553.0171762
|
|
33638
|
Untitled by @justin0711 | Stardance
|
justin0711
|
0
|
0.0
|
0
|
[]
|
[]
|
Title: Untitled by @justin0711 | Stardance
|
1792723753.85572
|
1793328553.85572
|