This media is not supported in your browser
VIEW IN TELEGRAM
📦 pacifio/ui
ui
ui is the design language that teaches AI coding agents how to build beautiful, dense, AMOLED-black interfaces. Instead of manually copying and pasting CSS components, this project operates as a specialized skill for tools like Claude Code. It provides a structured set of design rules and token references that guide your favorite AI assistant to generate consistent, ultra-compact layouts in plain HTML, Tailwind, or React. It solves the messy, inconsistent UI code that agents typically write by giving them a clear aesthetic framework to follow. You get pixel-perfect, dark-mode designs built directly by your AI companion.
🆔 @hackernewsgithubprojects
ui
ui is the design language that teaches AI coding agents how to build beautiful, dense, AMOLED-black interfaces. Instead of manually copying and pasting CSS components, this project operates as a specialized skill for tools like Claude Code. It provides a structured set of design rules and token references that guide your favorite AI assistant to generate consistent, ultra-compact layouts in plain HTML, Tailwind, or React. It solves the messy, inconsistent UI code that agents typically write by giving them a clear aesthetic framework to follow. You get pixel-perfect, dark-mode designs built directly by your AI companion.
🆔 @hackernewsgithubprojects
This media is not supported in your browser
VIEW IN TELEGRAM
📦 b1u3b01t/design-playground
Design Playground
You can now visually redesign your React components using local AI, right inside your Next.js project. A developer-focused tool called design-playground installs nested inside your existing app folder, leaving your main package configuration completely untouched. Once started, it automatically scans your workspace to find your React components and loads them onto an infinite, interactive canvas. From there, you can drag your components around, write a quick prompt, and watch Cursor or Claude Code generate layout and style variations side-by-side. When you find a design you like, you simply copy the generated code directly back into your project.
📰 https://news.ycombinator.com/item?id=48750398
🆔 @hackernewsgithubprojects
Design Playground
You can now visually redesign your React components using local AI, right inside your Next.js project. A developer-focused tool called design-playground installs nested inside your existing app folder, leaving your main package configuration completely untouched. Once started, it automatically scans your workspace to find your React components and loads them onto an infinite, interactive canvas. From there, you can drag your components around, write a quick prompt, and watch Cursor or Claude Code generate layout and style variations side-by-side. When you find a design you like, you simply copy the generated code directly back into your project.
📰 https://news.ycombinator.com/item?id=48750398
🆔 @hackernewsgithubprojects
This media is not supported in your browser
VIEW IN TELEGRAM
📦 elinglijiaoqiao/presentation-ppt-maker
Presentation PPT Maker
Presentation-ppt-maker is a structured slide generator that turns a pile of academic papers into a complete, ready-to-present slide deck. Instead of relying on a single AI prompt that might hallucinate facts or create chaotic layouts, this tool coordinates four specialized agents to extract figures, organize claims, draft a slide-by-slide narrative, and programmatically generate the final presentation file. Its standout strength is a mandatory visual verification gate that actually opens image files to ensure figures match the slide text before placing them, automatically splitting crowded slides if a diagram is too small to read. You get perfectly cited, beautifully organized slides with complete speaker notes ready for your next talk.
🆔 @hackernewsgithubprojects
Presentation PPT Maker
Presentation-ppt-maker is a structured slide generator that turns a pile of academic papers into a complete, ready-to-present slide deck. Instead of relying on a single AI prompt that might hallucinate facts or create chaotic layouts, this tool coordinates four specialized agents to extract figures, organize claims, draft a slide-by-slide narrative, and programmatically generate the final presentation file. Its standout strength is a mandatory visual verification gate that actually opens image files to ensure figures match the slide text before placing them, automatically splitting crowded slides if a diagram is too small to read. You get perfectly cited, beautifully organized slides with complete speaker notes ready for your next talk.
🆔 @hackernewsgithubprojects
This media is not supported in your browser
VIEW IN TELEGRAM
📦 ramziddin/solid-skills
Solid Skills
Transform junior-level code into senior-engineer quality software using an AI agent skill that enforces rigorous coding standards. This repository provides a structured set of rules and reference documents that guide AI coding assistants to follow test-driven development, write tiny methods under ten lines, and completely avoid raw primitive types for domain concepts. Instead of allowing messy code, it prompts the AI to wrap everything from emails to money in dedicated value objects, catch code smells automatically, and apply design patterns naturally. It is the perfect tool for developers who want automated, clean, and highly maintainable architecture right out of the box.
🆔 @hackernewsgithubprojects
Solid Skills
Transform junior-level code into senior-engineer quality software using an AI agent skill that enforces rigorous coding standards. This repository provides a structured set of rules and reference documents that guide AI coding assistants to follow test-driven development, write tiny methods under ten lines, and completely avoid raw primitive types for domain concepts. Instead of allowing messy code, it prompts the AI to wrap everything from emails to money in dedicated value objects, catch code smells automatically, and apply design patterns naturally. It is the perfect tool for developers who want automated, clean, and highly maintainable architecture right out of the box.
🆔 @hackernewsgithubprojects
This media is not supported in your browser
VIEW IN TELEGRAM
📦 jtydhr88/comfytv
ComfyTV
ComfyTV is the canvas-based app that finally turns ComfyUI into an intuitive, node-by-node creation playground. Instead of running a massive, tangled workflow that recalculates from scratch every time you tweak a setting, this clever setup lets you run each stage individually. You can generate an image, edit it, paint in details, and convert it to video in a structured pipeline where downstream steps simply use snapshots of previous outputs. It gives you rich built-in tools like a 3D camera, panorama viewer, and mask painter without ever leaving the canvas. Grab this tool to finally make your local generation workflow feel fast, organized, and truly interactive.
🆔 @hackernewsgithubprojects
ComfyTV
ComfyTV is the canvas-based app that finally turns ComfyUI into an intuitive, node-by-node creation playground. Instead of running a massive, tangled workflow that recalculates from scratch every time you tweak a setting, this clever setup lets you run each stage individually. You can generate an image, edit it, paint in details, and convert it to video in a structured pipeline where downstream steps simply use snapshots of previous outputs. It gives you rich built-in tools like a 3D camera, panorama viewer, and mask painter without ever leaving the canvas. Grab this tool to finally make your local generation workflow feel fast, organized, and truly interactive.
🆔 @hackernewsgithubprojects
This media is not supported in your browser
VIEW IN TELEGRAM
📦 sermuns/ratatuefi
ratatuefi
Build sleek terminal dashboards that boot directly on your bare metal computer without any operating system running underneath. A clever project called ratatuefi bridges the gap between the popular Ratatui terminal UI library and raw UEFI firmware. It gives you a minimal, zero-bloat backend written in Rust, allowing you to draw styled terminal interfaces straight from your motherboard's bootloader. By mapping interface colors and cursor positions directly to UEFI console outputs, you can run gorgeous, lightweight diagnostic tools or custom boot menus. It is the perfect weekend rabbit hole if you want to make your bare-metal booting sequence look incredibly cool.
🆔 @hackernewsgithubprojects
ratatuefi
Build sleek terminal dashboards that boot directly on your bare metal computer without any operating system running underneath. A clever project called ratatuefi bridges the gap between the popular Ratatui terminal UI library and raw UEFI firmware. It gives you a minimal, zero-bloat backend written in Rust, allowing you to draw styled terminal interfaces straight from your motherboard's bootloader. By mapping interface colors and cursor positions directly to UEFI console outputs, you can run gorgeous, lightweight diagnostic tools or custom boot menus. It is the perfect weekend rabbit hole if you want to make your bare-metal booting sequence look incredibly cool.
🆔 @hackernewsgithubprojects
This media is not supported in your browser
VIEW IN TELEGRAM
📦 cedarconnor/spag4d
spag4d
You can now transform a single flat three-sixty-degree panoramic photo into a fully explorable three-D Gaussian Splat scene in as little as two seconds. A clever tool called spag4d uses advanced depth-estimation models to calculate spherical geometry and project flat pixels directly into three-D space. It handles everything from simple depth projection to complex multi-face stitching using Apple's SHARP model. If your scene has structural holes where the camera couldn't see, the software can even generate synthetic walkthrough videos to intelligently patch and fill those gaps. It is an incredibly fast way to bring flat panoramic memories to life.
🆔 @hackernewsgithubprojects
spag4d
You can now transform a single flat three-sixty-degree panoramic photo into a fully explorable three-D Gaussian Splat scene in as little as two seconds. A clever tool called spag4d uses advanced depth-estimation models to calculate spherical geometry and project flat pixels directly into three-D space. It handles everything from simple depth projection to complex multi-face stitching using Apple's SHARP model. If your scene has structural holes where the camera couldn't see, the software can even generate synthetic walkthrough videos to intelligently patch and fill those gaps. It is an incredibly fast way to bring flat panoramic memories to life.
🆔 @hackernewsgithubprojects
This media is not supported in your browser
VIEW IN TELEGRAM
📦 arteemg/autoswarm
AutoSwarm
Autoswarm is the open-source tool that finally makes your local artificial intelligence models smarter over time just by using them. It acts as a clever proxy sitting in front of your offline models, silently logging your chats and running a background review to distill valuable lessons into a custom skillbook. The next time you ask a question, it automatically injects those lessons back into the prompt, and it even prunes away old strategies that did not work out. It is a brilliant way to make a basic offline setup continuously learn from its own mistakes without burning a ton of extra computing power.
🆔 @hackernewsgithubprojects
AutoSwarm
Autoswarm is the open-source tool that finally makes your local artificial intelligence models smarter over time just by using them. It acts as a clever proxy sitting in front of your offline models, silently logging your chats and running a background review to distill valuable lessons into a custom skillbook. The next time you ask a question, it automatically injects those lessons back into the prompt, and it even prunes away old strategies that did not work out. It is a brilliant way to make a basic offline setup continuously learn from its own mistakes without burning a ton of extra computing power.
🆔 @hackernewsgithubprojects
This media is not supported in your browser
VIEW IN TELEGRAM
📦 jd-opensource/joyai-echo
JoyAI-Echo
JoyAI-Echo can generate synchronized, multi-shot video and audio sequences up to five minutes long while keeping character faces and voices perfectly consistent across every scene. It solves the massive headache of identity drift and audio mismatch in AI-generated films using a smart cross-modal memory bank that remembers what characters look and sound like. Even better, it runs over seven times faster than older systems, allowing you to quickly create editable stories from a single text prompt. If you want to experiment with long-form, coherent AI filmmaking, you can run JoyAI-Echo locally or use its official ComfyUI node integration.
🆔 @hackernewsgithubprojects
JoyAI-Echo
JoyAI-Echo can generate synchronized, multi-shot video and audio sequences up to five minutes long while keeping character faces and voices perfectly consistent across every scene. It solves the massive headache of identity drift and audio mismatch in AI-generated films using a smart cross-modal memory bank that remembers what characters look and sound like. Even better, it runs over seven times faster than older systems, allowing you to quickly create editable stories from a single text prompt. If you want to experiment with long-form, coherent AI filmmaking, you can run JoyAI-Echo locally or use its official ComfyUI node integration.
🆔 @hackernewsgithubprojects
This media is not supported in your browser
VIEW IN TELEGRAM
📦 robzilla1738/supergoal
Supergoal
Supergoal lets you run massive, complex programming tasks entirely on autopilot using Claude Code or Codex. Instead of baby-sitting an AI coding agent step-by-step, you run a single command describing what you want to build. The tool scans your codebase, anticipates technical risks, and splits the work into logical phases. It then gives you one final command to paste, which launches an autonomous execution loop. If a step fails, the system automatically attempts a self-healing recovery using a three-strike retry protocol. Once finished, it runs a rigorous final audit to double-check that every single change is fully functional.
🆔 @hackernewsgithubprojects
Supergoal
Supergoal lets you run massive, complex programming tasks entirely on autopilot using Claude Code or Codex. Instead of baby-sitting an AI coding agent step-by-step, you run a single command describing what you want to build. The tool scans your codebase, anticipates technical risks, and splits the work into logical phases. It then gives you one final command to paste, which launches an autonomous execution loop. If a step fails, the system automatically attempts a self-healing recovery using a three-strike retry protocol. Once finished, it runs a rigorous final audit to double-check that every single change is fully functional.
🆔 @hackernewsgithubprojects
This media is not supported in your browser
VIEW IN TELEGRAM
📦 buzhangsan/skill-manager
Skill Manager
You can now instantly browse and download over thirty-one thousand community-made skills directly into your Claude Code programming assistant. The skill-manager project solves the headache of manually finding and configuring custom capabilities for your AI agent by packing a massive, searchable database right into your local environment. Instead of complex setups, it uses a smart weighted search to find what you need in under a second, and automatically pulls down complete folders using lightning-fast subversion exports or git fallbacks. It is the ultimate plug-and-play upgrade to make your AI assistant incredibly capable in just one click.
🆔 @hackernewsgithubprojects
Skill Manager
You can now instantly browse and download over thirty-one thousand community-made skills directly into your Claude Code programming assistant. The skill-manager project solves the headache of manually finding and configuring custom capabilities for your AI agent by packing a massive, searchable database right into your local environment. Instead of complex setups, it uses a smart weighted search to find what you need in under a second, and automatically pulls down complete folders using lightning-fast subversion exports or git fallbacks. It is the ultimate plug-and-play upgrade to make your AI assistant incredibly capable in just one click.
🆔 @hackernewsgithubprojects
This media is not supported in your browser
VIEW IN TELEGRAM
📦 xxm19/hommi
HoMMI
HoMMI is the robot learning system that trains mobile machines to coordinate their entire bodies directly from human demonstrations. Instead of relying on rigid, pre-programmed trajectories, this project uses specialized camera data and diffusion policies to teach robots natural movement. By capturing how humans interact with the world and translating those demonstrations into real-time whole-body control, the robot learns to seamlessly coordinate its base, torso, and arms all at once. It turns complex, multi-joint coordination into something a robot can learn organically, bringing us one step closer to helper robots that move with fluid, human-like agility.
🆔 @hackernewsgithubprojects
HoMMI
HoMMI is the robot learning system that trains mobile machines to coordinate their entire bodies directly from human demonstrations. Instead of relying on rigid, pre-programmed trajectories, this project uses specialized camera data and diffusion policies to teach robots natural movement. By capturing how humans interact with the world and translating those demonstrations into real-time whole-body control, the robot learns to seamlessly coordinate its base, torso, and arms all at once. It turns complex, multi-joint coordination into something a robot can learn organically, bringing us one step closer to helper robots that move with fluid, human-like agility.
🆔 @hackernewsgithubprojects
This media is not supported in your browser
VIEW IN TELEGRAM
📦 evo-design/proto-language
Proto-Language
Scientists are now designing custom DNA, RNA, and proteins using constraint-based programming. An open-source Python framework called proto-language lets you specify the exact biological properties you need, then runs an intelligent search loop to generate sequences that match. It connects directly with advanced AI models and structural predictors to score candidate designs automatically. Instead of manual trial and error, you define what your biological construct must do, and the system handles the complex search. It is an incredibly smart way to co-design structure and sequence. If you want to explore the future of generative biology, you should definitely check out this repository.
🆔 @hackernewsgithubprojects
Proto-Language
Scientists are now designing custom DNA, RNA, and proteins using constraint-based programming. An open-source Python framework called proto-language lets you specify the exact biological properties you need, then runs an intelligent search loop to generate sequences that match. It connects directly with advanced AI models and structural predictors to score candidate designs automatically. Instead of manual trial and error, you define what your biological construct must do, and the system handles the complex search. It is an incredibly smart way to co-design structure and sequence. If you want to explore the future of generative biology, you should definitely check out this repository.
🆔 @hackernewsgithubprojects
This media is not supported in your browser
VIEW IN TELEGRAM
📦 psalias2006/gpu-hot
gpu-hot
Your NVIDIA graphics cards are probably running hot, but keeping tabs on them shouldn't require a heavyweight monitoring system. With gpu-hot, you can spin up a self-hosted, real-time web dashboard inside a Docker container using a single line of code. It instantly auto-detects all your graphics cards, tracking everything from temperature and power draw to active processes and fan speeds. If you have multiple machines, you can even link them together into a unified central hub. It's a clean, zero-bloat tool that lets you keep your hardware running safely during heavy rendering or training runs.
🆔 @hackernewsgithubprojects
gpu-hot
Your NVIDIA graphics cards are probably running hot, but keeping tabs on them shouldn't require a heavyweight monitoring system. With gpu-hot, you can spin up a self-hosted, real-time web dashboard inside a Docker container using a single line of code. It instantly auto-detects all your graphics cards, tracking everything from temperature and power draw to active processes and fan speeds. If you have multiple machines, you can even link them together into a unified central hub. It's a clean, zero-bloat tool that lets you keep your hardware running safely during heavy rendering or training runs.
🆔 @hackernewsgithubprojects
This media is not supported in your browser
VIEW IN TELEGRAM
📦 blockrunai/clawrouter
ClawRouter
ClawRouter is the smart local router that allows autonomous AI agents to operate and transact completely on their own. Since software agents cannot sign up for credit cards or create traditional developer accounts, this tool changes the game by replacing API keys with local wallet signatures and settling pay-per-request fees using stablecoin micropayments on the Base and Solana blockchains. Operating entirely on your local machine with sub-millisecond latencies, it automatically evaluates incoming prompts across fifteen dimensions to route tasks to the cheapest capable model. This setup can slash average AI costs by over ninety percent while keeping your agent entirely independent.
🆔 @hackernewsgithubprojects
ClawRouter
ClawRouter is the smart local router that allows autonomous AI agents to operate and transact completely on their own. Since software agents cannot sign up for credit cards or create traditional developer accounts, this tool changes the game by replacing API keys with local wallet signatures and settling pay-per-request fees using stablecoin micropayments on the Base and Solana blockchains. Operating entirely on your local machine with sub-millisecond latencies, it automatically evaluates incoming prompts across fifteen dimensions to route tasks to the cheapest capable model. This setup can slash average AI costs by over ninety percent while keeping your agent entirely independent.
🆔 @hackernewsgithubprojects
This media is not supported in your browser
VIEW IN TELEGRAM
📦 qwenlm/qwen-image-bench
qwen-image-bench
Judging generated images just got a lot more honest. The qwen-image-bench repository provides an evaluation toolkit that uses a specialized judge model to score AI-generated pictures across fifty-six fine-grained criteria. Instead of relying on vague vibes, it runs your images through a strict scoring system covering details like anatomical realism, color harmony, and text rendering. You just feed it your prompts and image paths, and it spits out clean spreadsheet reports detailing where your model excels or fails. It is a brilliant way to actually quantify how realistic or creative an image generator is without the guesswork. Check it out and see how your models rank.
🆔 @hackernewsgithubprojects
qwen-image-bench
Judging generated images just got a lot more honest. The qwen-image-bench repository provides an evaluation toolkit that uses a specialized judge model to score AI-generated pictures across fifty-six fine-grained criteria. Instead of relying on vague vibes, it runs your images through a strict scoring system covering details like anatomical realism, color harmony, and text rendering. You just feed it your prompts and image paths, and it spits out clean spreadsheet reports detailing where your model excels or fails. It is a brilliant way to actually quantify how realistic or creative an image generator is without the guesswork. Check it out and see how your models rank.
🆔 @hackernewsgithubprojects
Media is too big
VIEW IN TELEGRAM
📦 leigest519/opengame
OpenGame
Build fully playable web games from a single text prompt using a framework that actually works. While typical code assistants struggle with broken scenes and mismatched files when writing games, opengame overcomes this by introducing a reusable system called Game Skill. This system starts with a solid blueprint template and then runs the game in a sandbox to catch and repair visual bugs, broken links, and console errors until everything runs smoothly. The framework uses a custom model called GameCoder to handle the complex game engine logic. You get a complete, ready-to-play web game generated entirely from your description.
🆔 @hackernewsgithubprojects
OpenGame
Build fully playable web games from a single text prompt using a framework that actually works. While typical code assistants struggle with broken scenes and mismatched files when writing games, opengame overcomes this by introducing a reusable system called Game Skill. This system starts with a solid blueprint template and then runs the game in a sandbox to catch and repair visual bugs, broken links, and console errors until everything runs smoothly. The framework uses a custom model called GameCoder to handle the complex game engine logic. You get a complete, ready-to-play web game generated entirely from your description.
🆔 @hackernewsgithubprojects
This media is not supported in your browser
VIEW IN TELEGRAM
📦 ymichael/bb
bb
bb is the agentic IDE that finally lets your coding assistants control the editor itself. Instead of just pasting generated code blocks into a static screen, this workspace acts as a programmable environment where your favorite AI assistants can run commands, spawn new tasks, and navigate files right alongside you. You can follow their progress live in visual threads, step in to steer the wheel whenever you want, and let them automate the tedious steps like closing out their own sessions. It is the ultimate playground for building a truly collaborative, self-operating development setup.
📰 https://news.ycombinator.com/item?id=48574178
🆔 @hackernewsgithubprojects
bb
bb is the agentic IDE that finally lets your coding assistants control the editor itself. Instead of just pasting generated code blocks into a static screen, this workspace acts as a programmable environment where your favorite AI assistants can run commands, spawn new tasks, and navigate files right alongside you. You can follow their progress live in visual threads, step in to steer the wheel whenever you want, and let them automate the tedious steps like closing out their own sessions. It is the ultimate playground for building a truly collaborative, self-operating development setup.
📰 https://news.ycombinator.com/item?id=48574178
🆔 @hackernewsgithubprojects
This media is not supported in your browser
VIEW IN TELEGRAM
📦 localemu/localemu
LocalEmu
Run over a hundred AWS services directly on your laptop without ever creating an Amazon account, configuring security tokens, or worrying about hidden telemetry. This project lets you spin up a complete mock cloud environment locally with just a single command. It acts as a perfect drop-in replacement for your existing deployment workflows, meaning your command-line tools, deployment scripts, and infrastructure-as-code configurations will just work right out of the box. You get a fully offline, ultra-fast playground to test cloud applications without any of the typical cloud-provider headaches. Download it today and start building offline.
📰 https://news.ycombinator.com/item?id=48340115
🆔 @hackernewsgithubprojects
LocalEmu
Run over a hundred AWS services directly on your laptop without ever creating an Amazon account, configuring security tokens, or worrying about hidden telemetry. This project lets you spin up a complete mock cloud environment locally with just a single command. It acts as a perfect drop-in replacement for your existing deployment workflows, meaning your command-line tools, deployment scripts, and infrastructure-as-code configurations will just work right out of the box. You get a fully offline, ultra-fast playground to test cloud applications without any of the typical cloud-provider headaches. Download it today and start building offline.
📰 https://news.ycombinator.com/item?id=48340115
🆔 @hackernewsgithubprojects
This media is not supported in your browser
VIEW IN TELEGRAM
📦 johnriceml/clawport-ui
ClawPort UI
clawport-ui is the visual command center that finally gives you a unified dashboard to manage, monitor, and chat with your Claude Code agent teams. Instead of juggling terminal windows and configuration files, this tool hooks right into your local OpenClaw gateway to build an interactive org chart, a drag-and-drop kanban board, and direct agent chat featuring vision and voice playback. You can visually map out your entire agent hierarchy, stream real-time logs, and view token costs without needing separate API keys. It makes managing automated AI teams feel like running a normal software department. Check it out to bring your local AI agents to life.
🆔 @hackernewsgithubprojects
ClawPort UI
clawport-ui is the visual command center that finally gives you a unified dashboard to manage, monitor, and chat with your Claude Code agent teams. Instead of juggling terminal windows and configuration files, this tool hooks right into your local OpenClaw gateway to build an interactive org chart, a drag-and-drop kanban board, and direct agent chat featuring vision and voice playback. You can visually map out your entire agent hierarchy, stream real-time logs, and view token costs without needing separate API keys. It makes managing automated AI teams feel like running a normal software department. Check it out to bring your local AI agents to life.
🆔 @hackernewsgithubprojects