This media is not supported in your browser
VIEW IN TELEGRAM
π¦ ninkch/dsh-infinite_canvas
Infinite Canvas: The AI Film Studio
Infinite Canvas lets you turn a single sentence into a finished, dubbed short film without writing a single line of code. It is a node-based studio that sits inside your chat interface, acting as a digital writers room and editing bay all at once. You talk to it like a director, and it builds the script, storyboards, and character designs on an infinite board you can drag around. The coolest part is that it remembers your characters across episodes, so the lead actor does not change shirts just because the scene cut. It even handles the camera angles and lighting styles for you.
π @hackernewsgithubprojects
Infinite Canvas: The AI Film Studio
Infinite Canvas lets you turn a single sentence into a finished, dubbed short film without writing a single line of code. It is a node-based studio that sits inside your chat interface, acting as a digital writers room and editing bay all at once. You talk to it like a director, and it builds the script, storyboards, and character designs on an infinite board you can drag around. The coolest part is that it remembers your characters across episodes, so the lead actor does not change shirts just because the scene cut. It even handles the camera angles and lighting styles for you.
π @hackernewsgithubprojects
This media is not supported in your browser
VIEW IN TELEGRAM
π¦ backenly/backenly
Backenly: The Backend That Builds Itself
Backenly is the autonomous backend platform that lets your AI coding agent actually run the app. While other tools just spit out code snippets, Backenly provides a live environment where the agent can create tables, define routes, and handle user logins right in front of you. It works over a protocol called MCP, which acts like a universal plug for your AI to safely interact with the database and server logic. The real magic, though, is the safety net. Every single change the agent makes is tracked, verified, and fully reversible, meaning you can see exactly what happened and roll it back if the AI goes off the rails.
π @hackernewsgithubprojects
Backenly: The Backend That Builds Itself
Backenly is the autonomous backend platform that lets your AI coding agent actually run the app. While other tools just spit out code snippets, Backenly provides a live environment where the agent can create tables, define routes, and handle user logins right in front of you. It works over a protocol called MCP, which acts like a universal plug for your AI to safely interact with the database and server logic. The real magic, though, is the safety net. Every single change the agent makes is tracked, verified, and fully reversible, meaning you can see exactly what happened and roll it back if the AI goes off the rails.
π @hackernewsgithubprojects
This media is not supported in your browser
VIEW IN TELEGRAM
π¦ michi71/picovintagesynthcollection
Thirteen Classic Synths on One Tiny Chip
Thirteen legendary synthesizers, from the Minimoog to the Korg M1, run natively on a single microcontroller chip. This project, called the Pico Vintage Synth Collection, doesn't fake the original hardware; it rewrites the vintage engines from scratch in C++ to run directly on the silicon. The surprise here is the scale: these are not simplified demos, but full implementations that play the original sound data, all squeezed onto a board with just half a megabyte of memory. It solves the problem of needing expensive, fragile vintage gear by turning a cheap, modern board into a reliable, portable instrument.
π @hackernewsgithubprojects
Thirteen Classic Synths on One Tiny Chip
Thirteen legendary synthesizers, from the Minimoog to the Korg M1, run natively on a single microcontroller chip. This project, called the Pico Vintage Synth Collection, doesn't fake the original hardware; it rewrites the vintage engines from scratch in C++ to run directly on the silicon. The surprise here is the scale: these are not simplified demos, but full implementations that play the original sound data, all squeezed onto a board with just half a megabyte of memory. It solves the problem of needing expensive, fragile vintage gear by turning a cheap, modern board into a reliable, portable instrument.
π @hackernewsgithubprojects
This media is not supported in your browser
VIEW IN TELEGRAM
π¦ gair-nlp/801-30b
801-30b: The AI That Built Itself
801-30b is the frontier model project that proved recursive self-improvement works during pre-training. Most AI teams treat training like a black box, but this team built a system where software agents constantly debug the infrastructure and data. Instead of guessing what is wrong, the agents find the exact code or data issue causing training problems. This means the model improves itself while it learns. It is the first time we have seen this level of automation on a massive scale. The result is a state-of-the-art model that shows how much headroom is left for future improvements.
π @hackernewsgithubprojects
801-30b: The AI That Built Itself
801-30b is the frontier model project that proved recursive self-improvement works during pre-training. Most AI teams treat training like a black box, but this team built a system where software agents constantly debug the infrastructure and data. Instead of guessing what is wrong, the agents find the exact code or data issue causing training problems. This means the model improves itself while it learns. It is the first time we have seen this level of automation on a massive scale. The result is a state-of-the-art model that shows how much headroom is left for future improvements.
π @hackernewsgithubprojects
This media is not supported in your browser
VIEW IN TELEGRAM
π¦ alexsergivan/kwant
Kwant: Your AI Team
Build a private crew of digital workers that actually finish jobs without you hovering. Kwant runs a self-hosted team of bots that hand tasks to each other and only mark work done after they verify it themselves. The coolest part is the second check: a separate bot re-runs the tests on a clean copy to prove the result is real, not just a promise. This turns your own computer into a reliable staff that handles browsing, coding, and scheduling. It is open source and runs on your hardware, so you keep total control over your data. Stop renting chatbots.
π @hackernewsgithubprojects
Kwant: Your AI Team
Build a private crew of digital workers that actually finish jobs without you hovering. Kwant runs a self-hosted team of bots that hand tasks to each other and only mark work done after they verify it themselves. The coolest part is the second check: a separate bot re-runs the tests on a clean copy to prove the result is real, not just a promise. This turns your own computer into a reliable staff that handles browsing, coding, and scheduling. It is open source and runs on your hardware, so you keep total control over your data. Stop renting chatbots.
π @hackernewsgithubprojects
Media is too big
VIEW IN TELEGRAM
π¦ agent-analytics/awesome-multi-agent-orchestrators
The Map for Your AI Agent Team
There is one place where you can actually see how the entire industry is building software that manages other software. That is the real power of the awesome multi-agent orchestrators list. It is not just a directory of tools; it is a living map of how we are learning to coordinate dozens of artificial intelliges working side by side on your code. You will find frameworks from major tech giants sitting right next to tiny, clever scripts that keep agents from making mistakes. If you are building teams of bots, this is your single source of truth for what is actually working.
π @hackernewsgithubprojects
The Map for Your AI Agent Team
There is one place where you can actually see how the entire industry is building software that manages other software. That is the real power of the awesome multi-agent orchestrators list. It is not just a directory of tools; it is a living map of how we are learning to coordinate dozens of artificial intelliges working side by side on your code. You will find frameworks from major tech giants sitting right next to tiny, clever scripts that keep agents from making mistakes. If you are building teams of bots, this is your single source of truth for what is actually working.
π @hackernewsgithubprojects
This media is not supported in your browser
VIEW IN TELEGRAM
π¦ simd-ai/brae
brae
Run your OpenFOAM simulations entirely on the GPU and watch the speed soar up to thirty times faster than standard GPU-accelerated tools. Brae moves the entire computational fluid dynamics workload off the traditional processor and onto modern graphics hardware, handling everything from complex mesh geometry to turbulence models directly on the device. This matters because engineering simulations often take days to finish; by shifting the heavy lifting, you can iterate on designs in hours instead. The result is a massive time saver for engineers who need precise flow data without waiting weeks for results.
π @hackernewsgithubprojects
brae
Run your OpenFOAM simulations entirely on the GPU and watch the speed soar up to thirty times faster than standard GPU-accelerated tools. Brae moves the entire computational fluid dynamics workload off the traditional processor and onto modern graphics hardware, handling everything from complex mesh geometry to turbulence models directly on the device. This matters because engineering simulations often take days to finish; by shifting the heavy lifting, you can iterate on designs in hours instead. The result is a massive time saver for engineers who need precise flow data without waiting weeks for results.
π @hackernewsgithubprojects
This media is not supported in your browser
VIEW IN TELEGRAM
π¦ mileson/chaojifeng-video-content-creator
Chaojifeng Video Content Creator
Chaojifeng Video Content Creator turns a simple chat prompt into a fully produced Chinese-language video. This agent skill handles the entire workflow, from writing the script and planning the storyboard to scrubbing filler words from recorded audio and timing visual effects against real subtitle data. The standout feature is its library of one hundred and forty-eight native motion effects, which it automatically syncs to your audio track so you never have to guess the timing. It even checks your cuts to ensure you are not accidentally clipping speech.
π @hackernewsgithubprojects
Chaojifeng Video Content Creator
Chaojifeng Video Content Creator turns a simple chat prompt into a fully produced Chinese-language video. This agent skill handles the entire workflow, from writing the script and planning the storyboard to scrubbing filler words from recorded audio and timing visual effects against real subtitle data. The standout feature is its library of one hundred and forty-eight native motion effects, which it automatically syncs to your audio track so you never have to guess the timing. It even checks your cuts to ensure you are not accidentally clipping speech.
π @hackernewsgithubprojects
This media is not supported in your browser
VIEW IN TELEGRAM
π¦ scottduncanai/public-chemical-manufacturing-datasets
Real Plant Data for AI
Government permit filings are quietly exposing the engineering blueprints of real industrial water treatment plants. This repository collects those public records, giving developers actual piping diagrams and live process data that were previously locked away in private files. It solves a major gap for anyone building AI to monitor chemical processes, offering real-world examples of faults and equipment behavior. You get the ground truth needed to test your models against physics, not just math. Now you can build reliable tools that actually understand how factories run.
π @hackernewsgithubprojects
Real Plant Data for AI
Government permit filings are quietly exposing the engineering blueprints of real industrial water treatment plants. This repository collects those public records, giving developers actual piping diagrams and live process data that were previously locked away in private files. It solves a major gap for anyone building AI to monitor chemical processes, offering real-world examples of faults and equipment behavior. You get the ground truth needed to test your models against physics, not just math. Now you can build reliable tools that actually understand how factories run.
π @hackernewsgithubprojects
Media is too big
VIEW IN TELEGRAM
π¦ jasonpersinger/ghoulbox-fm1-dungeon-synth
Ghoulbox FM1 Dungeon Synth
A tiny keyboard can compose entire medieval soundscapes by itself. Ghoulbox is custom software for a pocket synthesizer that turns it into a dedicated dungeon music machine. It strips away modern dance beats and focuses entirely on dark, medieval, and fantasy tones. The coolest part is a feature called Dream. You just pick a mood and press a key, and the device writes a slow, evolving piece of music for you. It handles drums, strings, and drones automatically, creating a unique track every time. It is perfect for people who want instant, atmospheric music without complex programming.
π @hackernewsgithubprojects
Ghoulbox FM1 Dungeon Synth
A tiny keyboard can compose entire medieval soundscapes by itself. Ghoulbox is custom software for a pocket synthesizer that turns it into a dedicated dungeon music machine. It strips away modern dance beats and focuses entirely on dark, medieval, and fantasy tones. The coolest part is a feature called Dream. You just pick a mood and press a key, and the device writes a slow, evolving piece of music for you. It handles drums, strings, and drones automatically, creating a unique track every time. It is perfect for people who want instant, atmospheric music without complex programming.
π @hackernewsgithubprojects
This media is not supported in your browser
VIEW IN TELEGRAM
π¦ tthanh2k6/turbo-browser-mcp
How Turbo Browser MCP Saves AI Tokens
Turbo Browser MCP is the browser automation server that makes AI agents faster by drastically cutting down the amount of data they process. It replaces dozens of small, slow commands with a few powerful tools that handle complex tasks like filling entire forms or managing multiple tabs in a single step. The real magic happens when it shows the AI only the parts of the page that actually changed, rather than reloading the whole screen every time. This tiny tweak saves a massive amount of processing power and keeps your chat history clean. It is a clever way to build smarter, quicker web automation without overwhelming your system.
π° https://news.ycombinator.com/item?id=50503930
π @hackernewsgithubprojects
How Turbo Browser MCP Saves AI Tokens
Turbo Browser MCP is the browser automation server that makes AI agents faster by drastically cutting down the amount of data they process. It replaces dozens of small, slow commands with a few powerful tools that handle complex tasks like filling entire forms or managing multiple tabs in a single step. The real magic happens when it shows the AI only the parts of the page that actually changed, rather than reloading the whole screen every time. This tiny tweak saves a massive amount of processing power and keeps your chat history clean. It is a clever way to build smarter, quicker web automation without overwhelming your system.
π° https://news.ycombinator.com/item?id=50503930
π @hackernewsgithubprojects
This media is not supported in your browser
VIEW IN TELEGRAM
π¦ olovalabs/kathamo
Kathamo: The terminal for AI agents
Kathamo is the native terminal that finally tells you when your AI coder is done. You know that awkward feeling when you spawn an agent to fix a bug and then just sit there, wondering if it crashed, finished, or is stuck? Kathamo fixes that. It is a fast, built-in terminal that runs multiple coding agents side by side, but the magic is the attention system. It tracks exactly when an agent is working, blocked, or finished, and only pings you when you actually need to look. It even remembers your exact workspace when you come back, so your tabs and code are right where you left them.
π @hackernewsgithubprojects
Kathamo: The terminal for AI agents
Kathamo is the native terminal that finally tells you when your AI coder is done. You know that awkward feeling when you spawn an agent to fix a bug and then just sit there, wondering if it crashed, finished, or is stuck? Kathamo fixes that. It is a fast, built-in terminal that runs multiple coding agents side by side, but the magic is the attention system. It tracks exactly when an agent is working, blocked, or finished, and only pings you when you actually need to look. It even remembers your exact workspace when you come back, so your tabs and code are right where you left them.
π @hackernewsgithubprojects
This media is not supported in your browser
VIEW IN TELEGRAM
π¦ davnords/loma
LoMa: The Smarter Way to Match Images
LoMa, a new image matching tool, spots identical details across photos even when they look completely different to the human eye. It was built by researchers at several major Swedish universities to solve a common problem: computers struggle to link points in one picture to the same points in another if the angle or lighting changes. By finding these invisible connections, LoMa helps robots map new rooms or allows apps to find a specific building in a photo. It is essentially a drop-in upgrade for existing vision systems that need to know exactly where they are in the real world.
π @hackernewsgithubprojects
LoMa: The Smarter Way to Match Images
LoMa, a new image matching tool, spots identical details across photos even when they look completely different to the human eye. It was built by researchers at several major Swedish universities to solve a common problem: computers struggle to link points in one picture to the same points in another if the angle or lighting changes. By finding these invisible connections, LoMa helps robots map new rooms or allows apps to find a specific building in a photo. It is essentially a drop-in upgrade for existing vision systems that need to know exactly where they are in the real world.
π @hackernewsgithubprojects
This media is not supported in your browser
VIEW IN TELEGRAM
π¦ guanmo-ai/design-style
Design Style: The Ultimate Visual Reference
Learn the visual language behind iconic design movements by exploring a library that breaks down styles like Bauhaus, Memphis, and Liquid Glass into short, high-quality motion films. Instead of just showing you a picture, this project hands you the entire recipe, including editable source code, practical design rules, and even the synthesized music used in the clips. It is essentially a masterclass for humans and A I alike, letting you see exactly how a specific aesthetic moves and feels. Whether you are a designer looking for inspiration or a developer building an interface, this repository gives you the exact tools to replicate the look.
π @hackernewsgithubprojects
Design Style: The Ultimate Visual Reference
Learn the visual language behind iconic design movements by exploring a library that breaks down styles like Bauhaus, Memphis, and Liquid Glass into short, high-quality motion films. Instead of just showing you a picture, this project hands you the entire recipe, including editable source code, practical design rules, and even the synthesized music used in the clips. It is essentially a masterclass for humans and A I alike, letting you see exactly how a specific aesthetic moves and feels. Whether you are a designer looking for inspiration or a developer building an interface, this repository gives you the exact tools to replicate the look.
π @hackernewsgithubprojects
This media is not supported in your browser
VIEW IN TELEGRAM
π¦ modalitydance/awesome-agent-as-a-judge
The AI Judge Is An AI
A recent survey reveals that the best judges for AI output are actually other AI agents, not humans. This repository, called awesome agent as a judge, catalogs the latest research on using language model agents to evaluate everything from code to medical reasoning. It solves the problem of scale, as human graders are too slow and expensive to check every single AI output. The coolest part is that these agent judges don't just give a simple yes or no. They use tools, debate each other, and plan out their evaluation steps to catch subtle errors. This is a game changer for anyone building reliable AI systems.
π @hackernewsgithubprojects
The AI Judge Is An AI
A recent survey reveals that the best judges for AI output are actually other AI agents, not humans. This repository, called awesome agent as a judge, catalogs the latest research on using language model agents to evaluate everything from code to medical reasoning. It solves the problem of scale, as human graders are too slow and expensive to check every single AI output. The coolest part is that these agent judges don't just give a simple yes or no. They use tools, debate each other, and plan out their evaluation steps to catch subtle errors. This is a game changer for anyone building reliable AI systems.
π @hackernewsgithubprojects
This media is not supported in your browser
VIEW IN TELEGRAM
π¦ starslingdev/skills
StarSling Skills: Why is your CI slow?
Diagnose exactly why your build is slow by analyzing real run history instead of guessing. StarSling Skills audits your GitHub Actions workflows to pinpoint specific bottlenecks using a catalog of over ninety optimization patterns. It measures actual wall clock wait times and runner minutes spent, then generates a prioritized report with ready to use prompts for your coding agent. This turns vague performance complaints into concrete, measured fixes you can apply immediately. Stop guessing what slows down your pipeline and start seeing the data. Grab these skills to make your CI faster and more efficient today.
π @hackernewsgithubprojects
StarSling Skills: Why is your CI slow?
Diagnose exactly why your build is slow by analyzing real run history instead of guessing. StarSling Skills audits your GitHub Actions workflows to pinpoint specific bottlenecks using a catalog of over ninety optimization patterns. It measures actual wall clock wait times and runner minutes spent, then generates a prioritized report with ready to use prompts for your coding agent. This turns vague performance complaints into concrete, measured fixes you can apply immediately. Stop guessing what slows down your pipeline and start seeing the data. Grab these skills to make your CI faster and more efficient today.
π @hackernewsgithubprojects
This media is not supported in your browser
VIEW IN TELEGRAM
π¦ ttillberg/codevember-2026
Codevember 2026: Paint a City
Scribble roads, bridges, and roundabouts onto a digital canvas to build a living city that reacts to your strokes in real time. Theo Tillbergβs Codevember 2026 challenges creators to build one small project a day in November, and this interactive map turns simple line drawings into a working traffic simulation. As you paint, the streets snap into place, cars navigate the new lanes, and the environment updates instantly, making it a playful way to explore urban design. It is a creative space for seeing how infrastructure changes traffic flow, offering a unique blend of art and logic.
π @hackernewsgithubprojects
Codevember 2026: Paint a City
Scribble roads, bridges, and roundabouts onto a digital canvas to build a living city that reacts to your strokes in real time. Theo Tillbergβs Codevember 2026 challenges creators to build one small project a day in November, and this interactive map turns simple line drawings into a working traffic simulation. As you paint, the streets snap into place, cars navigate the new lanes, and the environment updates instantly, making it a playful way to explore urban design. It is a creative space for seeing how infrastructure changes traffic flow, offering a unique blend of art and logic.
π @hackernewsgithubprojects
This media is not supported in your browser
VIEW IN TELEGRAM
π¦ link-ding/image-to-psd
Image to PSD: The Magic Layer Splitter
image to psd is the agent skill that finally turns a single flat character illustration into a fully layered project file without you touching a single brush. It takes one image, whether it is a photo, a scan, or a drawing, and breaks it down into nineteen distinct parts, from the hair behind the head to the earrings on the ears. The coolest part is that it doesn't just cut out what you see. It actually guesses what is hidden underneath, filling in the face beneath the bangs or the hair behind the neck so every layer is a complete, usable piece.
π @hackernewsgithubprojects
Image to PSD: The Magic Layer Splitter
image to psd is the agent skill that finally turns a single flat character illustration into a fully layered project file without you touching a single brush. It takes one image, whether it is a photo, a scan, or a drawing, and breaks it down into nineteen distinct parts, from the hair behind the head to the earrings on the ears. The coolest part is that it doesn't just cut out what you see. It actually guesses what is hidden underneath, filling in the face beneath the bangs or the hair behind the neck so every layer is a complete, usable piece.
π @hackernewsgithubprojects
This media is not supported in your browser
VIEW IN TELEGRAM
π¦ mit-han-lab/pear
Pear: Teaching Robots to Think
PEAR is the training engine that teaches computer vision models to physically control real robots without needing any human video examples. Instead of showing an AI thousands of hours of footage, this system uses reinforcement learning inside a digital sandbox. The model practices picking up objects and navigating spaces in a simulator until it understands the physical world well enough to drive actual hardware. It solves the massive data bottleneck of robotics by letting the algorithm learn through trial and error in code rather than relying on expensive, manual demonstrations. This approach allows a single brain to operate different bodies, making autonomous machines easier to scale.
π @hackernewsgithubprojects
Pear: Teaching Robots to Think
PEAR is the training engine that teaches computer vision models to physically control real robots without needing any human video examples. Instead of showing an AI thousands of hours of footage, this system uses reinforcement learning inside a digital sandbox. The model practices picking up objects and navigating spaces in a simulator until it understands the physical world well enough to drive actual hardware. It solves the massive data bottleneck of robotics by letting the algorithm learn through trial and error in code rather than relying on expensive, manual demonstrations. This approach allows a single brain to operate different bodies, making autonomous machines easier to scale.
π @hackernewsgithubprojects
This media is not supported in your browser
VIEW IN TELEGRAM
π¦ miaai-lab/claude-fable-5.2-html-files
Claude Fable 5.2 HTML Files
Browse seventy-six original visual studies generated by a language model, complete with the exact prompts used to create them. This gallery lets you see the final result and then read the specific instructions that produced it, turning abstract AI outputs into a clear, searchable archive of creative experiments. It works like a digital scrapbook where you can inspect the connection between human intent and machine interpretation. This transparency is rare, offering a direct window into how these tools actually think and render. You get the final image and the recipe used to make it, which helps anyone understand the process without guessing.
π @hackernewsgithubprojects
Claude Fable 5.2 HTML Files
Browse seventy-six original visual studies generated by a language model, complete with the exact prompts used to create them. This gallery lets you see the final result and then read the specific instructions that produced it, turning abstract AI outputs into a clear, searchable archive of creative experiments. It works like a digital scrapbook where you can inspect the connection between human intent and machine interpretation. This transparency is rare, offering a direct window into how these tools actually think and render. You get the final image and the recipe used to make it, which helps anyone understand the process without guessing.
π @hackernewsgithubprojects