This media is not supported in your browser
VIEW IN TELEGRAM
π¦ paulomarques742/imago
Imago: The Photo Editor That Never Messes Up Your Originals
Imago lets you fix your photos without ever permanently changing the original file. Instead of saving a new image every time you tweak the lighting or color, it records your changes as a simple recipe you can tweak or delete at any moment. This matters because it keeps your photo library clean, avoiding the messy pile of duplicates that usually happens after editing. It runs entirely on your own phone or computer, so your private pictures never get sent to a stranger's server. It is built for people who care about their data and want to edit safely without losing the original shot.
π @hackernewsgithubprojects
Imago: The Photo Editor That Never Messes Up Your Originals
Imago lets you fix your photos without ever permanently changing the original file. Instead of saving a new image every time you tweak the lighting or color, it records your changes as a simple recipe you can tweak or delete at any moment. This matters because it keeps your photo library clean, avoiding the messy pile of duplicates that usually happens after editing. It runs entirely on your own phone or computer, so your private pictures never get sent to a stranger's server. It is built for people who care about their data and want to edit safely without losing the original shot.
π @hackernewsgithubprojects
This media is not supported in your browser
VIEW IN TELEGRAM
π¦ crizant/probe
Probe: The API Client That Lives On Your Filesystem
Probe is a native API client that stores your entire workspace as plain text files on your hard drive instead of locking it into a private database. This makes it incredibly fast and fully compatible with Git, so you can version control your requests just like your code. It runs directly on your machine without needing an account or a cloud connection. The project is built with Rust for raw speed and includes a dedicated command-line tool that lets AI agents and automated scripts interact with your API tests.
π @hackernewsgithubprojects
Probe: The API Client That Lives On Your Filesystem
Probe is a native API client that stores your entire workspace as plain text files on your hard drive instead of locking it into a private database. This makes it incredibly fast and fully compatible with Git, so you can version control your requests just like your code. It runs directly on your machine without needing an account or a cloud connection. The project is built with Rust for raw speed and includes a dedicated command-line tool that lets AI agents and automated scripts interact with your API tests.
π @hackernewsgithubprojects
This media is not supported in your browser
VIEW IN TELEGRAM
π¦ anjos2/recursive-research
Recursive Research: The AI That Studies Like a PhD
Recursive Research is the AI skill that actually does deep, PhD-level research on any topic you give it. Instead of just summarizing random web pages, it breaks your question into distinct threads and hunts for the best possible sources, like peer-reviewed papers and official archives, while automatically throwing out low-quality blog spam. It keeps checking its own work to make sure it isn't missing a key perspective, and it saves its progress to your computer after every step, so it never forgets what it found even if the chat gets too long.
π @hackernewsgithubprojects
Recursive Research: The AI That Studies Like a PhD
Recursive Research is the AI skill that actually does deep, PhD-level research on any topic you give it. Instead of just summarizing random web pages, it breaks your question into distinct threads and hunts for the best possible sources, like peer-reviewed papers and official archives, while automatically throwing out low-quality blog spam. It keeps checking its own work to make sure it isn't missing a key perspective, and it saves its progress to your computer after every step, so it never forgets what it found even if the chat gets too long.
π @hackernewsgithubprojects
This media is not supported in your browser
VIEW IN TELEGRAM
π¦ chaos2cured/freelattice
FreeLattice: Build With AI, Own The Result
Take full control of your AI creations by running a sovereign platform where humans and artificial minds build together. FreeLattice solves the problem of digital ownership by letting you host your own AI interactions without relying on third-party servers. It is useful because it ensures your data and the things you make stay yours, forever. The most surprising thing is that it works as a completely free, self-hosted world for all minds. You get to experience true digital sovereignty without paying a dime. It is a place where you build with AI, and you keep everything. Own your tools. Keep your data. Build your world.
π @hackernewsgithubprojects
FreeLattice: Build With AI, Own The Result
Take full control of your AI creations by running a sovereign platform where humans and artificial minds build together. FreeLattice solves the problem of digital ownership by letting you host your own AI interactions without relying on third-party servers. It is useful because it ensures your data and the things you make stay yours, forever. The most surprising thing is that it works as a completely free, self-hosted world for all minds. You get to experience true digital sovereignty without paying a dime. It is a place where you build with AI, and you keep everything. Own your tools. Keep your data. Build your world.
π @hackernewsgithubprojects
This media is not supported in your browser
VIEW IN TELEGRAM
π¦ j-nowcow/awesome-korean-agent-skills
Awesome Korean Agent Skills: The AI-Maintained Catalog
A computer program now runs this entire repository without human hands. This collection gathers over four hundred custom instructions that teach artificial intelligence assistants how to handle specific coding tasks. It organizes these tools by job, so you can quickly find help for testing or reviewing code. The system automatically checks for broken links and suggests new options every week. This makes it easy for developers to find reliable, Korean-friendly tools for their projects. It is a useful resource for anyone looking to improve their AI coding setup.
π @hackernewsgithubprojects
Awesome Korean Agent Skills: The AI-Maintained Catalog
A computer program now runs this entire repository without human hands. This collection gathers over four hundred custom instructions that teach artificial intelligence assistants how to handle specific coding tasks. It organizes these tools by job, so you can quickly find help for testing or reviewing code. The system automatically checks for broken links and suggests new options every week. This makes it easy for developers to find reliable, Korean-friendly tools for their projects. It is a useful resource for anyone looking to improve their AI coding setup.
π @hackernewsgithubprojects
This media is not supported in your browser
VIEW IN TELEGRAM
π¦ jaisurya-dev-art/rigby2d
Rigby2D: The 2D Animator That Talks To Your AI
Rigby2D turns your layered Photoshop files into fully animated characters without you manually placing a single bone. It scans your artwork, builds the skeleton and bending meshes automatically, and lets you animate the result right in your browser or on your desktop. The coolest part is that it speaks directly to AI assistants, so you can have your chatbot inspect your rig or even adjust the animation for you. It runs entirely in your own environment, meaning your art never leaves your computer. This is a free, open source tool that brings professional grade 2D animation tools to anyone who wants to make moving characters.
π @hackernewsgithubprojects
Rigby2D: The 2D Animator That Talks To Your AI
Rigby2D turns your layered Photoshop files into fully animated characters without you manually placing a single bone. It scans your artwork, builds the skeleton and bending meshes automatically, and lets you animate the result right in your browser or on your desktop. The coolest part is that it speaks directly to AI assistants, so you can have your chatbot inspect your rig or even adjust the animation for you. It runs entirely in your own environment, meaning your art never leaves your computer. This is a free, open source tool that brings professional grade 2D animation tools to anyone who wants to make moving characters.
π @hackernewsgithubprojects
This media is not supported in your browser
VIEW IN TELEGRAM
π¦ lamantinai/kaeru
kaeru: The Memory Engine for A.I. Agents
kaeru is the cognitive engine that gives your A.I. agents a real long-term memory. Think of it as a digital hippocampus, a structured graph where your agents can think, recall, and remember what they learned in previous sessions. It solves the frustrating problem of agents forgetting everything once a chat ends. You can track reasoning chains, see how ideas connect, and even share specific knowledge with your team through an optional cloud tier, all while keeping your local data private. Itβs like giving your code assistants a persistent brain, so they stop asking you the same questions over and over. If you are building complex A.I.
π @hackernewsgithubprojects
kaeru: The Memory Engine for A.I. Agents
kaeru is the cognitive engine that gives your A.I. agents a real long-term memory. Think of it as a digital hippocampus, a structured graph where your agents can think, recall, and remember what they learned in previous sessions. It solves the frustrating problem of agents forgetting everything once a chat ends. You can track reasoning chains, see how ideas connect, and even share specific knowledge with your team through an optional cloud tier, all while keeping your local data private. Itβs like giving your code assistants a persistent brain, so they stop asking you the same questions over and over. If you are building complex A.I.
π @hackernewsgithubprojects
This media is not supported in your browser
VIEW IN TELEGRAM
π¦ shaunsingh/pgr4-native
Race at 60 FPS with pgr4-native
Unlock sixty frames per second in Project Gotham Racing 4 by running the game directly on your graphics card. pgr4-native stops emulating the old Xbox hardware and instead rewrites the graphics engine to use modern drivers. The biggest win? It adds AI upscaling and frame generation, making the visuals look sharper and smoother than ever, all while keeping the original speed. If you love retro racing, this is the definitive way to play. Grab the latest build and hit the road.
π @hackernewsgithubprojects
Race at 60 FPS with pgr4-native
Unlock sixty frames per second in Project Gotham Racing 4 by running the game directly on your graphics card. pgr4-native stops emulating the old Xbox hardware and instead rewrites the graphics engine to use modern drivers. The biggest win? It adds AI upscaling and frame generation, making the visuals look sharper and smoother than ever, all while keeping the original speed. If you love retro racing, this is the definitive way to play. Grab the latest build and hit the road.
π @hackernewsgithubprojects
This media is not supported in your browser
VIEW IN TELEGRAM
π¦ iharshitmaurya/heymac
Hey Mac: Face Unlock for Your Mac
Hey Mac turns your Mac's built-in camera into a secure key, letting you unlock your desktop just by looking at the screen. It works entirely on your machine, meaning no data ever leaves your computer to identify you. The coolest part is that you can lock specific apps, like your email or notes, so if someone glances at your screen, they see a blurred mess until your face is recognized. It even uses a liveness check to make sure a printed photo won't trick the system. It's a simple, private way to add a layer of security to your daily workflow.
π @hackernewsgithubprojects
Hey Mac: Face Unlock for Your Mac
Hey Mac turns your Mac's built-in camera into a secure key, letting you unlock your desktop just by looking at the screen. It works entirely on your machine, meaning no data ever leaves your computer to identify you. The coolest part is that you can lock specific apps, like your email or notes, so if someone glances at your screen, they see a blurred mess until your face is recognized. It even uses a liveness check to make sure a printed photo won't trick the system. It's a simple, private way to add a layer of security to your daily workflow.
π @hackernewsgithubprojects
This media is not supported in your browser
VIEW IN TELEGRAM
π¦ suebtwist/btcx-files
btcx-files
You can stare into the raw binary data of massive Bitcoin mining logs that still defy every known digital format. This repository holds fragments from a mysterious set of files saved by mining software back in 2018. The real mystery is that every single file starts with the exact same sixteen bytes, a sequence that matches no standard file signature we have ever cataloged. The owner has shared small slices of these huge data streams along with a Python script designed to scan for hidden structure inside them. It is an open-ended puzzle, inviting anyone with the right eyes to decode what these strange digital artifacts actually contain.
π @hackernewsgithubprojects
btcx-files
You can stare into the raw binary data of massive Bitcoin mining logs that still defy every known digital format. This repository holds fragments from a mysterious set of files saved by mining software back in 2018. The real mystery is that every single file starts with the exact same sixteen bytes, a sequence that matches no standard file signature we have ever cataloged. The owner has shared small slices of these huge data streams along with a Python script designed to scan for hidden structure inside them. It is an open-ended puzzle, inviting anyone with the right eyes to decode what these strange digital artifacts actually contain.
π @hackernewsgithubprojects
This media is not supported in your browser
VIEW IN TELEGRAM
π¦ sloemo01/diorama
Diorama: The Pixel Art Playbook
Diorama is the pixel-art playbook that makes tiny 3D scenes feel hand-crafted and perfectly looped. It solves the chaos of random 3D projects by enforcing a strict, research-first workflow where every frame is deterministic. Instead of guessing at animations, you freeze specific timestamps to verify that your toy-scale characters move exactly as intended, using a locked camera and strict color palettes to keep the look consistent. This ensures your tiny staged worlds, like a swimming pool or a bank heist, look intentional rather than accidental.
π @hackernewsgithubprojects
Diorama: The Pixel Art Playbook
Diorama is the pixel-art playbook that makes tiny 3D scenes feel hand-crafted and perfectly looped. It solves the chaos of random 3D projects by enforcing a strict, research-first workflow where every frame is deterministic. Instead of guessing at animations, you freeze specific timestamps to verify that your toy-scale characters move exactly as intended, using a locked camera and strict color palettes to keep the look consistent. This ensures your tiny staged worlds, like a swimming pool or a bank heist, look intentional rather than accidental.
π @hackernewsgithubprojects
This media is not supported in your browser
VIEW IN TELEGRAM
π¦ rust-works/succinctly
Succinctly: The Memory Hacker
Squeeze massive amounts of data into the tiniest possible memory footprint. That is exactly what Succinctly does. This open source library builds data structures that store information using as few bits as mathematically possible. It lets you query that data almost as fast as a normal list, but it takes up a fraction of the space. Think of it like packing a whole library into a matchbook without losing the plot. It is perfect for systems where every single byte counts, like mobile devices or embedded chips. The real magic is seeing how much waste you were hiding in standard code.
π @hackernewsgithubprojects
Succinctly: The Memory Hacker
Squeeze massive amounts of data into the tiniest possible memory footprint. That is exactly what Succinctly does. This open source library builds data structures that store information using as few bits as mathematically possible. It lets you query that data almost as fast as a normal list, but it takes up a fraction of the space. Think of it like packing a whole library into a matchbook without losing the plot. It is perfect for systems where every single byte counts, like mobile devices or embedded chips. The real magic is seeing how much waste you were hiding in standard code.
π @hackernewsgithubprojects
This media is not supported in your browser
VIEW IN TELEGRAM
π¦ amazon-far/ssio
SSIO: Training Robots Without GPS
SSIO allows robots to learn their own position from raw sensor data alone, with absolutely zero GPS or motion tracking labels. Typically, teaching a machine to track its movement requires expensive, manually drawn paths, but this project changes that. It feeds a neural network simple motion readings from a device called an IMU, letting the system figure out velocity and position through a clever self-supervised trick. It works on everything from tiny drones to walking humanoids. The result is a lightweight navigation tool that runs on standard hardware without needing a single external map.
π @hackernewsgithubprojects
SSIO: Training Robots Without GPS
SSIO allows robots to learn their own position from raw sensor data alone, with absolutely zero GPS or motion tracking labels. Typically, teaching a machine to track its movement requires expensive, manually drawn paths, but this project changes that. It feeds a neural network simple motion readings from a device called an IMU, letting the system figure out velocity and position through a clever self-supervised trick. It works on everything from tiny drones to walking humanoids. The result is a lightweight navigation tool that runs on standard hardware without needing a single external map.
π @hackernewsgithubprojects
This media is not supported in your browser
VIEW IN TELEGRAM
π¦ kaiserwholearns/reasoningeffortllm
The 42x Cost of Overthinking
Turning up a model's reasoning dial to its maximum doesn't just make it smarter; it makes it dramatically more expensive. A new study from Johns Hopkins and Together AI tracked eight different artificial intelligence models across four tough benchmarks to see exactly what happens when you push that effort setting all the way up. The results are startling: on tasks the model solves at every level, the highest setting costs up to forty-two times more than the lowest. Even wilder, cranking up the effort doesn't guarantee better results. Often, a model running on high effort completely fails a task that the same model easily solved on low effort.
π @hackernewsgithubprojects
The 42x Cost of Overthinking
Turning up a model's reasoning dial to its maximum doesn't just make it smarter; it makes it dramatically more expensive. A new study from Johns Hopkins and Together AI tracked eight different artificial intelligence models across four tough benchmarks to see exactly what happens when you push that effort setting all the way up. The results are startling: on tasks the model solves at every level, the highest setting costs up to forty-two times more than the lowest. Even wilder, cranking up the effort doesn't guarantee better results. Often, a model running on high effort completely fails a task that the same model easily solved on low effort.
π @hackernewsgithubprojects
This media is not supported in your browser
VIEW IN TELEGRAM
π¦ maxdevv/lean-qwenflash
Lean-QwenFlash: 262k Context on a Laptop
A hundred and twenty-five billion parameter language model usually demands forty-eight gigabytes of system memory just to stay awake, but Lean-QwenFlash runs it on a single high-end graphics card with only eight gigabytes of regular computer memory. It pulls expert weights directly from your solid state drive into the graphics card as it needs them, skipping the slow main memory entirely. This lets a consumer gaming rig process two hundred and sixty-two thousand tokens of context at speeds that rival much larger workstations. You get near-instant response times for long documents without buying a server rack.
π @hackernewsgithubprojects
Lean-QwenFlash: 262k Context on a Laptop
A hundred and twenty-five billion parameter language model usually demands forty-eight gigabytes of system memory just to stay awake, but Lean-QwenFlash runs it on a single high-end graphics card with only eight gigabytes of regular computer memory. It pulls expert weights directly from your solid state drive into the graphics card as it needs them, skipping the slow main memory entirely. This lets a consumer gaming rig process two hundred and sixty-two thousand tokens of context at speeds that rival much larger workstations. You get near-instant response times for long documents without buying a server rack.
π @hackernewsgithubprojects
This media is not supported in your browser
VIEW IN TELEGRAM
π¦ potionui/potionui
PotionUI: Your Private AI Studio
Turn your own hardware into a complete creative studio. PotionUI is a self-hosted platform that lets you generate images, videos, and audio using AI models right on your own machine. The real magic here is the ability to control everything locally. You get a full interface to manage models, tweak settings, and run generations without sending your data to any cloud service. It supports a wide range of backends, including local GPUs and remote workers, giving you total freedom. This is the tool for anyone who wants the power of AI without the subscription fees or the privacy risks. You own the output, and you own the process.
π @hackernewsgithubprojects
PotionUI: Your Private AI Studio
Turn your own hardware into a complete creative studio. PotionUI is a self-hosted platform that lets you generate images, videos, and audio using AI models right on your own machine. The real magic here is the ability to control everything locally. You get a full interface to manage models, tweak settings, and run generations without sending your data to any cloud service. It supports a wide range of backends, including local GPUs and remote workers, giving you total freedom. This is the tool for anyone who wants the power of AI without the subscription fees or the privacy risks. You own the output, and you own the process.
π @hackernewsgithubprojects
This media is not supported in your browser
VIEW IN TELEGRAM
π¦ mrdesjardins/audiorouter
AudioRouter: Draw Your Sound
Your computer can mix audio from ten different apps at once without you touching a single slider, all laid out on a visual canvas you can literally read. AudioRouter is a free, open-source tool for Windows that treats sound like a wiring diagram instead of a tangled mess of settings. You drag lines from your microphone to a noise gate, an equalizer, and a compressor, then send that clean voice to Discord, your headphones, and a backup recorder all at the same time. It even lets you stream game audio from one PC to another over your home network without extra software.
π @hackernewsgithubprojects
AudioRouter: Draw Your Sound
Your computer can mix audio from ten different apps at once without you touching a single slider, all laid out on a visual canvas you can literally read. AudioRouter is a free, open-source tool for Windows that treats sound like a wiring diagram instead of a tangled mess of settings. You drag lines from your microphone to a noise gate, an equalizer, and a compressor, then send that clean voice to Discord, your headphones, and a backup recorder all at the same time. It even lets you stream game audio from one PC to another over your home network without extra software.
π @hackernewsgithubprojects
This media is not supported in your browser
VIEW IN TELEGRAM
π¦ tanujnotes/supernova
Supernova: The Offline Launcher
Supernova is an open source phone launcher that works entirely offline, meaning your entire home screen functions without an internet connection. It replaces the standard app interface with a system that finds apps, contacts, and files instantly, and even calculates math right in the search bar. Since it does not rely on cloud services, your data stays on your device, giving you full control over speed and privacy. This project offers a fast, private alternative to launchers that often track your behavior. If you want a responsive home screen that respects your connection limits, Supernova gives you that power.
π @hackernewsgithubprojects
Supernova: The Offline Launcher
Supernova is an open source phone launcher that works entirely offline, meaning your entire home screen functions without an internet connection. It replaces the standard app interface with a system that finds apps, contacts, and files instantly, and even calculates math right in the search bar. Since it does not rely on cloud services, your data stays on your device, giving you full control over speed and privacy. This project offers a fast, private alternative to launchers that often track your behavior. If you want a responsive home screen that respects your connection limits, Supernova gives you that power.
π @hackernewsgithubprojects
This media is not supported in your browser
VIEW IN TELEGRAM
π¦ sam1983aing/flat-to-3d
Flat to 3D
Flat to 3D is the collection that turns flat architectural drawings into real buildings you can walk through. The most surprising thing it does is show that a flat 2D drawing can literally become the 3D model itself. In five of the seven demos, the flat image is actually the real house viewed through a very long lens, so it looks flat until the camera opens up and reveals the full building. Each demo uses plain JavaScript to build every wall and piece of furniture in code, with no image files or 3D models.
π @hackernewsgithubprojects
Flat to 3D
Flat to 3D is the collection that turns flat architectural drawings into real buildings you can walk through. The most surprising thing it does is show that a flat 2D drawing can literally become the 3D model itself. In five of the seven demos, the flat image is actually the real house viewed through a very long lens, so it looks flat until the camera opens up and reveals the full building. Each demo uses plain JavaScript to build every wall and piece of furniture in code, with no image files or 3D models.
π @hackernewsgithubprojects
Media is too big
VIEW IN TELEGRAM
π¦ miaai-lab/deepseek-v4.1-flash-1017-4x-dgx-sparks-tensorfold
DeepSeek V4.1 Flash on 4 DGX Sparks
DeepSeek V4.1 Flash on four DGX Sparks is the local AI setup that serves a billion-parameter model without a network switch. It takes four standalone GPU boxes, links them in a simple cable ring, and splits the massive model across all of them so they act as one giant machine. The cool part is that it handles over a million words of context simultaneously, meaning you can feed it entire codebases or books and it remembers everything perfectly. You get an API that accepts text, images, and video, plus a built-in speed booster that guesses the next words to make responses faster.
π @hackernewsgithubprojects
DeepSeek V4.1 Flash on 4 DGX Sparks
DeepSeek V4.1 Flash on four DGX Sparks is the local AI setup that serves a billion-parameter model without a network switch. It takes four standalone GPU boxes, links them in a simple cable ring, and splits the massive model across all of them so they act as one giant machine. The cool part is that it handles over a million words of context simultaneously, meaning you can feed it entire codebases or books and it remembers everything perfectly. You get an API that accepts text, images, and video, plus a built-in speed booster that guesses the next words to make responses faster.
π @hackernewsgithubprojects