📦 vavo/lora-pilot

One Container For All AI Training

A single Docker container can now run three separate Stable Diffusion training systems side by side without crashing. That is the core idea behind Lora Pilot, a prebuilt environment that solves the headache of managing conflicting software versions for custom AI model training. Instead of installing each tool separately and hoping they work together, this project bundles the trainers, visualizers, and image generation tools into one shared workspace. Everything saves to the same folder, so your work survives restarts and you never have to reconfigure paths.

🆔 @hackernewsgithubprojects

📦 lostb1t/remux

Remux: The Media Server That Doesn't Need Downloads

Remux streams movies directly from torrents without ever downloading the file to your hard drive. It is a self-hosted media server written in Rust that speaks the same language as Jellyfin, meaning your existing apps work with it immediately. The project combines local files, remote sources, and torrent streaming into a single library, so you can browse and play content without juggling multiple services. Because it handles the streaming process internally, you get instant playback with full support for subtitles and audio tracks. This approach keeps your storage clean while still giving you access to a vast array of media.

🆔 @hackernewsgithubprojects

📦 cswry/vosr

VOSR: The AI That Fixes Blurry Photos Without Text Prompts

VOSR is the image upscaler that restores sharpness without needing a text description. Most AI tools that fix blurry photos require you to type a prompt explaining what is in the picture, but this model relies entirely on its own visual understanding. It was accepted into the top computer vision conference for 2026, proving that you do not need language instructions to get high-quality results. By using a specialized neural network, it takes a low-resolution image and rebuilds the missing details directly from the visual data. This makes it incredibly useful for anyone who wants to improve old photos or screen captures without worrying about writing the right words.

🆔 @hackernewsgithubprojects

📦 ylchen333/comfyui-vosr2

VOSR 2.0: One-Step Image Upscaling in ComfyUI

ComfyUI-VOSR2 is the ComfyUI node that makes high-quality image upscaling feel instant. It wraps the VOSR 2.0 model, which uses a single-step diffusion process to turn low-resolution images into sharp, detailed versions without the usual multi-pass waiting. The coolest part is how it handles text and fine structures, making blurry letters and intricate patterns readable in one go. You just drop your image in, and it manages the heavy lifting, downloading the necessary model files automatically on first use. It’s perfect for anyone who wants professional-grade upscaling without complex setups.

🆔 @hackernewsgithubprojects

📦 grpcer/ownmem

OwnMem: Git-Native Memory for AI Coding Agents

An AI coding agent that forgets your project context is a liability, so OwnMem treats memory like source code. It stores project knowledge in plain Markdown files that live directly in your Git repository, meaning your agent's memory is version-controlled, reviewable, and travels with your code. When you ask an agent to recall something, it performs a deterministic, local search that requires no internet connection or extra API calls, ensuring the same query always yields the same result. This approach solves the problem of opaque agent memory by making every fact inspectable and reversible.

🆔 @hackernewsgithubprojects

📦 staatsgeheim/mathkernel

MathKernel: The Truth Engine for AI Math

Let an AI math engine verify its own answers. Math Kernel is a Python library that gives large language models a way to do math they can actually trust. Instead of just guessing, it uses different calculation styles, like exact logic or standard numbers, to check its work. It tags every result with a trust label, showing exactly how much you can rely on it. This solves a big problem where AIs confidently get math wrong. It is useful for anyone building tools that need reliable numbers. If you want your AI to be honest about what it knows, this is how you do it.

📰 https://news.ycombinator.com/item?id=49592366

🆔 @hackernewsgithubprojects

📦 blessedrebus/krawl

Krawl: The Deception Server That Catches Hackers

Krawl is the web deception server that turns your infrastructure into a trap for attackers. It runs a fake version of your application that looks completely normal on the surface but is actually filled with deliberately weak security holes that anyone with a basic scanner can find. When a hacker probes these vulnerable spots, the system quietly logs their activity and can even ban their IP address across your entire network. The real win here is that you are no longer just blocking bad traffic; you are actively learning how attackers think by watching them walk into a trap.

📰 https://news.ycombinator.com/item?id=47571680

🆔 @hackernewsgithubprojects

📦 majoorwaldi/comfyui-majoor-omnicam

Majoor OmniCam: Direct Your AI Video Camera

Majoor OmniCam is the camera layout tool that lets you choreograph your shots before the computer ever renders a single frame. Instead of guessing how a video model will move its camera and hoping for the best, this plug-in gives you a simple three-dimensional stage where you can physically place a virtual lens and animate its movement. You can scrub through time, watch a low-fidelity preview of the motion, and then hand that exact path to any compatible AI model. It solves the headache of trying to describe complex camera moves in text prompts by turning them into visual keyframes.

🆔 @hackernewsgithubprojects

📦 kayforkind/reimagine-it

Reimagine It: Design From Your Own Data

A single command can transform a plain web page into a visually stunning, fully functional design system without ever inventing a single detail. This tool, called Reimagine It, solves a common frustration where generic design prompts turn every website into the same sleek, corporate template. Instead of guessing what looks good, it reads the actual text, numbers, and colors already on the page to build a layout that is unique to that specific content. It extracts real facts to create charts, typography, and art that are completely offline and ready to use immediately. This means the final design is not just pretty, but actually accurate to the source material.

📰 https://news.ycombinator.com/item?id=49504599

🆔 @hackernewsgithubprojects

📦 20000419/fauxnix

fauxnix: The Windows Bash Translator

fauxnix lets your AI agent write standard Linux commands that run perfectly on Windows without installing a virtual machine or WSL. Because large language models are trained heavily on Bash, they often write PowerShell code that looks correct but fails in practice. Fauxnix solves this by taking those familiar commands, like listing files or searching for text, and deterministically translating them into native PowerShell. The output mimics the familiar Linux format, giving you clean results and clear error messages instead of confusing Windows stack traces. This makes it a reliable bridge for agents working on your desktop.

📰 https://news.ycombinator.com/item?id=49592864

🆔 @hackernewsgithubprojects

📦 mesqme/utanomori

Utanomori: A Painterly Forest Walk

Walk through an endless, hand-painted forest to find three hidden music spirits and hum their melodies back into stone. This browser game, called Utanomori, lets you wander a stylized night world where the ground and trees shift colors as you explore. Instead of fighting enemies, you solve a gentle puzzle by tapping stones in the right order to complete a song. Each spirit you free joins your journey, turning a quiet walk into a musical adventure. It is a calm escape from high-stakes gaming, offering a peaceful, artistic experience right in your browser.

🆔 @hackernewsgithubprojects

📦 google/magika

Magika: The AI File Type Detector

Magika is the AI-powered tool that identifies any file by reading its actual content instead of trusting its name. It solves the problem of mislabeled or hidden files by using a tiny deep learning model to pinpoint exactly what kind of data you have. In just a few milliseconds on a standard computer, it recognizes over two hundred different file types. This accuracy keeps your digital files safe and organized, making it a favorite for security experts and developers. If you want to know what a file really is, Magika gives you the answer in an instant.

🆔 @hackernewsgithubprojects

📦 jaromiru/diktafon

Diktafon: Your Voice, Your Rules

Diktafon runs a full AI brain directly inside your phone, meaning your voice notes never leave your device to be processed in a cloud server. This open-source app treats your recordings like physical cassette tapes, where you simply press record, speak your thoughts, and rewind to find them later. The software automatically turns that audio into readable text and creates short summaries right on your hardware, keeping your data completely private while you organize your ideas. You do not need an account, a subscription, or an internet connection to use it. It is a clean, nostalgic way to capture thoughts without worrying about data leaks.

📰 https://news.ycombinator.com/item?id=49005819

🆔 @hackernewsgithubprojects

📦 eigenwise/eigenwise-toolshed

Eigenwise Toolshed

Your coding assistant starts every new session completely blind, having forgotten everything it learned about your project's structure just minutes ago. The Eigenwise Toolshed fixes this by automatically building and maintaining a living map of your codebase that loads into every conversation instantly. Instead of wasting time re-explaining your file organization or coding patterns, the AI already knows how your software is built. This collection of tools keeps that knowledge current as you write new code, meaning the assistant picks up exactly where you left off. You stop teaching your robot its own house, and start actually getting work done.

🆔 @hackernewsgithubprojects

📦 salesforceairesearch/random-attention

Random Attention: Why Random Beats Smart

Save memory by randomly deleting old thoughts. That’s the whole trick behind Random Attention. When an AI reasons, it keeps a running memory of every token it processes. Most systems use complex math to guess which parts are important. This project proves you don’t need that. It just picks random chunks to keep and tosses the rest. Surprisingly, this simple method matches or beats fancy learned selectors on hard math and coding tasks. It’s also the fastest way to clear space, making long thoughts cheaper and quicker to run. The code includes the engine, tests, and benchmarks to verify these results.

🆔 @hackernewsgithubprojects

📦 paberr/ownscribe

ownscribe: Your Private Meeting Recorder

ownscribe captures every word spoken during a video call without sending a single byte to the cloud. This command-line tool records your system audio directly on your Mac, turning conversations into accurate text using local AI models that run entirely on your hardware. You get a full transcript and a structured summary with action items, all stored safely on your device. It even lets you ask natural language questions across all your past meetings to find specific details later. Because everything happens locally, your private discussions never leave your computer. If you want complete control over your data without sacrificing convenience, this tool is the one to try.

📰 https://news.ycombinator.com/item?id=47638532

🆔 @hackernewsgithubprojects

📦 omacom/omarchy-plugin-marketplace

The Omarchy Plugin Marketplace Is Here

Omarchy plugins execute unsandboxed code directly on your system, and this community-curated marketplace adds the first layer of automated security screening to help you decide what to trust. It is not just a list of extensions; it is a verification pipeline. Before any plugin appears in the catalog, a scanner statically analyzes the exact code you would install to check for known red flags. This matters because most install commands pull live, changing code, leaving you exposed to silent updates. The marketplace pins that code and tests it first. You get a clear, honest signal about safety, not a badge.

🆔 @hackernewsgithubprojects

📦 cozyblaze/portal-agent

Portal Agent: An AI Plays Portal

An artificial intelligence recently spent twenty-three hours playing Portal by itself until the end credits rolled. This project, called Portal agent, documents exactly how that run happened. It provides the specific code and settings used to let a large language model see the game, think through the next move, and control the character without human help. The system pauses the game while the agent plans, then advances the action just enough to show the result. This setup is interesting because it proves a computer can navigate complex, puzzle-based gameplay autonomously for hours on end.

🆔 @hackernewsgithubprojects

📦 darksidewalker/comfyui-dasiwa-nodes

ComfyUI DaSiWa Nodes: The Ultimate Video Node Pack

ComfyUI DaSiWa Nodes is the custom node collection that finally makes high-end video generation feel manageable. It bundles a suite of tools that handle the messy details, like a timeline-based director for complex video prompts and smart upscalers that keep your memory usage low. Instead of fighting with your interface, you get precise control over resolution, audio, and visual quality. It is the kind of toolkit that lets you focus on the art while the software handles the heavy lifting. If you are ready to stop wrestling with your workflow, this pack gives you the professional controls you need to create stunning, consistent results without the usual technical headaches.

🆔 @hackernewsgithubprojects

📦 wesleygrimes/omastorm

Omastorm

Omastorm puts a live weather radar directly into your desktop taskbar, and it shows you exactly when that data was captured. Built for the Omarchy Linux environment, it connects to real National Oceanic and Atmospheric Administration feeds so you can watch storms form without guessing if the picture is fresh. The app even tells you if the signal is stale or if you are looking at archived footage. It feels like a pro tool that just happens to live on your screen. If you want honest weather data that respects your system theme, this is the one to watch.

🆔 @hackernewsgithubprojects