📦 windows-gpu-unlock/windows-gpu-unlock

Windows GPU Unlock: Boot RTX Cards Without a Reset

Windows GPU Unlock is the experimental boot loader that finally lets specific Nvidia graphics cards run on Windows without needing a second monitor or a full system reset. The project works by carefully guiding your computer through a special startup process that releases the graphics card from its initial locked state, allowing it to hand off control directly to your operating system. This solves the frustrating problem of needing extra hardware or complicated manual steps just to get your graphics card working correctly at boot. It is a fascinating look at how deep hardware tinkering can go, turning a rigid system process into something much more flexible for enthusiasts.

🆔 @hackernewsgithubprojects

📦 anemll/flash-moe

Flash-MoE: Running a 400B Model on a Mac

Flash-MoE is the inference engine that streams a massive language model from your solid state drive. Instead of fitting the entire network into memory, this pure C project reads only the specific parts needed for each word. It processes a model with four hundred billion parameters on a MacBook Pro by pulling data directly from the disk. This design avoids the need for expensive server clusters. It proves that local hardware can handle very large artificial intelligence tasks. You get real-time responses without the cloud. This approach changes how we think about local computing power. It makes high-end language models accessible to everyone.

🆔 @hackernewsgithubprojects

📦 shenysun/skills-manager

How to Manage All Your AI Agents with One Command

Skills Manager treats your AI helper abilities like a shared library that updates itself without asking permission. Instead of manually copying files between different coding tools, you install one central hub and let your chat agent handle the rest. The project solves the messy problem of keeping skills in sync across dozens of different applications. You simply tell your chat bot what to install, and it manages the files behind the scenes. This approach saves time and prevents outdated skills from causing errors. It is a simple way to organize your AI toolkit without technical overhead.

🆔 @hackernewsgithubprojects

📦 super-phenix/superphenix

Superphenix: Your Own Cloud

Superphenix is an open-source platform that lets you build a full cloud provider on the hardware you already own. It runs on Kubernetes to manage everything from virtual machines and storage to networking and managed services, all running as first-class workloads on top. This solves the problem of vendor lock-in and high costs by giving you complete control over your infrastructure and data. Whether you are building a public cloud or a private one, it is designed to be resilient and scalable across multiple datacenters. It is already being used in production by companies looking for independence and total control.

📰 https://news.ycombinator.com/item?id=49714404

🆔 @hackernewsgithubprojects

📦 git-fed/museai-skills-guide

Museai Skills Guide: The Offline Audit Ledger

Track every move an A I agent makes without needing secret server logs. This guide provides a private, offline tool that records actions locally on your device, so you can see exactly what happened during a task. It solves the problem of blind trust by giving you a simple ledger to log evidence one step at a time. Instead of guessing whether a tool worked or what data was sent, you get a clear, permanent record stored right in your browser. This project is a practical field guide for anyone who wants to understand how these assistants actually operate. It keeps your data private and your questions answered.

🆔 @hackernewsgithubprojects

📦 tencentyouturesearch/palm-infra

Run 100B+ AI Models on Your Laptop with Palm-Infra

Run massive one hundred billion parameter AI models directly on your laptop or a single workstation. Palm-Infra solves the memory bottleneck of large language models by using a clever SSD offloading technique. Instead of forcing your computer to hold the entire model in its limited fast memory, it keeps the core data there and streams only the specific parts needed for each word from your hard drive. This allows you to run complex expert models that would normally require expensive data center hardware, right from your local machine. The project wraps this logic in a simple C++ engine that converts standard models into a single portable file.

🆔 @hackernewsgithubprojects

📦 polyend/tracker-ce

The Open Source Polyend Tracker Firmware

Tracker CE is the open-source firmware that finally puts the power of the Polyend Tracker in your own hands. It takes the official code for all three hardware models and makes it completely modifiable. The coolest part is the new open synth engine, which lets you write your own sound generators from scratch. You can drop these custom engines right onto your device and build sounds that never existed before. It is a massive win for developers and musicians who want to push the instrument further. So if you own one of these boxes and love coding, this is your playground.

🆔 @hackernewsgithubprojects

📦 usd-wg/usd-wg-webview

USD Web View: 3D in Your Browser

USD Web View is the browser-based tool that lets you open full 3D scenes without a server. It takes complex 3D files and runs the entire engine right in your browser using web assembly. This means you can see meshes, lights, and even high-detail photo-realistic splats without installing heavy software. It handles everything from simple shapes to complex animations and material setups. No download, no install, just a file and your browser. This is huge for quick reviews and sharing 3D content. If you work with 3D assets, this saves you a ton of setup time. Check it out if you want to see 3D scenes instantly.

🆔 @hackernewsgithubprojects

📦 victorzakharov/threejs-nanites

threejs-nanites: 1 Trillion Triangles on the Web

threejs-nanites is the web graphics demo that renders one trillion triangles without dropping a frame. This project recreates the next-generation rendering technology found in modern video games, but it runs entirely in your browser using the newest web standards. It draws a massive forest containing a million trees and two hundred fifty thousand detailed statues, all at once. The magic happens on the graphics card, which automatically simplifies distant objects into flat images to save power. This means you can fly from the forest floor to nine kilometers up in the sky while maintaining a smooth sixty frames per second.

🆔 @hackernewsgithubprojects

📦 roboninecom/sts32xx-firmware

STX32XX Firmware: Smarter Robot Arms

STS32XX Firmware is the custom motor brain that finally stops robot arms from overshooting their targets. If you have ever built a small robotic arm, you know the frustrating reality: the stock software makes the joints snap into place with a jittery, oscillating buzz that ruins precision. This project rewrites the internal code to plan every move with a smooth, S-curve acceleration profile instead of jerky jumps. The real magic is gravity compensation, where the system pre-calculates the weight of each joint so the arm stays perfectly still without straining. It turns a twitchy toy into a precise tool by letting you tune the exact force response.

🆔 @hackernewsgithubprojects

📦 canitcode/video2rig

Turn AI Video Into 3D Animation With video2rig

video2rig is the open source tool that turns AI video clips into professional game animations without manual keyframing. It works by having a video generator create a short clip from a still image of your specific 3D character. The tool then uses a custom neural network to track the movement of every joint in that video. It automatically applies this motion to your character's skeleton inside Blender. This gives you a clean, editable animation ready for your game engine. It is a powerful way to create unique monster or boss animations from simple text prompts. You no longer need to animate every frame by hand.

🆔 @hackernewsgithubprojects

📦 laike9m/theysay

One Screen for All Your Socials: TheySay

TheySay puts every voice you follow into one single desktop window. It combines feeds from X, Threads, and Discord into a customizable grid, so you can watch them all side-by-side instead of bouncing between separate browser tabs. The posts appear as clean chat bubbles, making it easy to read updates without the usual clutter. It is a simple way to keep an eye on multiple conversations at once. If you follow a lot of different people, this tool keeps everything organized on your screen. It is a neat solution for anyone who wants to manage their digital connections without constant switching.

🆔 @hackernewsgithubprojects

📦 armelhbobdad/bmad-module-skill-forge

Bmad Module Skill Forge: The Memory Machine

Transform sprawling codebases into reliable, version-pinned skills for your AI agents. The bmad module skill forge solves the problem of context drift by capturing the provenance of developer discourse and documentation. It ensures your agents remember exactly which version of the code they were trained on, preventing them from hallucinating outdated patterns. This is the single most important feature: it turns messy, evolving repositories into precise, auditable skills that your agents can trust. No more guessing or stale data. Just clear, verifiable knowledge. Your AI agents will finally know their source. Watch how they learn from your code.

📰 https://news.ycombinator.com/item?id=47590450

🆔 @hackernewsgithubprojects

📦 kohei-wada/houritsu

Houritsu: Japanese Law as Git History

Houritsu is the open-source repository that turns the entire body of Japanese law into a standard code history. Every amendment that takes effect becomes a single commit, so you can use familiar version control commands to see exactly which lines changed in each update. Instead of scrolling through endless legal documents, you browse the timeline like code, isolating the precise impact of every new rule. This makes tracking legal changes simple and transparent for anyone who uses a computer. The project transforms dry statutory text into a living, searchable archive. Now you can audit the evolution of the law with the same ease as reviewing software changes.

🆔 @hackernewsgithubprojects

📦 sharktastica/shork-486

Shork 486: Linux on a 1989 Computer

Shork 486 is a working Linux distribution that fits entirely on a single floppy disk and runs on computers from 1989. This project solves a critical problem: modern operating systems have abandoned these old machines, making them useless for anything but collecting dust. By patching the Linux kernel to support hardware that was dropped years ago, Shork 486 brings a fully functional terminal to these vintage devices. It packs a web browser, code compiler, and file manager into just twelve megabytes of storage, proving that old hardware can still handle modern software.

🆔 @hackernewsgithubprojects

📦 nanboy-ronan/rvcbench

RVC Bench: The Truth About Voice Cloning

RVC Bench is the evaluation suite that finally tells you if a voice clone actually sounds human. It stops us from guessing which AI audio model is best by running every major tool through the same rigorous gauntlet. You hand it a few seconds of audio, and it grades the output on seven different scales, from clarity to emotional stability. This matters because most models claim to be realistic, but only the numbers prove it. You get a single, objective scorecard instead of vague opinions. It turns the wild world of deepfake audio into a fair contest.

🆔 @hackernewsgithubprojects

📦 dotpm/obsidian-pm

Obsidian PM: Project Management Inside Your Notes

Your coding agent can now directly edit your project board while you work in Obsidian. This plugin turns plain markdown notes into a full project manager with table, gantt, and kanban views. The real magic is the local API: when you enable it, your vault serves a Model Context Protocol endpoint, meaning a tool like Claude can pick up a task, update its status, and close it, all while the changes appear instantly in your interface. Since everything is just text files, you keep total control without locking your workflow into a proprietary cloud service.

🆔 @hackernewsgithubprojects

📦 yihaohu0118/trajectory2gym

Trajectory2Gym

Trajectory2Gym generates high-quality training data for AIs that need to use tools. Instead of letting models guess blindly, this project builds specific scenarios where every step is verified and grounded in actual decisions. It then uses a special math trick to ensure that when one complex scenario creates multiple training examples, the model doesn't accidentally overlearn one part of the conversation. This is the official code release for the research paper, including the training tools and examples. If you are building agents that need to handle complex real-world tasks, this is the blueprint for making them actually learn from their interactions.

🆔 @hackernewsgithubprojects

📦 tanishqkancharla/diffmap

diffmap: See Your Code Changes Visually

Your coding agent writes more code than you can review, but diffmap lets it explain its changes to you visually. Instead of scrolling through endless lines of text, you get interactive diagrams where every part links directly back to the source code. It is a skill that turns complex updates into clear, step-by-step visuals, helping you focus on design decisions rather than boilerplate. You can even step through animated service diagrams to see exactly how data moves and state changes over time. It is an interesting way to understand what your agent actually did, making the review process much more human-friendly.

🆔 @hackernewsgithubprojects

📦 nichokas/grokbot-linux-port

Grok Bot Linux Repack: How Arch and Fedora Users Install It

The most surprising thing about the Grok Bot Linux Repack is that it takes an official application file and splits it into pieces so you can install it using your favorite tools without changing a single line of code. The developers only release their app as a single file format, which leaves users on other systems stuck. This project solves that by automatically grabbing the official file, breaking it apart, and repacking it into formats that work for Arch, Fedora, and any other system. It runs daily to keep everything up to date.

🆔 @hackernewsgithubprojects