📦 animan-ai/duckbuddy

DuckBuddy: The Robot Duck With A Life

DuckBuddy is the open-source robot duck that actually has a life of its own. Forget standard bots that just follow commands; this little guy walks, hears, and sees, running entirely on its own brain without needing a phone or cloud connection. The coolest part? It has a real personality, managed by a system that tracks its energy, mood, and even body temperature. If it gets too hot or tired, it literally slows down to rest, just like a real pet. It is a fully open project where you can build your own duck from scratch.

🆔 @hackernewsgithubprojects

📦 reacher-z/awesome-rea

Awesome REA: The Ultimate Reverse Engineering Catalog

Awesome REA is the reverse engineering catalog that finally organizes the chaos of analyzing software. It solves the problem of finding the right tools, case studies, and research papers for dissecting websites, games, apps, and even hardware firmware. Instead of scattering across random blogs, you get a curated, searchable list of resources for understanding how digital things work under the hood. The most exciting part is how it tracks real-world reconstructions, showing you exactly how people rebuilt complex systems from scratch. Whether you are a curious developer or a security researcher, this is your single source for learning how to take things apart.

🆔 @hackernewsgithubprojects

📦 arpanjot-coding/avault

AVault: The Encrypted Call Recorder

AVault is the Android app that finally records your calls without needing to root your phone. It uses a clever system trick to capture audio that standard apps simply cannot touch, all while keeping the data locked away. The really cool part is that the recordings are encrypted right on your device, so the file is useless to anyone who tries to steal it. You can even set it to automatically delete old calls unless you mark them as important. It is a smart, private way to keep your voice records safe, right on your phone.

🆔 @hackernewsgithubprojects

📦 techgenius1/tvos-launcher

tvOS Launcher

Transform your clunky Android TV into a sleek, Apple-inspired home screen. tvOS Launcher replaces the default, bloated interface with a fast, lightweight experience that looks and feels just like the new Apple TV system. The coolest part? It runs entirely in pure Java with zero extra dependencies, meaning it stays buttery smooth even on budget TV boxes with minimal memory. You get a gorgeous glassy dock, rotating background scenes, and a handy control panel for quick settings, all without needing a computer for setup. If you want your living room tech to feel premium without buying a new box, this is your move.

🆔 @hackernewsgithubprojects

📦 storytold/craft-anything

Craft Anything: The AI Tool That Rebuilds Software

A piece of software can now watch you use an app, study its design, and then ask an AI to build a brand new copy of it from scratch. This project, called Craft Anything, solves the mystery of how digital things are made by turning complex code into a simple visual map. It acts like a digital detective, inspecting websites, games, and desktop programs to understand their structure without needing to read a single line of code. Once it understands the layout and behavior, it hands that blueprint to an AI builder to create a fresh version you can actually run.

🆔 @hackernewsgithubprojects

📦 muellerberndt/cadence

Cadence: A Brain That Learns Live

Cadence is the simulation framework that finally treats artificial intelligence like a biological organism rather than a static math function. It builds a continuing digital brain that perceives its environment, remembers past experiences, and adjusts its internal wiring in real time without needing a massive training dataset or a backward pass through time. The most fascinating part is how it handles mistakes; instead of crashing or freezing, the brain repairs only the specific connections that failed while keeping everything else stable. It runs this complex, living process right on a standard laptop using plain Python.

🆔 @hackernewsgithubprojects

📦 renanqueiroz/mcla-recomp

Midnight Club: Los Angeles Runs Natively on PC

Midnight Club: Los Angeles now runs natively on modern PCs and PS5 consoles by directly recompiling the original Xbox 360 code, eliminating emulation overhead entirely. This project takes the specific game files you legally own and builds a custom executable right on your machine, meaning the software contains zero game assets and no one ever has to host your files. It is not a wrapper or a patch, but a true translation of the console logic into native Windows instructions that lets the classic open-world racer hit high frame rates at fourK resolution.

🆔 @hackernewsgithubprojects

📦 solleo95/reuc-recomp

Resident Evil: The Umbrella Chronicles

Resident Evil: The Umbrella Chronicles runs natively on Windows, turning a twenty-year-old Wii title into a modern PC experience. The most surprising part is that it supports online co-op, allowing players to team up remotely in a game built for local play. The project recompiles the game code for modern processors, unlocking the frame rate and adding mouse aiming, high dynamic range, and ray-traced shadows. It also includes a full modding platform, so you can tweak textures, audio, and gameplay mechanics in real-time. You bring your own game disc image, and the launcher handles the rest.

🆔 @hackernewsgithubprojects

📦 humpalumps/ultra-elements

Ultra Elements

Ninety percent of the visual magic in this browser-based arena is calculated by your graphics card in under three milliseconds per frame. Ultra Elements is a real-time effects laboratory that lets you cast thirty-nine elemental spells at training dummies without downloading a single video file. The entire environment, from the fluid simulations to the particle swarms, is generated procedurally on your hardware in real time. It is not a game, but a precision tool for seeing how complex shaders interact with physics and light. You can tweak every variable, from the wind speed to the fire temperature, and watch the changes happen instantly.

🆔 @hackernewsgithubprojects

📦 flutter/agent-plugins

Agent Plugins: The Flutter Team's Cheat Sheet for AI Coding

Agent Plugins is the instruction set that finally makes AI coding assistants actually understand Flutter. Maintained by the official Flutter team, this repository solves a massive headache: generic AI agents often guess at best practices, leading to messy, broken, or slow code. Instead of relying on guesswork, these plugins act like a senior engineer’s guide, teaching the AI exactly how to handle tricky tasks like fixing layout errors, writing proper tests, or setting up routing. The coolest part is how it forces the AI to follow strict, repeatable workflows, meaning it stops hallucinating random solutions and starts building apps the way a pro would.

🆔 @hackernewsgithubprojects

📦 kassandraoftroy/kohaku-cli

Move Crypto Privately With One Command

Take your Ethereum and move it into private mode without touching a web interface. Kohaku is a command line wallet that connects your seed phrase directly to privacy protocols like Tornado Cash and Railgun. It handles the complex cryptography for you, letting you shield funds to hide balances or unshield them back to public accounts with simple prompts. You even get name management and stealth address support right from your terminal. It is not a casual tool and the developers warn you to test thoroughly, but for anyone wanting real privacy without the browser clutter, it is a fascinating look at how on-chain secrecy actually works.

🆔 @hackernewsgithubprojects

📦 firezone/sanstun

Sanstun: The WireGuard Engine

Sanstun is a WireGuard engine that refuses to touch your network cards or clock, handing you raw, parallel-ready crypto operations instead. It strips away the slow, blocking layers that usually throttle data, letting you feed it packets in batches and process them across many cores without locks or hidden buffering. The real surprise is that it is fully deterministic, meaning the same input seed always produces the exact same keys, which makes testing bulletproof and performance predictable. It is the raw engine for building your own ultra-fast, custom virtual private networks. If you want total control over your encrypted tunnel without the usual overhead, this is the tool to study.

🆔 @hackernewsgithubprojects

📦 divagr18/qwenpu

The LLM That Runs Inside An LLM

QwenPU is the language model that runs a tiny computer inside its own brain. It takes a popular four billion parameter model and compiles a full RISC-V processor and vector unit directly into its neural network weights. The result is a machine that can execute real C programs without any external hardware. It actually runs Andrej Karpathy’s tiny story writer, which uses this internal computer to generate text. Every step is calculated by the model’s own layers, making it a computer inside a computer. It is still very large and slow, but the concept is wild. A single neural network that thinks and computes at the same time.

🆔 @hackernewsgithubprojects

📦 rowow-llc/open-sourced-off-the-shelf-ion-exchange-membrane

Build a $1 Ion Exchange Membrane at Home

Fabricate a functional ion exchange membrane for under one dollar per square foot using materials found in any hardware store. This project provides the complete open-source recipe and patent to create this critical component for electrochemistry without specialized suppliers or industrial equipment. By mixing pulverized water softener resin with standard PVC plastic and common solvents, you can cast your own membrane that filters ions as effectively as expensive commercial alternatives. This dramatically lowers the barrier to entry for recovering precious metals from e-waste or building flow batteries. It turns a costly industrial monopoly into a DIY hobbyist project.

🆔 @hackernewsgithubprojects

📦 jaydenteoh/soft-mtp

Soft Multi Token Prediction Speeds Up AI

Soft Multi Token Prediction is the training method that finally makes language models generate text faster without sacrificing quality. The repository provides the official code for a technique that fixes a hidden flaw in how neural networks are taught to predict multiple words at once. Standard methods force the model to treat its internal calculations as separate, which wastes a massive amount of computational power. By using a clever mathematical trick to share information between the model's internal layers, this project allows the network to draft several words simultaneously.

🆔 @hackernewsgithubprojects

📦 mikeparcewski/wicked-studio

Wicked Studio: The Control Room for Coding Agents

Wicked Studio is the control room that lets you watch your coding agents work in real time. It solves the problem of flying blind when AI writes your code, because here you start a job with a simple chat, then sit back and observe the agents working inside safe, isolated environments. The coolest part is that you don't have to trust the process blindly; the interface shows you exactly what the agent did, so you can review the evidence and approve only what actually matters before it touches your real files. This turns a mysterious black box into a transparent workspace where you stay in charge of the final result.

🆔 @hackernewsgithubprojects

📦 ethbak/icon-composer-mcp

Icon Composer: Liquid Glass Icons via AI

Icon Composer is the tool that turns a flat logo into a living Apple Liquid Glass icon without opening a single design app. It speaks directly to AI assistants, letting you build, tweak, and render high-fidelity icon bundles right from your chat. This solves the tricky problem of matching Apple’s strict design standards by automating the complex rendering pipeline. It is the perfect bridge for developers who want pixel-perfect, store-ready assets without the usual design friction. If you build for Apple platforms, this is your shortcut to professional-looking visuals.

🆔 @hackernewsgithubprojects

📦 synchopate/nemotron-30b-cpu-256k

Nemotron 30B CPU 256K

A thirty billion parameter language model now runs entirely on a standard laptop processor without any graphics card, achieving speeds that feel instant for interactive coding. This repository explains how to run Nemotron thirty B on a central processing unit using a hybrid architecture that replaces most attention layers with state space models. This design drastically reduces memory usage, allowing a massive two hundred and fifty six thousand token context window to fit comfortably in system memory. By combining this efficient model with low level system optimizations, the setup handles large context windows at speeds rivaling dedicated hardware.

🆔 @hackernewsgithubprojects

📦 bendbss/riposte-frontline-source

Riposte: Frontline

Riposte: Frontline is the open-source first-person shooter that builds every single 3D object from pure math code instead of importing standard 3D model files. You might not expect a full-featured game with dynamic water and complex vegetation to run so smoothly in a plain web browser, but this project proves the engine can handle it all using just JavaScript. It is completely free to download, run locally, or remix for your own projects under a permissive license. The codebase is massive and runs entirely in your browser without any install. If you want to see how game developers build worlds from scratch, grab the source and start exploring.

🆔 @hackernewsgithubprojects

📦 agent-passport-system/agent-passport-system

Agent Passport: Giving AI Agents a Verifiable Identity

Give any AI agent a cryptographically signed identity that proves exactly what it is allowed to do. The agent passport system is an open protocol and SDK that stops agents from acting on vague trust by checking their permissions before they perform any task. Think of it as a digital badge that a system verifies in milliseconds, ensuring an agent only does what it was specifically hired to do. If the agent tries to step out of bounds, the system blocks the action instantly and leaves a permanent, signed record of the attempt. This gives developers a way to build autonomous tools without handing over the keys to the unknown.

🆔 @hackernewsgithubprojects