📦 plasma-ai/wiki

Wiki: The Self-Healing Knowledge Base for AI

Wiki is the command-line tool that makes sure your AI agents never forget what your project is actually about. Instead of asking an AI to guess how your code works or to manage its own messy notes, you keep all your project knowledge in plain text files. The coolest part is that the tool builds its own index automatically, so when two people edit the same file, the tool fixes the structure for you while you only write the actual content. It gives agents a clean, searchable map of your project without any manual cleanup, letting them find exactly what they need instantly.

📰 https://news.ycombinator.com/item?id=48776924

🆔 @hackernewsgithubprojects

📦 ratatui/ratatui-spinner

Spinners for Your Terminal

Turn your command line into a canvas of moving graphics with Ratatui Spinner. This library gives Rust developers six distinct types of loading indicators that run directly inside text-based applications. The standout feature is that you can drop these spinning animations right into table cells or text widgets, meaning you can show a live progress indicator inside a data grid without breaking the layout. It solves the problem of making terminal interfaces feel alive and responsive during long processes. You get full control over the motion, colors, and size, so your app looks professional.

🆔 @hackernewsgithubprojects

📦 dopbase/dopbase

Dopbase: Your Secrets in One File

Dopbase is the single-file secrets manager that puts your entire security stack in your pocket. It solves the messy problem of tracking passwords and keys across different teams without needing a complex cloud setup. The entire server, web interface, and command-line tool are packed into one tiny program you can run locally. This means your data never leaves your infrastructure, giving you total control. If you are tired of scattered environment files, this is the clean, self-hosted solution you have been waiting for.

🆔 @hackernewsgithubprojects

📦 mizorewww/laya-mlx

Laya-MLX: The 7 Millisecond AI

Laya-MLX is the Apple Silicon runtime that makes AI decisions in a single flash of light, without ever generating a word. Instead of spitting out endless text like a chatbot, it processes your question in one swift motion to instantly pick a choice or assign a score. This speed makes it perfect for real-time games where the AI actually plays a snake, making every move locally on your chip in seven milliseconds. It strips away the heavy cloud infrastructure, proving that smart, structured answers can happen right on your device in the blink of an eye.

🆔 @hackernewsgithubprojects

📦 haraduka/mevion

MEVION: The Cheap Dual-Arm Robot

MEVION is an open-source system that lets researchers build a powerful, dual-armed robot for a fraction of the cost of commercial alternatives. The project solves the problem of expensive hardware by providing complete hardware designs and the software code needed to control two arms simultaneously at high speed. It is interesting because it removes the financial barrier to studying complex robot manipulation, allowing anyone to test how machines can work with their hands. The system runs on standard computers and uses simple parts, making advanced robotics research accessible to small labs. You get a working platform for collecting real data on how robots move two arms together.

🆔 @hackernewsgithubprojects

📦 haraduka/mevius2

MEVIUS2: The Open-Source Quadruped Robot

Build a four-legged robot that actually walks on real terrain using welded sheet metal and advanced computer vision. MEVIUS2 is a practical, open-source project that gives you the complete hardware designs and software code to assemble a functional quadruped. Instead of relying on fragile, expensive factory parts, it uses robust, welded metal structures that can handle the rigors of real-world testing. The coolest part is how it combines multiple sensors to navigate its surroundings while running complex walking algorithms trained through reinforcement learning. You are not just buying a robot; you are getting the full blueprint and the brain to build one yourself.

🆔 @hackernewsgithubprojects

📦 seldonframe/seldonframe

Seldonframe: The AI Office for Local Businesses

Give every local business a digital front office that runs itself. That is exactly what Seldonframe does. Instead of juggling separate apps for websites, calendars, and customer lists, this open source tool builds a complete workspace from a single prompt. You get a live website, booking system, and automated customer agents all working together in one place. The real magic is the factory approach. Agencies can spin up fully functional digital storefronts for clients in minutes, not weeks. It is self hostable, meaning you keep full control over your data and infrastructure. Think of it as hiring a tireless, twenty four seven digital receptionist for any small business.

🆔 @hackernewsgithubprojects

📦 tigrisdata/objgit

objgit: The Git Server That Doesn't Need a Hard Drive

objgit is the Git server that runs entirely on object storage, proving you can host repositories without a traditional hard drive. It takes your code commits and stores them directly in a cloud bucket, which means if you ever need a backup, you can just download the raw files. The coolest part is that it runs sandboxed scripts every time you push your code, letting you automate tasks right from your repository. It is honestly a wild experiment, not ready for production, but it is fascinating to see how it makes your local filesystem completely irrelevant.

📰 https://news.ycombinator.com/item?id=49764571

🆔 @hackernewsgithubprojects

📦 danfromtico/autorun

Play PC Games on Your Switch

Run Halo on your Nintendo Switch. That is the whole trick. Autorun is a homebrew app that turns your Switch into a retro gaming powerhouse by running actual Windows PC games directly on the hardware. It does this by translating the old PC code into something the Switch chip understands, letting you play classics like Quake Three or WarCraft Three right from your micro SD card. You just copy your game folder onto the card, add it to the library, and hit play. It is experimental, so not every game works perfectly, but for the titles that do, the experience is genuinely wild.

📰 https://news.ycombinator.com/item?id=48717962

🆔 @hackernewsgithubprojects

📦 alexanderradahl/mac-developer-bridge

Mac Developer Bridge: Give ChatGPT a Terminal

Mac Developer Bridge is the open-source bridge that gives ChatGPT a real terminal on your Mac. Instead of just chatting, you can ask it to run specific shell commands, edit files, and manage long-running background jobs directly on your system. The project acts as a simple connection layer, letting the AI reason through your actual code and terminal without adding a second, complicated agent in the middle. It is a fascinating look at how we might blend large language models with everyday developer tools. The key takeaway is that it treats your computer as the execution environment, not just a place to store files.

🆔 @hackernewsgithubprojects

📦 pandorafuture/wx-cli

wx-cli: Your WeChat Chat History is Actually Open

wx-cli is the command-line tool that finally unlocks your encrypted WeChat chat history on Mac. It automatically finds and decrypts the local database files where your messages are stored, so you can actually read them again. Once opened, you can search through years of conversations, find that one specific message you forgot about, or even export entire chats as readable text files. It turns a locked, private mess of data into something you can actually use and understand. It's the perfect little utility for anyone who wants their own data back without asking for it.

🆔 @hackernewsgithubprojects

📦 sutro-sh/jev-align

How Jev Align Learns from You

A computer program can now learn what you think a thing is by asking you directly, instead of guessing. This tool, called Jev Align, looks at your data and finds the examples where an AI model is most confused. It shows those specific cases to you, and you simply tell it the right answer. The tool then adjusts its internal instructions to match your judgment, making the AI smarter every time you label something. It is not just a training run; you can keep using it in your own app. When the AI gets stuck on a new real-world example, it quietly saves that moment.

📰 https://news.ycombinator.com/item?id=49770872

🆔 @hackernewsgithubprojects

📦 mingchenchen/torchx

TorchX: Designing Proteins with AI

Design novel proteins that bind to specific targets by inverting a structure predictor. TorchX is a unified framework for biomolecular interactions that handles prediction, design, and scoring. While similar tools often require manual redesign steps, TorchCraft generates nanomolar binders directly from raw output. This means the sequences it produces are ready to use immediately, saving significant time in the lab. By combining these modules into one open stack, researchers can move faster from idea to experiment. It is a powerful resource for anyone working with antibody or binder design who wants to see immediate, high-quality results without extra processing steps.

🆔 @hackernewsgithubprojects

📦 daniellemky/omarchy-iphone-mirror

iPhone Mirror for Omarchy: Your Phone on the Desk

iPhone Mirror is the desktop app that turns your Omarchy Linux setup into a live, interactive mirror of your iPhone. It solves the annoying problem of constantly switching between your phone and computer by streaming your phone’s screen directly to a window on your desk. You can tap, drag, scroll, and even type on your phone using your keyboard, all over a USB cable or Wi-Fi. The coolest part is that it uses your computer’s clipboard to paste text directly into your phone, making it feel like one seamless device. It’s still an early alpha, so it works best with newer iPhones on ARM-based systems.

🆔 @hackernewsgithubprojects

📦 officialgr/agent-artificium

Artificium: An AI That Actually Lives

An artificial intelligence can now work on a single goal for days without a human touching its keyboard. This is Artificium, a new open source framework that treats a Linux computer like a physical body for a digital mind. Instead of forgetting everything after a single chat session, it manages its own memory like a real person would, saving lessons to files so it can pick up exactly where it left off. The creator built it to be a general harness for long term autonomous work, meaning it can run indefinitely, build its own tools, and even revise its own sense of purpose.

🆔 @hackernewsgithubprojects

📦 mapika/decider

decider: The AI That Doesn't Generate Text

This AI plays video games and makes business decisions without generating a single word. It is called decider, and it works by reading a situation and immediately spitting out a probability score for every possible choice you gave it. Instead of writing a reply, it looks at a support ticket and calculates the chance that a refund is needed, or which team should handle the case, all in one single pass. This solves a huge problem for developers because there is no messy text to parse, no hallucinated answers, and no risk of the model making things up.

🆔 @hackernewsgithubprojects

📦 10xchengtu/harness-engineering

Stop Blaming Your AI for Bad Code

Stop blaming your AI for messy code. This project teaches your coding assistant to actually work. Think of it as building an operating system for your bot. It gives the agent clear rules, checks its own work, and remembers what it learned. Most bad output comes from missing context, not a dumb model. This tool fixes that. It turns a chatty helper into a reliable engineer that follows your rules. Give your AI a proper harness. You will get better results with less babysitting. Stop fighting your tools. Start giving them the structure they need to succeed. Your future self will thank you for this small setup.

📰 https://news.ycombinator.com/item?id=47616335

🆔 @hackernewsgithubprojects

📦 robert-dean/deadair

Deadair: The AI Director For Radio Stations

Deadair acts as an automated director that keeps your radio station on air, even when the schedule runs out. This tool manages the running order by shuffling tracks and filling gaps with generated content, ensuring a continuous broadcast. It solves the critical problem of dead air, which is the total loss of signal or audio. By handling the playout logic, it allows broadcasters to maintain a professional presence without constant manual intervention. The system integrates with your catalog to keep the stream flowing smoothly. You get a reliable, hands-off solution for managing your broadcast schedule. It is a practical way to automate the technical side of radio.

🆔 @hackernewsgithubprojects

📦 qwenlm/qwen-image-2.1

Qwen Image 2.1: The AI Model That Creates Transparent Images

Qwen Image 2.1 is the open-source image model that finally handles transparent backgrounds without a single extra step. It takes a simple text prompt or an existing photo and builds a high-quality picture where the background is actually gone, not just covered in white. This is huge because designers and developers can now drop these images directly onto websites or apps without needing to manually cut out shapes in expensive design software. The model uses a compact structure to run efficiently while still producing sharp details and realistic textures. It turns a blank idea into a ready-to-use asset in one go.

🆔 @hackernewsgithubprojects

📦 gylive/ccodex-sleep-state

ccodex-sleep-state: The Local Fix for AI Throttling

A single Go service now sits between your browser and AI models to stop them from getting dumber or cutting you off mid-thought. Codex Sleep State runs entirely on your machine, using a web panel to let you pick which server your requests go through without touching your global computer settings. It takes over your local AI configuration automatically, backing up your files first so you can always revert if things go wrong. The goal is simple: keep your connection stable and your answers consistent, no matter what the server is doing.

🆔 @hackernewsgithubprojects