📦 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

📦 to3akarin/mac-computer-use

mac-computer-use

Hand over your Mac to an AI that can actually see your screen and move the mouse for you. This tool gives large language models a real set of hands to click buttons, type text, and open windows, effectively turning your computer into an obedient assistant. The coolest part is the proof: it built a three-dimensional model of a museum exhibit from a single photo, with no human touching the keyboard for twelve minutes. It works with almost any agent you already use, like Claude or Cursor, and verifies every step to make sure it did not just guess. Your next project might be one prompt away from finishing itself.

🆔 @hackernewsgithubprojects

📦 context-labs/whip

Why Whip Is The Fastest Coding Agent

Whip is the Go-based coding agent that finally makes open-source models feel as fast as the cloud giants. While most coding assistants rely on slow, heavy runtimes that bog down your terminal, Whip compiles into a single, lightweight binary with zero external dependencies. This means it boots instantly and streams results to your screen without the usual lag. It was built specifically to keep pace with the rapid growth of local, open-weight models, giving developers a native, high-speed way to run complex coding tasks directly from their terminal.

🆔 @hackernewsgithubprojects

📦 hanyang9/umr

How UMR moves human motion to robots

Take a human dance clip and make a humanoid robot perform the exact same moves without manual tweaking. UMR handles this by looking at the surface of the body rather than counting joints. It learns how points on a moving human surface match points on a robot surface. Then it uses that match to guide the robot motion. This lets the same system work across many motion sources and many robot bodies. That is the key idea. You get a repeatable path from human movement to robot movement. The result is a tool for anyone who wants to move human motion onto humanoid robots in a consistent way.

🆔 @hackernewsgithubprojects

📦 git-pkgs/brief

Brief: The Ultimate Project X-Ray Tool

Turn any codebase into a clear, instant report with Brief. It scans a project to find the language, package manager, test runner, and linter, then outputs a structured summary. This is built specifically for AI coding agents and new contributors who need to understand a project's conventions without reading every file. The most impressive part is the outline command, which packs your source tree into a single, compact document. It strips out function bodies and keeps only the signatures and imports, giving an LLM a perfect, token-friendly map of your code. It also tells you exactly which tools are missing from your setup.

🆔 @hackernewsgithubprojects

📦 wfzyx/von

Von: Instant AI Decisions

Classify complex support tickets in under fifteen milliseconds without waiting for a giant language model to type out its thoughts. Von is a local, open-source tool that makes instant, probabilistic decisions by analyzing your data in a single pass rather than generating text word by word. It handles tricky tasks like routing urgent issues or detecting secret leaks with high accuracy, all while running right on your own machine. The best part is that it answers multiple distinct questions about the same input simultaneously, saving you from slow back-and-forth calls. If you need rapid, reliable logic for your apps, this is the lightweight engine you have been looking for.

🆔 @hackernewsgithubprojects

📦 himovo/movo

MOVO

Movo is the self-hosted platform that turns a single AI agent into a managed enterprise tool. Instead of just chatting with a model, it gives your team a shared workspace where they can search internal documents, draft reports, and generate files. The surprising part is how it handles real files. It does not just read text. It understands charts and tables inside PDFs and spreadsheets, then uses that context to write new documents back. You can run this entire system on your own hardware with a single command. It keeps your data private and gives admins full control over who sees what.

🆔 @hackernewsgithubprojects

📦 video-rebirth/hyperflow

HyperFlow: 8-Step Video Magic

HyperFlow is the video accelerator that cuts generation time by nearly thirty percent without swapping out your base model. Usually, creating video and audio with MiniMax requires forty-nine slow passes to refine every frame, which takes forever. HyperFlow drops that to just eight passes using a lightweight adapter that teaches the original model to work smarter, not harder. It keeps the official quality but makes rendering three times faster on standard hardware. If you are generating video clips, this is the shortcut you need to stop waiting around for results.

📰 https://news.ycombinator.com/item?id=49756840

🆔 @hackernewsgithubprojects