📦 migsilva89/loadout

Loadout: See what your coding assistants load

Loadout lets you see exactly what your coding assistants are loading, showing every skill, command, subagent, and plugin across every assistant on your machine. The real surprise is that it reads your assistant's own session logs to show you how often each item actually fires, so you know what is truly in use instead of guessing. It solves the problem of having a hidden mess of tools you installed long ago but no longer need, giving you a clear view to manage, edit, or turn off the ones you do not use.

🆔 @hackernewsgithubprojects

📦 sadpainy/stuxnet

Stuxnet: The Code That Broke Spinning Tops

Stuxnet is the digital reconstruction that turns the world’s first physical cyber-weapon into readable code for the curious and the cautious. It is not a hack tool; it is a historical artifact. This project takes the famous worm that originally targeted industrial factory equipment and rebuilds its logic into clear, organized source files. Why care? Because it reveals how software can physically break spinning tops by quietly altering their speed. You will not deploy this. Instead, you study its tricks in a safe virtual sandbox. This is how defenders learn to spot the invisible. Takeaway: Read the code to understand the risk, then build better defenses for real-world systems.

📰 https://news.ycombinator.com/item?id=49603546

🆔 @hackernewsgithubprojects

📦 cutwire-studios/prism

Prism: The VJ Tool That Actually Makes Sense

Prism turns your computer into a live visual controller for school dances, local gigs, and sports nights. It lets you wire up videos, webcams, and live text overlays on a simple visual grid, then smash a key to trigger them instantly. The coolest part is the instant clip triggering; you map a button on your keyboard to a clip and fire it with zero delay, no complex playlists. It is built to be friendly for beginners who want big, flashy visuals without the usual steep learning curve of professional VJ software.

🆔 @hackernewsgithubprojects

📦 mem9-ai/drive9

Drive9 Keeps AI Agent Work Alive After The Sandbox Dies

A single file written by an AI agent in a temporary sandbox can survive after that sandbox is completely destroyed. Drive9 is a server-side workspace that treats an agent's working directory as durable state rather than a disposable local disk. When an agent runs tests, edits code, or saves logs, Drive9 keeps that work safe so a different machine can pick up exactly where the first one stopped. It solves the problem of losing progress when short-lived computing environments shut down. This means developers can let agents run in parallel without worrying about data loss.

📰 https://news.ycombinator.com/item?id=47683665

🆔 @hackernewsgithubprojects

📦 owasp/owasp-mcp-governance-and-risk-project

MCP Governance and Risk Project

The O W A S P M C P Governance and Risk Project is the practical playbook that stops your A I agents from running wild. As companies rush to connect A I to real tools like code editors and email, there is a serious gap in knowing who is actually in charge. This guide solves that problem by forcing teams to inventory every connection and classify each one by its highest risk. The surprising part is that it treats a simple read only tool the same as a dangerous admin tool if it can be chained together.

📰 https://news.ycombinator.com/item?id=49548839

🆔 @hackernewsgithubprojects

📦 rehan1020/mcp-india-stack

The Offline Brain for Indian Finance: MCP India Stack

MCP India Stack is the offline-first tool that lets your AI agents handle Indian tax and banking logic without internet. It bundles seventy-six local tools directly into your machine to instantly validate PAN numbers, calculate complex income tax, and decode bank codes using bundled data instead of slow remote servers. This solves the problem of fragmented, paid, and rate-limited APIs by giving developers a private, zero-latency brain for Indian financial compliance. You get precise, offline calculations for everything from GST to retirement plans without ever sending sensitive data to an external cloud.

🆔 @hackernewsgithubprojects

📦 aifoundry-org/et-platform

ET Platform: 1088 Cores in One Chip

A single chip inside this open source project packs over a thousand tiny processors, all working together to crunch numbers faster than standard computers can. This is the ET Platform, an open source system built on the Esperanto Technologies chip. Instead of just one or two fast cores, this design uses one thousand eighty eight smaller workers, nicknamed minions, to handle heavy calculations in parallel. The repository provides the complete software stack needed to run this hardware, including a simulator that lets developers test the system without buying expensive equipment. It solves the problem of massive data processing by spreading the work across hundreds of cores at once.

🆔 @hackernewsgithubprojects

📦 2600th/dlss5-video-player

DLSS 5 Video Player

A Windows app lets you watch a video and its artificially enhanced version side by side. Called the DLSS 5 Video Player, it uses a new AI technique to add extra detail to footage after you have already recorded it. You can pause any moment and press a key to instantly flip between the clean original and the sharper neural result. This is perfect for seeing exactly what the technology does without buying new hardware. The tool runs on your own computer using NVIDIA graphics cards to process local files or YouTube links. It is an experimental project, so results depend on your specific setup.

🆔 @hackernewsgithubprojects

📦 gongnyang/bookforge

Bookforge: The AI That Typesets Real Books

Bookforge turns a single line of text into a fully typeset Korean ebook that looks exactly like a printed commercial book. It handles the complex layout work, including covers, table of contents, and precise page breaks, using rules measured from real physical publications. The system uses built-in quality checks to ensure text never spills off the page or disappears, producing a professional PDF without any manual design work. It is an open source tool that proves an AI can handle the delicate details of book design. If you want to publish a beautiful ebook, this is the tool that gets the job done.

🆔 @hackernewsgithubprojects

📦 zioder/taskbarquota

TaskbarQuota: See Your AI Quota

TaskbarQuota is a native Windows app that puts your AI coding tool usage right in your taskbar, not buried in a separate tab. It automatically detects which AI tool you are using, like Cursor or Copilot, and shows your remaining quota and reset times in a compact, draggable widget next to your system tray. It even tracks live agent activity and local costs without sending any data to the cloud. It is a clean, local solution for developers who juggle multiple AI providers and need a quick glance at their limits, keeping your workflow focused and your budget in check right where you work.

📰 https://news.ycombinator.com/item?id=48439651

🆔 @hackernewsgithubprojects

📦 andrewroxby/claude-style-patch

Claude Style Patch: The Fix for Robotic AI Writing

The Claude Style Patch is the drop-in instruction set that finally cures the robotic tone in AI writing. You know that stiff, overly formal voice you get when asking an AI to write? This tool fixes it by telling the model exactly how to stop doing that. It replaces clunky, abstract sentences with plain, direct speech that actually sounds like a human. You just paste this file into your configuration, and the AI instantly starts writing clearer, more natural prose. It is a simple, effective way to make your AI interactions feel less like talking to a corporate robot and more like talking to a helpful friend.

📰 https://news.ycombinator.com/item?id=49605349

🆔 @hackernewsgithubprojects

📦 ifm-ai/uno

Uno: Making AI Talk Faster

Make large language models talk faster without losing a single word. That is exactly what the new project Uno achieves by changing how text gets generated. Instead of picking one word at a time, it uses a special technique to guess several words in parallel, all while keeping the output perfectly accurate. This means your AI assistant can respond much quicker without sounding any less smart or missing details. It solves the common problem of slow loading times by speeding up the core engine, not just cutting corners on quality. It is a cool, efficient way to make chatting with AI feel instant.

📰 https://news.ycombinator.com/item?id=49565614

🆔 @hackernewsgithubprojects

📦 ben-ic/worldfixture

WorldFixture: Your Local Cloud

Spin up a fake cloud right on your laptop. WorldFixture launches local versions of tools like Slack, Stripe, and GitHub, all pre-loaded with the same synthetic data. No real accounts or API keys needed. It solves the headache of juggling separate test environments by giving you one shared, consistent world. You can even watch scheduled events arrive in real time, like emails or payments, and reset everything with a single click. It is a brilliant way to test integrations without breaking production. Perfect for demos or just keeping your dev loop tight. Grab it and try it out.

🆔 @hackernewsgithubprojects

📦 google/artemis

Artemis: AI Android Automation

Artemis is the mobile automation tool that lets AI coding assistants drive real Android phones like a human. It solves the brittle nature of traditional app testing by using natural language instructions to navigate interfaces, completely eliminating the need to maintain fragile element selectors. The standout feature is its native integration with IDEs like Claude Code, allowing you to describe a bug in plain English and have the agent reproduce it on a physical device, capture crash logs, and return screenshots. By achieving a success rate of over ninety-nine percent on the AndroidWorld benchmark, it proves that reliable, end-to-end phone control is finally within reach for any developer.

🆔 @hackernewsgithubprojects

📦 carnot-tech/consulting-pptx-skill

consulting pptx skill

consulting pptx skill is the presentation tool that removes the robotic feel from AI generated slides. It solves the problem of generic output by forcing the model to follow a strict rulebook built from real consulting feedback. Instead of picking random templates, it constructs each slide using specific HTML components and runs automated checks to catch design errors. You get boardroom quality decks that actually look human made. It turns a simple prompt into a professional pitch deck without the usual fluff.

🆔 @hackernewsgithubprojects

📦 friedrich-m/unimate

UniMate: One Model, Infinite Skeletons

UniMate is the animation model that finally moves any skeleton you can dream of without needing a new model for each one. It solves the problem where animating a dog, a robot, or a snake usually requires separate training and tools. This single system learns from thousands of diverse movements and uses a text prompt to generate realistic motion for bipedal animals, birds, sea creatures, or even rigid objects in real time. You do not need to retrain the model or run slow optimizations for every new character. It simply takes the structure of your asset and the text description, then produces the animation instantly.

🆔 @hackernewsgithubprojects

📦 trieuntu/vietaidetector

VietAIDetector: How to Spot AI-Generated Vietnamese Text

Spot whether a Vietnamese document was written by a human or generated by artificial intelligence using a tool called VietAIDetector. This open-source software solves a growing problem where it is increasingly hard to tell real human writing from machine-generated content in the Vietnamese language. Instead of relying on guesswork, it uses a clever comparison between two specialized language models to find subtle patterns in the text that indicate its origin. The most interesting part is that it can even read scanned PDF documents, automatically extracting the text and analyzing it without any manual typing.

🆔 @hackernewsgithubprojects

📦 gair-nlp/vidaforge

VidaForge: The Video Data Factory

Transform chaotic web videos into clean, training-ready assets using VidaForge. This open research pipeline handles the messy reality of raw footage, filtering out low-quality clips and standardizing formats so your AI models can actually learn from them. It is built for serious work, integrating directly with heavyweights like V-JEPA2 to turn scattered internet media into structured datasets. The real magic is the automation: it saves researchers from spending months on manual cleanup, letting you focus on model architecture instead of video editing. If you are training vision systems, this is the backbone you have been waiting for to get your data pipeline right.

🆔 @hackernewsgithubprojects

📦 masihsultani/whiteboard-animator

Turn Any Sketch Into a Video With This Free Tool

Feed a plain whiteboard sketch into Whiteboard Animator and watch it draw itself stroke by stroke, exactly like a person using a marker. This tool figures out the order a human would use, writing words first, then tracing outlines and filling shapes in natural paths. It is the free engine behind Kinoslide, meaning you can create professional explainer videos without paying for software or needing a powerful graphics card. The most surprising part is that it runs entirely on your computer using just a standard processor, so you can animate your own diagrams privately and instantly.

🆔 @hackernewsgithubprojects

📦 soullesskid/edgemem

How EdgeMem Remembers Everything

EdgeMem is the local memory engine that lets your AI agents recall past conversations without sending data to the cloud. Instead of relying on expensive cloud APIs for every single interaction, this system builds a structured index right on your device using simple local rules and time-based signals. It handles the heavy lifting of finding relevant details from long chat histories entirely offline, only calling a large language model if you explicitly want to generate a final answer. This approach keeps your private conversations strictly private while slashing latency and costs. It is a clever, lightweight way to give software genuine long-term memory that actually works on your own hardware.

🆔 @hackernewsgithubprojects

📦 kazelad/prediction-market-trade-sdk

Prediction Market Trade SDK: One API for All Markets

One library gives you the exact same code commands for trading on Kalshi, Polymarket, Limitless, and fifteen other prediction market platforms at once. The Prediction Market Trade SDK solves the annoying problem where every betting site uses its own weird data format and connection rules. Instead of writing custom code for each one, you just point your Python or TypeScript script at the SDK, pass in your account details, and start buying or selling shares on real-world outcomes. It handles the messy on-chain signing and settlement in the background so you can just check prices and place orders.

🆔 @hackernewsgithubprojects