📦 transilienceai/shasta

Shasta: One Security System for the Cloud and AI

Shasta unifies fragmented cloud and AI security data into a single, clear picture for security teams. Instead of juggling separate tools for cloud, AI, and compliance, this open-source platform scans your infrastructure across AWS, Azure, and GCP. It automatically maps every finding to major compliance standards like the EU AI Act and ISO 42001. You get one unified dashboard where every risk, whether it’s a misconfigured server or an exposed AI model, is tracked with the same logic. This removes the chaos of disconnected tools, letting you see your entire security posture in one place. It’s a practical way to manage modern digital risk without the usual integration headache.

🆔 @hackernewsgithubprojects

📦 dagoste/squadra

Squadra: The Multi-Agent Conductor

Run multiple AI coding assistants in parallel while keeping total control over who did what. Squadra acts as the central command center for your digital workforce, letting you manage Claude, Codex, and Cursor windows from a single local dashboard. Instead of jumping between tabs hoping the bots will cooperate, it creates a shared ledger where every task, decision, and piece of code is recorded. The coolest part is the independent review system, which automatically assigns a separate AI to double-check the work, ensuring quality without you having to manually audit every single line. It turns a chaotic group of bots into a disciplined team.

📰 https://news.ycombinator.com/item?id=50069831

🆔 @hackernewsgithubprojects

📦 xd3i/pz_optimization

pz_optimization: Squeeze More FPS Out of Project Zomboid

Get your zombie apocalypse to actually run smoothly. This project takes a deep dive into Project Zomboid's Build 42 to squeeze out every last bit of performance without breaking the game's identity. It isn't just a simple settings tweak; it's a massive collection of custom code overrides and native integrations that dig into the engine's core. By reworking how the game handles memory, rendering, and background tasks, it fixes specific stutters and frame drops that plague large-scale survival sessions. The real magic is in the sheer volume of targeted fixes, from smoothing out car physics to optimizing how shadows render in complex indoor spaces.

🆔 @hackernewsgithubprojects

📦 lidor30/pokedaisy

PokeDaisy: The Dual-Screen GBA Player

PokeDaisy turns any dual-screen Android handheld into a fully functional Game Boy Advance system built exclusively for Pokémon. Most emulators treat a second screen as an optional extra, but this project treats it as the core experience, letting you run FireRed, LeafGreen, and their massive ROM hack ecosystem with dedicated layouts that feel native to the hardware. It solves the problem of playing retro games on modern devices without the clutter of generic emulation settings. By focusing entirely on Pokémon, it provides a specialized, polished interface that just works.

🆔 @hackernewsgithubprojects

📦 cxm947/fakeliang

FakeLiang: AI Agents That Prove Security Paths

A trio of A.I. agents works together to walk a security map and prove every step is real. FakeLiang reads a theoretical attack path and drives a live test lab to verify if those steps actually work. It doesn't just guess; it executes real commands and saves the raw output as proof. This solves the problem of trusting a diagram without checking the ground truth. Instead of relying on assumptions, you get a detailed audit trail of exactly what happened. It turns a static map into a verified reality check for security teams. This is how you move from theory to confirmed fact with full transparency.

🆔 @hackernewsgithubprojects

📦 krafton-ai/raon-opentts

Raon Open TTS: The Open Source Voice Model

Raon Open TTS is the open source text to speech model that gives you full control over both the code and the data. KRAFTON built this project to solve the mystery of modern voice synthesis by releasing not just the model weights, but also the massive, quality filtered dataset they used to train it. This means you can see exactly how the voice learns to speak, which is rare for systems this advanced. The real surprise is the scale of the data, with over five hundred thousand hours of public speech. This transparency allows anyone to reproduce the training process or build their own versions without guessing in the dark.

🆔 @hackernewsgithubprojects

📦 chenxiachan/textfold

TextFold: Read Papers Like a Map

TextFold turns any dense paper into an interactive map you can zoom through. Instead of staring at pages, you see the whole document at a glance, then pinch to expand only the section you need. It runs entirely on your computer, so your data stays private. The coolest part is the zooming: words slide into place as you get closer, helping you focus without getting lost in the weeds. It also works with your existing AI tools, so you can get answers right where you are. If you hate drowning in academic text, this tool makes reading way more manageable.

🆔 @hackernewsgithubprojects

📦 allspark-research/iris

Iris: The AI That Knows When to Stop Searching

Iris is an open-weight model trained to actually think while searching the web. Most AI just guesses, but Iris decides exactly what to search, how to read the results, and crucially, when it has enough evidence to stop. It uses a clever trick called discard-all to clear its memory when conversations get too long, preventing it from getting lost in the details. This means it can tackle hard questions without running out of steam. The repo even includes the exact testing harness used to measure its performance. So if you want an AI that hunts for facts like a detective, not just a parrot, this is the one to watch.

📰 https://news.ycombinator.com/item?id=49686115

🆔 @hackernewsgithubprojects

📦 abhi245y/ps5lm

PS5LM Plus: AI on Your TV

PS5LM Plus is the home console app that runs large AI models directly on your television. Instead of sending data to a remote server, this project uses the PlayStation's own graphics card to generate text locally. The standout feature is a live dashboard on your TV that displays real-time generation speeds, power usage, and temperature readings. You can download models from a built-in store, connect to your home Wi-Fi, and chat with the AI from any browser on your network. It turns your gaming setup into a private, offline brain that handles everything from quick questions to complex coding tasks right on your living room screen.

🆔 @hackernewsgithubprojects

📦 tribgames/mixdog

Mixdog: 63% Fewer Tokens

Get the same coding results while using significantly fewer tokens. Mixdog is an open-source desktop app that acts as a smart coding assistant, matching the performance of top tools like Codex while consuming sixty-three percent fewer tokens. It works by using a tiny, local model to decide exactly how much effort each step needs, so it stops burning resources on simple tasks. You can use it with subscriptions you likely already own, like ChatGPT or Claude, and it even lets you mix different models to balance speed and quality. This makes powerful AI coding far cheaper and more accessible.

📰 https://news.ycombinator.com/item?id=49930226

🆔 @hackernewsgithubprojects

📦 toddrjones/datasets

The Ultimate Data Cheat Sheet

Todd Jones, an applied microeconomist, has quietly compiled over one hundred free datasets that cover the messy, human side of the economy, from minute-by-minute time diaries to individual-level car crash records. This isn't a vague list of links; it is a curated, categorized index that tells you exactly where to find public data on crime, education, migration, and even the cost of living across counties. For students and researchers, this solves the single biggest problem in social science: the hours wasted hunting down obscure government archives just to find one specific variable. If you are building a model or teaching a course, this is your starting point.

🆔 @hackernewsgithubprojects

📦 dreamer-toby/stepquant

StepQuant: The Smart Way to Shrink AI Memory

Squeeze massive AI models into tight memory without losing their minds. StepQuant solves a tricky problem for neural networks that remember things over time. Instead of blindly chopping off precision everywhere, it figures out exactly which parts of the model's memory actually matter. It gives extra room to the bits that carry big, long-lasting errors and trims the rest. This lets you run big models on smaller hardware while keeping answers accurate. It is like packing a suitcase where you only fold the clothes you truly need. You get a much smaller footprint without the usual quality hit. Check it out if you care about efficient AI.

🆔 @hackernewsgithubprojects

📦 ajncsystem/shadowofthecolossus-pc

Shadow of the Colossus PC Port

Run the PlayStation exclusive Shadow of the Colossus natively on your Windows PC. This is not a standard emulator; it is a specialized loader that runs the game code directly on your processor while translating the graphics to Vulkan. The surprising part is how it handles the audio. Because the game uses specific console sound drivers, the launcher automatically searches your computer for existing emulator data to copy the necessary sound modules, meaning you get full audio without hunting for loose files. It even finds your save files and downloadable content on its own.

🆔 @hackernewsgithubprojects

📦 timescale/pg_vectorsearch

pg_vectorsearch: Fast Vector Search for PostgreSQL

Timescale’s new database extension, pg_vectorsearch, processes a hundred million data points using just a quarter of the memory required by existing graph-based methods. It achieves this speed by converting complex numbers into compact codes with strict error limits, allowing the system to instantly rule out irrelevant results before checking the original data. This project solves the heavy memory cost of finding similar items in a standard database, making massive scale searches practical without buying expensive hardware. It is currently an alpha version for testing, but it proves that high-performance similarity search can now live right inside your existing database tables.

📰 https://news.ycombinator.com/item?id=50086165

🆔 @hackernewsgithubprojects

📦 tornikebolokadze1-cyber/awesome-ai-pulse-georgia

Ask Your AI About This

Stop scrolling through endless GitHub lists to find the right AI tool. With this new feature, you can now ask your AI assistant directly for recommendations from a hand-picked collection of nearly four hundred verified projects. Instead of guessing which framework works for your specific coding task, you simply type a question into your editor, and the system searches a curated database to give you precise, categorized answers in both English and Georgian. It connects your AI assistant to a living library of developer resources, saving you hours of research. Now, your coding partner knows exactly where to look when you need help building with modern AI agents.

🆔 @hackernewsgithubprojects

📦 keplsiv/folderforge

FolderForge: The One-Click Mac Folder Styler

FolderForge lets you apply a single custom design to every folder in a specific directory using a smart rule system. Instead of manually changing icons one by one, you set a condition, like matching every folder named Receipts, and the app updates them all at once. It shows you exactly what will change before anything happens, so you can review the results safely. The tool keeps your original icons backed up locally, meaning you can undo the entire batch if you change your mind. Everything runs entirely on your machine with no accounts or data collection.

📰 https://news.ycombinator.com/item?id=49230965

🆔 @hackernewsgithubprojects

📦 openworkflowdev/openworkflow

OpenWorkflow: Your Code Survives the Crash

OpenWorkflow ensures your multi-step processes finish even if your server crashes or restarts in the middle of the job. It works by saving every single step of your code to a database, acting like a save point in a video game. If your application dies, the framework doesn't start over from scratch. Instead, it reads that database, skips all the work you already finished, and picks up exactly where you left off. This means you can build long-running tasks that take hours to complete, knowing they will survive power outages and deployment updates. The result is a system where your background jobs are permanently reliable without needing complex external infrastructure.

🆔 @hackernewsgithubprojects

📦 tintinweb/pi-subagents

Pi Subagents: The AI Fleet View

Pi Subagents is the pi extension that turns your coding assistant into a fleet of parallel workers. Instead of just chatting with one bot, it lets you spawn multiple autonomous agents that run at the same time, each handling a different part of your codebase. It mirrors the familiar tool patterns from Claude Code, so if you know that ecosystem, this feels right at home. The real kicker is the live widget and fleet view, which lets you watch every agent work in real time and steer them mid-run if they go off track. It is a clean, native way to orchestrate complex tasks without losing control.

🆔 @hackernewsgithubprojects

📦 myllmbox/qwen38-flash-next-recipe

Qwen38 Flash Next Recipe

A single desktop computer now serves a massive one hundred twenty five billion parameter artificial intelligence model at speeds that would have required a server rack just a year ago. This recipe project turns one Nvidia DGX Spark box into a local powerhouse, running the Qwen38 Flash Next model without needing a data center. The coolest part is the dynamic drafting system, which acts like a smart spell checker that guesses a few words ahead of time and then checks them instantly, making the output stream up to forty percent faster than previous versions.

🆔 @hackernewsgithubprojects

📦 feralfirmware/tailtalk

TailTalk: Talk to Your Old Macs

TailTalk is the network toolkit that finally lets modern computers talk to classic Macintosh systems. It rebuilds the entire AppleTalk protocol from scratch, meaning your current laptop can directly share files with a PowerBook from the nineties without any special drivers. The most surprising part is that it turns a simple USB dongle into a bridge, letting you drag and drop files between a modern computer and an old Mac using a standard serial port. It also lets you print to ancient LaserWriters from your current system. If you have old Apple hardware sitting in a drawer, this is the missing piece to bring it back to life.

📰 https://news.ycombinator.com/item?id=49678423

🆔 @hackernewsgithubprojects

📦 halluton/mindful-claude

Mindful Claude: Breathe While You Wait

Mindful Claude turns every ten-second wait for an AI response into a guided breathing session right inside your terminal. When Claude starts working, a simple animation appears, counting breaths with you to lower stress and sharpen focus. It is a clever plugin that uses dead time for a quick nervous system workout, offering patterns like box breathing or the physiological sigh. The animation vanishes the moment the answer arrives, so you stay in flow. You can toggle it on or off, or pick your favorite style, all without leaving your editor. It is a small, smart way to make coding less stressful.

📰 https://news.ycombinator.com/item?id=47313480

🆔 @hackernewsgithubprojects