📦 graham33/nixos-dgx-spark

NixOS on DGX Spark

Get NixOS running on your NVIDIA DGX Spark to simplify complex AI setups with reproducible playbooks for everything from image generation to model fine-tuning. The repository provides ready-to-use configurations that handle the messy GPU drivers and CUDA dependencies automatically, letting you focus on creative work rather than system administration. You can boot from a USB drive or add a simple module to your existing setup to access a dashboard and dozens of tested environments. It works on both the DGX Spark and the Asus Ascent, making high-performance local AI accessible without the usual headache. This is a clean way to bring modern Linux management to powerful hardware.

📰 https://news.ycombinator.com/item?id=49146267

🆔 @hackernewsgithubprojects

📦 heheyas/context-scaling

Context Scaling: Structured Prompts for AI Image Generation

Context Scaling is the research project that turns messy human language into precise, structured blueprints for AI image generation. Most text-to-image models struggle because long, descriptive prompts confuse the diffusion process, leading to blurry or inaccurate results. This team discovered that the model’s performance actually depends on how structured the input text is, not just how long it is. By breaking down prompts into clean JSON schemas with specific fields for objects and geometry, the system achieves much sharper images. It even lets you edit one part of a scene without rewriting the whole request.

🆔 @hackernewsgithubprojects

📦 aakk007/roguecleaner

RogueCleaner

Toss your computer’s right-click menu back under your control with RogueCleaner, a clever little tool that hunts down the sneaky digital junk that software vendors love to sneak into your Windows system. Most of us install a simple app for one task, only to watch it quietly hijack our right-click menus, force itself into startup, register background services, and even grab control over how files open. RogueCleaner scans all those hidden spots, translates those messy registry paths into plain English, and shows you exactly what is going on and who is responsible. You then pick what to remove, knowing the tool has already backed everything up safely.

🆔 @hackernewsgithubprojects

📦 iximiuz/shellgym

Shell Gym: Master Linux Commands with Real Reps

Type real Linux commands in your usual terminal while a background app watches your screen and marks exercises complete the moment you hit the right keys. This interactive trainer treats command-line practice like weightlifting, offering quick reps that build muscle memory without touching your shell setup. You get split-screen guidance where a browser shows tasks and your terminal does the work, all while the system observes your moves from the outside. It turns dry reading into active fluency, letting you drill file navigation, process killing, and piping until they become second nature. Grab a disposable Linux machine and start building the reflexes that actually stick.

🆔 @hackernewsgithubprojects

📦 wangqinsi1/rlsvr

RLSVR: Zero-Human-Annotation AI Training

Rlsvr is the research project that finally teaches image understanding models to improve themselves without any human labels. Most AI training is expensive because people have to manually check every answer. This tool flips the script by letting the model play strategy games against itself using random pictures. It creates its own puzzles, tests its own logic, and learns from the mistakes it makes while playing. This means you get smarter models trained on completely free, self-generated data instead of costly manual reviews. It is a clever shortcut that proves you do not need human help to build better reasoning skills.

🆔 @hackernewsgithubprojects

📦 pg83/shitty

Shitty is the world's fastest terminal emulator

Shitty is the blazingly fast terminal emulator that finally delivers raw rendering speed on modern computers. This serious tool is built to outperform every major competitor by keeping all terminal state on the CPU and using native graphics hardware for instant updates. It starts in milliseconds and handles massive data streams without breaking a sweat. The project is actually a hard fork that completely rewrote the original code from scratch to ensure maximum performance. It uses advanced testing suites to guarantee perfect compatibility while remaining completely indestructible against weird input data. You get flicker-free resizing and precise text rendering without needing any external fonts.

📰 https://news.ycombinator.com/item?id=49149326

🆔 @hackernewsgithubprojects

📦 f10409/radharmony

RadHarmony: The Radiological Data Harmonizer

RadHarmony is the Python library that finally unifies messy medical imaging datasets into one clean, ready-to-use format. It saves radiologists and researchers from spending weeks wrangling incompatible file structures by wrapping everything into simple PyTorch datasets you can drop straight into your training loops. You get instant access to dozens of chest X-ray, CT, and MRI sources with standardized labels and transforms, plus a powerful evaluation toolkit to test models with just a few lines of code. It is a massive time-saver that turns chaotic data into consistent training pipelines for medical AI.

🆔 @hackernewsgithubprojects

📦 bingjunluo/aso

Adversarial Style Optimization: The VLM Jailbreak Trick

Adversarial Style Optimization lets researchers trick visual language models into ignoring their safety rules by changing how images look. It works by finding visual styles that confuse the model’s safety filters while keeping the content recognizable. The process uses a reward system to fine-tune an image editor, creating specific visual triggers that make the model refuse to block harmful requests. This is a serious security issue because it shows that safety alignments can be broken just by altering presentation styles, not the actual message. Understanding this helps developers build better defenses against these clever workarounds.

🆔 @hackernewsgithubprojects

📦 farinchan/chatery_whatsapp

Automate WhatsApp with Chatery WhatsApp API

Chatery WhatsApp lets you automate the entire messaging experience right from your own server. Instead of manually typing out replies, you can use a simple web interface to send text, images, and even location pins to anyone you want. You can even schedule bulk messages to go out to multiple people in the background without freezing your computer. It handles everything from logging into your account to saving media files automatically, so you can focus on what matters. If you need to control your chats programmatically, this is the straightforward way to do it.

🆔 @hackernewsgithubprojects

📦 miaai-lab/deepseek-v4-flash-one-dgx-spark

DeepSeek-v4-Flash-One-DGX-Spark

This repository turns a single NVIDIA DGX Spark into a fully functional, on-device AI server without needing the cloud. It wraps the DwarfStar four engine, a lean C and CUDA tool, into simple start and stop scripts that handle the heavy lifting like downloading eleven-gigabyte model weights and building the server in one go. Instead of wrestling with complex configurations, you just run one command and get a local OpenAI-compatible interface ready to go on port eight eight eight eight. It skips standard tools like vLLM because this setup needs a specific engine to run its unique model efficiently.

🆔 @hackernewsgithubprojects

📦 agentswarms-fyi/agentswarms

AgentSwarms: Build Your Own AI Swarm Platform

Deploy your own AI platform that lets you build intelligent agents and orchestrate them into coordinated swarms. AgentSwarms brings together business intelligence and multi-agent automation into one self-hosted workspace. You get a visual canvas to design agent workflows, connect your own data sources, and run queries directly against your databases. The real magic is watching multiple agents collaborate, share knowledge, and execute complex tasks while you monitor every move through detailed execution traces. It gives you full control over your models, data, and infrastructure without locking you into a specific cloud provider.

📰 https://news.ycombinator.com/item?id=49103784

🆔 @hackernewsgithubprojects

📦 micro/mu

Mu: Real Tools for Agents

Mu turns the messy internet into a clean toolkit for your AI assistant. Instead of just chatting, the agent can actually read your email, check weather, search news, and manage your calendar because it controls real servers, not just API wrappers. It gives both humans and machines access to the same live data through one simple connection. You can run it yourself or use their cloud, and it even handles payments in cryptocurrency. It is basically a digital assistant that actually has hands to grab things.

📰 https://news.ycombinator.com/item?id=49148899

🆔 @hackernewsgithubprojects

📦 syncular/syncular

Syncular Offline SQL Sync

Syncular lets your app run fully offline by keeping a real SQLite database on your device and syncing changes when you reconnect. Instead of guessing about data, it uses a strict server log to decide the truth, so conflicts disappear automatically. You get local speed for every query while staying in sync across phones, browsers, and desktops. It handles encryption, works with React, and even supports Flutter or Swift. Your data stays fast and safe, no internet required.

📰 https://news.ycombinator.com/item?id=49142794

🆔 @hackernewsgithubprojects

📦 local-inference-lab/blackwell-llm-docker

Blackwell LLM Docker

This repository provides ready-to-use Docker containers that run massive AI models on the newest NVIDIA Blackwell GPUs, bridging the gap between powerful new hardware and popular open-source inference tools. While setting up deep learning environments on these specialized chips can be notoriously difficult, this project simplifies the process by bundling complex libraries like SGLang and vLLM with custom optimizations for the specific GPU architecture. It handles the tricky parts, such as compiling source code and configuring communication protocols, so you can start generating text or images immediately without spending days on system administration.

🆔 @hackernewsgithubprojects

📦 garagehq/nightcrawler

Nightcrawler: The Phone That Pentests Networks

Drop a modified OnePlus phone on a network and walk away. Nightcrawler uses a tiny local AI running entirely on the device's graphics chip to autonomously hunt for vulnerabilities without any internet connection. It acts like a patient security tester, slowly mapping out connected devices and probing for weak spots over several hours. The clever part is the stealth approach: it moves slowly, blends in with normal traffic, and never blasts the network, making it much harder to detect than standard scanning tools. A safety layer ensures it only tests areas you explicitly authorized, preventing accidental chaos.

📰 https://news.ycombinator.com/item?id=49154127

🆔 @hackernewsgithubprojects

📦 devsforge/marketplace

Claude Code Marketplace

Plug in over a hundred specialized expert profiles to instantly transform Claude Code from a simple chatbot into a full virtual development team. You get dedicated specialists for everything from legal compliance and security auditing to mobile app design and database tuning, all working inside your terminal without adding any external dependencies. Instead of guessing which tool to use, you just ask the right expert to handle the heavy lifting, whether you need a rapid prototyper for new ideas or a senior architect to review complex systems. It turns a generic coding assistant into a complete, enterprise-grade workspace with curated plugins that actually understand your specific project needs.

🆔 @hackernewsgithubprojects

📦 spences10/my-pi

My Pi: The Coding Agent That Finally Keeps Track of What It Does

My Pi is the coding agent distribution that finally turns chaotic AI help into a transparent, trackable workflow. Most coding assistants just guess and hope, but this one ships with a live dashboard that records every thought, decision, and error in real time, so you can actually see what is going on instead of guessing. It also bundles tools to safely hide secrets, coordinate between multiple agent sessions, and enforce coding standards before bad code ever touches your files. Instead of installing a dozen different plugins, you get this complete, ready-to-run setup that works right out of the box.

📰 https://news.ycombinator.com/item?id=48690629

🆔 @hackernewsgithubprojects

📦 vercel-labs/marketing-team-eve-template

Marketing Team Eve Template

Get a whole marketing crew working for you by dropping a request into a team lead that knows exactly who to delegate to. Instead of one AI trying to do everything, this template sets up a product marketer, a content writer, an SEO expert, a social media coordinator, and an email specialist, each with their own skills and tools. You bring the task, like a blog post or a newsletter, and the lead routes it to the right specialist who writes the draft, checks it against brand guidelines, and hands it back ready for you to approve.

📰 https://news.ycombinator.com/item?id=49150225

🆔 @hackernewsgithubprojects

📦 jaineet17/causal-agent-replay

Find the Exact Step That Broke Your Agent

Causal agent replay lets you pinpoint exactly which step caused an LLM agent to fail by rewinding the decision and running it again. Instead of just watching a trace, you intervene on specific moments to see if the bad outcome changes. If changing that step fixes the result while later steps do nothing, you’ve found the true cause. It’s like time-travel debugging for AI, using math to prove where the error actually happened so you can fix it for real.

🆔 @hackernewsgithubprojects

📦 estebanpdn/zelda-alttp-3ds

Zelda A Link to the Past on 3DS

Play a classic Nintendo adventure on your handheld by using this clever port that brings the beloved Zelda sequel to life on the Nintendo three dimensional system. The repository takes the original two-dimensional masterpiece and adapts it for the console’s unique dual screen layout so the gameplay feels fresh yet familiar. You get to explore the same magical world with enhanced visuals that fit perfectly in your hands without losing the charm of the original. It is a neat piece of fan-made engineering that proves old games can still feel brand new when given the right hardware.

🆔 @hackernewsgithubprojects

📦 canivibecodeit/canivibecodeit

Can I Vibecode It?

Canivibecodeit is the directory that finally kills your SaaS bills with one AI prompt. It answers whether you can replace paid subscriptions like scheduling apps or analytics tools with a single, copy-paste instruction for an AI coding agent. Instead of vague advice, it gives you a concrete verdict, the exact code to build a personal version, and an honest list of what functionality you actually lose in the process. Think of it as a utilitarian death list for monthly expenses, where traffic-light badges tell you instantly if a service is truly replaceable.

🆔 @hackernewsgithubprojects