📦 commandcodeai/slash-design-showcase

Slash Design Showcase: Which AI Has Better Taste?

Stop guessing which AI model has the best eye for design. This open-source project is a massive collection of receipts, where developers took the same creative prompt and ran it through over a dozen different large language models. The result is a side-by-side gallery of working games and websites, built entirely by these AIs without human coding. It’s not just about seeing which model writes the most code, but which one actually produces something that looks and feels good. You can dig through the files to see how models like Opus, GPT, and Gemini handle specific tasks like building a 3D earth or a racing game.

🆔 @hackernewsgithubprojects

📦 mjoyufull/fsel

fsel: The All-In-One Terminal Launcher

Pull up your favorite app without touching your mouse, right inside your terminal. Fsel is a fast text-based launcher that scans your system for everything you have installed, letting you jump into Firefox or your code editor with just a few keystrokes. It really shines because it acts as a smart filter that learns from your habits. The more you use an app, the higher it climbs in the list, so you stop hunting for things you use daily. It even works as a drop-in replacement for your old menu tools, meaning your existing shortcuts just keep working.

🆔 @hackernewsgithubprojects

📦 accio-org/commerceagentbench

The Benchmark That Simulates Real Online Stores

Commerce Agent Bench is the test suite that finally proves AI agents can handle real store management. It builds fully working copies of platforms like Shopify and Amazon, letting software agents publish products, fix invoices, and manage inventory without breaking anything. This solves the problem of testing long, multi-step tasks in safe, repeatable environments that actually behave like the real world. It matters because it shows exactly how well these tools perform when the stakes are high and the steps are long. Use it to see if your agent is ready for the grind.

🆔 @hackernewsgithubprojects

📦 hackerest/pwneye

pwneye: The Tool That Makes Hacking Security Cameras Easy

This tool can literally type a message onto a live video feed from a physical security camera. Pwneye is a command line utility for security professionals who need to test the defenses of network video systems. It handles the messy work of finding cameras on a local network and figuring out which brand they are. The standout feature is its ability to use standard camera management protocols to not just view the feed, but to write text directly onto the screen to prove a vulnerability. It even remembers how to undo the change later so you can restore the original settings.

📰 https://news.ycombinator.com/item?id=47837626

🆔 @hackernewsgithubprojects

📦 roman-16/proton-cli

Proton CLI: Your Entire Proton Account in the Terminal

One static binary replaces your entire web browser workflow for Proton Mail, Drive, Calendar, Pass, and Contacts. This project handles end-to-end encryption locally on your machine, meaning your secret keys never leave your computer and your password never touches Proton’s servers during the login process. It is designed specifically for people who script their workflows, allowing you to pipe data directly into commands, automate backups with cron jobs, and manage encrypted files without ever opening a web interface. Because it mirrors the exact encryption logic used by official apps, it maintains full security while giving developers the raw, scriptable power of a terminal tool.

🆔 @hackernewsgithubprojects

📦 1mrnewton/cutlass

Cutlass: The Video Editor That Takes Orders

Cutlass is an open-source video editor where you can just say what you want, like 'cut out the silence,' and it handles the rest. It’s built in Rust, so it’s fast and runs locally without needing a cloud subscription. The coolest part? The AI assistant doesn’t just guess; it applies edits using the same standard commands as the timeline, meaning every change is visible, reviewable, and easily undone if you mess up. It’s currently in early alpha, so expect some rough edges, but the core editing loop is solid.

🆔 @hackernewsgithubprojects

📦 paulsp94/omacosy

omacosy: The Tiling Desktop for Mac

Your Mac just stopped feeling like a Mac and started feeling like a power tool. omacosy is a desktop environment that turns macOS into a tiling workspace with a real Super key, letting you fly through windows using trackpad swipes instead of hunting for mouse clicks. It solves the problem of macOS clutter by automatically arranging apps in a dynamic grid, so you never have to drag a window again. The coolest part is how it handles focus; your cursor simply points to any app to activate it, and the whole system idles at just one hundred and fifty-seven megabytes of memory.

📰 https://news.ycombinator.com/item?id=49374830

🆔 @hackernewsgithubprojects

📦 glitch-gaming-platform/ai-prompts-for-game-development

The Secret Order for AI Game Devs

AI Prompts for Game Development is the prompt sequence that finally stops your AI from rewriting your whole codebase every time you ask for a new feature. Most people just feed the AI random ideas and end up with messy, duplicated code that breaks everything. This repository gives you the exact, step-by-step prompts to build a game properly, ensuring the AI remembers its previous decisions instead of forgetting them. It saves you massive amounts of time and token costs by keeping your project organized from day one. The best part is seeing a full, playable game prototype come together in just two days.

📰 https://news.ycombinator.com/item?id=49288582

🆔 @hackernewsgithubprojects

📦 mondaycom/hatcha

HATCHA: The CAPTCHA for AI Agents

HATCHA flips the CAPTCHA concept on its head by proving you are not human, making it the perfect gatekeeper for AI agents in an era where bots mimic people. Instead of showing you distorted letters, it throws out brutal math problems, like multiplying five-digit numbers or reversing long strings, which computers solve instantly but humans find maddening. This open-source tool from Monday.com lets you verify AI access without needing a database, using simple cryptographic tokens to keep everything secure and stateless. If you are building tools that talk to AI, this is how you make sure the agent is actually smart enough to get in.

📰 https://news.ycombinator.com/item?id=48685677

🆔 @hackernewsgithubprojects

📦 doby-xu/witheveryone

WithEveryone: Group Photos That Actually Know Who Is Who

WithEveryone can generate a single, coherent photo of five to ten people while making sure every specific face stays exactly who it is. Most group generators today blur identities together, creating a jumbled mess where you cannot tell who is who, but this new research project solves that by assigning a dedicated token to each person and planning their layout before drawing a single pixel. It actively supervises the right face in the right spot, so the result looks like a real group shot rather than a distorted collage. An open source version is currently in training, so the full tools are on the way.

🆔 @hackernewsgithubprojects

📦 awslabs/keys_values

How Keys Values Beats Memory Limits

Keys Values lets large AI models process massive amounts of text without running out of memory. This AWS open-source tool acts like a smart filter for the model's working memory, keeping only the most important details while discarding the rest. Instead of forcing your computer to hold every single word it has ever read, it dynamically decides which pieces of information matter for the current task. This means you can fine-tune powerful models on long documents using standard hardware that would otherwise crash under the weight of data. It turns a massive memory bottleneck into a manageable calculation, making advanced AI training accessible to more researchers and developers.

🆔 @hackernewsgithubprojects

📦 solerezhang/gc-opd

GC-OPD: Making AI Reasoning Sharper on Long Tasks

GC-OPD makes small AI models reason better on long documents by fixing how they learn from mistakes. Instead of just copying a teacher’s answers, it uses a clever scoring system that weighs the teacher’s advice against a strict checker. This helps the model understand exactly which words in a long answer were wrong and why. By balancing these two signals, the model learns to be more accurate without needing massive amounts of compute. It’s a smart, efficient way to boost performance for complex tasks like answering questions from huge documents. If you’re working with AI on long text, this method could save you time and improve your results.

🆔 @hackernewsgithubprojects

📦 bawadou/ai-data-extractor

Grab Your AI Coding Chat History with AI Data Extractor

Pull every conversation from your AI coding assistants into one clean file, right on your machine. This open-source tool grabs your chat history from tools like Claude Code, Cursor, and Aider, handling all the messy local storage differences for you. It saves you from losing years of code reviews and debug sessions when an app clears its database or updates. You get normalized, easy-to-read data perfect for personal backups or fine-tuning models, without ever sending your private code to a cloud server. If you live in your IDE, this is your safety net. Grab it before it's gone.

🆔 @hackernewsgithubprojects

📦 donkeycut/donkey

Edit Videos With Chat? Donkey Cut Is Real

Donkey Cut is a free, open source video editor that runs entirely in your browser, but it lets you generate video, images, voiceovers, and music just by typing a description in a chat. It’s like having a creative director in the sidebar who can shoot the scenes you can’t actually film. You can create projects that stay local on your Mac or save them to the cloud, and the interface works the same either way. If you have a Mac companion app, it even uses your local hardware for faster transcription and screen recording.

📰 https://news.ycombinator.com/item?id=49384105

🆔 @hackernewsgithubprojects

📦 warpfront/hipfire

Run Big AI Models on Your Gaming GPU

Run large language models directly on your AMD Radeon graphics card without needing a dedicated AI chip. Hipfire is a native inference engine written in Rust that squeezes massive AI capabilities out of the GPU hardware you already own. It bypasses the usual middleman software layers, talking straight to the card to process text and images with speed that surprised even the developers. This is huge for anyone who wants powerful, private, local AI without buying expensive, power-hungry enterprise equipment. If you have a modern AMD graphics card, this project proves it is more than just a gaming tool, turning your desktop into a serious AI workstation today.

🆔 @hackernewsgithubprojects

📦 addyosmani/factory

Factory: The AI Software Factory Setup

Factory turns your GitHub issues into a self-driving code assembly line using stock Claude Code and Codex. Instead of constantly steering an agent, you install a version-controlled set of rules that lets the system triage new tickets, pick safe tasks, write the code, and open a draft pull request on its own. The real surprise is that the machine never merges anything; it stops right before the finish line to wait for your human approval. This setup uses your existing test scripts and a separate verifier to prove the code actually works before it even asks for your attention.

🆔 @hackernewsgithubprojects

📦 spade-rl/spade

SPADE: The AI That Writes Its Own Homework

SPADE is a framework where one language model does two jobs at once: it designs its own practice problems and then solves them. Usually, AI training gets stuck because we hand it a fixed list of puzzles that become too easy to figure out. This project flips that script. The model generates executable coding environments in real time, adjusting the difficulty to match its current skill level. It’s like a student writing their own test questions and then grading their own work. The result is a self-updating curriculum that keeps the learner challenged instead of letting them plateau.

🆔 @hackernewsgithubprojects

📦 milkdargon/omnialign

OmniAlign: One Model for All Language Pairs

OmniAlign does something rare: it figures out exactly which word or sentence in one language matches which in another, even when the grammar is totally different. This open source tool uses a single model to handle both word and sentence alignment across dozens of languages like English, Chinese, and German. It solves a major translation problem by finding the precise links between texts without needing a separate tool for every pair. That means you can trace exactly where a meaning shifted or how a phrase was translated, which is huge for checking quality or studying language patterns. It is built on a strong foundation and works on long documents.

🆔 @hackernewsgithubprojects

📦 udpsendtofailed/ninfer-4090

Run Qwen on a 4090

A single consumer graphics card can now run a massive twenty-seven billion parameter AI model. The project called NInfer ports the Qwen 3.8 architecture onto an RTX 4090, solving a critical problem: usually, models this large need expensive data center hardware to run smoothly. By optimizing the code specifically for this specific GPU, NInfer makes it possible to handle complex text generation and vision tasks right on your desktop without needing a cluster of servers. This is huge for developers because it puts serious, high-performance AI capabilities within reach of anyone who owns a modern graphics card.

🆔 @hackernewsgithubprojects

📦 battlewen/jailbreakskill

JailbreakSkill: The Self-Evolving AI Red Team

JailbreakSkill is the automated red-teaming framework that turns failed attacks into permanent, reusable tools. It works by first trying a standard library of prompt tweaks to stress-test an AI model. If those don't work, the system doesn't just give up. Instead, it analyzes exactly why the attack failed and automatically writes new, specialized techniques to fix it. This means the system gets smarter with every mistake it makes, creating a growing library of evolved skills. It is a brilliant way to see how AI safety gaps can be found and patched without a human manually guessing every single variation.

🆔 @hackernewsgithubprojects