📦 kelsidavis/wowee

WoWee: The Open Source WoW Client

WoWee runs the massive, complex game World of Warcraft on your own computer, but it ignores the official launcher entirely. Instead of relying on closed-source code, this project rewrites the entire client from scratch in C++, allowing it to talk directly to your game data. The coolest part? It builds its own graphics engine using modern Vulkan technology, meaning you can play classic expansions with crisp, modern visuals and smooth performance that the old client never offered. It is a fascinating look at how game engines actually work under the hood. If you are into open source development or just love the history of gaming, this project is a must-see.

📰 https://news.ycombinator.com/item?id=49821907

🆔 @hackernewsgithubprojects

📦 spotify/portal-ai-plugins

Spotify Portal AI Plugins

Spotify Portal AI Plugins is the coding helper that turns your AI assistant into a full-time operations partner. Instead of hunting through endless documentation to find out who owns a specific service or why it is failing, this tool connects your AI directly to Spotify’s internal software catalog. You simply ask your assistant a plain language question, and it instantly fetches the right owner, health status, and technical details for you. This saves developers hours of manual digging by letting the AI handle the busywork while you focus on the actual code.

🆔 @hackernewsgithubprojects

📦 sevenevesai/riso-windowseat

riso-windowseat

Create short, hand-drawn animated films that look exactly like vintage ink prints, all from a single web page. The riso-windowseat project uses computer code to simulate the messy, textured look of a screen-printer without any actual ink. You get full control over the colors, the paper grain, and the movement, making it possible to produce professional-looking visual stories right in your browser. This is a fantastic way to learn how to mix coding with traditional art techniques, and it gives you a ready-made toolkit to start making your own unique pieces immediately.

📰 https://news.ycombinator.com/item?id=49817101

🆔 @hackernewsgithubprojects

📦 socai-io/jev-social

Jev Social: An AI That Browses Social Media for You

Jev Social makes an AI agent drive your actual Chrome browser to find social media posts on Instagram, TikTok, and LinkedIn. Instead of guessing what is online, Jev chooses specific actions like searching for a topic or opening a particular profile. It uses the Socai command line tool to perform these tasks in a real browser session. The system records every click and piece of text it sees, creating a detailed report with direct links to the source posts. This means you get verifiable proof of what was found, not just a vague summary.

🆔 @hackernewsgithubprojects

📦 ethanplusai/astra-flash-orchestrator

Astra Flash Orchestrator: The AI Workflow That Cuts Costs

Astra Flash Orchestrator is the coding workflow that keeps your expensive AI on the important decisions while letting a cheaper model handle the heavy lifting. It works by having your main AI plan the project and review the final result, while a separate, budget-friendly builder handles the actual writing and testing of code. This approach ensures that you only pay top-tier rates for the parts that truly need deep reasoning. In a real test, this method reduced costs by nearly ninety-eight percent without sacrificing quality. It is a simple way to get more done without overspending.

🆔 @hackernewsgithubprojects

📦 drobiazkin/ai-agent-architecture

AI Agent Architecture: The Free Engineering Book

ai agent architecture is the free engineering book that finally teaches you how to build systems you actually own, not just rent. It cuts through the marketing noise to show you the real mechanics, costs, and trade-offs of running your own models, from fine-tuning to serving, without needing a vendor’s permission. If you want to stop guessing why your AI fails and start understanding exactly how it works under the hood, this is the blueprint you need to take back control.

🆔 @hackernewsgithubprojects

📦 dynamiq-ai/pragmatiq

Pragmatiq: Banking Data Made Simple

Take messy bank histories and turn them into smart, usable signals. That is exactly what Pragmatiq does. It is an open source tool that builds a foundation model for financial behavior without needing your actual private data. It uses a clever synthetic simulator to generate realistic fake bank accounts, complete with transactions and app sessions. This lets you train and test your AI models safely before touching real customer information. The project handles everything from data generation to final model serving. It even includes built in checks to ensure your model works reliably over time. It is a fantastic starting point for anyone building risk systems.

📰 https://news.ycombinator.com/item?id=48601945

🆔 @hackernewsgithubprojects

📦 winchxyz/spiralist

Spiralist: The Photo-to-Line-Art Converter

Turn any photo into a drawing made of one continuous line, then watch a film of it being drawn. Spiralist is a browser app that takes your picture and redraws it with a single unbroken stroke, mimicking real drawing media like fountain pen or pencil. It calculates exactly how long it would take a human to draw it by hand and films the process in a cinematic timelapse. Everything runs locally, so your photo never leaves your device. It’s a fun way to see your favorite images transformed into elegant, one-line portraits.

🆔 @hackernewsgithubprojects

📦 keltokhy/jgrep

grep, but you describe the meaning

A command line tool called jgrep lets you filter data by meaning instead of matching exact words. You type a plain description, like a user is getting frustrated, and it uses a fast, tiny artificial intelligence to judge if each line fits that idea. It works in about two hundred milliseconds and costs less than a thousandth of a cent per line. That means you can pipe live logs through it and get instant, natural language results. It turns the old search command into something that actually understands what you are looking for. You stop hunting for specific keywords and start finding the stories behind your data.

🆔 @hackernewsgithubprojects

📦 shinshin86/still2rig-psd

Still2Rig PSD: The AI Tool That Animates Your Anime Art

Still2Rig PSD is the automated workflow that turns a single static anime character image into a fully layered and motion-ready file. The tool connects to a secure cloud computer to run a specialized model that splits your picture into individual parts, like hair and clothing, without you touching a single slider. It then assembles these pieces into a structured document and runs strict checks to ensure the layers align correctly. You can even preview the motion right in your browser before exporting. It is a clever way to bridge the gap between static art and animation without manually separating every pixel yourself.

🆔 @hackernewsgithubprojects

📦 yedp123/comfyui-yedp-uv-painter

ComfyUI Yedp UV Painter

Paint textures directly onto your 3D models using AI, right inside ComfyUI, without ever leaving your browser. ComfyUI Yedp UV Painter lets you isolate specific parts of a complex mesh, like a belt or a shoulder pad, and generate unique textures for each one independently, just like working with layers in Photoshop. The coolest part is the live sketch tool: draw hard-surface details directly on the two-dimensional map and watch them project onto the three-dimensional geometry in real-time. This is perfect for artists who want precise control without needing a massive graphics card, as it runs smoothly on modest hardware.

🆔 @hackernewsgithubprojects

📦 shitagaki-lab/see-through

See-Through: Turn One Anime Image Into 23 Layers

Turn a single static anime drawing into a fully manipulatable twenty-five-dimensional model with just one click. This open-source research tool, known as See-Through, takes a flat illustration and automatically slices it into up to twenty-three distinct semantic layers, handling everything from hair and eyes to clothing and accessories. It solves the tedious, manual labor of separating character parts and filling in hidden areas by guessing what lies behind overlapping objects. You get a professional-grade layered file ready for animation, effectively skipping the most boring hours of traditional character rigging. It is a clever bridge between a flat sketch and a live, moving avatar.

📰 https://news.ycombinator.com/item?id=47587319

🆔 @hackernewsgithubprojects

📦 billy-enrizky/openbrowser-ai

OpenBrowser: The AI That Codes Your Way Around the Web

OpenBrowser is the browser automation framework that lets an AI write its own Python code to do the clicking for you. Instead of guessing where a button might be, the large language model generates actual code to interact with the page in a persistent workspace. This means it can navigate complex sites, fill out forms, and scrape data with the precision of a developer, not just a script. It works directly with your existing browser, so you can watch it think, type, and extract exactly what you need.

🆔 @hackernewsgithubprojects

📦 sharziki/semdecide

SemDecide: grep for meaning in your terminal

Pipe text into SemDecide and get a typed semantic decision back, right in your terminal. It acts like grep for meaning, letting you ask if a log entry describes an account takeover or if a customer is about to churn. The tool returns a clear verdict with a probability score and a stable exit code, so your shell scripts and CI pipelines can handle AI judgments without messy parsing or flaky glue code. It keeps uncertainty visible, so you never accidentally treat a low-confidence guess as a hard fact. It’s a slick way to bring semantic intelligence into Unix workflows without writing prompts.

🆔 @hackernewsgithubprojects

📦 openrsi-foundation/openrsi-index

OpenRSI Index: Can AI Do Real Science?

Test whether AI can actually do original research, not just follow instructions. OpenRSI Index is a growing collection of hard, real-world scientific tasks designed to see if AI agents can push the frontier of knowledge instead of just repeating known results. The coolest part? It runs these tasks on massive clusters of GPUs, like hundreds of them, to handle genuinely complex problems like optimizing training for huge language models or improving video understanding. Think of it as a stress test for AI's ability to be a real researcher. It’s not about speed or simple math; it’s about sustained, high-level scientific progress.

🆔 @hackernewsgithubprojects

📦 contrastive-lm/clm

CLM: The AI That Decides at Light Speed

CLM is the fast decision engine that picks the right action in milliseconds without the usual heavy lifting. Instead of a massive model thinking through every step, it uses a clever trick to instantly match the current situation with the best possible move. This makes it perfect for real-time tasks like playing games or quickly checking if your code is correct. You can even plug it into your own projects to make your bots smarter and way cheaper to run. If you need an AI that acts on instinct rather than slow reasoning, this is the tool to watch.

🆔 @hackernewsgithubprojects

📦 mihailescu2m/llama.cpp

Run Huge AI Models On Your Mac

llama.cpp is the C engine that lets your laptop run massive AI models that are far too big to fit in its memory. While most software demands expensive cloud servers for these tools, this project streams the model's heavy parts directly from your hard drive as you need them, letting you run a two hundred billion parameter model on a standard Mac with just sixty four gigabytes of memory. By treating your disk speed as the real limit rather than your memory, it opens the door for local, private, and massive language processing on hardware you already own.

🆔 @hackernewsgithubprojects

📦 midspiral/lemmascript

Lemmascript: Proving TypeScript Code

Lemmascript lets you write ordinary TypeScript while proving your code is actually correct. You add simple comments to your files describing what should be true. The tool then turns your TypeScript into a format that a formal proof checker can analyze. It hands off your logic to serious verification engines to confirm that your functions behave exactly as intended. If the math checks out, you get a guarantee that your logic is sound. This is huge for developers who want certainty without rewriting everything in a new language. It bridges the gap between daily coding and deep verification.

📰 https://news.ycombinator.com/item?id=47849102

🆔 @hackernewsgithubprojects

📦 geastack/examples

GeaStack Examples: Run One App Everywhere

Take a single piece of code and run it on a browser, a tiny microcontroller, or a custom operating system without touching a single line. GeaStack Examples is a collection of ready-made demo apps that prove exactly how that works. The coolest part is the manifest file inside each app. It is just a simple list that tells the system where the app lives and what hardware it can run on. No more juggling separate builds or rewriting logic for different screens. One project, one set of rules, infinite targets. If you want to build software that truly doesn't care where it runs, this is your cheat sheet.

📰 https://news.ycombinator.com/item?id=49807021

🆔 @hackernewsgithubprojects

📦 samyost1/3dicon

Make Animated 3D Icons with AI

Drop in a single text prompt and get a finished, transparent WebP icon that loops perfectly inside your app. This tool is a skill for Claude Code that handles the entire workflow, starting with a generated image and using a clever trick to make the video loop seamlessly by matching the first and last frames. It also handles the tricky background removal mathematically to ensure soft edges stay clean, so you are not left with ugly halos around your icon. You stop for approval after every major step to avoid wasting money, giving you total control over the final result.

🆔 @hackernewsgithubprojects