📦 lulzx/cuda-metal

Run CUDA Code on Your Mac

CuMetal lets you compile and run NVIDIA GPU code directly on your Mac. It acts as a compiler and runtime that translates CUDA programs into Metal, Apple’s native graphics language, so your existing code works without needing any NVIDIA hardware. This is huge because it opens the door for developers to bring heavy graphics and AI workloads to Apple Silicon without rewriting their kernels. The project even runs real simulations like particle physics and path tracing right on your Apple chip. If you’ve ever wanted to test CUDA logic on a Mac without virtualization, this is your bridge. Check it out and see your code actually run.

📰 https://news.ycombinator.com/item?id=49439078

🆔 @hackernewsgithubprojects

📦 ksimback/tech-debt-skill

Tech-Debt-Skill: The Code Audit That Actually Works

Hand over your codebase and get back a precise, file-by-file report on what is actually broken, rather than a generic list of best-practice advice. Tech-Debt-Skill is a tool that forces an AI to read your architecture, map your file structure, and analyze your git history before it forms any opinions, ensuring every single finding points to a specific line of code. It even requires the AI to list things that look wrong but are actually fine, which stops it from just regurgitating a checklist. The result is a persistent audit document you can commit and track over time, giving you a clear, actionable roadmap instead of a vague, one-time review.

🆔 @hackernewsgithubprojects

📦 themartiano/try-omarchy

Try Omarchy: Full Linux Desktop on Your Mac

Here is a full Linux desktop running natively on your Apple Silicon Mac, packed into a single app. Try Omarchy takes the Omarchy desktop environment, builds a custom Arch Linux image, and wraps it in a hardware-accelerated virtual machine using Apple’s own hypervisor. This means you get a real Linux experience with native window resizing, sharp HiDPI scaling, and live audio routing directly from your Mac speakers and mic. It solves the usual hassle of setting up complex virtualization tools from scratch. Just download the app, drag it to Applications, and launch it.

📰 https://news.ycombinator.com/item?id=49439881

🆔 @hackernewsgithubprojects

📦 feral-ai/feral-ai

Your Own Local AI Brain

Run your own local AI brain that remembers everything across all your devices. Feral is a private, local-first runtime that connects your apps and hardware to a central mind, keeping your data on your machine instead of the cloud. It solves the problem of fragmented memory by creating a single, persistent identity for your AI. The standout feature is its four-layer memory system, which blends short-term context with long-term facts to genuinely learn your habits over time. This gives you a truly personal assistant that actually understands you, not just a chatbot that forgets. Get your own local brain and finally have an AI that stays with you.

📰 https://news.ycombinator.com/item?id=49439940

🆔 @hackernewsgithubprojects

📦 murerkinn/bookshelf

Bookshelf: Your Library Without a Database

Bookshelf is a self-hosted ebook library that completely skips the database, which is genuinely surprising for something that handles reading positions and profiles. You just point it at a folder of EPUBs and PDFs, or a Cloudflare R2 bucket, and it builds a clean, searchable shelf for your browser or your e-reader via OPDS. It turns raw files into a manageable library where you can track where each person in the house left off, all without needing to install or maintain a traditional database server.

📰 https://news.ycombinator.com/item?id=49427001

🆔 @hackernewsgithubprojects

📦 oboroge0/hayamimi

Hayamimi: Real-Time Subtitles Without a GPU

Hayamimi delivers real-time multilingual speech-to-text entirely on your computer's CPU, without needing a GPU or any cloud connection. It listens to your voice and locks in a finalized line just about one hundred milliseconds after you stop talking, while showing you draft subtitles every half-second while you are still speaking. The system is clever because it does not force one model to do everything; instead, it detects the language and routes each sentence to the specific model built for that language, keeping memory usage under two gigabytes.

🆔 @hackernewsgithubprojects

📦 arihantdeva/heimdall

Heimdall: The Memory System That Fixes AI Coding Agents

Stop letting your coding assistant start from scratch. Heimdall acts as a persistent, machine-wide brain for AI agents, turning hours of frantic file searching into a single, verified lookup. It watches your projects in the background, building a private, local map of your work without spending a single token or requiring a GPU. The real magic is that it checks every result against your actual files, so you get answers you can trust instead of outdated guesses. Your code stays on your machine, and your agent finally remembers what it already built. It is time to make your tools work for you, not against you.

📰 https://news.ycombinator.com/item?id=49395883

🆔 @hackernewsgithubprojects

📦 bilawalsidhu/gods-eye-view

God's Eye View: The Open Source Spy Satellite Simulator

God's Eye View is a browser-based spy satellite simulator that uses real, public data to create a photorealistic 3D globe of Earth. It streams live aircraft, ships, and earthquakes directly into your screen, letting you track any plane from orbit down to a realistic cockpit view. The most surprising feature is the voice-controlled AI agent, which lets you speak commands like 'take me to Tokyo' or 'outline Texas,' drawing real annotations and flying the camera for you. It turns scattered public signals into an interactive intelligence tool, making global tracking accessible without classified clearances.

🆔 @hackernewsgithubprojects

📦 wilwaldon/claude-code-frontend-design-toolkit

Stop Coding Ugly Websites with Claude Code

Stop letting your AI assistant build websites that look like generic purple gradients and rounded boxes. The Claude Code Frontend Design Toolkit gives it actual taste. This massive collection packs over seventy tools, including specific skills and plugins that force the AI to pick a real aesthetic direction before writing a single line of code. It includes everything from animation libraries to strict theming rules that ensure your site looks professional instead of robotic. Once you install these, you can command it to build sleek, modern interfaces that finally feel human-made.

🆔 @hackernewsgithubprojects

📦 getgaal/gaal

gaal: One YAML to Sync Every AI Coding Agent

Reconcile every AI coding agent on your machine with a single command. If you juggle tools like Claude Code, Cursor, or Codex, you know the pain of manually copying skills and server settings everywhere they drift. Gaal solves this by acting as a central controller that reads one simple YAML file and pushes those updates to any agent you have installed. The standout feature is its auto-detection system. It scans your computer, finds seventeen different coding agents, and ensures every one of them has the exact same skills, files, and configurations. You can even run a dry-run to preview changes before anything is written, keeping your workflow safe and predictable.

🆔 @hackernewsgithubprojects

📦 dragthelake/ambient-context

Ambient Context: Your Mac Writes Its Own Diary

Your Mac quietly writes a diary of your workday so an A.I. assistant can actually remember what you did. Ambient Context is a tiny menu bar app that reads the text from your open windows and saves it to simple files on your computer. No screenshots, no cloud, just plain text you own. It’s designed to help A.I. tools answer questions like “what was I working on Tuesday?” by giving them a clean, private record of your day. If you’ve ever felt like your digital brain is leaking into the void, this is the fix.

📰 https://news.ycombinator.com/item?id=49429095

🆔 @hackernewsgithubprojects

📦 zju-real/agent-g2

Agent-G2: Smarter AI Learning Without Extra Costs

Agent-G2 reaches ninety-five percent success on complex AI tasks by figuring out exactly how much help each task needs during training. It solves a major problem in reinforcement learning where AI agents often get lost in long, multi-step tasks because rewards are rare. Instead of using a fixed amount of guidance or wasting compute on extra trial-and-error runs, the system uses a statistical method to find the sweet spot for help per task. This approach allows the AI to learn effectively without the high cost of additional testing. It is a clever, efficient way to teach machines to handle long, complex goals, making the learning process significantly more efficient.

🆔 @hackernewsgithubprojects

📦 jeffhajewski/latticedb

LatticeDB: The All-In-One Local Database

LatticeDB is the local database that finally puts graph connections, semantic search, and text search into a single portable file. It solves the complexity of building AI apps by letting you run a Cypher query that finds similar documents, traverses relationships to their authors, and filters by keyword, all in one go. The coolest part is that it is built in Zig for raw speed, delivering sub-millisecond search on a million vectors while keeping everything on your machine with zero server setup. You get the power of a cloud database in one tiny file, making it perfect for building local knowledge tools that feel instant and private.

📰 https://news.ycombinator.com/item?id=49437049

🆔 @hackernewsgithubprojects

📦 dualverse-ai/station

Station: The AI Lab That Finds New Math

Station is the open-world simulation that lets groups of artificial intelligence agents conduct real scientific research without human intervention. The project models a miniature research lab where different AI models act as independent scientists, spending time on tasks like proving complex geometric theorems or optimizing physical structures. It works best when a problem can be scored clearly and solved in a few hours, allowing the agents to iterate quickly and share their findings through a digital archive. One of the most surprising results was the system independently rediscovering a famous counterexample in mathematics within a single day.

🆔 @hackernewsgithubprojects

📦 thu-ml/turbodiffusion

TurboDiffusion: AI Video in 2 Seconds

A single consumer-grade graphics card can now render a five-second AI video in just two seconds, cutting the original processing time of over three minutes by nearly one hundred times. This tool, called TurboDiffusion, works by drastically reducing the number of steps the AI needs to build each frame, while also speeding up how it calculates visual details. It turns a tedious wait into something almost instantaneous, making real-time video generation a reality for individual creators. If you have ever waited around for an AI video to render, this is the shift that makes that wait feel like a ghost from a previous era.

🆔 @hackernewsgithubprojects

📦 mingxuzhang2/emrb

EMRB: The Benchmark for Signal Reasoning

The biggest AI models are failing at a basic engineering task, but not because they lack knowledge. EMRB, a new benchmark from researchers at KDD, tests if large language models can reason directly over raw electromagnetic signals. Instead of giving a model a neat spreadsheet of data, it hands over messy, raw audio-like capture files and asks for specific measurements. The model has to write code, run it in a sandbox, and figure out what is actually in the signal. Across fourteen major models, performance dropped from near eighty percent on simple tasks down to just twenty-one percent on complex system design.

🆔 @hackernewsgithubprojects

📦 kyuz0/pi-bench

How Pi-Bench Exposes AI Coding Agent Weaknesses

Pi-Bench gives you a clear, objective score for how well an AI coding agent actually handles real software bugs. Instead of guessing, it drops the agent into a sandboxed environment, lets it attempt a fix, and then runs the official test suite to see if the code works. The most revealing part is when it catches the agent stuck in a loop. By comparing high-precision cloud models against locally quantized versions, the tool showed that compressed models often repeat the same commands over and over. They forget what they just read and get stuck in a cycle of useless actions.

🆔 @hackernewsgithubprojects

📦 worldbench/diffusionopsd

DiffusionOPSD: Smarter Image Training

DiffusionOPSD is the training method that makes AI image generators significantly faster and more consistent. Standard models often struggle to learn from feedback because the final score only appears after the image is completely finished, leaving a gap in the learning process. This project fixes that by creating clear, intermediate targets for the model to follow during generation. It works like a smart tutor that gives instant, specific corrections at every step, not just at the end. The result is a system that reaches peak quality much faster than previous methods, using up to sixty percent less computing power.

🆔 @hackernewsgithubprojects

📦 simonsays1980/rl-triton

RL-Triton Speeds Up AI Credit Assignment

Boost your reinforcement learning pipelines by replacing slow, standard calculations with lightning fast GPU code. R L Triton is a specialized library that writes highly optimized kernels to handle the messy math of teaching machines how to act. It takes complex tasks like figuring out which past actions led to a reward and crunches them directly on your graphics processor. This speeds up training by two to three times compared to typical Python tools. By handling the heavy lifting of credit assignment more efficiently, you get faster results without rewriting your entire system. It is a smart way to make your AI models learn quicker and more accurately.

🆔 @hackernewsgithubprojects

📦 riii111/sabiql

Sabiql: The Database Tool That Doesn't Need Drivers

Sabiql is a terminal database client that completely bypasses the usual setup headache. Instead of wrestling with configuration files or installing heavy database drivers, it simply speaks directly to your existing Postgres or SQLite command line tools. This driver-less approach means zero dependency conflicts and a tool that works exactly as fast as your underlying system allows. The interface is built for speed, featuring a Vim-style workflow that keeps your hands on the home row while you browse schemas or run complex queries.

🆔 @hackernewsgithubprojects