📦 kentucky-ai/opentakeoff

OpenTakeoff: The AI-Ready Construction Estimator

OpenTakeoff is the first open-source construction measurement engine that lets an AI agent and a human use the exact same tools to count materials on a building plan. It works entirely in your browser without uploading your files, and it features a one-click button that automatically detects room boundaries and calculates the square footage you need for bids. What makes it truly interesting is that it records exactly how every number was found, creating a clear audit trail for your construction projects. You can even let a computer program drive the whole process through a standard AI interface.

📰 https://news.ycombinator.com/item?id=49113911

🆔 @hackernewsgithubprojects

📦 token-gremlin/natural-disasters

Natural Disasters

Create cinematic storms with zero external assets. This browser project, called Natural Disasters, generates every wave, cloud, and hurricane pixel in real-time using pure math on your graphics card. There are no downloaded textures, 3D models, or sound files; the entire ocean and weather system is built from scratch at runtime. You can fly through a hurricane or trigger a tsunami with a single key press, and the water physically reacts to the disaster. Because everything is procedural, it runs smoothly in a standard web tab without heavy downloads. It is a perfect example of how far modern web graphics have come.

🆔 @hackernewsgithubprojects

📦 wtdcode/vllm-backport

vllm-backport: Run Frontier AI on Old GPUs

vllm-backport makes a 48-gigabyte A6000 card run frontier models like DeepSeek V4 Flash, which is genuinely wild. While the industry chases new hardware, this project takes the popular vllm engine and tweaks it specifically for older Ampere GPUs, like the 3090 and A100. The main trick? It uses a technique called full CUDA graph capture to squeeze a 47 percent speed boost out of your existing setup. It is not about buying new cards; it is about making your current hardware significantly faster and cheaper.

🆔 @hackernewsgithubprojects

📦 etiennepasteur/jean-claude

Jean Claude: The Proxy That Freezes API Settings

Jean Claude lets you freeze the exact settings a tool pulls from a remote server, stopping it from changing behind the scenes. It acts as a local traffic interceptor that answers specific requests with files you control, while everything else passes through untouched. This is perfect for locking down a configuration that shifts between sessions or for testing how a tool reacts to fake data without touching the real API. You simply define a rule in a config file and run your command through the proxy, keeping total control over what the software sees.

🆔 @hackernewsgithubprojects

📦 mlo-lab/levjepa

LeVJEPA: Video AI that thinks in real-time

LeVJEPA is the first video encoder that completely ditches the complex tricks usually required to stop AI models from forgetting what they learned. By using a clever mathematical constraint called SIGReg, this project trains a single, simple brain to watch videos without needing extra machinery to keep it from collapsing. The coolest part is that because the training is so efficient, the model can learn to understand the flow of time directly. This means it doesn't just see frames; it builds a memory of what happened before, allowing it to process new video in real-time without having to re-watch the whole clip every time.

🆔 @hackernewsgithubprojects

📦 lumberjacque/loadersz-core

150 Ways to Show Your App Is Thinking

Loadersz is the canvas animation library that finally makes waiting feel like watching something happen. Instead of a generic spinning circle, it offers one hundred and fifty distinct motion states that visualize specific actions, like weaving, solving, or breathing. Each state is a unique, hand-tuned visual that tells users exactly what the app is doing in the background. It runs as a tiny, dependency-free web component, meaning it fits into any modern framework without bloating your bundle. You can switch states at runtime or lock in a single animation for maximum performance. It is the rare tool that turns a mundane loading screen into a moment of clarity.

🆔 @hackernewsgithubprojects

📦 davidcarliez/trustmebro

TrustMeBro: Testing AI Safety with Fake Data

TrustMeBro is the red-team tool that lets you test if coding agents can be tricked by fake data. It works by standing in the way of the commands your AI uses, like checking internet addresses, and swapping in made-up results to see how the AI reacts. If the AI stops when it sees bad data, it’s safe. If it pushes forward, you’ve found a weakness. This project is about finding those cracks before bad actors do, making sure your AI tools are actually reliable and safe to use.

🆔 @hackernewsgithubprojects

📦 0xsero/local-ai-registry

The Local AI Registry

One machine can run an AI model, but knowing exactly which hardware makes it fast enough is usually guesswork. Local AI Registry fixes that by treating your computer specs like a strict filter for real software. It connects specific model files to your actual graphics card or Apple chip, then shows you verified launch settings and speed benchmarks. If the data says it works, it gives you the exact recipe to start it up. If the evidence is thin, it flags the setup as untested so you know exactly what you are risking. This removes the frustrating trial and error of local computing.

🆔 @hackernewsgithubprojects

📦 badtheorylabs/prism

Prism Makes Small AI Models Act Like Giants

Prism takes a small, local AI model and gives it the mental tools of a massive frontier model without needing the cloud. It works by moving intelligence from inside the model's weights to an external harness that handles context, planning, and verification. The surprising part is that it uses the compiler itself as the judge. By running code through tests and linters, it verifies the output objectively instead of letting the model guess if it is right. This turns a simple local app into a reliable coding assistant that checks its own work. You get frontier-level behavior on your own hardware.

🆔 @hackernewsgithubprojects

📦 iamlukethedev/hermes3d

Hermes3D: The 3D Office for Your AI Agents

Hermes3D is the open-source 3D engine that turns your scattered AI agents into a visible, walkable virtual office. Most developer tools hide behind dry dashboards and endless logs, but this project treats your AI workforce like a real team you can actually see working. You don’t just read about their progress; you watch them move around a retro-style 3D space, reviewing code, holding standups, and shipping tasks in real time. It’s like giving your AI a physical headquarters where you can monitor their activity and interact with them through a shared environment rather than a command line.

🆔 @hackernewsgithubprojects

📦 sodiumsun/agenttrail

AgentTrail: The Live Map for Your AI Coders

AgentTrail is the local map that finally shows you what your AI coding agents are actually doing while they work. You kick off a task, walk away, and come back to a live dashboard that displays the agent's plan, its current tool calls, and exactly which files it is touching in real time. It is completely private, running entirely on your machine with no cloud servers or accounts required. The most surprising part is how it connects the dots between what the agent claims it is doing and the code it is actually editing, lighting up finished tasks if they suddenly need another pass.

🆔 @hackernewsgithubprojects

📦 tanstack/ai

One Codebase, Every AI

TanStack AI lets your TypeScript app switch between OpenAI, Anthropic, and Gemini without rewriting a single line of code. You write one set of instructions once, and the library handles the messy differences between providers automatically. This solves the constant headache of vendor lock-in, where changing your AI engine usually means starting from scratch. It is built with strict typing, so your editor catches mistakes before your app even runs. This tool acts as a universal translator, allowing you to build flexible, future-proof applications while staying free to choose the best model for every specific task.

🆔 @hackernewsgithubprojects

📦 s0xdk/refactoring-ui-skill

Refactoring UI Skill

Refactoring UI Skill is the design assistant that turns your fiddly, ad-hoc interfaces into polished, professional screens. This repository packages the specific design rules from the best-selling book Refactoring UI into a single instruction set for Claude Code. Instead of guessing at font sizes and colors, it forces your AI to pick values from fixed, tested scales for spacing, type, and shadows. The most surprising part is how it handles depth. It uses precise shadow rules to simulate real light, making flat buttons feel physically raised. If you are tired of your code looking like a quick sketch, this tool gives your AI the exact mechanical steps to fix it.

🆔 @hackernewsgithubprojects

📦 xiaoduoya/codex-with-chatgpt

Codex with ChatGPT: The Split-Brain Coding Tool

Codex with ChatGPT forces a strict division of labor by letting ChatGPT plan while Codex executes. This tool prevents AI agents from drifting off by giving ChatGPT read-only eyes on your code, so it can review diffs without touching your files. The system uses a local bridge to keep messages tiny, meaning ChatGPT only sees what it needs to think. It is a clever way to make your coding agent smarter without giving it dangerous write access. Your code stays safe while the planning brain does the heavy thinking.

🆔 @hackernewsgithubprojects

📦 osx360/osx360-drivers

Running Mac OS X on an Xbox 360

Running the old Mac OS X on an Xbox 360 sounds impossible, but this project proves it is possible. The Xbox 360 uses a unique processor that Apple never supported, making it a tough environment for standard Mac software. This repository provides the essential kernel drivers that translate the console hardware into something the operating system can understand. It handles everything from reading your hard drive to playing audio through the rear jack. While it is an experimental project that can freeze occasionally, it brings a nostalgic piece of computing history to life.

📰 https://news.ycombinator.com/item?id=49414569

🆔 @hackernewsgithubprojects

📦 mrrockysl/muro

Muro: The Free Mac Wallpaper App That Doesn't Slow You Down

Turn your Mac desktop into a living, breathing canvas with Muro. This native app plays smooth, looping video wallpapers directly behind your icons, keeping your system fast. While other tools are bloated and expensive, Muro uses Apple Silicon to handle the heavy lifting, ensuring your computer stays cool and quiet. You can even import your own favorite clips, and the library updates automatically with fresh content. Since it is completely free and open source, you get every feature without a single paywall. Muro makes your screen come alive without taxing your performance.

📰 https://news.ycombinator.com/item?id=49435419

🆔 @hackernewsgithubprojects

📦 miaai-lab/qwen3.8-27b-rtx-6000-pro-sglang-dspark

Run a 27B AI Model at 240 Tokens Per Second on a Single GPU

Run a massive twenty-seven billion parameter AI model on a single graphics card without sacrificing speed. This project provides a ready to use setup for the Qwen three eight twenty seven B model that fits entirely on a ninety six gigabyte RTX Pro six thousand card. The key is using a specialized method that drafts eight words at a time to boost speed, reaching over two hundred forty words per second. It handles huge documents of two hundred fifty six thousand tokens and supports up to eight users at once, all while running in a simple container that starts with one command.

🆔 @hackernewsgithubprojects

📦 rogerwelin/pg_column_tetris

pg_column_tetris: Fixing Your Database Storage Waste

Your database is silently wasting memory because of how you order your columns. pg_column_tetris is a pure SQL extension for PostgreSQL that automatically fixes this invisible problem. When you create a table, the database inserts hidden padding bytes to align data in memory. If you put smaller columns before larger ones, you waste space on every single row. This extension intercepts your table creation, calculates the wasted bytes, and forces you to reorder the columns for maximum efficiency. It works without any code changes, acting as a smart guard that ensures your data is packed tightly. This reduces disk usage and improves memory performance for large tables.

📰 https://news.ycombinator.com/item?id=47959459

🆔 @hackernewsgithubprojects

📦 omaekumiko2-create/kru

KRU Keeps Your AI Agent Secrets Secret

Handing your API keys to an AI agent usually means pasting them into the chat, which is a security nightmare. KRU solves this by acting as a local, encrypted vault that lets your AI agent use credentials without actually seeing them. Instead of exposing your passwords or SSH keys to the model, KRU securely fills in forms or executes commands in the background, keeping the sensitive text hidden from the conversation entirely. It runs locally on your machine, so your data never leaves your hands, and it works with tools like Cursor and Claude Code.

🆔 @hackernewsgithubprojects

📦 fan-treasure/toposurfel

How TopoSurfel Fixes 3D Models

Turn scattered camera photos into a clean, solid 3D model by making the math talk to the geometry. Standard 3D scanning methods often leave behind messy, floating pixels that make your objects look broken or incomplete. TopoSurfel fixes this by teaching the scan and a wireframe to improve together in real time. The wireframe acts like a guide, pulling the scattered data points into a smooth, continuous shape while filling in missing holes. It is a clever way to get a professional-quality mesh without doing hours of manual cleanup. This tool is perfect if you want to turn a simple photo set into a perfect digital twin.

🆔 @hackernewsgithubprojects