📦 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

📦 paradise-runner/toast

Toast: The Full IDE Hidden In Your Terminal

One tiny binary quietly packs a full code editor, file explorer, and spell checker directly into your terminal, saving you from installing heavy desktop apps. Toast is built for developers who refuse to leave their command line but are done spending hours tweaking Vim or Neovim just to get basic features like syntax highlighting and autocomplete. It handles the boring setup for you by automatically managing language servers, so you can just start typing code immediately.

📰 https://news.ycombinator.com/item?id=49135184

🆔 @hackernewsgithubprojects

📦 iaga-team/iaga-sentinel

How IAGA Sentinel Proves Your AI Didn't Lie

IAGA Sentinel watches your AI agents and answers the one question they can't: proof that they didn't cheat. When an agent touches your system, this tool signs every action with a cryptographic receipt that links into a tamper-proof chain. The coolest part is that you can verify this evidence offline using a simple binary, with no server or network needed. It solves the trust gap where agents act autonomously but leave no auditable trail. If you're building systems that need to pass strict regulations, this gives you real, verifiable proof instead of just code that says it worked. Stop guessing if your AI is safe, and start demanding the receipt.

🆔 @hackernewsgithubprojects

📦 edoardobambini/iaga-sentinel

IAGA Sentinel Proves Your AI Agent's Actions

IAGA Sentinel captures a cryptographic proof for every decision your AI agent makes, solving the problem of verifying agent actions without trusting the system itself. By sitting alongside your tools, it turns each verdict into a signed, linked receipt that can be checked offline with no network or server required. This gives you tamper-proof evidence that meets strict compliance standards, ensuring your records remain valid even after the fact. It is not just a log, but a verifiable chain of accountability. Get your AI actions into a state of provable trust today.

🆔 @hackernewsgithubprojects

📦 herdrdev/herdr

Herdr Keeps Your Coding Agents Alive

Herdr acts as the persistent home base for your coding agents. It runs as a lightweight background server that keeps your terminal sessions alive even if you close the laptop or lose your internet connection. The best part is that it doesn't just keep them running. It actively watches every pane to see if an agent is stuck waiting for your input. When that happens, it clearly flags the status so you know exactly which agent needs your attention. Instead of frantically switching between windows to find the one that stopped, you get a clear view of what is working, what is blocked, and what is idle.

🆔 @hackernewsgithubprojects

📦 nanako0129/sepia

sepia: Fixing AI Writing at the Source

Researchers found that swapping out words won't make your AI fiction sound human, because the tells are in the plot structure. sepia is a writing tool that fixes that deep down, using science to repair narrative architecture instead of just polishing surface style. It works with major AI coding tools to help you craft stories or professional docs that actually feel written by a person, not a machine. This is the smart way to ditch the robotic feel for good.

🆔 @hackernewsgithubprojects

📦 kacperkapusciak/goldie

Goldie: Auto-Generate App Store Screenshots

Goldie takes the tedious work of creating App Store assets and turns it into a simple, automated pipeline. It runs your app on a simulator to capture real screens, then wraps them in beautiful, editable frames with headlines and backgrounds. The coolest part? It works directly with your coding agents. You can just ask your AI to create store previews, and Goldie handles the capture, framing, and Apple's strict upload rules automatically. It’s a lifesaver for developers who want their app to look professional without hiring a designer or spending hours on manual screenshots. Give Goldie a try to get your store assets done in minutes, not days.

🆔 @hackernewsgithubprojects

📦 douglasdemoura/chroncal

Chroncal: Your Entire Calendar Lives in the Terminal

Chroncal is a terminal-first tool that turns your command line into a full-featured calendar, todo list, and journal, all while keeping your data local in SQLite. The most surprising part is that it speaks standard iCalendar and CalDAV, so it syncs with your existing online calendars like Google or Apple without uploading your data to a new cloud service. It gives you an interactive interface for browsing events and a powerful command line for scripting, meaning you can manage recurring meetings, check availability, and log daily notes without leaving your keyboard.

📰 https://news.ycombinator.com/item?id=49453176

🆔 @hackernewsgithubprojects

📦 qphutu/golden_critic

The Golden Critic Method for AI Math

Train math models by letting a smart AI critic grade its own work. Golden Critic, built on the VERL framework, gives large language models a built-in reviewer that spots errors in reasoning, not just final answers. Instead of guessing, the model learns from detailed feedback on where its logic broke down, drastically improving accuracy on complex math problems. It’s like having a tutor check your homework before the final exam, making the learning process smarter and more efficient. If you want your AI to actually solve problems, not just guess, this is the tool to watch.

🆔 @hackernewsgithubprojects