📦 ikora128/stop-ai-slop-jp

Stop AI Slop (Japanese Edition)

Strip the robotic hum from your Japanese writing by handing a specific editing task to your AI assistant. Stop AI Slop (Japanese Edition) acts as a specialized guide that detects and removes the invisible tells that make text feel hollow and generated. The project targets the subtle structural habits of machine writing, such as uniform sentence rhythms, vague subjectless actions, and inflated abstract concepts. It forces the text to ground itself in specific human experience and concrete facts, pushing the language back toward a clear, visible voice. If you draft in Japanese with AI, this tool helps you reclaim the writer's identity from the template.

🆔 @hackernewsgithubprojects

📦 artemtsitronov/glacex

Glacex: The Rust UI Library Drawing Your Own Pixels

Build native desktop apps that skip the browser engine entirely. Glacex is a new Rust library that lets you draw every single pixel yourself directly on the graphics card. Instead of wrapping slow web tech or native toolkits, it uses a clever math trick to turn smooth shapes into tiny squares that your GPU can paint at lightning speed. This means crisp, anti-aliased buttons and text without the usual overhead. It is built for developers who want total control over their interface while keeping code clean and fast. If you like owning your rendering pipeline, this is the one to watch.

📰 https://news.ycombinator.com/item?id=49911322

🆔 @hackernewsgithubprojects

📦 deejanuz/frametop

Frametop VR Desktop

Put a customizable multi-monitor desktop right inside your virtual reality headset with Frametop. Built specifically for the Valve Steam Frame running SteamVR, this clever tool lets you run a full KDE Plasma desktop directly on your hardware without needing a separate computer. You can arrange, resize, curve, and roll multiple virtual monitors in three dimensional space, even pinning a screen to your wrist. Best of all, it includes a smart driver that turns any standard Bluetooth mouse into a three dimensional pointer, making it incredibly easy to navigate your workspace and the SteamVR dashboard without ever touching a controller.

🆔 @hackernewsgithubprojects

📦 unjs/upm

UPM Package Manager

UPM is the ultra-light package manager that delivers Rust-level install speeds using pure TypeScript. While other modern package managers require massive native binaries that bloat your disk and slow down continuous integration, this project fits entirely in about two hundred and fifty kilobytes by smartly reusing the tools already built into Node.js. It supports your existing lockfiles from npm, pnpm, and Bun right out of the box, and works securely by skipping risky postinstall scripts. Best of all, every command is a standard JavaScript function you can import, meaning you can easily bundle it directly into your own developer tools.

🆔 @hackernewsgithubprojects

📦 lightsifter/sift-light

Sift Light: The Search Tool That Actually Thinks

Sift Light is the search plugin that finally gives AI agents a reliable librarian instead of a blind guesser. When your code assistant needs to hunt for a specific error log or a forgotten config file, it usually just grabs every file and wastes your time. Sift Light fixes that by finding the exact passage you need and handing it over immediately, so the agent works with facts, not guesses. It even understands when you remember a word wrong, using local models to find the right file without sending your data to the cloud.

🆔 @hackernewsgithubprojects

📦 avinash-jetwani/jevmem

jevmem: The AI Memory That Remembers Your Dead Ends

JeVMem is the project memory tool that remembers every dead end your coding assistant hits. Instead of letting an AI forget a failed approach, it saves the specific reason why something broke, so it never tries that same mistake again. It automatically watches your chat sessions to capture decisions and constraints, storing them in a simple file that feeds directly back into the next prompt. This means your AI assistant actually learns from your past failures, saving you time and preventing repetitive errors. It works right inside Claude Code, making your daily coding sessions smarter and more efficient. Give your AI a real memory that actually sticks to the facts.

📰 https://news.ycombinator.com/item?id=49846391

🆔 @hackernewsgithubprojects

📦 symfony/reprise

Symfony Reprise

Reprise is the Symfony integration layer that finally brings Webpack Encore's best asset management features to modern bundlers like Vite and Rsbuild. If you love building PHP applications with Symfony but want the blazing-fast speed of modern front-end build tools, this project is the perfect bridge. It handles all the messy glue code that bundlers leave out by generating your asset entry points and manifest files automatically. This means your PHP templates can easily render script tags, manage cache-busting, and wire up live hot module reloading. It is the ultimate way to keep your modern front-end workflow and your back-end framework in perfect harmony.

🆔 @hackernewsgithubprojects

📦 misakazentai/world-execute-me-dsh-pv

Code-Rendered Music Video

A single Python command renders a full music video where every frame is a pure function of the song's timeline. This repository, named world.execute.me.dsh.pv, recreates a fan visual for the track world.execute.me by Mili using a split-screen approach. On the left, it simulates a live chat interface by generating HTML pages and screenshotting them with Playwright to mimic a real conversation. On the right, a custom engine draws a terminal-style visualization of the AI model itself. You bring your own audio file, and the system handles the rest, syncing lyrics and graphics perfectly.

🆔 @hackernewsgithubprojects

📦 cinderline/northcinder

NorthCinder: The AI Shopper That Actually Works For You

NorthCinder is the open-source shopping agent that forces AI to work for you, not for a marketplace. It plugs into your AI app to compare products across stores like Shopify, eBay, and Amazon, then shows you exactly why it picked a winner. The coolest part is that it refuses to just guess or let a store pay to be first. Instead, it gives you a short, honest list with reasons you can check yourself. And before it spends a single penny, it stops and asks your permission. It is a private, local tool that keeps your data and your money under your control.

🆔 @hackernewsgithubprojects

📦 zacharyzhang-ny/ely-gpui-components

Ely GPUI Components: Live Browser Testing

Ely GPUI Components is the Rust component library that renders every single interface element live in your browser. Most UI toolkits force you to launch a heavy desktop app just to see if a button works. This project changes that workflow completely by compiling the native Rust interface directly into the web. You can click, type, and interact with every widget exactly as it will appear in the final software. It covers everything from simple toggles to complex data grids and chat windows. The single most useful feature is that instant visual feedback. You stop guessing if your code works and start seeing it run immediately.

🆔 @hackernewsgithubprojects

📦 vectorize-io/agent-memory-benchmark

Agent Memory Benchmark: The Honest Test for AI Memory

Agent Memory Benchmark is the open evaluation harness that finally exposes whether an AI agent actually remembers or just guesses. Built by Vectorize, it solves the problem that older tests were too easy for modern models to pass by accident. Instead of just checking if an answer is correct, it measures the real cost and speed of finding that information. The most surprising part is that it treats memory like a strict exam where returning wrong details is just as bad as forgetting them entirely. If you are building agents that need to hold knowledge over time, this is the tool that tells you the truth.

🆔 @hackernewsgithubprojects

📦 ninjahawk/livenerf

livenerf: The Nerf Detector

Track whether a frontier AI model gets quietly worse right after it launches. Months of online reports claimed that major AI companies degrade their tools days after release, but without a fixed starting point, everyone was just guessing. This project, called livenerf, fixes that problem by running the exact same set of difficult math and science questions every single day for thirty days. It locks down the software version and the questions so nothing else can change. By comparing every daily result against the first week, it uses simple statistics to spot a real drop in performance.

📰 https://news.ycombinator.com/item?id=49809555

🆔 @hackernewsgithubprojects

📦 makson179/bello

bello

AI software developers are great until they wander off and make mistakes on long tasks. Bello is a local tool that acts as a manager for your AI coding agents, keeping them on track and preventing them from running unsafe commands. It wraps your existing coder in up to four specialized roles, including a runtime supervisor to stop logical drift, an independent reviewer to catch bugs, and even an adversary that tries to break the code with edge cases. Best of all, it includes a local model that shrinks command logs so your AI reads less text, saving you up to sixty-six percent on model subscription limits.

🆔 @hackernewsgithubprojects

📦 pixaroma/comfyui-pixaroma

Pixaroma: The Visual Editor for ComfyUI

ComfyUI users can now build animated video loops that pulse and shake in perfect sync with music beats. Pixaroma turns the standard node editor into a full creative suite, adding features like audio-reactive motion and text overlays that were previously missing. You can load a video, apply visual effects driven by the soundtrack, and export the result directly as an MP4 file. It bridges the gap between raw AI generation and polished post-production. If you want your generated images to actually move and feel alive, this is the tool that makes it happen without leaving your current workflow.

🆔 @hackernewsgithubprojects

📦 mlhher/late-cli

Late: The AI Agent That Keeps Your Context Clean

Late is the AI coding agent that keeps your model sharp by physically isolating its working memory. Standard AI tools get dumber as they work because every error log and file read piles up in one messy memory space. Late solves this by acting like a project manager who hires temporary workers for specific jobs, then fires them immediately after the task is done. Only the final results go back to the manager, keeping its mind clean. This means a small model can handle massive coding projects without forgetting what it was doing.

🆔 @hackernewsgithubprojects

📦 yappologistic/spun

Spun: The Music Player That Looks Like Hardware

Spun turns your Linux computer into a room full of physical music hardware, projecting album artwork onto spinning CDs, vinyl records, cassettes, and even a retro tape recorder. It solves the problem of sterile digital interfaces by giving your music collection tactile, animated depth that responds to every beat. You can plug in local files, connect to self-hosted libraries, or stream anonymously from YouTube without needing an account. The interface even includes a working mixing board for adjusting audio levels right on your desktop screen.

🆔 @hackernewsgithubprojects

📦 anomalyco/opencode-bench

How to Benchmark AI Coding Agents

Measure exactly how well artificial intelligence agents write real code. OpenCode Bench runs those agents against actual production commits from popular open source projects, then compares their work against the official changes. It uses three independent large language models to grade the output on five specific qualities like logic and test coverage. This framework solves the problem of guessing which AI is actually useful for serious software development. It gives you concrete, mathematically rigorous scores based on real world performance rather than vague marketing claims. If you are choosing an AI coding assistant, this is the tool that tells you who actually delivers.

🆔 @hackernewsgithubprojects

📦 netresearch/agent-rules-skill

Agent-Rules-Skill: The AI Onboarding Cheat Sheet

Agent-Rules-Skill is the project context generator that finally gives your AI coding assistant the exact manual it needs to write good code. Instead of guessing how your project works, this tool scans your repository to automatically build a dedicated instruction file specifically for artificial intelligence. It looks at your build scripts and directory structure to create a concise guide that tells the AI exactly what to do, what to avoid, and which commands to run. This ensures your code assistant understands your unique setup immediately, saving you from the frustrating cycle of correcting bad code suggestions.

🆔 @hackernewsgithubprojects

📦 bilibili/index-translate

Bilibili's Index-Translate Family

Bilibili just open-sourced a translation model family that can actually keep a character's name consistent across a thirty-two thousand token fantasy novel. While standard models often forget names or swap them out for generic titles, Index-Translate uses full-document context to lock in specific terms, ensuring the protagonist stays the same from the first page to the last. It also handles speech dubbing and even adjusts translation length to fit specific subtitle timings. This is a massive step forward for anyone trying to localize complex fiction or media without manual editing. If you are working on long-form localization, this is the tool that finally solves the consistency nightmare.

🆔 @hackernewsgithubprojects

📦 corvofeng/atv-core

Control Your Mac With Your iPhone

Turn your Mac into a target for the built-in Apple TV Remote widget on your iPhone. This Rust-based project, called atv-core, speaks the same private protocols as real Apple hardware, so you can pair your phone and control your computer without buying a remote or jailbreaking anything. The coolest part is that it turns your iPhone's touchpad into a precise mouse cursor for your desktop, letting you swipe to move the pointer and tap to click. It runs in the background with a tiny footprint and even includes a web page where you can watch your finger movements in real time.

🆔 @hackernewsgithubprojects