📦 erickong/penecho

penecho

You can now solve complex math and sketch diagrams directly on an open digital canvas, and watch an AI read your handwriting to solve the problem right next to your pen strokes. This tool, called penecho, bridges the gap between raw brainstorming and artificial intelligence by turning your visual scribbles into structured, editable drafts. Instead of typing formulas into a boring chat box, you simply write or draw naturally with your mouse or stylus on a massive workspace. The app sends your visual layout to a model to generate a movable draft that you can resize, tweak, or accept. Grab a stylus, run a quick local command, and start sketching...

🆔 @hackernewsgithubprojects

📦 pwilkin/trellis.cpp

Trellis dot CPP

You can now transform a flat two-dimensional image into a fully textured, three-dimensional digital model with zero Python dependencies. A clever new project called trellis.cpp delivers a complete rewrite of Microsoft's advanced image-to-three-D pipeline in pure C++. By utilizing a custom neural engine and running directly on your GPU, it handles everything from automatic background removal and shape decoding to generating a high-quality three-D mesh with beautifully baked textures. It is incredibly lightweight and easily fits onto consumer graphics cards. If you want to integrate high-fidelity three-D generation directly into your native applications, this is the ultimate starting point.

🆔 @hackernewsgithubprojects

📦 bouzidanas/pynote-notebook-editor

PyNote Notebook Editor

You can now run a complete Python data science notebook directly in your web browser with zero server setup or cloud costs. This is pynote-notebook-editor, a serverless, local-first environment powered entirely by WebAssembly. Because your code runs in a sandboxed browser thread, your data never leaves your machine, making it completely private and secure. What makes it incredibly cool is its built-in interactive UI system; you can design custom web forms, reactive sliders, and polished charts directly from your Python code, and they will update in real time without you ever needing to write frontend JavaScript. It is the perfect way to build and share gorgeous, interactive reports that look...

🆔 @hackernewsgithubprojects

📦 huytieu/cog-second-brain

cog-second-brain

Your markdown files can now think for themselves. COG-second-brain turns a local folder of text files into a self-evolving knowledge engine using local AI agents and git. Instead of wasting hours organizing notes, you just dump your raw thoughts into a text file. The system automatically classifies the domain, links related topics, and extracts action items. It even tracks your professional network with a progressive people database that gets smarter the more you mention them. It works directly with tools like Claude Code and Cursor to build structured, self-healing frameworks from your scattered thoughts. It is the ultimate zero-maintenance system that actually grows with you.

🆔 @hackernewsgithubprojects

📦 vlm-run/mm

Fast Multimodal Context with mm

mm is the command-line tool that finally gives classic UNIX commands like cat, grep, and find multimodal powers. Instead of hitting a wall when your scripts encounter images, videos, audio, or PDFs, this clever tool lets you inspect and search binary formats as if they were plain text. Backed by a fast Rust core, you can instantly extract audio transcripts, scan PDF tables, or generate detailed image descriptions right from your terminal. It even packs a python API to build multimodal prompts for your favorite AI models in just a few lines. Toss it into your terminal, and let your command line finally see the world.

🆔 @hackernewsgithubprojects

📦 stephenleo/openmicro

OpenMicro

OpenMicro is the macOS tool that finally lets you control your AI coding agents with a gaming controller. Instead of hunting through terminal tabs, you can just plug in a PlayStation, Xbox, or GameSir controller and drive tools like Claude Code and Codex with physical buttons. A simple flick of the thumbstick triggers common workflows like reviewing code, debugging, or writing tests, while rotating the stick dials your thinking depth up or down. Real-time lights on your controller even change color to show if your agent is busy, waiting, or hit an error, making coding feel like playing a video game.

🆔 @hackernewsgithubprojects

📦 mihneaptu/opencode-fusion

opencode-fusion

Slash your AI coding costs by up to fifty-four percent by separating the brains from the brawn. This clever setup for opencode locks your expensive, high-intelligence main model out of editing files entirely, forcing it to focus only on planning, reviewing, and high-level strategy. When it is time to write code, the main agent hands precise specifications to a cheaper, lightning-fast sidekick model to do the actual typing. You get top-tier results and cross-vendor review for a fraction of the price. Give your budget a break and try opencode-fusion to experience smart, multi-model delegation today.

🆔 @hackernewsgithubprojects

📦 eps-acoustic-revolution-lab/ear_vae

ear_vae

Reconstruct studio-quality music with incredible spatial depth and crystal-clear high frequencies using a smart neural network designed to mimic how humans actually hear. While typical audio AI models struggle to keep stereo sound feeling wide and realistic, ear_vae solves this by introducing a brilliant perceptual filter and phase-aware training. This means it doesn't just look at raw math data; it optimizes for actual auditory perception, keeping your left and right channels in perfect sync. It is the ultimate tool for developers building next-gen audio generators who want their music to sound open, punchy, and alive.

🆔 @hackernewsgithubprojects

📦 kirakun0328/text-to-vrma

Text-To-VRMA

Text-to-vrma is the animation tool that finally lets you control 3D virtual avatars using plain text. Instead of spending hours manually editing keyframes, you just type a simple action like having a character happily jump or wave, and the app instantly generates a smooth movement file. By combining smart language models with a specialized motion engine, it automatically handles body physics, timing, and even natural facial expressions. You can drop in any virtual character, watch them move in real-time, and export the file instantly. It is a fantastic way to bring virtual characters to life without needing professional animation skills.

🆔 @hackernewsgithubprojects

📦 mysterypancake/houdini-opencl

Houdini OpenCL

Houdini artists can bypass standard vex programming and tap directly into their graphics card using the low-level power of OpenCL. The houdini-opencl repository provides much-needed documentation and examples for utilizing this incredibly fast but notoriously difficult language. While vex runs solely on the processor, OpenCL executes directly on the graphics card, making it ideal for heavy simulation tasks like feedback loops or neighbor calculations. However, it requires manual memory management and is highly prone to crashes. This project demystifies the setup, teaching developers how to bind data correctly and avoid memory leaks. It is the ultimate guide to unlocking maximum viewport performance.

🆔 @hackernewsgithubprojects

📦 shubhamj010/screenshotjanitor

ScreenshotJanitor

Keep your Android phone clutter-free by automatically sweeping away temporary screenshots you no longer need. This clever tool monitors your device in the background and intercepts every new screenshot you take, giving you a quick notification to archive, save, or delete it on the spot. If you do nothing, its built-in daily scheduler quietly runs in the background to clean up the leftovers and reclaim your storage space. It is completely local with no cloud integration, ensuring your personal photos stay private. It is the perfect, set-it-and-forget-it way to keep your gallery pristine without lifting a finger.

🆔 @hackernewsgithubprojects

📦 nesdev-org/mesence

mesence

Play classic console games across seven different retro systems using a single, high-performance application built for modern computers. The mesence project is a community-managed, multi-system emulator that lets you run games from iconic hardware like the NES, SNES, Game Boy Advance, and WonderSwan on Windows, Linux, and macOS. This community fork keeps the beloved emulator active, updating it to run on modern frameworks like dot net ten. It solves the hassle of managing separate emulators for every retro console by combining them into one fast, lightweight package that even runs on the Steam Deck, giving classic games a permanent home on modern hardware.

🆔 @hackernewsgithubprojects

📦 calesthio/generative-media-skills

Generative Media Skills

Equip your AI coding assistants with a massive library of specialized instructions to plan, direct, and refine professional-grade video, audio, and images. The generative-media-skills repository provides over one hundred and fifty research-backed agent skills covering everything from cinematography and sound design to automated quality checks. Instead of relying on generic prompts, your AI helper can consult deep operating knowledge of specific media tools, helping you coordinate complex workflows like syncing voiceovers, rendering 3D assets, and finishing videos with proper color grading. It is a brilliant way to turn standard language models into highly capable, detail-oriented digital media producers.

🆔 @hackernewsgithubprojects

📦 ruhan-wang/harness_handbook

Harness Handbook

Harness Handbook is the developer tool that turns entire codebases into structured, interactive maps to help AI coding assistants find where changes need to be made. Large software repositories can be completely overwhelming for a language model to digest, often causing it to miss critical files when planning updates. This project parses your source code and uses an AI to generate a highly organized, step-by-step handbook of your system architecture. When you feed this handbook to a code agent, it can easily navigate your files and pinpoint exactly where to make edits without drowning in context. Give it a try to build smarter, more precise coding assistants today.

🆔 @hackernewsgithubprojects

📦 bitpainter75/ferrumpix

FerrumPix

The desktop photo manager that actually bridges the gap between local files and your self-hosted cloud, FerrumPix is a free, open-source gallery and editor designed specifically for Linux and Windows. While it lets you browse local folders, crop images, and paint with brush tools, its real standout feature is a direct, built-in integration with Immich. You can view your cloud albums, download originals, and even edit your hosted photos, saving the polished results right back to your server. It is a surprisingly complete, lightweight tool built with modern tech that makes organizing your personal photo library feel incredibly simple.

🆔 @hackernewsgithubprojects

📦 tonyd2wild/glm-5.2-quanttrio-200k-4x-dgx-spark--36tok-s

glm-5.2-quanttrio-200k-4x-dgx-spark--36tok-s

The specialized cluster recipe that serving teams are using to run the massive GLM-5.2 model at full quality without deleting any of its two hundred fifty-six experts. Instead of surgically hacking the model down to fit on your hardware, this setup orchestrates four NVIDIA GB10 nodes to host the unpruned model at a massive two hundred thousand token context. It squeezes out up to thirty-six tokens per second using smart trickery like built-in speculative decoding and custom Triton kernels. It even includes an indexer patch to prevent multi-user crashes. If you want to deploy full-scale reasoning models across high-end hardware, grab this recipe, spin up your cluster, and start serving.

🆔 @hackernewsgithubprojects

📦 xang1234/stock-screener

Stock Screener

This multi-market stock scanner lets you run institutional-grade technical and fundamental scans across twelve global markets simultaneously, including the US, India, and Hong Kong, without paying for expensive data feeds. The platform orchestrates complex trading strategies like William O'Neil's CANSLIM and Mark Minervini's trend templates, combining eighty technical filters with an AI chatbot to research trending themes from live feeds. It solves the massive headache of managing scattered market data and high API costs by pulling information into a single, Docker-deployed system backed by PostgreSQL and Redis. Anyone looking to level up their trading workflow gets a self-hosted, industrial-strength screening pipeline that runs entirely on local hardware.

🆔 @hackernewsgithubprojects

📦 drsexo/frosty

Frosty

You can now reclaim your Android phone's battery life by freezing power-hungry background services with a single tap. Frosty is an advanced Magisk, KernelSU, and APatch module designed specifically to stop background battery drain and rein in persistent Google services. Through its clean web interface, it lets you disable unnecessary telemetry, automate screen-off power saving, and apply deep sleep optimizations without breaking your favorite features. It even auto-tunes system memory and block storage performance based on your device's actual hardware. It is the ultimate tool for anyone wanting complete, smart control over their phone's standby power.

🆔 @hackernewsgithubprojects

📦 open-compass/agentcompass

AgentCompass

Benchmark and evaluate your AI agents under realistic conditions using this unified testing suite. It runs parallel tests across over twenty major benchmarks to systematically grade how well your language models handle complex, multi-step operations like writing code, executing terminal commands, browsing the web, and navigating visual interfaces. By spinning up secure, isolated environments using Docker or Modal, it lets you safely watch your agents attempt real-world software engineering tasks and deep research assignments. You get back clear metrics and step-by-step trajectory graphs showing exactly where an agent succeeded or got stuck. Grab the repository to start stress-testing your agents today.

🆔 @hackernewsgithubprojects

📦 harahan/meanflownft

MeanFlowNFT

Train image and video generators to produce high-quality, aesthetic results in only four steps. This project introduces a clever way to apply reinforcement learning directly to fast, velocity-based AI generators without destroying their speed or efficiency. Usually, fine-tuning these models with human feedback rewards requires slow, complex calculations during training. This framework solves the problem by optimizing the model's trajectory in a simulated space while keeping the actual generator lightweight and fast. In practice, this means you can generate stunning media using Stable Diffusion and video models with incredible detail, beating older, slower methods. Give this repository a try to see how efficient AI generation can really be.

🆔 @hackernewsgithubprojects