📦 vincentwei1021/video-talkcraft

Video Talkcraft

Video Talkcraft is the AI agent skill that turns your coding assistant into a motion design studio for narrated videos. You simply give it a script and a voice recording, and it handles the heavy lifting. It maps every single word to a precise moment in time, ensuring that every visual animation hits exactly when you say it. The coolest part is its anti-slideshow system, which forces constant motion so your video never feels like a static PowerPoint presentation. It handles everything from camera moves to sound effects automatically. You get a professional, polished explainer video without touching a single timeline.

🆔 @hackernewsgithubprojects

📦 googlechromelabs/webmcp-tools

WebMCP Tools: Let AI Drive Your Website

WebMCP Tools is the developer toolkit that lets AI agents drive your website like a human user. Google Chrome Labs built this collection to make the WebMCP API practical, providing utilities and demos that show exactly how to connect language models to web interfaces. The most surprising demo here is a maze game where you play entirely by typing prompts to an AI, with no keyboard or mouse input at all. This shows how a web page can expose structured actions to an agent, replacing fragile screen scraping with direct, reliable control.

🆔 @hackernewsgithubprojects

📦 ezzy1630/downright

Downright: The Native Markdown Editor for Mac

Turn plain text files into beautiful, native Mac documents. Downright is a free, open source editor for macOS that renders Markdown with crisp, system-level typography. It solves the problem of clunky web-based editors by working entirely offline with your local files. The most surprising part is how it handles your text. It keeps your original source code exactly as you wrote it while displaying a polished preview. No hidden formats, no lock-in. It feels like a standard Mac app, not a browser window. If you write notes or docs on a Mac, this tool keeps your files simple and your workflow clean.

🆔 @hackernewsgithubprojects

📦 miaai-lab/qwen3.8-27b-dflash2-exl3-5.0bpw

Qwen 3.8 27B DFlash2 EXL3 5.0bpw

A twenty-seven billion parameter AI model now runs on a single consumer graphics card while generating text almost thirty percent faster than standard setups. This repository provides a complete deployment kit for the Qwen 3.8 27B model, specifically optimized to fit inside twenty-four gigabytes of GPU memory. It solves the problem of running massive, high-quality language models on local hardware without sacrificing speed. The system uses a specialized quantization format to shrink the model size and employs a smaller companion model to guess words, allowing the main engine to verify them rapidly. This makes it possible to run complex reasoning tasks on your own desktop.

🆔 @hackernewsgithubprojects

📦 kingoftheseas56/colosseum

Colosseum: One App for All Your Media

Colosseum is the native desktop application that finally unifies your entire media library. Instead of juggling separate apps for manga, audiobooks, and movies, it brings them all into one fullscreen home. The most surprising part is how it handles your own files. A feature called Vault scans your local folders to index your existing movies and comics. It then opens them directly in the built-in readers and player, so your personal collection lives right next to your downloaded media. It even remembers your spot across every medium. If you have ever wanted one clean place for all your stories, this is it.

🆔 @hackernewsgithubprojects

📦 circuitvalley/chc5_open_camera

CHC5 Open Camera System

Point a camera at a machine and capture two thousand frames per second. The CHC5 Open Camera System turns a standard sensor into a high-speed industrial workhorse by using dedicated hardware to process images as they arrive. Most cameras drop frames when data gets heavy, but this open design keeps up by handling massive data streams directly on the chip. You can plug in almost any lens and swap out sensors to fit your specific needs. It streams video simultaneously over USB, Ethernet, and HDMI. If you need to track fast-moving objects without lag, this open hardware gives you the control and speed to make it happen.

🆔 @hackernewsgithubprojects

📦 henrikekblad/codelight

codelight: Control Your AI Coding Agents From Your Phone

You can now approve code changes and answer questions from your AI coding agents right from your phone, even if your computer is locked. This project, called codelight, turns your desktop into a remote control center for tools like Claude Code and GitHub Copilot. It watches your agents in real time and pushes any permission requests or questions to your phone, a smart screen, or your desktop panel. If an agent is stuck waiting for your approval, you can simply tap to allow it or answer its question from anywhere in your house.

🆔 @hackernewsgithubprojects

📦 alphaxiv/openresearch

OpenResearch: Your AI Lab Partner

OpenResearch is the local-first workspace that lets you run multiple AI research agents in parallel without leaving your machine. Instead of juggling separate chat windows, it gives each agent its own isolated branch to test ideas, read papers, and run code simultaneously. The coolest part is that it acts like an autonomous lab partner, proposing hypotheses, executing experiments, and logging the evidence so you can actually see which direction worked. It keeps all your data and code safely on your laptop, so you own the results. If you want to explore research directions faster and smarter, this is the tool to try.

🆔 @hackernewsgithubprojects

📦 merserk/dlss5-visual-enhancer

DLSS 5 Visual Enhancer

This Windows tool runs the new DLSS 5 neural rendering pipeline directly on your images and videos, not just in games. It uses your RTX graphics card to analyze motion and detail, then reconstructs a higher-quality version of your media right on your computer. You can batch process files, adjust specific visual styles, and export in formats like HEVC or AV1. It is a portable, community-driven project that brings advanced AI upscaling to your personal media library. If you have an NVIDIA card, this is how you get that game-level visual clarity on your own photos and clips.

🆔 @hackernewsgithubprojects

📦 fregacmols/rotarycell

Turn a Rotary Phone into a Cell Phone

Take a vintage rotary phone and make it a portable cell phone without drilling a single hole. That is exactly what RotaryCell does. It slips a small battery and cellular circuit inside the original case, using the existing dial and ringer to connect you to the modern network. You can carry it to a meeting or a park and make real calls, all while keeping the classic phone completely intact and reversible. It is a beautiful piece of engineering that proves old technology can still work today. If you love clever hardware, this project is one you will want to see up close.

📰 https://news.ycombinator.com/item?id=49517297

🆔 @hackernewsgithubprojects

📦 orwa-mahmoud/nightshift

Nightshift: Your AI Coding Shift Manager

Nightshift is the coding companion that stops AI agents from quietly quitting halfway through a job. It turns long, unattended AI coding sessions into accountable, time-bounded shifts where the task list lives on disk, not buried in a disappearing chat window. The real magic? If your AI coding session crashes or gets stuck, Nightshift’s watchman automatically revives it, picking up exactly where it left off from the saved list. You get a clear morning handoff showing exactly what is done, what is blocked, and what is parked for later review. No more scrolling through marathon chats to find the status.

🆔 @hackernewsgithubprojects

📦 brayonpi/hexstellar

HexStellar: The AI Solver That Actually Proves Its Answers

Your AI chatbot can talk about the perfect delivery route, but HexStellar actually solves it. This tool hands complex optimization puzzles to a specialized engine that returns a mathematically verified answer, not just a guess. You get a clear receipt proving the result is optimal, which is huge when you are making real financial decisions. It is the difference between asking a friend for advice and having a mathematician sign your work. It is fast, honest, and built for developers who need certainty. Stop letting your AI hallucinate the solution, and start verifying it instead. This is how you get real results from your agents.

🆔 @hackernewsgithubprojects

📦 lisitskyaa/comfyui-dlss5-nr

ComfyUI Gets Neural Rendering

Nvidia's newest neural rendering engine now runs directly inside ComfyUI without launching separate programs or saving temporary files. This experimental project bridges a gap by letting users apply advanced AI-based image enhancement right within their existing workflow. It solves the problem of complex setup by handling the heavy lifting internally, which makes testing new visual styles much faster. You just plug in your own compatible runtime file and start rendering. This is useful for anyone wanting to push the limits of local image processing. The key takeaway is that you can now experiment with next-gen rendering tools without leaving your familiar interface.

🆔 @hackernewsgithubprojects

📦 git-agni/prod-farm-ios-core

Phone Farm iOS: Control Real iPhones From Your Mac

Phone Farm iOS is the self-hosted tool that turns a pile of physical iPhones into a programmable farm running directly on your Mac. It solves the annoying problem of automating real phones by giving you live video and remote tap control, backed by a database scheduler that keeps track of every task. The standout feature is the built-in TikTok plugin, which lets you schedule actions like scrolling or posting on a recurring basis. It is interesting because you get genuine device automation without renting expensive cloud services. If you want to test apps or run bots on hardware you already own, this is the place to start.

🆔 @hackernewsgithubprojects

📦 co-l/cache-hunter

Cache Hunter: The LLM Proxy That Catches Cache Invalidation

Cache Hunter is the LLM proxy that finally catches cache invalidation before it blows up your costs. It sits quietly between your app and the model, logging every request to a local database so you can see exactly when the cache breaks. The coolest part? It builds a hash grid to visualize context coherence, letting you spot broken conversation chains at a glance instead of guessing. If you are running local models or debugging latency spikes, this tool turns invisible behavior into clear data. It is the missing piece for anyone trying to understand why their inference is slower than it should be.

🆔 @hackernewsgithubprojects

📦 openlair/dr-claw

Dr. Claw: Your AI Research Lab

Dr. Claw is the AI-powered research environment that turns your computer into a full-scale digital laboratory. Instead of just chatting with an assistant, this tool gives you a team of specialized AI agents that handle the heavy lifting of academic work. It can scan thousands of papers, write your code, run your experiments, and even draft your grant proposals or rebuttal letters. The coolest part is that it understands the entire research lifecycle, so you spend less time on admin tasks and more time on actual discovery. It’s like having a tireless postdoc who never sleeps and never forgets a citation.

🆔 @hackernewsgithubprojects

📦 openclaw-easy/viralmint

ViralMint: Your Local Video Factory

ViralMint is an open-source pipeline that runs entirely on your own computer, meaning your scripts and footage never leave your machine. It handles the entire workflow from scouting trends across YouTube and TikTok to actually uploading your finished videos. The coolest part is the clip studio, which lets you drag handles on a real timeline to cut long videos into shorts. You can even chat with the AI through WhatsApp or Discord to control the whole process. It is a self-contained tool that gives you total control without any cloud dependency. If you are tired of juggling ten different apps, this is the one tool that does it all.

📰 https://news.ycombinator.com/item?id=48221229

🆔 @hackernewsgithubprojects

📦 kodustech/agent-readiness

Agent Readiness: Is Your Code Ready for AI?

Agent Readiness instantly scores your project to see if it can actually handle AI coding assistants. It runs thirty-nine automated checks right on your own machine to measure how well your codebase supports autonomous tools like Claude Code or Copilot. Instead of guessing, you get a clear maturity level from one to five, revealing exactly where you stand. The coolest part is the interactive dashboard that opens in your browser, giving you a visual radar chart of your strengths and weak spots across seven key pillars like testing, documentation, and security.

📰 https://news.ycombinator.com/item?id=47378675

🆔 @hackernewsgithubprojects

📦 tencent/megastyle

MegaStyle: AI Style Transfer That Actually Works

Tencent just dropped a tool called MegaStyle that lets you take any picture and repaint it to match a specific artistic style, without losing the actual content of the image. It’s not just a filter; it uses a massive dataset of eight million images to teach the model exactly what a consistent style looks like. The coolest part is that it plugs directly into ComfyUI, so you can drop it into your existing workflow and start generating in minutes. If you’ve ever wanted to turn your photos into digital paintings or match a specific aesthetic, this is the tool that makes it actually happen.

🆔 @hackernewsgithubprojects

📦 cogevol/cogevol-4b

Cogevol-4B: Offline Course Generator

Cogevol-4B is the on-device model that turns a one-line course brief into a complete interactive classroom. It takes a simple request like 'teach me pendulum motion' and instantly generates structured slides and a working HTML simulation with adjustable sliders. The coolest part is that it runs entirely offline on your laptop, meaning you can kill your Wi-Fi and still build a full, functional physics lab in minutes. No cloud servers, no API keys, just your computer doing the heavy lifting. It is a tiny model that punches way above its weight, proving you do not need a massive data center to build real learning tools.

🆔 @hackernewsgithubprojects

📦 instituto-ia-lncc/manaca-1b-base

Manacá: The Open Brazilian AI Brain

Manacá is the open language model that proves you can build serious Brazilian Portuguese intelligence without a giant data center. Developed by a team at Brazil’s National Computing Center with partners from Japan, this project took the entire recipe for training an AI from scratch and made it completely transparent. Instead of just handing you a black box, they share the exact data, the code, and the steps needed to recreate the whole thing. It’s a rare case of true scientific open source in the AI world, where anyone can verify how the model learned to speak.

🆔 @hackernewsgithubprojects