📦 thumai-lab/llava-uhd-v4

LLaVA UHD v4: Smarter Vision AI

LLaVA UHD v4 is the vision model that finally stops wasting energy on blurry details. It changes how computers see by squeezing information down inside the image processor itself, not after the fact. This means the AI can read tiny text and understand complex diagrams without needing a massive amount of computing power. It cuts the required math by more than half while keeping the same sharp accuracy. It is a clever way to make high-resolution vision models fast and cheap. If you want to see how AI can be both smart and efficient, this is the one to watch.

🆔 @hackernewsgithubprojects

📦 sarpstar/cinecode

Films Made Entirely With Code

A single AI agent can write the script, build every visual frame from code, design the audio, and export a finished movie file for your computer. This project, called cinecode, turns a simple text prompt into a complete video, handling everything from animation to sound mixing. It runs locally on your machine using standard tools, so you keep total creative control without relying on cloud servers. You choose the visual style, from realistic 3D to hand-drawn ink, and the agent handles the technical heavy lifting. The result is a fully mastered video file, ready to share.

🆔 @hackernewsgithubprojects

📦 truongfelix/workflow

Workflow: The AI Workflow That Actually Remembers

Workflow is the Claude Code setup that finally stops your AI from forgetting what it did yesterday. It solves the headache where an agent starts every session with amnesia, blindly trusting old notes about work that is already done or broken. The magic is its ground truth script, which checks the actual git history and running jobs to verify reality before the AI acts. Instead of repeating lies, it compares its notes against the facts and flags the contradictions. You get a smart assistant that knows exactly where your project stands, keeping long-term builds consistent across weeks and machines.

🆔 @hackernewsgithubprojects

📦 cloudopsbench/cloudopsbench

CloudOpsBench Tests AI Cloud Skills

CloudOpsBench gives AI agents forty five real world cloud tasks to complete, like fixing broken services or cleaning up unused resources, to test if they can actually operate infrastructure safely. Each task comes with a specific starting state and a strict checker that verifies the final result, ensuring the AI didn't just guess but truly solved the problem. This is useful for anyone building automated cloud tools who needs to know if their AI assistant is ready for real work. It turns vague promises of AI capability into concrete, measurable results.

🆔 @hackernewsgithubprojects

📦 0xs4n4tg/papercut-explainer

Turn Any Topic Into a Paper-Cut Video

Turn any topic into a snappy, vertical video that looks like a 3D paper diorama, without touching a single line of code. The Papercut Explainer project uses Claude Code to handle the entire workflow, writing the script, planning the camera moves, and generating the voiceover for you. It then builds the scenes using a library of paper textures and sound effects, so you just describe the video you want and let the AI do the heavy lifting. It’s like having a mini production team that speaks code. If you want to make stylish explainer reels without hiring an editor, this is your new shortcut.

🆔 @hackernewsgithubprojects

📦 leag1234/elixiroffice

ElixirOffice: The Open Source Word That Actually Feels Like Word

Edit documents with the exact same ribbon, menus, and keyboard shortcuts you know from Microsoft Office, but on free software. ElixirOffice is an open source office suite built for people who are used to Word, Excel, and PowerPoint. It solves the problem of switching away from Microsoft Office by making the new tool feel familiar from day one, so your muscle memory still works. The most surprising part is its speed: it uses a special WebAssembly converter that opens large files ten times faster than a standard build.

🆔 @hackernewsgithubprojects

📦 jesdga95/basalt

Basalt: Run Massive AI Models Locally

Basalt is the local engine that lets massive language models run on a single computer without cloud dependence. It solves the problem of models that are too big to fit in your graphics card memory by cleverly parking the parts that do not fit in your regular system memory, allowing a workstation to handle complexity that usually requires a server farm. It also supports image analysis, turning your hardware into a fully private, capable assistant. The result is high performance without the overhead of external data centers. If you want to own your AI infrastructure and run powerful tools locally, this is the project to watch.

🆔 @hackernewsgithubprojects

📦 ashalliants/ninfer-3090

Ninfer-3090: The AI Engine for One Card

Ninfer-3090 is the inference engine that makes a massive twenty-seven billion parameter AI run fast on a single consumer graphics card. Most people think you need a server farm of expensive chips to run this class of model, but this project squeezes every drop of performance out of a single RTX 3090. It uses specialized math techniques to process the model’s data much faster than standard tools, letting you get answers at real-time speeds without breaking the bank. It’s a masterclass in making heavy software run on normal hardware, proving that you don’t need a data center to run the latest tech.

🆔 @hackernewsgithubprojects

📦 restsend/opus-rs

Opus-RS: Audio Compression Without the Heavy Lifting

The entire Opus audio codec is now running on a microcontroller with zero heap memory. Opus-RS is a pure Rust implementation of the standard audio compression format used by Zoom and Discord. The original C version needs a standard operating system to run, which locks you out of embedded devices and web browsers. This project solves that by removing all dynamic memory allocation, allowing the encoder to run on bare metal hardware with no global allocator. It performs just as well as the C version, proving you don't need a heavy runtime to compress high-quality audio.

🆔 @hackernewsgithubprojects

📦 dioxuslabs/rustd

rustd: The Fast Rust Builder

Rustd swaps out your standard build command for a significantly faster replacement that compiles your Rust code much quicker without changing how you write it. If you spend hours waiting for your project to compile, this tool tackles that exact pain point by acting as a drop-in upgrade to your existing setup. The interesting part is the speed: it reworks the way the compiler processes your code, turning long wait times into short pauses. For anyone building large Rust applications, this means iterating on ideas without the usual lag. It is a practical tool for developers who want their machines to work as hard as they do.

🆔 @hackernewsgithubprojects

📦 comfy-org/comfy-openjutsu

Comfy Openjutsu: Swap Video Characters

Comfy Openjutsu is the video tool that swaps the actor in a clip with a character from a single image. You upload a short video segment and a character picture, then the app replaces the person in the footage with that character while keeping the original background, movements, and sound exactly as they were. It is a standalone web app built on a specific Comfy workflow that you can clone and run locally. The best part is how realistic it feels; the character matches the lighting and scene of your original video seamlessly.

🆔 @hackernewsgithubprojects

📦 stewdioai/blank-page

Blank Page: The Skill That Fixes Your Vague Prompts

Blank Page solves the frustrating moment when you have a vague idea for a video clip but no clear visual direction. Instead of asking you to describe every detail, this skill takes your one line of text and turns it into a fully detailed prompt. It does this by automatically finding five reference images to lock in the style and three motion examples to define the movement. It then writes out a numbered sequence of beats for your clip, including a creative twist like a zoom or a reveal. The result is a rich, specific prompt that gets you a much better first draft than a generic request.

🆔 @hackernewsgithubprojects

📦 pch/omafeed

omafeed: Your Offline RSS Command Center

omafeed is the native Linux reader that treats your news feed like a scriptable database. It keeps your subscriptions and articles entirely on your computer, but the real surprise is the built-in command line that lets you query, search, and star articles from a terminal without opening the window. You can pipe this data into scripts or give it to an AI agent to build custom daily digests. It is a privacy-focused tool that works offline, uses no cloud sync, and offers a clean three-pane view for human reading.

🆔 @hackernewsgithubprojects

📦 thusi-lab/prismwam

PrismWAM: The Robot Brain That Splits Sight From Motion

PrismWAM is the robot model that finally separates what a scene looks like from how it moves. Most AI systems get confused when the lighting changes, but PrismWAM solves this by splitting its thinking into two distinct parts. It uses a simple color snapshot to understand the goal, then relies on detailed depth maps to plan the actual physical movement. This clever trick allows it to guide real robots with impressive accuracy, even without years of extra training. If you are building autonomous machines, this approach to vision is a major breakthrough.

🆔 @hackernewsgithubprojects

📦 twehrbein/exmr

ExMR: Full Body Motion Capture from One Camera

ExMR is the motion capture tool that finally nails down hand and foot details from a single camera. Usually, figuring out exactly how someone moves in three dimensions requires expensive, marker-covered suits. This project solves that by taking an ordinary video and reconstructing a complete, ground-level skeleton. It goes beyond just tracking the main body; it specifically refines the tricky movements of your fingers and toes. That level of detail is what animators and robot engineers need to make their characters feel real. You can export this data directly into game engines or animation software. It turns your phone into a professional motion capture studio.

🆔 @hackernewsgithubprojects

📦 einsia/embodiedevo

EmbodiedEvo: The Robot That Learns By Doing

Watch a coding agent figure out how to fold clothes, stack bowls, or play tic-tac-toe by actually moving a robot in a simulation. This project connects an AI coder to a physics engine, letting it watch what happens, rewrite its own control code, and try again until it works. The coolest part is how it remembers. After practicing on easy tasks, it saves reusable tricks and written notes about what went wrong. Then, when it faces a brand-new challenge, it starts fresh with those notes in hand, acting like a seasoned intern who learned from past mistakes.

🆔 @hackernewsgithubprojects

📦 hazyresearch/ncm

Next-Concept Modeling: The Fast Text Generator

Next-Concept Modeling is the text generation framework that writes whole sentences in parallel instead of word by word. It solves the slow speed problem of standard language models by using a two-stage system. First, it sketches a rough version of your text, then it refines that sketch into a detailed paragraph in just a few steps. This means it generates text up to thirty-one times faster than other methods while keeping the same quality. It’s like watching a rough draft turn into a polished essay in seconds.

🆔 @hackernewsgithubprojects

📦 tyrichards/omarchy-tray

omarchy-tray: The System Tray That Swallows Your Bar

omarchy-tray is the system tray plugin that turns your entire desktop bar into a hidden drawer. If you use Omarchy, you know how cluttered the bar gets with clocks, workspaces, and weather widgets. This project solves that mess by letting you drag any bar widget directly into the tray, tucking it away until you hover the chevron to slide out the drawer. It is a strict upgrade over the stock tray because it keeps all your standard features like pinning and app menus while adding this new capability.

🆔 @hackernewsgithubprojects

📦 tool-bunker/code-buster

Code Buster: Your Code's GPS

Code Buster tells an A I coding agent exactly where its changes broke the rules, all without sending your code to the cloud. It acts as a local guardrail that maps every dependency and logic cycle in your project before the agent writes a single line. Instead of guessing, it gives the machine a deterministic map of dead code and architecture violations, so it can fix errors while it still has context. It’s like giving a new intern the entire building’s blueprints before they start moving furniture. No more hallucinated imports. Just grounded, offline verification that keeps your AI honest and your codebase clean.

🆔 @hackernewsgithubprojects

📦 igtoth/tracedraw

TraceDraw: The Vector Editor Rebuilt in Rust

TraceDraw is the open-source vector editor that finally brings full-featured illustration to your browser and desktop without bloat. This project is a clean-room rewrite of a classic drawing suite, built entirely in Rust to run natively on Windows, macOS, Linux, and even in your web browser via WebAssembly. It solves the problem of heavy, proprietary software by offering a lightweight, native experience that still handles complex tasks like live effects, page layout, and print-ready PDFs. The most surprising part is that it natively opens and writes Corel Draw files, meaning you can swap between old projects and this new tool without losing your work.

🆔 @hackernewsgithubprojects