56 subscribers
7.27K videos
7.88K links
Download Telegram
This media is not supported in your browser
VIEW IN TELEGRAM
πŸ“¦ shinshin86/live2d-add-motion-sample-web-ui

Live2D Add Motion Sample Web UI: Add Animations with JSON

Live2D Add Motion Sample Web UI is the development tool that lets you add new animations to characters without opening heavy editing software. Normally, making a 2D model blink or nod requires a complex rigging environment, but this project proves you can do it with simple text files. It uses a smart pipeline to turn basic code into valid motion data, ensuring the character actually moves correctly in your browser. You can drag, zoom, and test new poses instantly, making it perfect for developers who want to experiment with character behavior quickly. Skip the expensive setup and just focus on the creative side of animation today.

πŸ†” @hackernewsgithubprojects
This media is not supported in your browser
VIEW IN TELEGRAM
πŸ“¦ zyora-dev/zse

ZSE: The LLM Engine That Installs in 5 MB

ZSE is the inference engine that runs large language models without the heavy machinery usually required. While standard tools demand massive packages and minutes of setup, ZSE uses pure Python and a custom compiler to load models in seconds with a tiny memory footprint. This project proves you can build production-grade AI servers from scratch, eliminating complex dependencies while still supporting NVIDIA, AMD, and Apple hardware. It is a compelling look at how raw engineering can strip away bloat to deliver speed and simplicity for developers who need efficiency over convenience.

πŸ†” @hackernewsgithubprojects
This media is not supported in your browser
VIEW IN TELEGRAM
πŸ“¦ sylphai-inc/atskills

The End of Skill Installation

A new protocol called atskills treats agent skills like simple files you read on demand, rather than software you install. By using a file path as the address, the system loads instructions only when needed and leaves no permanent trace in your agent's memory. This solves the problem of clutter, where unused skills consume valuable space and create confusion. It turns a messy catalog into a clean, readable tree where you grab exactly what you need without any setup. The result is a cleaner workflow where your tools remain uncluttered and ready for action.

πŸ†” @hackernewsgithubprojects
This media is not supported in your browser
VIEW IN TELEGRAM
πŸ“¦ sunblaze-ucb/vero

Vero: Testing if AI Code is Actually Correct

Vero is the benchmark that finally checks if AI-written code actually works. While other tools just ask an agent to write code, this project forces it to prove that code is correct using a formal logic system called Lean. The problem it solves is that AI can sound confident while being completely wrong. Vero takes real software from things like banking ledgers and cryptography and turns them into puzzles. The AI agent has to write the code and then build a mathematical proof that the code follows the rules. If the agent can't prove it, the code is rejected.

πŸ†” @hackernewsgithubprojects
This media is not supported in your browser
VIEW IN TELEGRAM
πŸ“¦ caviraoss/pagelm

PageLM: The AI That Studies For You

Stop reading dry PDFs and start actually learning with PageLM. This open source tool takes your messy lecture notes or textbooks and turns them into interactive quizzes, flashcards, and even custom AI podcasts you can listen to on your commute. It’s like having a personal tutor that digests the heavy lifting for you so you can focus on understanding the material instead of just memorizing it. The best part is that it’s built to be fully customizable, letting you swap between different AI models to match your specific study style.

πŸ†” @hackernewsgithubprojects
This media is not supported in your browser
VIEW IN TELEGRAM
πŸ“¦ rai-opensource/vernata

How Vernata Teaches Robots to See Without Labels

Vernata is the self-supervised learning framework that teaches computers to understand outdoor LiDAR point clouds without expensive human labels. Developed by researchers at the Robotics and AI Institute, this new method uses a clever multi-teacher distillation approach to solve a major problem in robotics. The system uses a high-resolution 2D image model to provide semantic hints to a 3D point cloud model, allowing it to learn fine-grained features from unlabeled data. By combining sparse view augmentation with a memory bank, Vernata creates representations that remain robust even when sensor data is noisy or incomplete.

πŸ†” @hackernewsgithubprojects
This media is not supported in your browser
VIEW IN TELEGRAM
πŸ“¦ swordandsnow/mm26-ags

The Thinking Trick for AI Vision

Make multimodal AI think faster without losing accuracy. This new tool, AGS, solves a major problem where visual models often get stuck in deep reasoning loops that waste time and energy. Instead of forcing the model to constantly generate text for every thought, this system watches how the AI is paying attention to the image. If the focus is on seeing, it switches to a fast, hidden mode. If it needs to solve a logic puzzle, it flips back to normal text reasoning. This is a training-free hack that works instantly on existing models, letting them process complex images much more efficiently.

πŸ†” @hackernewsgithubprojects
This media is not supported in your browser
VIEW IN TELEGRAM
πŸ“¦ cesarferreira/rip

The Easiest Way To Kill Processes In Your Terminal

Your terminal has a hidden superpower that lets you hunt down misbehaving software like a hawk. This tool, called rip, solves the headache of trying to kill background processes that are hogging your computer's resources. Instead of digging through endless, confusing lists of numbers, it shows you a clean, interactive dashboard where you can just type a few letters to find what you need. It’s like having a targeted radar for your system. You can spot the troublemakers eating up memory or CPU, pick them out, and send them away with a simple command.

πŸ†” @hackernewsgithubprojects
This media is not supported in your browser
VIEW IN TELEGRAM
πŸ“¦ kubara-io/kubara

Kubara: The Single Binary for Kubernetes Platforms

Kubara takes the chaotic, multi-hour process of setting up a production-ready Kubernetes cluster and boils it down to a single command. It’s a lightweight Go binary that handles the heavy lifting of bootstrapping your platform, automatically installing Argo CD and applying industry-proven best practices for you. The real magic is in its GitOps-first workflow: instead of manually wrestling with endless YAML files, you simply define your environment, and Kubara generates the reproducible artifacts and provisions the entire stack. It’s built for scale, supporting multi-cluster setups out of the box. If you’re looking to turn complex infrastructure into a simple, repeatable process, this tool is your shortcut.

πŸ“° https://news.ycombinator.com/item?id=49327257

πŸ†” @hackernewsgithubprojects
This media is not supported in your browser
VIEW IN TELEGRAM
πŸ“¦ eri64/dsh-claude-ux

The AI Plugin That Cuts Conversations Off

DSH Claude UX is the chat plugin that mimics how major AI companies handle risky conversations. It works locally to detect user traits like time zones and browser settings to enforce regional rules without sending data off your machine. The standout feature is its ability to gracefully end abusive chats. Instead of just blocking text, it warns users first and then terminates the session entirely if they continue, much like a real support agent walking away. This project solves the problem of unwanted interactions in local AI setups by giving the bot the autonomy to stop talking.

πŸ“° https://news.ycombinator.com/item?id=49322653

πŸ†” @hackernewsgithubprojects
This media is not supported in your browser
VIEW IN TELEGRAM
πŸ“¦ meridiona/meridian

Meridian Writes Your Standup For You

Meridian quietly watches your screen to rebuild your entire workday into a searchable timeline, saving every hour of your focus so you never have to guess what you actually did. It cuts through the noise of app switching and idle time to figure out exactly which project you were tackling, then automatically drafts your ticket updates and standup notes for you to review. This tool removes the mental tax of remembering your past work, turning a chaotic day of coding into a clean, ready-to-post summary. It’s the perfect fix for developers who lose track of their progress, ensuring your contributions are visible without you having to type a single word.

πŸ“° https://news.ycombinator.com/item?id=49318130

πŸ†” @hackernewsgithubprojects
This media is not supported in your browser
VIEW IN TELEGRAM
πŸ“¦ babon-innovations-b-v/movalytics

Movalytics: Clinical Angles Without Kinematics

Movalytics pulls precise clinical joint angles directly from raw body model rotation matrices, completely bypassing the heavy inverse kinematics steps that usually slow down motion analysis. This Python package acts as a fast bridge between digital avatars and real-world medical data, converting simple rotation data into standard joint movements like knee flexion or hip rotation. The system uses a unique calibration method to map these movements accurately, delivering results with sub-millisecond speed per joint. It is a free research tool designed to help scientists and developers turn computer vision outputs into usable clinical metrics without complex modeling software.

πŸ†” @hackernewsgithubprojects
This media is not supported in your browser
VIEW IN TELEGRAM
πŸ“¦ realfakenerd/openskyrim

OpenSkyrim: Skyrim Without Loading Screens

OpenSkyrim is building a modern, open-source engine for Skyrim that completely eliminates loading screens. By converting old game files into modern formats like glTF and KTX2, the engine streams assets in real-time, letting you walk from a dungeon straight into the city without ever waiting. This project, inspired by OpenMW, uses Rust and the Bevy engine to handle everything from physics to a new scripting system, aiming for smooth, high-performance gameplay on both desktop and mobile. It’s a massive technical undertaking to bring a classic game into the modern era with zero interruptions, and it’s a fascinating look at how engine reimplementation works.

πŸ“° https://news.ycombinator.com/item?id=49327662

πŸ†” @hackernewsgithubprojects
This media is not supported in your browser
VIEW IN TELEGRAM
πŸ“¦ danielle34/cavewoman

Cavewoman: Why Talking Like a Caveman Costs You More

CAVEWOMAN is a benchmark that reveals why talking to AIs like a caveman actually costs you more money. The project strips language down to bare nouns and numbers across nine different models to see what breaks. Surprisingly, compressing your input prompts makes models write longer, more expensive replies to compensate for the missing context. On the other hand, forcing the AI to speak in short, blunt sentences genuinely saves you up to three times the money on API fees. It is a clever, data-driven way to find out exactly where your token budget is leaking. Stop guessing which style is efficient and just check the numbers.

πŸ†” @hackernewsgithubprojects
This media is not supported in your browser
VIEW IN TELEGRAM
πŸ“¦ aigeeksgroup/anydepth

AnyDepth: The Tiny Depth Engine

AnyDepth is the depth estimation framework that shrinks the heavy lifting part by eighty-five percent without losing the accuracy. If your computer vision project needs to figure out how far objects are from the camera, this tool plugs right in and does the job with a fraction of the brain power. It uses a compact decoder that cuts down the mathematical work, making it fast enough to run smoothly on tiny, low-power hardware like a Jetson card. You get professional grade depth maps while keeping your system light and efficient. It is the smart, lightweight way to add spatial awareness to your AI models.

πŸ†” @hackernewsgithubprojects
This media is not supported in your browser
VIEW IN TELEGRAM
πŸ“¦ olorehq/olore

How olore stops your AI from making things up

Olore is the local documentation tool that stops your AI coding agents from making stuff up. It works like a package manager, but instead of code, it installs full, offline-ready reference books for tools like Prisma or Next JS directly onto your machine. This means your assistant actually reads real, verified documentation instead of guessing, so you get accurate code without needing any cloud infrastructure. Once you install a pack, it links to all your different AI agents at once, keeping everything consistent and private. It is a simple, local first way to give your bots the knowledge they need to get it right the first time.

πŸ†” @hackernewsgithubprojects
This media is not supported in your browser
VIEW IN TELEGRAM
πŸ“¦ kubeswift-io/kubeswift

KubeSwift: Run VMs Like Kubernetes Pods

KubeSwift is the Kubernetes-native tool that finally lets you run full virtual machines with the same ease as deploying a simple container. It bridges the gap between lightweight microVMs and heavy traditional virtualization by treating every VM like a standard workload you manage with kubectl. The coolest part is the warm-pool sandbox, which keeps pre-booted, isolated VMs ready to go so you can spin up secure environments for untrusted code in fractions of a second. This solves the pain of needing hardware isolation without the slow, clunky setup of a traditional virtualization stack.

πŸ“° https://news.ycombinator.com/item?id=48834952

πŸ†” @hackernewsgithubprojects
This media is not supported in your browser
VIEW IN TELEGRAM
πŸ“¦ pcm720/dvrpwned

The PSX DVRP Custom Firmware Breakthrough

The PlayStation X finally accepts any hard drive. This new project, DVRPwned, delivers the first working custom firmware for the PSX DVRP. For years, this console locked you into expensive, original Sony hard drives because of a strict security check. This tool patches the internal firmware to bypass that restriction, letting you use almost any standard hard drive instead. The clever part is that it tricks the drive controller into accepting a generic identity, removing the need for expensive proprietary hardware. It is a massive win for retro gaming enthusiasts who want to save their old consoles from failing original disks.

πŸ“° https://news.ycombinator.com/item?id=49328893

πŸ†” @hackernewsgithubprojects
This media is not supported in your browser
VIEW IN TELEGRAM
πŸ“¦ strelov1/freehire

Freehire: The Job Search Engine That Actually Works

Freehire is the open-source job search engine that cuts through the clutter of modern recruiting. Most job boards are just noisy lists where you spend hours scrolling past stale postings and duplicate entries. Freehire solves this by ingesting data from dozens of different sources, including niche boards and direct company pages, and cleaning it all up in one place. It uses smart background processes to merge similar jobs, flag dead links, and even extract key details like seniority and skills so you can filter for exactly what you need. It turns a chaotic hunt into a clear, organized pipeline.

πŸ†” @hackernewsgithubprojects
This media is not supported in your browser
VIEW IN TELEGRAM
πŸ“¦ elder-plinius/fable-showcase

One Prompt, 57 Demos

The Fable Showcase is the creative web gallery that proves one prompt can build an entire universe. It starts with a simple challenge to an AI system, asking it to spend its weekly credit limit on generating complex, interactive art. The result is fifty-seven self-contained demos, from simulated fish schools to generative tarot cards, all built in a single day. What makes this genuinely surprising is the engineering behind the curtain. Every single project is just one HTML file with zero external dependencies, meaning you can open any of them directly in a browser without needing a server or internet connection.

πŸ“° https://news.ycombinator.com/item?id=49046110

πŸ†” @hackernewsgithubprojects