📦 kaansenol5/vibeos

Building a Complete Operating System from Scratch

Ever wondered what it takes to build an entire operating system from scratch? VibeOS is a hobbyist project developed for Aarch64, featuring a custom kernel with cooperative multitasking, a modern desktop interface, and even support for hardware like the Raspberry Pi Zero 2W. Built in collaboration with an AI, this project demonstrates a full TCP/IP stack, a functional web browser, and a working port of DOOM. It solves the challenge of creating a persistent environment with its own filesystem, window manager, and compiler. Explore how this unique project brings a cohesive, nostalgic computing experience to life on real hardware.

🆔 @hackernewsgithubprojects

📦 aaronjmars/miroshark

Simulate Anything with MiroShark: A Universal Swarm Intelligence Engine

Ever wondered how the world would react to a specific headline or policy change before it even happens? Meet MiroShark, a powerful swarm intelligence engine that lets you simulate complex scenarios for just one dollar. By feeding in a document, news draft, or historical question, you trigger a network of hundreds of grounded agents that interact, trade, and debate in real-time. You can even inject breaking news mid-simulation to see how the story branches. It is a game-changer for PR testing, market analysis, and creative storytelling. Try it out to see the future unfold today.

🆔 @hackernewsgithubprojects

📦 0xmassi/webclaw

Clean Web Data for AI Agents with Webclaw

Are you tired of feeding your AI agents messy HTML filled with ads and broken code? Meet Webclaw, a powerful, local-first tool designed to turn any website into clean, structured markdown, JSON, or LLM-ready context. Whether you are using the CLI, the MCP server for tools like Claude and Cursor, or the self-hostable API, it intelligently strips away navigation and boilerplate to give you only the data that matters. It even handles complex tasks like crawling documentation and extracting brand assets, making it the perfect engine for your RAG pipelines. Start scraping smarter and give your AI the high-quality data it needs.

🆔 @hackernewsgithubprojects

📦 darthnorse/dockmon

Take Control of Your Docker Containers with DockMon

Are you tired of constantly checking if your containers are running? Meet DockMon, a modern monitoring solution designed to keep your Docker environment healthy without the headache. This tool acts as a dedicated agent that tracks your containers, offering essential capabilities like automated restarts if something goes down and real time alerting to keep you informed. By connecting directly to the Docker daemon, it provides a reliable way to maintain uptime and performance. Whether you are managing simple setups or complex services, DockMon helps you stay proactive. Give your containers the care they need and start monitoring smarter today.

🆔 @hackernewsgithubprojects

📦 future-agi/future-agi

Stop Stitching AI Tools: Meet the All-in-One Platform for Self-Improving Agents

Are you tired of juggling a dozen different tools just to keep your AI agents reliable? Future AGI is an open-source platform that simplifies the entire lifecycle of your LLM applications by bringing tracing, evaluations, simulations, and guardrails into one connected system. Instead of managing separate tools for observability and testing, this platform lets you simulate adversarial scenarios, catch hallucinations in real time, and automatically optimize your prompts based on production data. By closing the loop between monitoring and improvement, it helps your agents actually get better over time. Dive in, start tracking your agents, and finally build with confidence.

🆔 @hackernewsgithubprojects

📦 ahekot/comfyui_vnccs

Create Consistent Visual Novel Characters Easily with VNCCS

Struggling to keep your visual novel characters looking consistent across every image? Meet the Visual Novel Character Creation Suite, a powerful pipeline for ComfyUI designed specifically to solve this headache. Instead of fighting with inconsistent AI outputs, this suite guides you through a structured five-stage workflow, from creating a base character to managing outfits, emotions, and pose generation. It even helps you organize your assets and prepare datasets for custom training. Whether you are building a new game or experimenting with sprite design, this tool streamlines the entire process. Start creating your perfect visual novel cast today.

🆔 @hackernewsgithubprojects

📦 hyhmrright/brooks-lint

Stop Writing Bad Code: Meet brooks-lint

Are you tired of AI writing code that works today but creates a maintenance nightmare tomorrow? Enter brooks-lint, a powerful tool that brings fifty years of software engineering wisdom directly into your terminal. Instead of just checking for simple syntax errors, it uses AI to analyze your project against twelve classic engineering books, identifying risks like cognitive overload and architectural decay. You get actionable, traceable findings with specific book citations, severity labels, and even automated fixes. Whether you need a quick PR review or a deep architectural audit, start using expert-backed insights to build better, more resilient software.

📰 https://news.ycombinator.com/item?id=48490591

🆔 @hackernewsgithubprojects

📦 finstep-ai/contesttrade

Build Your Own AI Trading Team with ContestTrade

Ever wanted to build your own autonomous AI trading team? Meet ContestTrade, an innovative framework that uses a unique internal contest mechanism to handle event-driven stock selection. By simulating a real investment firm, it uses a two-stage pipeline where data agents first process market signals, which then compete for selection, followed by research agents that submit and refine final trading proposals. This clever, multi-agent approach filters out noise to help you discover high-value opportunities without constant human oversight. Ready to explore a new paradigm in quantitative trading? Start building your own automated financial analyst today and level up.

🆔 @hackernewsgithubprojects

📦 shandaai/alayarenderer

AI-Powered Game World Rendering with AlayaRenderer

Ever wondered how AI could reshape virtual worlds? Meet the Generative World Renderer, an AI-native engine designed for advanced game editing. This project provides a powerful framework for inverse and forward rendering, letting you decompose game footage into essential G-buffer maps like depth, albedo, and normals. You can then use these to synthesize stunning, stylized video sequences controlled entirely by text prompts. Whether you are transforming lighting or changing the atmosphere of a scene, this framework offers creative new possibilities for virtual environments. Dive into the code and start experimenting with these generative rendering tools today.

🆔 @hackernewsgithubprojects

📦 bobek-balinek/claude-lamp

Turn Your Lamp into a Claude Code Status Indicator

Ever wanted a physical way to track what your AI assistant is doing? This project lets you turn your Moonside LED lamp into a real-time status indicator for Claude Code on macOS. By using Python scripts and Bluetooth, it creates a persistent connection that updates your lamp’s lighting based on Claude’s activity. You get visual cues like a white and navy animation while it works, a steady orange when it is idle, or a bright purple glow when it needs your input. It is a clever way to keep an eye on your workflow without checking your screen.

🆔 @hackernewsgithubprojects

📦 ammaar-alam/minebench

Is Your AI Actually Smart? Test Its 3D Spatial Reasoning!

Ever wonder if your favorite AI model is truly intelligent or just good at predicting text? Meet the project that puts spatial reasoning to the test using Minecraft-style voxel construction. Instead of simple text prompts, these models must generate complex 3D structures using precise coordinate math and specialized construction tools. By visualizing these builds and ranking models through blind head-to-head comparisons, it reveals which AI truly understands geometry and space. It is a brilliant way to cut through the marketing hype and see which models perform best in the real world. Go ahead and explore the leaderboard today.

🆔 @hackernewsgithubprojects

📦 mrdoob/starter-kit-racing

Build Your Own 3D Racing Game in the Browser

Ever wanted to build your own racing game right in the browser? This project is a powerful JavaScript starter kit that brings high-quality 3D racing to the web using Three.js and the crashcat physics engine. It serves as an impressive port of a classic racing starter kit, complete with vehicle physics, track building, and even sound effects. Whether you are curious about how game loops work or want to experiment with custom track layouts, this toolkit provides a perfect foundation. Dive in, start customizing your own tracks, and discover how easy it is to launch a 3D driving experience today.

🆔 @hackernewsgithubprojects

📦 xit-vcs/haxy

Haxy: The Git Forge of the Future-Past

Ever wonder what a git forge would look like if it were built for the future but felt like the past? Meet Haxy, an ambitious, experimental project aiming to rethink how we manage repositories. Instead of keeping issues and pull requests on a central server, Haxy stores all project metadata directly within the repository itself, using a special branch and JSON-based event sourcing. It even features a unique text user interface accessible directly over SSH, which also powers its web experience. It is a bold, federated take on version control that puts your workflow right in your terminal.

📰 https://news.ycombinator.com/item?id=48490880

🆔 @hackernewsgithubprojects

📦 visa/visa-vulnerability-agentic-harness

Automate Security Triage with Visa's AI Vulnerability Harness

Are you struggling to keep up with security vulnerabilities in your codebase? Meet the Visa Vulnerability Agentic Harness, an open-source tool designed to speed up your security triage process using the power of frontier AI. Instead of just finding bugs, this harness uses a nine-stage pipeline to perform everything from threat modeling and deep-dive research to adversarial verification and automated report generation. It focuses on reducing false positives through multi-agent voting and structured triage, helping you get from discovery to a validated fix faster than ever. It is time to transform your security workflow and stay ahead.

📰 https://news.ycombinator.com/item?id=48492829

🆔 @hackernewsgithubprojects

📦 emirce/bullstudio

Take Control of Your Queues with Bullstudio

Struggling to manage your background jobs? Meet Bullstudio, a powerful, developer-focused dashboard built specifically for Bull and BullMQ. It solves the headache of queue visibility by providing a clean, intuitive interface to monitor and manage your tasks. You can run it as a standalone process for quick Redis discovery or embed it directly into frameworks like Next.js, Express, or NestJS to keep your operations secure and centralized. Whether you are debugging or just keeping an eye on your workflow, Bullstudio gives you the insights you need to stay in control. Level up your queue management experience today.

📰 https://news.ycombinator.com/item?id=48494931

🆔 @hackernewsgithubprojects

📦 abdelstark/awesome-jepa

Understanding JEPA: The Future of AI World Models

Ever wonder how AI can learn to understand the world without just memorizing pixels? Meet the Joint Embedding Predictive Architecture, or JEPA, a revolutionary approach to self-supervised learning that focuses on abstract representations. Instead of reconstructing every detail, JEPA predicts latent features to help machines reason and plan like humans. This repository acts as your ultimate hub, gathering essential research, canonical models like I-JEPA and V-JEPA, and practical frameworks for robotics and data analysis. Whether you are into medical imaging or AI planning, it is the perfect place to explore how these world models are shaping autonomous intelligence.

🆔 @hackernewsgithubprojects

📦 leonxlnx/lumenshaders

Create Perfect Looping Abstract Art with LUMEN

Unlock your creativity with a powerful generative shader studio that lets you craft stunning, abstract digital art directly in your web browser. This tool enables you to generate mesmerizing visuals like liquid chrome, silk ribbons, and data glyphs using real-time WebGL2 rendering. Every animation is designed as a mathematically perfect loop, making it perfect for creative projects. You can fine-tune textures, lighting, and color palettes, then export your creations as high-quality images, seamless looping videos, or GIFs. Simply randomize, experiment with different styles, and share your unique designs using simple codes. Start creating your own infinite motion art today.

🆔 @hackernewsgithubprojects

📦 shraga100/claude-desktop-rtl-patch

Get Right-to-Left Support in Claude Desktop for Windows

Struggling with messy Hebrew or Arabic text in Claude Desktop? Many Windows users find that right-to-left languages simply do not display correctly, but this clever community patch finally solves the problem. By injecting custom CSS, it automatically detects and aligns your text in real time while keeping code blocks perfectly readable. It even fixes common window UI display bugs on RTL systems. The installation is straightforward, providing a secure, automated way to patch your files and even handle future app updates effortlessly. Take control of your interface and enjoy a smooth, native-feeling writing experience for your RTL projects today.

🆔 @hackernewsgithubprojects

📦 no1msd/seance

Stop Losing Your AI Coding Agents: Meet Séance

Struggling to keep track of your AI coding agents? Meet Séance, a powerful Linux-native terminal multiplexer designed specifically to monitor your AI workflows. It automatically detects sessions from tools like Claude Code and tracks their status in real time, showing you exactly when they are working, idle, or waiting for your input. Using a unique scrolling horizontal layout inspired by Niri, it keeps your long sessions organized and easy to navigate. Plus, it is fully scriptable, allowing AI agents to manage their own workspaces. Upgrade your terminal experience and bring order to your AI projects today.

🆔 @hackernewsgithubprojects

📦 minimax-ai/msa

Supercharge LLMs with MiniMax Sparse Attention

Unlock massive performance gains for your AI models with MiniMax Sparse Attention, a specialized toolkit designed specifically for NVIDIA SM100 GPUs. This repository provides high-performance kernels for both dense FlashAttention and advanced sparse attention, allowing you to optimize memory usage and compute efficiency. It features flexible JIT-compiled kernels and a powerful CuTe-DSL stack that supports various quantization formats like FP8, FP4, and NVFP4. Whether you are handling sparse prefill or paged decoding, these tools help you push the limits of modern hardware. Dive into this repository to start accelerating your attention workflows and see the difference in your model performance today.

🆔 @hackernewsgithubprojects