📦 anthonysturdy/micro-radar

Build Your Own Miniature Desktop Flight Radar

Ever wanted to track live air traffic right from your desk? The Micro Radar project lets you build a tiny, dedicated hardware device that visualizes nearby aircraft in real time. Using an ESP32-C3 module and a compact display, this open-source project pulls flight data from the OpenSky network to animate planes moving across a custom circular interface. You will need to 3D print an enclosure and assemble the electronics, but the result is a functional, elegant aviation tracker for your workspace. Grab your soldering iron and some basic components to start monitoring the skies above your home today.

📰 https://news.ycombinator.com/item?id=48547732

🆔 @hackernewsgithubprojects

📦 917dhj/deeppapernote

Stop Manually Summarizing Papers: Use DeepPaperNote

Do you find it exhausting to manually turn complex academic papers into useful, organized notes? DeepPaperNote is an agent skill that solves this by automating the heavy lifting of your research workflow. It integrates with tools like Claude Code and Codex to ingest papers, extract key mechanisms, and generate high-quality, Obsidian-ready Markdown notes. Instead of jumping between files, you get structured summaries that prioritize technical details, equations, and clear figure contexts. It effectively handles the mechanical work of note production so you can focus on mastering the actual content. Streamline your study process and build a better knowledge base today.

🆔 @hackernewsgithubprojects

📦 lyra-stellai/web-browser-agent

Build Your Own Knowledge Graph from the Web!

Struggling to keep track of everything you read online? This lightweight web application turns your browsing into a personal knowledge base. It lets you search the web, summarize articles with AI, and highlight key points to save as structured notes. The coolest part is its ability to integrate these chunks into a persistent knowledge graph, using LLMs to automatically extract entities and connect related ideas over time. Whether you use popular AI models or a local fallback, you can finally turn scattered web content into a connected, searchable brain. Start building your own intelligent knowledge network today!

🆔 @hackernewsgithubprojects

📦 dbwls99706/ros2-engineering-skills

Supercharge Your ROS 2 Development with AI Agents

Want to build professional-grade robotics software without getting lost in complex configurations? This project provides a powerful engineering skill module designed to give AI coding agents deep expertise in ROS 2. Instead of generic advice, you get precise decision frameworks for production challenges like QoS profile tuning, lifecycle node management, and hardware interfacing with ros2_control. It uses a progressive disclosure structure to keep your AI assistant focused and efficient, whether you are setting up workspaces, navigating Nav2, or deploying multi-robot fleets. Stop guessing and start coding with reliable, distro-aware patterns that ensure your robot projects are truly production-ready.

🆔 @hackernewsgithubprojects

📦 boogu-project/boogu-image

Meet Boogu-Image: High-Performance Open-Source AI Generation

Ever wonder how to get professional-grade image generation without the massive data requirements of closed systems? Meet Boogu-Image, an impressive open-source model family designed for high-quality text-to-image generation and precise image editing. By refining training pipelines and data quality, it delivers near-closed-source performance using significantly less training data than typical models. Whether you need stable bilingual text rendering, photorealistic visuals, or flexible editing tools, this model provides powerful capabilities in a compact package. Explore their diverse variants like the fast Turbo mode or the Base model and start creating high-quality AI visuals on your own local hardware today.

🆔 @hackernewsgithubprojects

📦 openhands/agent-canvas

Build Smarter with OpenHands Agent Canvas

Tired of repetitive coding tasks slowing you down? Meet OpenHands Agent Canvas, a powerful self-hostable platform designed to automate your development workflow right from your local machine. This project lets you connect your own tools and build intelligent agents to handle complex coding projects efficiently. With features like built-in terminal access, file system integration, and advanced task tracking, it transforms your browser into a command center for AI-assisted development. Whether you are managing backend services or launching custom automation, this platform gives you full control. Take charge of your coding process and start building your own automated workspace today.

🆔 @hackernewsgithubprojects

📦 hongyang-du/videogpa

Boost Your AI Video Consistency with VideoGPA

Ever notice how AI-generated videos sometimes warp or lose their shape? VideoGPA is a powerful new self-supervised framework designed to solve this exact problem by enhancing 3D consistency in video diffusion models. By using a clever Direct Preference Optimization training pipeline, it helps models maintain geometric stability, resulting in much more reliable and realistic video generation. Whether you are working with text-to-video or image-to-video tasks, this repository provides specialized adapters to upgrade your output quality. Check out this project to explore these advanced geometry priors and take your AI video production to the next level.

🆔 @hackernewsgithubprojects

📦 zetaneko/animadex

Build Your Own AI Anime Character Gallery with AnimaDex

Ever wanted a perfectly organized, searchable home for your AI-generated anime collection? Meet AnimaDex, a slick self-hosted gallery designed to manage your character and artist references with ease. It features a lightweight Flask backend and an intuitive interface that makes browsing your library simple. You can import datasets directly or build your own pipeline to generate and score images automatically. Whether you are tracking specific copyrights or curating your favorite artists, this tool keeps everything tidy using a robust SQLite database. It is a fantastic project if you want total control over your creative assets without any bloat.

🆔 @hackernewsgithubprojects

📦 alibaba-quark/liveavatar

Real-time AI Avatars with Live Avatar

Have you ever wanted to bring a digital character to life in real-time using nothing but your own voice? The Live Avatar repository introduces a powerful framework designed for exactly that. By utilizing a sophisticated fourteen-billion-parameter diffusion model, this project enables streaming, audio-driven avatar generation that can last for thousands of seconds without interruption. It achieves impressive speeds of forty-five frames per second through advanced algorithm-system co-design, including techniques like block-wise autoregressive processing. Whether for interactive AI agents or virtual assistants, this tool turns audio input into smooth, high-quality video, setting a new standard for responsive, immersive digital communication.

🆔 @hackernewsgithubprojects

📦 avibebuilder/claude-prime

Stop Prompting, Start Priming: Master Claude Code Workflows

Are you tired of constantly repeating project rules or struggling with inconsistent AI output while coding? Meet Claude Prime, an open-source toolkit that streamlines your development by adding a structured layer of reusable skills and workflows to Claude Code. Instead of manual setup, you can prime your repository in one command to install project-specific context, guardrails, and slash-command workflows like fixing bugs, discussing plans, or reviewing code. It solves the problem of context rot by loading only what you need exactly when you need it. Install it today to simplify your AI-assisted workflow and keep your team consistent.

🆔 @hackernewsgithubprojects

📦 smthemex/comfyui_sensenova_u1

SenseNova U1: True Multimodal AI in ComfyUI

Ever wanted a single AI model that truly understands and generates both text and images natively? The SenseNova U1 repository brings this breakthrough technology into the ComfyUI workspace. By using the NEO-Unify architecture, it eliminates the need for separate encoders and decoders, allowing you to handle complex tasks like infographic generation, interleaved text and image creation, and advanced reasoning all from one pipeline. Whether you are building structured layouts or detailed visual stories, this toolset offers a powerful and efficient way to integrate native multimodal intelligence into your creative workflows, making high-end AI performance more accessible than ever before.

🆔 @hackernewsgithubprojects

📦 inertia-rails/skills

Stop Building Inertia Rails the Wrong Way

Are you tired of your AI coding assistant generating outdated or inefficient patterns for your Rails and Inertia projects? This repository is a powerful collection of Claude Code plugins specifically designed to fix common anti-patterns in the Inertia Rails stack. It acts as a specialized guide that forces your AI to respect the server-driven architecture where Rails owns the data, auth, and routing. From providing better form handling with the Form component to enforcing correct controller responses, this toolkit ensures your code stays clean and scalable. Level up your development workflow and keep your application architecture robust and modern today.

🆔 @hackernewsgithubprojects

📦 zuzuleinen/algotutor

Master Go with AI-Powered Training

Struggling to level up your Go programming skills? Stop aimlessly coding and start training with an intelligent tutor that evolves alongside you. This project functions as an AI-powered personal coach designed specifically for Go developers, offering structured tracks in algorithms, data structures, and concurrency. It tracks your skill level across various concepts, generates progressively difficult problems, and uses spaced repetition to ensure you actually retain what you learn. By providing tailored feedback and mistake logging, it helps you build genuine mastery. Dive into the repository to start your automated training journey today and sharpen your Go expertise.

🆔 @hackernewsgithubprojects

📦 nyxawroo/img-dataset-refiner

Master Your AI Training Datasets with IMG Dataset Refiner

Struggling to get your AI model training data perfectly organized? Meet IMG Dataset Refiner, a powerful local desktop tool designed to help you build clean, balanced datasets for LoRA, Flux, and Stable Diffusion workflows. This application streamlines the entire process, allowing you to quickly edit captions, batch-process images, and detect duplicates with ease. You can even leverage local AI models to automate captioning or perform smart crops. By providing advanced analytics and seamless export options, it takes the headache out of dataset preparation. Take control of your training data today and see the difference in your final results.

🆔 @hackernewsgithubprojects

📦 newjhez01/gdns

Build Your Own DNS Server with Go

Want to take control of your network privacy? This project is a custom DNS resolver built from scratch in Go, designed to run on a Raspberry Pi. It acts like your own personal traffic controller by parsing DNS requests at the bit level and blocking ads and trackers by routing them to NXDOMAIN. It uses a high-performance SQLite database for blocklists and Redis for lightning-fast response caching. By handling requests locally before forwarding legitimate traffic to Cloudflare, it gives you a powerful, self-hosted alternative to standard network filters. Try it out to see how deep network protocols really go.

🆔 @hackernewsgithubprojects

📦 tencent/hpc-ops

Supercharge Your AI Models with HPC-Ops

Are your large language models struggling with slow inference times? Meet the high-performance operator library from the Tencent Hunyuan AI Infra team. This project provides production-grade kernels specifically optimized for modern NVIDIA hardware to accelerate critical tasks like attention, MoE, and GEMM computations. By fusing complex operations—like combining AllReduce with RMSNorm or streamlining token sampling—it significantly reduces bottlenecks that typically drag down performance. Whether you need precision-sensitive computations or massive throughput for your AI workloads, these tools are built to help. Explore these advanced kernels to unlock faster, more efficient inference and take your deployments to the next level.

🆔 @hackernewsgithubprojects

📦 rawfilejson/awesome-osint-arsenal

Supercharge Your Recon with Awesome OSINT Arsenal

Are you struggling to manage dozens of scattered security tools? The Awesome OSINT Arsenal is a massive, curated collection of over seven hundred fifty powerful utilities designed to streamline your reconnaissance and security workflows. Whether you are performing network scans, diving into digital forensics, or conducting red team operations, this toolkit simplifies everything with one-command installers for major Linux distributions and even Termux. It effectively solves the problem of tedious manual setups by organizing tools into fifty specific categories, from web application testing to hardware analysis. Grab this ultimate library today and take your security research to the next level.

🆔 @hackernewsgithubprojects

📦 osu-nlp-group/quest

Meet QUEST: Powerful New Open-Source Deep Research Agents

Ever wish you had an AI that could handle complex, long-form research tasks just like a human expert? Meet QUEST, a new family of open-source models ranging from two to thirty-five billion parameters. These models are specifically designed to tackle deep research by mastering fact seeking, citation grounding, and detailed report synthesis. Whether you need to automate research workflows or improve your data generation pipelines, QUEST provides the necessary tools and model checkpoints to get the job done effectively. Dive into this repository to explore the future of automated research and see how these agents can transform your workflows today.

🆔 @hackernewsgithubprojects

📦 haru-lcy/voidpadding

Stop Model Failures with VoidPadding

Have you ever noticed your language model getting stuck or acting weird with padding tokens during complex tasks? Masked diffusion language models often struggle when empty padding gets confused with semantic endings, leading to annoying errors where the model overproduces tokens. VoidPadding is a clever new approach that solves this by introducing a dedicated void signal specifically for padding, while leaving the conventional ending token to handle true semantic termination. By clearly separating these two roles, this method improves model robustness, prevents overflow errors, and even enables smarter adaptive canvas expansion. It is a powerful way to make your model decoding more efficient.

🆔 @hackernewsgithubprojects

📦 opendfm/xcientist

Automate Your Research with AI Scientists

Ever wonder if AI could handle the heavy lifting of scientific research? Meet Xcientist, a powerful multi-agent workflow designed to turn any research topic into a complete scientific journey. This system automates everything from gathering paper surveys and generating structured research ideas to executing actual code experiments and drafting technical blog articles. By using specialized agents for tasks like MCTS-based ideation and workspace orchestration, Xcientist streamlines complex research cycles into a single, cohesive pipeline. Whether you are validating new theories or conducting experiments, this framework provides the harness you need to accelerate discovery. Try it out to supercharge your research workflow.

🆔 @hackernewsgithubprojects