📦 lovablelabs/oj

OJ: The Rust React Build Tool That Fixes Memory

OJ is the build tool that finally makes running React apps on a tight budget a reality. It is a native Rust compiler that replaces the heavy JavaScript overhead of traditional development environments, meaning it starts up faster and uses a tiny fraction of the computer memory you are used to wasting. While other tools can eat up gigabytes of your system’s resources, OJ keeps things lean and snappy, even when you are running multiple builds at once for testing or deployment. This makes it a game changer for anyone who cares about efficiency, proving that you do not have to sacrifice speed for reliability.

📰 https://news.ycombinator.com/item?id=49746713

🆔 @hackernewsgithubprojects

📦 syv-ai/hyperqwen

HyperQwen: 27B on 24GB

HyperQwen lets a single twenty-four gigabyte graphics card serve a massive twenty-seven billion parameter language model at speeds that rival dedicated server clusters. This project solves a common problem where huge AI models simply do not fit on consumer hardware by using a specialized pipeline to compress and optimize the data flow. It achieves this through a series of precise technical patches and a unique way of predicting the next words to generate, which dramatically speeds up the process. The result is a fast and responsive local assistant that runs entirely on your own machine.

🆔 @hackernewsgithubprojects

📦 raemote/raemote_server

Raemote: Your Home Server Pocket Edition

Raemote is the private bridge that puts your home server apps in your pocket. If you run media players or smart home dashboards on your computer, you usually have to be in the same room or set up complicated network tricks to reach them from your phone. Raemote solves this by running quietly in the background, finding the web apps already running on your machine, and creating a secure, encrypted tunnel directly to your iOS device. No accounts, no public IP addresses, and no port forwarding required. It works like a magic remote control for your own hardware, whether you are on the same Wi-Fi or miles away.

🆔 @hackernewsgithubprojects

📦 qxoticai/qxotic

AI in a jar? Qxotic AI is real

Run entire artificial intelligence models directly on your Java application without needing Python or external servers. This is the big idea behind Qxotic AI, a complete open source stack that brings local AI capability right into the Java Virtual Machine. The coolest part is how they built it from scratch for Java, meaning you get a self-contained binary with millisecond startup times and no messy sidecar processes. It handles everything from tokenizing text to running the actual inference engine, all wrapped up in a simple library. You write your app, drop in the model, and it just works locally on your machine.

🆔 @hackernewsgithubprojects

📦 iman/caspian

Caspian: The DIY VPN Hotspot That Works On Any Device

Caspian is the open source gateway that turns any old computer into a private wireless hotspot. If you have ever wanted to protect your whole house without installing apps on every phone or tablet, this tool changes the rules. You simply plug your computer into a router, paste your proxy config into a simple web panel, and Caspian broadcasts a standard WiFi signal. Any device connecting to that network is instantly routed through your tunnel, keeping your traffic private and helping it slip past basic network inspection.

🆔 @hackernewsgithubprojects

📦 mhsanaei/3x-ui

The One-Stop Proxy Panel

3x-ui is the web panel that turns a blank server into a fully managed network gateway without touching a single line of code. It wraps the Xray core engine in a friendly dashboard, letting you spin up secure connections like WireGuard or Shadowsocks with just a few clicks. The real magic is how it handles every user individually. You can set strict traffic limits and expiry dates for specific clients, track exactly who is connected in real time, and manage everything from a phone or desktop browser. It is the perfect way to self-host a private, high-performance network without hiring a sysadmin.

🆔 @hackernewsgithubprojects

📦 amnezia-vpn/amnezia-client

Amnezia Client: The VPN That Builds Itself

Amnezia Client is the self-hosted VPN client that actually builds your server for you. Usually, setting up a secure connection means digging through server logs and configuring files by hand, which is a headache most people just skip. This tool changes that by letting you type in your server details, then it handles the rest. It automatically installs the necessary software on your machine and sets up the secure tunnel so you can start browsing privately without becoming a sysadmin. It works across all your devices, from laptops to phones, making it a true power move for anyone who wants control over their own internet security without the technical pain.

🆔 @hackernewsgithubprojects

📦 net4people/bbs

Net4People BBS: The Multilingual Censorship Forum

The Net4People BBS is a multilingual forum where developers and researchers discuss how to bypass Internet censorship. It is not a standard chat app; it uses GitHub issues to host open, public conversations. The most striking feature is its inclusive policy: you can start a topic in your own language, and the community commits to translating it for everyone else. This setup solves a massive problem. Technical knowledge about blocking filters or accessing blocked sites often gets trapped in one language, leaving the rest of the world in the dark. By forcing translation, the project ensures that clever workarounds and research findings spread globally.

🆔 @hackernewsgithubprojects

📦 therobotstudio/so-arm100

The $200 Robot Arm That Teaches AI

Build a low cost robot arm that lets you teach AI by simply moving it yourself. The so arm one hundred is a compact project where you print and assemble a pair of arms to mimic human motion. This setup solves the expensive data problem by allowing you to physically demonstrate tasks for a machine to copy. It works with the LeRobot library to turn your hand movements into training data for robotics. You do not need to write complex control code to get started. The whole system is designed to be accessible and open for hobbyists. It is a practical way to explore how machines learn physical skills.

🆔 @hackernewsgithubprojects

📦 ace-trump-tech/mindpaw

MindPaw: The 50 Dollar AI Robot Dog

MindPaw is the open source desktop robot dog that proves you can build a real AI companion for under fifty dollars. Instead of buying an expensive pre made gadget, you assemble a tiny four legged machine from basic parts like cheap motors and a small screen. The coolest part is that it doesn't just move around, but actually understands you. It can talk to you using a large language model, recognize your hand gestures through a camera, and even show different moods on its little face.

🆔 @hackernewsgithubprojects

📦 pollen-robotics/reachy_mini

Reachy Mini: The Robot Head That Actually Listens

Reachy Mini turns a small, friendly robot head into a fully interactive companion that can see, hear, and speak. Instead of wrestling with low level hardware drivers, you get a polished tool that connects your code directly to the robot's eyes, ears, and mouth. This means you can build an assistant that tracks your face, records your voice, or chats back with you using natural speech, all without needing a PhD in robotics. It handles the messy parts of motor control and audio so you can focus on creating cool behaviors. If you want to build a personal AI buddy that actually feels alive, this is your head start.

🆔 @hackernewsgithubprojects

📦 sigrobotics-uiuc/lekiwi

LeKiwi: The $500 Robot Arm That Moves

LeKiwi is a fully open-source mobile manipulator that costs roughly five hundred dollars to build. Most robot arms are fixed to a heavy base, making them useless if you need to move across a room. This project solves that by mounting a dexterous, six-degree-of-freedom arm on a compact, three-wheel omnidirectional drive. That combination allows the machine to slide sideways, spin on its axis, and grab objects without backing up. It runs on a standard Raspberry Pi and uses common off-the-shelf servos, so you can assemble it in your garage. The repository provides every 3D-printed part, the wiring diagrams, and the software stack to stream video and control the joints.

🆔 @hackernewsgithubprojects

📦 hedioum/hedioum-pool-tunnel

Hedioum Pool Tunnel: The Disguise That Beats Censorship

Hedioum Pool Tunnel is the anti-censorship tunnel that disguises itself so well it becomes invisible to deep packet inspection. Instead of looking like a suspicious data pipe, it dresses up as everyday internet services, pretending to be a secure shell, a mail server, or even a popular monitoring tool. It builds a coherent fake identity that changes every time it connects, making it look exactly like normal, noisy traffic. This clever trick allows it to bypass strict government firewalls and keep people connected when other methods fail. It is a fascinating piece of engineering that proves you can hide in plain sight right under the nose of the censors.

🆔 @hackernewsgithubprojects

📦 gen-verse/sciencebuddy

ScienceBuddy: The Agent That Improves Itself

ScienceBuddy is the scientific agent that improves its own code while it works. Most AI tools just answer questions, but this system takes a step further by rewriting its own instructions to get better results. It starts with a fixed model and a set of rules. Then, it watches how the model performs and suggests new ways to organize that work. Once the rules are updated, the model is retrained to fit them. This creates a loop where the agent and its logic improve together, round after round. It is a fascinating look at how software can learn to collaborate with itself.

🆔 @hackernewsgithubprojects

📦 claude-reverser/ida-instances-mcp

Give Your AI a Disassembler

AI assistants can now directly control professional disassembly tools to analyze complex code, which is exactly what this project does. It lets you host multiple, isolated instances of the famous IDA Pro analyzer at the same time, giving each one its own secure workspace. This is a big deal because it means an AI can dig into different pieces of software simultaneously without the sessions crashing or stepping on each other's toes. The developer focused heavily on making sure these background workers stay stable, even when they are running long, complicated analysis tasks.

🆔 @hackernewsgithubprojects

📦 vrgamegirl19/yue2_studio

YuE2 Studio

Turn a messy playlist into a custom AI music trainer with YuE2 Studio. This local web app takes the raw power of the YuE2 model and wraps it in a friendly workspace where you write lyrics, pick a style, and generate original songs on your own hardware. The coolest part is the dataset builder: it downloads your authorized playlists, finds the lyrics, and lets you train a small adapter to make the AI sound like your favorite artist. It’s not just a music generator; it’s a full creative studio that runs right in your browser without any cloud setup.

🆔 @hackernewsgithubprojects

📦 nvidia/soma-retargeter

SOMA Retargeter: Human Motion for Robots

NVIDIA’s SOMA Retargeter takes a single video capture of a human walking and turns it into precise motor commands for a physical robot. The tool solves a fundamental engineering headache: human bodies and robot chassis have completely different proportions and joint structures. By mapping human movement to a robot’s specific hardware, the software generates a data file ready for simulation or control. This is built on NVIDIA’s Newton physics engine to ensure the motion is physically plausible. It is a beta tool, but it provides a direct bridge from human performance to robotic execution.

🆔 @hackernewsgithubprojects

📦 gen-verse/dfm-plans

How AI Can Discover New Science

AI systems are finally moving beyond answering questions to actively discovering new scientific facts. This project, known as Discovery Foundation Models, acts as a central roadmap for a research lab called PhAI Labs. It brings together three distinct efforts designed to teach computers how to conduct real science. One tool creates interactive workspaces for researchers, another converts existing scientific code into safe practice environments, and a third predicts how experiments will change physical systems. This is not just about building a chatbot. It is about building a machine that can identify unknown problems, form hypotheses, and verify answers through evidence.

🆔 @hackernewsgithubprojects

📦 bentang18/mapa

How MAPA Reads Brain Data Faster

MAPA is the neural interface tool that makes brain decoding possible with almost no data. It works by training a model on unlabeled brain recordings, letting it learn the patterns of thought without needing a single manual label. The real win is speed: where a standard system needs thousands of labeled trials to get accurate, MAPA achieves the same result with about a hundred and sixty-four. This means building a personalized brain-computer interface could take minutes instead of hours. It turns raw electrical signals from the brain into usable features, proving that pretraining on unlabeled data is the key to making these devices practical and accessible for everyone.

🆔 @hackernewsgithubprojects

📦 yihangchen9/bilevel-coordinated-reflection

Bilevel Coordinated Reflection: When AI Agents Learn to Trust

Bilevel Coordinated Reflection lets multiple artificial intelligence agents coordinate complex tasks without ever changing their underlying code. The system solves a problem where agents get stuck in loops by using a two-step memory process. One agent plans the overall strategy, while others handle the specific work. The interesting part is that workers only save new thoughts to the shared memory if a strict check confirms they are actually better. This gate stops bad information from clogging up the system. It shows that structured memory, not just bigger models, helps AI teams work together. The result is a smarter, more reliable group of assistants.

🆔 @hackernewsgithubprojects