📦 john-paul-ruf/novel-engine

Novel Engine: Your AI Editorial Team

Novel Engine is the desktop writing app that gives you a full editorial team running right on your laptop. Instead of wrestling with complex prompts, you guide a pipeline of seven specialized AI agents that act as your ghostwriter, developmental editor, and copy editor all at once. The most fascinating part is how it handles your voice. You start with a quick chat that captures your unique style, and then the AI generates chapters that sound exactly like you while keeping your manuscript safe and private on your own machine.

🆔 @hackernewsgithubprojects

📦 koakno/small-portable-weather-radar-dome

Turn a Salvaged RV Satellite Dome Into a Portable Weather Radar

A salvaged RV satellite dome can detect approaching storms from your own vehicle without relying on distant, outdated government data. This project repurposes a cheap motorized dish and a software-defined radio to create a self-contained, mobile weather radar that works completely offline. When the creator nearly missed a tornado because national radar missed it, he built this system to get immediate, local warnings right in time. It scans for rain and debris, tracks storm movement, and projects where the storm is heading, all running on a simple web interface you can watch on any phone or laptop in the car.

📰 https://news.ycombinator.com/item?id=49097081

🆔 @hackernewsgithubprojects

📦 richlegrand/bitbang

Turn Any Machine Into a URL with BitBang

Turn any device into a clickable link. BitBang lets you run a simple command on a machine and instantly get a URL you can open in any browser to access a remote terminal, file browser, or even a 3D printer stream. It uses browser-based WebRTC to create a direct peer-to-peer connection, meaning it bypasses standard network barriers like NATs and firewalls without needing port forwarding or account creation. The signaling server only helps introduce the two parties once; after that, it never sees your data, ensuring full end-to-end encryption.

📰 https://news.ycombinator.com/item?id=47675661

🆔 @hackernewsgithubprojects

📦 biagiomaf/smart-comfyui-gallery

SmartGallery DAM for ComfyUI

SmartGallery DAM is the local browser gallery that turns your ComfyUI outputs into a searchable, team-friendly media library. Instead of hunting through messy folders, you can instantly find images or videos by asking questions in plain English, like "show me the best portraits from last week." It works directly with your ComfyUI workflow files, letting you tweak prompts and seeds in a clean interface without ever touching the node canvas. You can organize everything into virtual collections, rate your favorites, and even share specific albums with clients while keeping your raw data secure. It is the perfect bridge between heavy generation and simple curation.

🆔 @hackernewsgithubprojects

📦 sophiamyang/finger-frame-effect-ai

Finger Frame AI: AI World Inside Your Hands

Finger Frame AI is the browser tool that fills a hand-made window with a completely animated world. You upload a short clip of yourself making a frame with your fingers, and it uses an advanced video model to repaint every frame in a new style like a cartoon or claymation movie while perfectly matching your original movements. MediaPipe then tracks your hands to keep that animated scene locked inside the gesture as you move. The result is a fun, downloadable video where a digital world lives behind your real fingers. It turns a simple hand trick into a creative playground for anyone to use without needing complex software.

📰 https://news.ycombinator.com/item?id=49169377

🆔 @hackernewsgithubprojects

📦 kijai/comfyui-solattn_triton

comfyui-solattn_triton

Speed up ComfyUI image generation with a new attention method. This project uses a technique called Sol-Attn to make the rendering process faster and more efficient. It works by balancing speed and quality through simple settings, allowing you to control how much effort the computer puts into each part of the image. The code relies on a low-level tool called Triton, which can be slow to load at first but then runs much quicker on modern graphics cards like the forty-nine-zero and fifty-nine-zero. While it is still an experimental work in progress, early tests show it can handle complex scenes without losing detail.

🆔 @hackernewsgithubprojects

📦 nfzerox/virtualmaconipad

Virtual Mac on iPad

Run a full Mac desktop right on your iPad by jailbreaking and installing this clever community tool. It tricks Apple Silicon iPads into hosting macOS inside a virtual machine, so you get Xcode, Terminal, and classic Mac apps without waiting for Apple to release a hybrid device. The trick involves stripping macOS frameworks from their shared cache and patching them to talk to iPadOS, which is honestly wild engineering. You will see a real Mac interface with working graphics, letting you code or browse on a tablet. It only works on specific M1 or M2 iPads running older iPadOS versions, so check your device first.

📰 https://news.ycombinator.com/item?id=49163896

🆔 @hackernewsgithubprojects

📦 kernel/hypeman

Hypeman: One Codebase, Every Hypervisor

Hypeman is a single Go runtime that spins up virtual machines using whichever engine is actually on your machine right now. It automatically picks between Firecracker, QEMU, Cloud Hypervisor, or even Apple’s built-in virtualization layer, so you stop writing platform-specific scripts. You just hand it a standard container image, and it figures out the fastest way to run it. That means your code works identically on a Linux server or a Mac laptop without any extra setup. It handles the heavy lifting of networking, snapshots, and resource limits behind the scenes.

📰 https://news.ycombinator.com/item?id=49170271

🆔 @hackernewsgithubprojects

📦 melqtx/xeet

xeet: Post to X From Your Terminal

Post directly to X from your command line without touching a browser. This tool lets you read your timeline with colorful inline images, reply, and like posts right inside your terminal. It works by borrowing your existing browser session, so there are no API keys to hunt down or configure. Just log into X in Chrome or Firefox, run a simple auth command to link your session, and then type your posts or scroll through your feed using keyboard shortcuts. It even supports attaching images and videos directly from your disk.

🆔 @hackernewsgithubprojects

📦 hm-runninghub/comfyui_rh_minmaxh3

Generate Video and Audio Simultaneously with MiniMax-H3

MiniMax-H3 generates synchronized video and audio at the same time instead of adding sound after the video is already done. This ComfyUI plugin brings that joint generation process into your workflow, letting you create content where the visuals and the soundtrack are built together from the start. You can drive the generation with simple text prompts, use a starting image to animate a scene, or chain together video and audio references for precise control. The best part is that it runs smoothly on a single twenty-four-gigabyte graphics card by using smaller, optimized model weights.

🆔 @hackernewsgithubprojects

📦 ucsc-vlaa/visualclaw

VisualClaw: The AI Agent That Evolves Its Own Brain

VisualClaw is the modular agent system that finally gives AI a way to learn from its own mistakes in real time. Most AI tools just guess when they fail, but VisualClaw actually keeps score. It watches what the AI does, spots the exact moment it messes up, and then writes a new, better set of instructions for next time. Think of it as a robot that gets smarter every time it drops a tray. It handles video, remembers past conversations, and even works with smart glasses. It turns a dumb, one-trick AI into a self-improving assistant that gets better the more you use it.

🆔 @hackernewsgithubprojects

📦 mikeluu99/searxng-rust

Searxng Rust: Multi-Engine Search Aggregator

Searxng Rust lets you build a private search engine that checks multiple sources like DuckDuckGo and Brave at once, then blends the results into a single clean list. It solves the annoyance of searching multiple sites individually by automating the comparison process. The cool part is its ranking system, which gives higher scores to pages that show up in several engines, proving their relevance. It strips out tracking links to keep results clean and returns everything as simple JSON, making it a perfect tool for developers who want a fast, customizable search experience without relying on big tech.

📰 https://news.ycombinator.com/item?id=49158141

🆔 @hackernewsgithubprojects

📦 poxk/falco

Falco: A Tiny Browser Engine in Rust

Falco is a tiny browser engine written from scratch in Rust that renders web pages to PNG images or live interactive windows without relying on Chromium or WebKit. It builds every component including the HTML parser, CSS engine, layout system, and JavaScript virtual machine from the ground up. The project supports modern features like CSS Grid and Flexbox while keeping the binary size remarkably small. You can feed it a URL or local file and get a high-quality screenshot, or open a live window to scroll, click links, and fill out forms. It is a fascinating look at how a browser actually works under the hood.

📰 https://news.ycombinator.com/item?id=49146759

🆔 @hackernewsgithubprojects

📦 cursor/mixture-of-kittens

Mixture of Kittens: The MoE Megakernel

Mixture of Kittens is a custom training megakernel for Cursor that squeezes up to two and a third times more speed out of NVIDIA Blackwell chips by merging all expert computations into one single block of code. It completely removes the usual bottleneck of talking back and forth between your processor and graphics cards, letting the GPUs chat directly with each other while crunching numbers at lightning speed. This means you can train massive language models without wasting time waiting for slow data transfers, effectively turning a chaotic assembly line into a silent, synchronized dance of pure computation.

🆔 @hackernewsgithubprojects

📦 codegraph-ai/codegraph

CodeGraph: Your Codebase as a Searchable Map

CodeGraph turns your sprawling codebase into a living map that AI agents can actually read. Instead of blindly scanning files, it builds a detailed graph of functions, classes, and connections, then serves that structure through forty-two tools. Think of it as giving your coding assistant a complete overhead view of the project, highlighting exactly how pieces relate. It tracks which functions call others, spots unused imports, and even checks if your documentation matches the actual code. You can even save debugging notes for future sessions so the agent remembers past fixes.

🆔 @hackernewsgithubprojects

📦 xmarre/comfyui-spectrum-minimax-h3

ComfyUI Spectrum MiniMax H3

Speed up your MiniMax H3 video and audio projects by skipping expensive steps. This tool predicts the next phase of your generation instead of recalculating it from scratch. It learns from past steps to forecast the outcome, cutting generation time by over a third. You might notice small shifts in fast motion or fleeting details, but the speed gain is real. Try it when speed matters more than perfect pixel accuracy.

🆔 @hackernewsgithubprojects

📦 nihalashetty/forge

Build AI Agents Visually with Forge

Build, test, and ship AI agents visually without writing code or handing over your data. Forge lets you drag and drop agents, tools, and logic onto a canvas to wire them together, then deploy them anywhere you choose like an API, email, or a website widget. The coolest part is it stays entirely on your own infrastructure, so you keep full control without vendor lock-in. You can even watch the AI build itself in real time. It’s perfect for developers who want the power of custom AI workflows without the messy backend plumbing. Grab it, host it, and start building smarter automations today.

🆔 @hackernewsgithubprojects

📦 hermannbjorgvin/clawdmeter

Clawdmeter: Your Desk Dashboard for AI Usage

Watch your Claude Code usage climb right on your desk. Clawdmeter is a tiny ESP32 dashboard that connects over Bluetooth to your computer and displays your session and weekly API limits. The coolest part is the pixel art mascot, Clawd, which gets busier and more frantic as you burn through your quota, giving you a funny visual cue when you are getting heavy. It even doubles as a keyboard, sending space and tab shortcuts directly to your app so you can control voice mode without touching the mouse.

🆔 @hackernewsgithubprojects

📦 neelm0906/mference

Run Huge AI Models on 8GB Macs

Mference lets you run massive artificial intelligence models on small Apple computers by keeping only the active parts in memory while streaming the rest from your hard drive. It uses Swift and Metal to pull data directly from your solid-state drive, allowing huge systems with billions of parameters to work on just eight gigabytes of random access memory. You get a simple app to chat with large language models or a server you can connect to locally without uploading your data to the cloud. It is a clever way to keep your private conversations private while enjoying powerful computing on everyday hardware.

🆔 @hackernewsgithubprojects

📦 makazhanalpamys/soup

Train an 8B Model on a 4GB Laptop

You can actually fine-tune a massive eight billion parameter AI model on a laptop with just four gigabytes of graphics memory. That sounds impossible until you see how this tool called Soup works. Instead of trying to load the entire model into your video memory all at once, which usually crashes your machine, Soup uses a clever technique called layer streaming. It feeds the AI model to the GPU one piece at a time while keeping the heavy frozen parts sitting in your regular system RAM. This means you can train powerful models right on your own hardware without needing expensive cloud servers or specialized data center cards.

📰 https://news.ycombinator.com/item?id=49166984

🆔 @hackernewsgithubprojects

📦 yhfgyyf/vllm-deepseek-v4-sm89

Run DeepSeek V4 Flash on RTX 4090 with vLLM

This is the vllm-deepseek-v4-sm89 project, the hardware bridge that finally lets you run the massive DeepSeek V4 Flash model on standard RTX 4090 graphics cards using vLLM. Most people think this powerful AI requires expensive enterprise server chips, but this repository patches the underlying code to translate complex neural network operations into instructions your consumer GPU can actually understand. It effectively unlocks the full speed of this advanced language model on hardware you can buy today. By bridging the gap between high-end model architecture and accessible hardware, it proves you do not need a data center to experiment with state-of-the-art artificial intelligence.

🆔 @hackernewsgithubprojects