📦 cardchase/vibeetl

VibeETL: Visual Data Pipelines Without The Code

VibeETL is the visual data platform that turns complex code pipelines into a drag-and-drop canvas. It solves the headache of messy data preparation by letting you connect nodes like wires on a screen, processing millions of rows instantly using a lightning-fast engine. Instead of writing scripts, you simply drag in a database, add a filter, and hit run. The real magic is the built-in AI node that can analyze images, video, and text files directly within your workflow, pulling useful data out of unstructured content without you needing to code a single line. It is a powerful, self-hosted tool that makes enterprise-grade data engineering accessible to anyone who prefers clicking...

🆔 @hackernewsgithubprojects

📦 wenaka2004/comfyui-anima-ipadapter

ComfyUI Anima IP-Adapter: Keep Characters Consistent

ComfyUI Anima IP-Adapter is the custom node that finally keeps characters consistent in Anima image generation. It solves the common headache of losing character likeness by injecting reference features directly into the model. You simply load a reference image, which the tool converts into a special embedding, and then apply it to your workflow. This ensures your generated visuals look exactly like your inspiration. It is incredibly useful for artists who need precise control over character appearance without manual tweaking. You can even pre-calculate these embeddings to save memory. It turns chaotic variations into reliable, recognizable results. Grab it to make your character designs stay true to the original every...

🆔 @hackernewsgithubprojects

📦 puffinsoft/mousecrack

Mousecrack: AI That Moves Your Mouse Like a Human

A deep learning model can now drive your computer mouse with genuine human quirks, complete with natural drift and hesitation. Mousecrack treats cursor movement like a time forecasting puzzle, predicting tiny position shifts to simulate organic hand motion rather than robotic lines. You simply tell it where to go, and it generates a path that looks like a real person is holding the device. It works as a simple command line tool or a developer library, making it easy to add realistic automation to scripts or AI agents without looking like a bot. It is a clever way to make digital interactions feel alive, proving that artificial intelligence can mimic...

📰 https://news.ycombinator.com/item?id=49104642

🆔 @hackernewsgithubprojects

📦 flagos-ai/kernelgenbench

KernelGenBench: Benchmarking AI Kernel Generation

KernelGenBench is a specialized benchmark that tests how well artificial intelligence models can automatically write high-performance low-level code for hardware accelerators. Instead of just checking if a model can generate simple scripts, this project throws complex mathematical operations at AI agents and sees if they can produce efficient, optimized kernels for platforms like NVIDIA GPUs or various custom accelerators. The repository provides a massive library of real-world test cases, ranging from basic tensor math to intricate machine learning operations, ensuring that any generated code actually runs fast and accurately. It is incredibly useful for developers who need to validate whether their AI tools can handle the gritty, detailed work of...

🆔 @hackernewsgithubprojects

📦 cporcellijr/bookbridge

BookBridge: Sync Audiobooks and Ebooks

Get BookBridge running to seamlessly sync your reading progress between audiobooks and ebooks. This tool connects Audiobookshelf with KOReader so you can start listening in the car and pick up exactly where you left off on your Kindle or Kobo. It acts as a smart bridge, tracking your exact spot across different devices and services. The standout feature is its ability to handle mixed formats intelligently. You can match an audiobook to an ebook, and the system keeps them perfectly in sync. It even lets you see which app last updated your progress. Setup is simple via Docker, making it perfect for self-hosting. Finally, check out BookBridge to keep your...

📰 https://news.ycombinator.com/item?id=49123041

🆔 @hackernewsgithubprojects

📦 faze-hsw/rfmsr

RFMSR

RFMSR turns blurry, low-res photos into sharp, high-definition images using a clever two-step process. First, it learns how to add noise to high-quality images, then it masters the reverse: stripping that noise away to reveal crisp details from a blurry input. The coolest part is its one-step mode, which skips the usual slow iterations to deliver surprisingly good results instantly. It handles everything from portrait faces to text and landscapes without messing up textures or inventing weird artifacts. If you want to upscale images without waiting forever, this project is a fantastic, practical tool that makes super-resolution fast and accessible. Check it out to see how AI can clean up...

🆔 @hackernewsgithubprojects

📦 alibaba-damo-academy/clinfusion

ClinFusion: AI That Reads 3D Medical Scans

ClinFusion is the medical AI system that finally understands three-dimensional body scans without losing context. Most models struggle with medical images because they treat complex scans as flat pictures, but this tool uses a special vision encoder to read volumetric data like CTs and MRIs as true 3D objects. You can feed it standard image files or full volume scans, and it generates detailed clinical reports that board-certified radiologists actually trust. It even supports custom tools to pull in outside medical knowledge for more accurate answers. This is a rare moment where open-source research matches proprietary power for serious clinical work.

🆔 @hackernewsgithubprojects

📦 bhabishnu/gitcric

GitCric: The Cricket Rating Card Generator

GitCric is the cricket data engine that turns ball-by-ball match records into FIFA-style rating cards for every player across every format. It tackles the boring but massive task of downloading, parsing, and aggregating years of cricket data into a neat SQLite database. Instead of just listing stats, it calculates a cool overall rating out of ninety-nine and even tells you which legendary player you most resemble in that specific format. What makes it genuinely clever is how it balances raw performance with career longevity, ensuring a short, explosive T20 career feels different from a long, steady Test career. You can run it locally, grab a player's name, and instantly see...

🆔 @hackernewsgithubprojects

📦 amazon-science/patientagentbench

PatientAgentBench: Testing Health AI

PatientAgentBench puts AI health assistants through rigorous, realistic role-play simulations to measure how well they handle real-world medical tasks. Instead of simple quizzes, the framework pits a smart chatbot against a simulated patient with a detailed health history. The AI must then navigate complex workflows like booking appointments, managing prescriptions, or recommending telehealth visits. Every interaction is judged by a panel of AI jurors using over a hundred criteria covering safety, helpfulness, and task completion. Because every scenario is generated on demand, there are no memorizable answer keys, ensuring the system truly understands healthcare rather than just guessing. This approach provides a honest, standardized way to compare how different large...

🆔 @hackernewsgithubprojects

📦 wloner0809/cast

How Cast Solves the Credit Assignment Problem in LLM Games

Cast turns game solvers into turn-level teachers for large language model agents, fixing the sparse reward problem by measuring how close each move gets the agent to victory. This method provides dense, per-action feedback that accelerates training and improves generalization across puzzles and real-world tasks. By using a deterministic solver to estimate remaining work, the system shapes rewards to credit progress, making it easier for agents to learn complex strategies without needing full outcome signals. The result is a faster, more reliable way to train AI that can solve Sokoban, Minesweeper, and Rush Hour while transferring skills to new environments. This approach bridges the gap between simple prompting and deep...

🆔 @hackernewsgithubprojects

📦 sqliteai/waste

WASTE: Running 2.78 Trillion Parameters on a Laptop

Run the full 2.78-trillion-parameter Kimi K3 model beyond available RAM by streaming activated weights directly from NVMe. A dependency-free, embeddable C inference engine. WASTE keeps the model trunk in memory, streams selected experts directly from disk, and uses the remaining RAM as a bounded expert cache. It keeps the model trunk in memory, streams selected experts directly from disk, and uses the remaining RAM as a bounded expert cache. Its current proof point is the complete open-weights Kimi K3 model: 2.78 trillion parameters, converted into a 982 GiB container and running on a 64 GB MacBook Pro at 0.49–0.54 tokens per second.

📰 https://news.ycombinator.com/item?id=49106591

🆔 @hackernewsgithubprojects

📦 subhan-code/amicro--micro-transitions-

Amicro: React Micro-Transitions Library

Amicro is the React component library that brings professional-grade micro-transitions and UI interactions to your frontend projects with zero configuration. Instead of manually coding complex animations or wrestling with CSS keyframes, developers can simply install it and use a command-line tool to add ready-made effects like 3D card carousels, arc layouts, and haptic-feedback buttons directly into their apps. The repository ships with over thirty-five pre-built, lightweight, and tree-shakeable components that work seamlessly with React and Tailwind CSS, ensuring your website feels polished and responsive without bloating the bundle size.

🆔 @hackernewsgithubprojects

📦 nxtg-ai/forge-orchestrator

Forge Orchestrator: Multi-AI Coding Coordination

Forge Orchestrator is a Rust tool that lets multiple AI coding assistants work on the same project without stepping on each other's toes. It stops tools like Claude and Codex from accidentally overwriting the same files by using file locks, so you never lose code to conflicting edits. It also captures decisions and patterns in a knowledge base that all tools can access, meaning the next session starts with context instead of a blank slate. You just generate a task plan from your specs, and the orchestrator coordinates the work across different AI providers. It’s basically a project manager for your bots, ensuring they actually collaborate instead of fighting.

🆔 @hackernewsgithubprojects

📦 factory-ai/cursed-plugins

Cursed Plugins: Code Reviews That Roast You

The cursed plugins repository from Factory AI transforms your codebase into a source of dark humor by using AI agents to generate absurd analysis reports. Instead of standard technical feedback, you can ask your coding assistant to write a dating profile for your repository, conduct a therapy session for your files, or produce a dead-serious migration plan from modern JavaScript back to COBOL. These modules work with popular AI coding tools to turn messy legacy code into entertainment, letting you share funny roasts of your own projects on social media. It is a lighthearted way to cope with technical debt without taking the stress too seriously.

📰 https://news.ycombinator.com/item?id=49124125

🆔 @hackernewsgithubprojects

📦 puffinsoft/peek-cli

Let AI Agents See Your Browser

Let coding agents see your browser. Peek-cli allows artificial intelligence assistants to capture a screenshot of any open tab in your browser. Your agents can now iterate on frontend designs until they are flawless. Works with Claude Code, Codex, Copilot and many more. See it in action: It works by using a browser extension to stream screenshots over web sockets. For security, you need to connect the agent once on every startup. Start the web socket daemon. Connect your browser. You are good to go. View available tabs. Capture screenshot. Install the chrome extension. Install the cli. Install the skill. For claude code. For codex. Is this safe?

📰 https://news.ycombinator.com/item?id=48799078

🆔 @hackernewsgithubprojects

📦 llamastash/llamastash

LlamaStash: Launch Local AI in Seconds

LlamaStash is the terminal tool that lets you launch local AI models with a simple init wizard and zero technical overhead. It solves the headache of complex setup by automatically detecting your computer's hardware, finding AI models you already downloaded, and starting a chat interface in just one step. Instead of wrestling with command-line arguments, you get a fast, interactive screen to manage your models easily. It works as a simple command, a visual app, or a background service, making private artificial intelligence actually accessible on your own machine. You finally get to run smart, local language models without needing to be a system expert.

📰 https://news.ycombinator.com/item?id=48369499

🆔 @hackernewsgithubprojects

📦 pachterlab/paperpush

PaperPush: Auto-Fill Journal Submissions

PaperPush automatically fills out academic journal submission forms using browser automation and optional artificial intelligence extraction. It supports dozens of major publishers and preprint servers by generating a local template file from your manuscript metadata. You can manually edit this file, use an AI agent to populate it, or let the tool read your paper directly. The software then opens the specific submission portal for your chosen venue, logs you in, and fills every field automatically. Crucially, it never clicks the final submit button, leaving you to review the completed form and press confirm yourself.

📰 https://news.ycombinator.com/item?id=49112424

🆔 @hackernewsgithubprojects

📦 jintae-00/redesign

ReDesign: Turn Flat Images Into Editable Designs

ReDesign is the AI agent that finally turns flat images back into editable design files. Most people lose their original source files and are stuck with uneditable flat exports, but ReDesign solves this by breaking a single image down into real text, vector shapes, and stacked layers. It works like a smart detective that looks at the picture, makes a guess about which tool to use, and then checks its own work before moving to the next piece. The most fascinating part is how it peels the image apart layer by layer until you have a clean, editable structure instead of just pixels.

🆔 @hackernewsgithubprojects

📦 tum-avs/chat2scenic

Chat2Scenic

Chat2Scenic transforms plain English descriptions into fully executable autonomous driving test scenarios in just a few steps. Instead of manually coding complex traffic simulations, this framework uses an interactive chatbot to interpret your natural language requests and iteratively refines them into precise Scenic script files. It leverages retrieval-augmented generation to ground the creation process in real-world regulatory documents and existing code examples, ensuring the output is both legally compliant and technically accurate. The system breaks the scenario down into logical components like vehicle behavior and environmental conditions, then assembles them into a ready-to-run script for the Carla simulator. This approach dramatically outperforms traditional methods, achieving a seventy-six percent compilation success...

🆔 @hackernewsgithubprojects

📦 skrabe/tweakcc-fixed

tweakcc-fixed: Customize Claude Code Prompts

Claude Code only exposes so much through its settings. tweakcc reaches the rest: it patches the installed binary directly — the cli.js, and the JavaScript baked into the native Bun build — so you can restyle the interface, rewrite the prompts Claude actually runs on, and change how it behaves. You pick what you want from a terminal UI, apply it in one command, and roll it back whenever you like. This is tweakcc-fixed, a fork of Piebald's tweakcc that keeps everything the original does and pushes further — over four times the prompt coverage, a deeper set of patches, and overrides that reach the native install where upstream stops.

🆔 @hackernewsgithubprojects