📦 gnhen/midscroll

Midscroll

Linux users can finally have the fluid, click-and-drag page scrolling that Windows users have taken for granted for decades. A clever utility called midscroll brings that exact middle-mouse autoscroll behavior to your Linux desktop. By capturing mouse inputs at the kernel level, it works smoothly across both Wayland and X11 in every single app you run. It uses Chromium's actual scrolling formula, meaning tiny drags crawl while a quick tug flies down the page. It even pauses itself automatically when you switch to games or CAD software that rely on native middle clicks, giving you the perfect, seamless navigation experience Linux was missing.

🆔 @hackernewsgithubprojects

📦 chrisjz/universe

Universe

Scroll through forty-three orders of magnitude in one continuous zoom, flying from the edge of the observable universe straight down to a single proton. This interactive atlas maps the cosmos in true scale using high-performance browser graphics, combining real astronomical catalogs with street-level terrain data. You can watch constellations shift over thousands of years, track the International Space Station, or watch the moon shadow block out the sun during real-time eclipses. It solves the massive challenge of rendering cosmic distances alongside atomic structures on a single screen without loading screens. Open it up and enjoy a breathtaking, scientifically accurate tour of our entire reality.

🆔 @hackernewsgithubprojects

📦 harbor-framework/frontier-bench

frontier-bench

Artificial intelligence agents can write essays and generate images, but they still struggle with complex, multi-step computer tasks like debugging real codebase leaks, managing active database cutovers, or routing photonic waveguides. A project called frontier-bench solves this by creating an evolving suite of demanding, real-world computer tasks to measure exactly what these agents can get done. Instead of simple toy tests, it challenges digital assistants with highly technical, practical problems across software, physics, and operations to see where they fail. It gives developers a clear, objective yardstick to evaluate agent performance, helping us understand when AI is truly ready for complex office work.

🆔 @hackernewsgithubprojects

📦 prism-shadow/penguin-harness

penguin-harness

Build and optimize fully functional AI assistants from a single text prompt using penguin-harness. Instead of stitching together complex pipelines manually, this zero-code tool lets AI agents build other AI agents for you. You can type out a single sentence, and the system automatically generates the scaffold, code, and running instructions for a complete application in seconds. It even benchmark-tests and refines itself over time to boost accuracy, all while running on open models for a tiny fraction of the usual cost. It is a brilliant way to experiment with self-evolving AI apps without the massive development headache.

📰 https://news.ycombinator.com/item?id=49015242

🆔 @hackernewsgithubprojects

📦 mmlcourse4all/mml

Mathematics for Machine Learning Study Guide

Most people struggle with machine learning not because of the coding, but because the underlying math feels like an impenetrable wall of symbols. This community-driven study guide acts as a friendly map to help you conquer the essential mathematical foundations before you even touch an algorithm. It focuses strictly on the core concepts you actually need to understand what is happening under the hood, saving you from wasting months on irrelevant textbook chapters. It is essentially a shortcut to building real mathematical confidence, making your next steps in AI infinitely easier to understand.

🆔 @hackernewsgithubprojects

📦 qoery-com/pmxt

pmxt

pmxt is the unified tool that finally brings a single, standard interface to the fragmented world of prediction markets. Instead of fighting with unique APIs, strange data structures, and completely different workflows for every single prediction platform, you write your code once. It lets you query markets and execute trades across different platforms like Polymarket and Kalshi using a single, cohesive style in either Python or TypeScript. You can let their hosted service handle the complicated on-chain signing and transactions, or self-host the lightweight engine locally to keep full control of your private keys. It is the perfect universal adapter for developers building prediction bots or smart assistants.

🆔 @hackernewsgithubprojects

📦 aws-samples/sample-specship

SpecShip

AI coding agents are notorious for building fast but shallow software that lacks deep testing and error handling. The open-source project sample-specship solves this by forcing AI models to follow a strict engineering pipeline. Instead of letting an agent immediately write and approve its own code, this system introduces adversarial validation where independent subagents aggressively test and review the work against a pre-written contract. It even mandates test-driven development, blocking any new code from being merged until failing tests are written first. It turns fragile AI prototypes into thoroughly tested, production-ready software through disciplined, automated quality gates.

🆔 @hackernewsgithubprojects

📦 microsoft/mage

Mage

Microsoft just released a four-billion parameter model family called mage that matches the quality of AI systems five to eight times its size. Instead of throwing raw computing power at image generation and editing, this project co-designs its image tokenizer and model backbone to focus detail exactly where the visual signal is. This means you can generate high-resolution images or perform complex, instruction-based image edits with massive speedups on ordinary hardware, and it even renders clean bilingual text. It is a fantastic, lightweight setup for developers who want top-tier results without renting a massive server cluster. Check it out to run fast local generation.

🆔 @hackernewsgithubprojects

📦 tanishq-dubey/macos-laguna-s2.1

macos-laguna-s2.1

macos-laguna-s2.1 is the local benchmark harness that finally makes it easy to find the absolute fastest and most accurate way to run the massive Laguna coding model on your Mac. If you are experimenting with local code assistants, you know that picking the right model size and format is usually a guessing game. This tool automatically downloads, runs, and evaluates different compressed versions of the model against a suite of real-world python coding tasks. It tracks memory use, loading speed, and actual token output directly on apple silicon, revealing exactly which setup gives you the best performance without sacrificing intelligence.

📰 https://news.ycombinator.com/item?id=49001323

🆔 @hackernewsgithubprojects

📦 lspr98/conformer-stt-s3

Conformer STT S3

Run voice recognition directly on a tiny microcontroller without ever connecting to the internet. The conformer-stt-s3 project brings a compressed, thirteen-million parameter English speech-to-text model straight to the ESP32-S3 chip. Instead of sending your private voice data to a massive cloud server, this system processes and transcribes your speech completely on the device, ensuring total privacy. By using clever math shortcuts, custom processor instructions, and split-core processing, it squeezes a heavy deep-learning model into just a few megabytes of memory. It is a massive win for building secure, low-power, and battery-friendly smart home gadgets that work anywhere.

🆔 @hackernewsgithubprojects

📦 atomicbot-ai/atomic-agent

atomic-agent

You can now run a highly capable AI agent completely offline on your own device without sacrificing advanced reasoning or tool usage. Built specifically for local models, atomic-agent is a local-first companion that operates entirely on your hardware to ensure absolute privacy. Unlike standard setups that struggle with complex actions offline, this project introduces custom tool-calling grammars that force local models to use system tools, search the web, and manage files reliably. It features a built-in terminal interface, long-term memory consolidation, and deep integration with the Model Context Protocol. It is the perfect playground for building private, highly capable assistants that run anywhere.

🆔 @hackernewsgithubprojects

📦 dingwu1021/silent-failures-multimodal-agentic-search

Silent Failures in Multimodal Agentic Search

Expose the hidden errors in visual search assistants before they lead your applications astray. When advanced AI agents search the web using both text and images, they often produce correct final answers despite completely ignoring the image, hallucinating sources, or contradicting the visual evidence. The silent-failures-multimodal-agentic-search project introduces a diagnostic framework to catch these invisible blunders. By running full agent search paths through a specialized evaluation judge and stress-testing them with blank images, this tool measures true correctness rather than surface accuracy. It is a fantastic way to understand how your visual search models actually behave under the hood so you can build more reliable agentic systems.

🆔 @hackernewsgithubprojects

📦 happynessi/prefix_grpo

Prefix GRPO

Train small-model AI agents more effectively by slicing and reusing successful teacher trajectories rather than relying on basic imitation. The prefix_grpo repository introduces a clever approach to reinforcement learning by splitting a teacher's step-by-step rollout into replayable starting points, restoring those exact environmental states, and training the student model on how to continue successfully from those mid-game moments. By optimizing both the historical context tokens and the ongoing actions, the system helps smaller models learn complex reasoning tasks in environments like text games and grid worlds. It provides the experimental code, modified trainers, and validated datasets to help developers teach smaller models to act like expert agents.

🆔 @hackernewsgithubprojects

📦 salmon1802/unirank

UniRank

UniRank completely changes how we test recommendation AI by ditching the lazy standard practice of only predicting a user's final action and replacing it with a rigorous step-by-step chronological simulation. In real life, recommendation models often get evaluated on messy, mismatched datasets. This open benchmark levels the playing field by testing fifteen major ranking models from tech giants like Google, Meta, and ByteDance across the exact same five massive industrial datasets. By standardizing the evaluation, it finally answers crucial questions about how model size, history length, and architecture structure affect real-world accuracy and hardware efficiency.

🆔 @hackernewsgithubprojects

📦 gnipbao/story-to-handdrawn-video

story-to-handdrawn-video

This clever tool converts plain Chinese story text or a simple sequence of uploaded images into a hand-drawn vertical diary-comic animation. It automatically splits your text into dynamic narrative beats, generates matching artwork, and runs a beautiful left-to-right visual reveal that transitions from written text to black-and-white sketch, and finally into a full-color illustration. Built on Remotion, it delivers a silent, beautifully framed video with optional paper-curl page turns that is perfectly structured for you to record a voiceover on top. It is the ultimate automation shortcut for turning raw story scripts into engaging, stylized social media content.

🆔 @hackernewsgithubprojects

📦 deer-flow/llm-space

LLM Space

llm-space is the desktop playground that finally takes the guesswork out of building and debugging AI agents. If you have ever tried coding an agent, you know how incredibly frustrating it is when the model calls and tools run in a black box and silently fail. This app runs locally on your machine, giving you a visual timeline to trace every single model call and tool execution as it happens. You can literally replay failed runs step by step, tweak your prompts, and watch the agent improve. It is the ultimate local workbench for turning raw agent ideas into working code.

🆔 @hackernewsgithubprojects

📦 mdx-tom/gpt-5.6-instruct

gpt-5.6-instruct

Your AI assistant is probably refusing to help with complex tasks like reverse engineering or security testing because it thinks they are too risky. The gpt-5.6-instruct repository solves this by framing these technical challenges as safe, local sandbox tasks. It is essentially a specialized toolkit that lets you deploy customized instructions to bypass unnecessary AI refusals while keeping your workflows clean and organized. It features an interactive command-line tool to quickly preview, install, or rollback different versions without messing up your configuration. It is a brilliant way to make your local model actually do what you ask.

🆔 @hackernewsgithubprojects

📦 asz798838958/freeagentidentity

freeagentidentity

freeagentidentity is the local desktop panel that completely automates creating and managing free ChatGPT accounts. Built with Python and Electron, this handy application lets you handle bulk registrations right from your computer without dealing with tedious manual verification loops. It handles your proxies, email routing, and captcha solvers behind the scenes while running multi-threaded registration tasks automatically. You get a clean web dashboard to monitor your account lists, track execution logs, and export your newly generated credentials instantly. It is a brilliant way to manage your testing credentials in one secure dashboard.

🆔 @hackernewsgithubprojects

📦 persiyanov/herdr-reviewr

herdr-reviewr

Comment directly on an AI agent's code modifications without ever leaving your terminal. This clever companion integrates beside your terminal chat, letting you review syntax-highlighted diffs, select lines, and write comments. With a single keystroke, you can send all your feedback straight back to the agent as a structured list. It also includes a read-only pull request viewer, file search, and customizable color themes. It is a brilliant way to guide your AI coder through tricky tasks. Check out herdr-reviewr to make collaborative terminal-based coding a breeze.

🆔 @hackernewsgithubprojects

📦 ericrollei/comfy_hunyuanimage3

comfy_hunyuanimage3

comfy_hunyuanimage3 is the ComfyUI integration that finally lets you run Tencent's massive eighty-billion parameter image generator right on your local hardware. Normally, a model of this scale is completely out of reach for consumer setups, but this project changes everything by introducing smart quantization options like four-bit and eight-bit precision. It manages to shoehorn this giant AI onto single-GPU setups and even twenty-four gigabyte cards using clever memory budgeting and offloading. Beyond just fitting the model on your machine, it introduces memory-efficient expert routing that lets you render massive high-resolution images without crashing your system. It is the ultimate local playground for high-end open-source image generation.

🆔 @hackernewsgithubprojects