📦 sakuraaa0/rabitqcache

Rabitqcache

Running long-context AI models usually slows to a crawl because storing the conversation history eats up massive amounts of GPU memory. Rabitqcache fixes this by compressing that history down to tiny binary representations using randomized rotation and high-speed math. Instead of guessing which past tokens to look at with expensive calculations, this system uses an incredibly fast math trick to dynamically grab only the exact history it needs on the fly. It even hides the compression process in the background so your hardware never has to wait around. If you want to run massive prompt histories on normal hardware without your generation speeds falling off a cliff, you should definitely...

🆔 @hackernewsgithubprojects

📦 ruvnet/ruvector

RuVector

RuVector is the self-learning vector database that actually gets smarter the more you use it. While standard databases just search the same way forever, this clever tool watches your queries to automatically improve search results and tune itself on the fly. It runs AI models locally on your own hardware without any expensive cloud APIs, and it can drop right into PostgreSQL or run inside a web browser from a single file. It is basically a brain for your data that fits anywhere. You get better, faster search that adapts to your workflow without the headache of managing complex cloud clusters.

🆔 @hackernewsgithubprojects

📦 johnviljoen/jaxipm

jaxipm

An open-source tool called jaxipm can solve hundreds of complex mathematical optimization problems at the exact same time on a single graphics card. Typically, hardware-accelerated math solvers run tasks one after another, which leaves valuable computing power sitting idle. This project solves that waste by bundling those separate problems into batches, fully saturating the processor's capacity. By utilizing specialized hardware libraries to handle these groups simultaneously, it achieves massive speedups compared to traditional methods. It shows that we do not need massive supercomputers for heavy optimization tasks when we can coordinate our existing hardware more efficiently.

🆔 @hackernewsgithubprojects

📦 timjaspers0801/atlas

Atlas

Teach computers to recognize real-time human anatomy during surgery by setting up a massive medical imaging pipeline. This project provides the downloading and processing tools for a massive dataset of over one hundred and twenty thousand annotated video frames spanning fourteen different surgical procedures. Instead of forcing you to store massive video files, it lets you download public surgical videos and automatically extract only the precise frames containing key organs and tools, perfectly aligned with expert-labeled anatomical masks. It is a brilliant way to train medical artificial intelligence without drowning in raw video storage, giving you clean, curated data for smarter surgical assistants.

🆔 @hackernewsgithubprojects

📦 brain0-ai/brain0

Brain0

Brain0 is the black box for AI-written code that connects every single commit back to the exact agent prompts that wrote them. While git shows you what changed, this tool watches your workspace offline and links actual code modifications to the original prompts and agent logs. It even flags drift when an AI claims it changed one thing but secretly touched another, and audits whether your coding agents read sensitive files before talking to remote servers. It is like an automated flight recorder for your codebase that gives you real, evidence-driven risk scoring without slowing down your existing development loop.

🆔 @hackernewsgithubprojects

📦 ninjahawk/subtext

Subtext

Subtext is the real-time visualizer that finally exposes the hidden, unspoken thoughts of an artificial intelligence as it reads and types. Normally, we only see the final words a language model outputs, but this project taps directly into the model's inner mind using a diagnostic lens. By running a local model and reading its neural activity at multiple depths, Subtext captures concepts before they are spoken. For example, if you ask the model to check an incorrect math equation, the word incorrect instantly lights up in its internal workspace while it is still reading your prompt, several steps before it actually starts typing a reply. It lets you watch the...

📰 https://news.ycombinator.com/item?id=48811892

🆔 @hackernewsgithubprojects

📦 vbiroshak/ai-project-architect

AI Project Architect

ai-project-architect is the workspace framework that finally solves AI memory loss by giving your local assistant its own persistent filesystem diary. Instead of letting your AI helper forget everything the moment you close a chat, this system sets up a structured directory on your local drive that the AI reads, writes, and updates directly. It tracks its own tasks, manages an inbox of new files, and even uses a clever file-timestamp trick to know exactly how much time has passed since your last session. You get a portable, local knowledge base that naturally picks up right where you left off.

🆔 @hackernewsgithubprojects

📦 sunflower-of-parchman/codex-hygiene

Codex Hygiene

Codex-hygiene is the local agent skill that finally makes it easy to monitor and clean up your Codex Desktop environment without losing your active workflows. If you have ever noticed your AI assistant lagging or burning through tokens, it is usually because of hidden junk like bloated tool lists, forgotten background plugins, or massive chat histories reloading behind the scenes. This clever utility uses safe, read-only database queries to pinpoint exactly what is eating up your context window. It measures your active memory footprint and suggests reversible settings tweaks, giving you a clean slate while keeping your core project goals completely intact.

🆔 @hackernewsgithubprojects

📦 evolvinglmms-lab/skillopt-lite

skillopt-lite

AI coding agents can now automatically train themselves to get better at complex tasks without you writing a single line of training code. An open-source project called skillopt-lite lets you point your favorite AI coding assistant at your workspace and trigger an optimization loop with a single chat command. The tool guides your agent to run evaluations, analyze its own failures, update its natural-language instructions, and roll back any changes that decrease performance. It handles the entire trial-and-error cycle of self-improvement completely inside your editor chat. Just run the loop, sit back, and let your agent polish its own skills.

🆔 @hackernewsgithubprojects

📦 iamcheyan/fudoki

Fudoki

Fudoki automatically breaks down complex Japanese text to instantly show you parts of speech, readings, and translations directly in your browser. If you are learning Japanese, trying to read native material can feel like running into a wall of kanji with no idea where words begin or end. Fudoki solves this by instantly segmenting sentences, color-coding nouns, verbs, and adjectives, and overlaying phonetic readings and English definitions. It even includes a built-in markdown editor and high-quality speech synthesis so you can listen to any word or sentence read aloud at your own pace. It is like having a patient, sharp-eyed language tutor built right into your browser.

🆔 @hackernewsgithubprojects

📦 scaleapi/scale-agentex

scale-agentex

Build and scale intelligent AI systems that can run complex, autonomous tasks instead of just waiting for simple back-and-forth chat responses. While most AI applications are stuck handling quick, basic questions, scale-agentex gives you a complete framework to run advanced, long-running agent workflows. It lets you spin up a local development server, try out pre-made templates, and test everything instantly in a built-in web dashboard. It is a fantastic way to experiment with multi-agent setups that actually work in the real world. Get your first system running locally and watch your AI take on real work.

📰 https://news.ycombinator.com/item?id=48831782

🆔 @hackernewsgithubprojects

📦 open-space-sdr/main

QuadRF Phased Array SDR

QuadRF is the software-defined radio kit that finally brings advanced phased array technology right to your workbench. It combines a modular radio tile with an open antenna architecture and an onboard Raspberry Pi 5, turning standard signal processing into a real-time spatial radio camera. Instead of just analyzing frequencies on a screen, you can actually see where signals are coming from at thirty frames per second, allowing you to map local wireless networks or track devices in mid-air. It is an incredibly fun way to explore how radio waves interact with the physical world around us.

🆔 @hackernewsgithubprojects

📦 sleekdotdesign/agent-skills

Agent Skills

You can now design fully interactive mobile app screens directly through your favorite developer tools and terminal agents. A clever repository called agent-skills allows software agents to instantly communicate with Sleek, a professional mobile design platform, to generate customized app projects using simple text requests. It lets your tools spin up projects, apply stylish design systems, download clean HTML prototypes, and automatically capture screenshots for you to preview. It is a fantastic way to bypass manual design work and get straight to building with accurate, ready-to-use code. Check it out to see how quickly you can bring your next app idea to life.

🆔 @hackernewsgithubprojects

📦 tiliondev/fortress

Fortress

Fortress is a stealth Chromium engine that keeps your scrapers and browser agents from getting blocked. Unlike traditional tools that try to hide automation by patching JavaScript on the page, this project actually alters the browser fingerprint directly inside Chromium's C++ code. Because the spoofing happens natively inside the engine, bot detectors cannot find any modified JavaScript files or suspicious overrides, meaning your automated browsers look exactly like ordinary, human-operated Chrome. It works as a drop-in replacement that exposes a standard debugging port, so you can connect your existing automation tools with just a single line of code.

📰 https://news.ycombinator.com/item?id=48825745

🆔 @hackernewsgithubprojects

📦 ln-dev7/icons-animated

icons-animated

icons-animated is the open-source library that finally brings effortless, reactive motion to your favorite standard web icons. Instead of building complex SVG hover effects from scratch, this handy tool provides meticulously pre-animated versions of popular libraries like Tabler, Huge Icons, and Phosphor. Under the hood, it uses Framer Motion to make elements slide, rotate, or bounce the second a user hovers over them. Best of all, it integrates directly with the shadcn command-line tool, meaning you can drop these animated UI elements straight into your project with a single terminal command. It is a brilliant way to add immediate visual polish.

🆔 @hackernewsgithubprojects

📦 jiguang132/storyai-3d-director-desk

StoryAI 3D Director Desk

StoryAI 3D Director Desk is the browser-based previsualization tool that finally makes scene layout and camera blocking accessible to anyone. Built on React and Three.js, it provides a lightweight virtual sandbox for directors and storytellers to plan shots, position 3D characters, import panoramic backdrops, and test camera angles without ever needing heavy software. You can seamlessly cycle through camera viewpoints, experiment with different character models and poses, and instantly snap storyboard screen captures. It is the perfect creative workspace for turning rough story ideas into clear visual layouts directly in your browser. Start designing your next scene today.

🆔 @hackernewsgithubprojects

📦 nicholasslattery/sony-head-tracker

Sony Head Tracker

You can now use the built-in motion sensors already inside your Sony headphones as a high-precision, real-time head tracker for PC flight and racing simulators. A clever Windows application called sony-head-tracker connects directly to the standard Android head-tracking protocol exposed by devices like the WH-1000XM5, streaming raw orientation data directly to OpenTrack. This completely eliminates the need for webcams, infrared clips, or expensive dedicated tracking hardware when playing your favorite games. It is a lightweight, driver-free solution that runs entirely in user space to breathe new life into the gear you already own. Grab your headset, load up your favorite simulator, and experience hands-free camera control today.

🆔 @hackernewsgithubprojects

📦 tdeverx/contained-app

Contained App

Contained is the native macOS control surface that finally brings Apple's container command-line tool into a beautiful, visual interface. Instead of typing endless commands in the terminal, this app gives you elegant, personalized cards to manage your local containers, images, and networks using a sleek SwiftUI interface. The coolest part is that it respects your command line: it reveals the exact terminal command before running any operation, so you always know what is happening under the hood. It is the perfect bridge between visual simplicity and terminal power, giving you complete control over your local development workflow.

🆔 @hackernewsgithubprojects

📦 wouterdebie/davit

Davit

Davit is the native macOS dashboard that finally brings Apple's lightweight Linux container platform to life with a beautiful user interface. While tools like Docker Desktop consume massive system memory, this lightweight app speaks directly to Apple's native container framework over secure connections, completely bypassing heavy background emulators. You get a sleek interface to pull images, manage volumes, and view real-time charts showing your actual CPU and memory usage. It even lets you browse files directly inside your running containers and effortlessly import your existing Docker Compose files. It is the perfect way to run lightweight containers natively on Apple silicon.

🆔 @hackernewsgithubprojects

📦 iebb/mithka

Mithka

Mithka runs a complete, independent Telegram client directly on your phone using your own API credentials. Built on top of Telegram's official database library and Flutter, it completely replaces the standard chat screen with an incredibly light, customized interface. You get your real accounts, group chats, and contacts, alongside custom details like animated stickers, full audio features, and location sharing. Because it bypasses the heavy stock design, the entire experience feels snappy and fast on both iOS and Android. It is the perfect way to reclaim your chat experience with a highly responsive, personalized client.

🆔 @hackernewsgithubprojects