📦 199-biotechnologies/claude-deep-research-skill

Claude Deep Research Skill

The claude-deep-research-skill is a specialized extension for Claude Code that turns the AI into a rigorous, self-correcting research assistant. Unlike typical AI search tools that summarize the first few web pages they find, this tool runs an intensive, multi-phase pipeline that gathers deep evidence from several search providers at once. It automatically tracks sources, scores credibility, and runs internal quality checks to weed out hallucinations. Best of all, it can recursively generate reports of eighteen thousand words or more while preserving context. It is perfect for developers who need honest, citation-backed analyses of complex technical topics without the usual AI fluff.

🆔 @hackernewsgithubprojects

📦 demchaav/graphcompose

GraphCompose

GraphCompose is the declarative Java document engine that finally makes generating professional PDFs painless by replacing manual coordinates with a semantic layout system. Instead of fighting with low-level page math, you write clean, modern Java code describing what your document contains, from tables and lists to beautiful vector charts and gradients. The engine handles all the measurement, pagination, and styling behind the scenes, and its deterministic design lets you snapshot and regression-test layouts before deployment. If you need clean, reliable, and beautifully designed business documents from your Java backends, you should definitely check out graphcompose.

📰 https://news.ycombinator.com/item?id=48618028

🆔 @hackernewsgithubprojects

📦 robbyant/lingbot-va

LingBot-VA

Control robots with smarter decision-making by blending visual foresight and action into one smooth process. The lingbot-va project introduces a causal video-action world model that unifies how a robot predicts what will happen next and how it should move to get there. Instead of treating sight and physical action as separate problems, this clever system interleaves them using a high-efficiency transformer architecture. It achieves incredible success rates in complex, multi-step physical tasks, even in brand-new scenes. If you want to train or deploy smarter robots that genuinely understand the consequences of their actions, this is the blueprint to check out.

🆔 @hackernewsgithubprojects

📦 lilxyzw/nontoon

NonToon

Anime characters in 3D games often look completely disconnected from realistic, physically lit environments. A clever tool called NonToon solves this by blending realistic physical rendering with stylized anime shading into a single hybrid Unity shader. Instead of forcing you to choose between flat cartoon styling and realistic lighting, it lets your characters exist naturally in both worlds with smart features like custom hair specularity, light-blocking outlines, and gradient shading ramps. The project is built entirely out of modular pieces, meaning you can swap features in and out without bloat. It is the perfect bridge for making stylized avatars look gorgeous in any world.

🆔 @hackernewsgithubprojects

📦 meta-models/meta-model-cookbook

Meta Model Cookbook

Build autonomous computer-control systems and smart coding assistants using the meta-model-cookbook. This repository provides copy-paste python recipes to construct intelligent agents that can diagnose bugs from screenshots, write code, and run it inside secure sandboxes. You can even build an agent that drives a real Mac computer, clicking and typing through a desktop GUI just like a human. It works with a massive context window of over one million tokens, making it easy to feed in entire codebases. You get a perfect starting point to build self-correcting agents that verify their own work.

🆔 @hackernewsgithubprojects

📦 raresense/nova3d

Nova3D

Build fully interactive 3D assets directly from text prompts or reference photos. While traditional generators spit out a single, fused lump of static geometry, this system translates your prompt into clean, executable Blender Python code. This means your generated object is born as a structured assembly with named, separately addressable parts, real joint pivots, and clean materials. You can easily select individual components, adjust joint rotations, or swap out textures without restarting from scratch. It is a brilliant way to create production-ready, editable models that fit perfectly into standard design pipelines.

📰 https://news.ycombinator.com/item?id=48122781

🆔 @hackernewsgithubprojects

📦 provos/ironcurtain

IronCurtain

IronCurtain is the secure runtime that finally lets you run autonomous AI agents without giving them complete control of your computer. Normally, giving an AI access to your files or terminal is a security nightmare, since one bad prompt injection could let it wipe your hard drive or steal your API keys. This project solves that by putting the agent inside a strict sandbox and routing every single action through a clever policy engine. Instead of writing complex code to restrict the agent, you just write your security rules in plain English. The system compiles your plain-text instructions into deterministic rules, intercepts every tool call, and blocks or escalates risky...

📰 https://news.ycombinator.com/item?id=48902269

🆔 @hackernewsgithubprojects

📦 open-webui/computer

Open WebUI Computer

Open WebUI Computer is the self-hosted tool that finally brings your entire workstation into a single web browser tab. By running a simple command on your machine, you can access your real files, a terminal, a code editor, and git status from any phone, tablet, or secondary laptop. It also features a built-in AI agent that can run commands, edit code, and browse the web directly on your machine. You can even connect your existing coding assistant subscriptions to work alongside you. It is the ultimate way to securely manage your projects, run terminal tasks, or push a quick hotfix from anywhere.

🆔 @hackernewsgithubprojects

📦 opensquilla/opensquilla

opensquilla

Large language model agents consume massive amounts of data, running up massive API bills just to keep track of their own conversation history. This project solves that problem by acting as a smart context manager that packs maximum reasoning capability into a strict token budget. By constantly optimizing what the model remembers, compacting tool outputs, and pruning unnecessary clutter from the chat history, it gives you a highly capable assistant without the skyrocketing costs. It even features a built-in terminal interface and a web dashboard to track your token savings in real time. Grab the code and build smarter, leaner AI assistants today.

🆔 @hackernewsgithubprojects

📦 zjunlp/lightmem-ego

LightMem-Ego

Stream first-person camera and audio directly from your smart glasses or web browser to build a continuous, searchable digital brain. LightMem-Ego processes your daily real-world experiences in real time, breaking everything you see and hear into current scene understanding, short-term events, and long-term habits. It solves the massive headache of trying to recall fleeting details by turning raw video and audio feeds into a structured, queryable knowledge base. It is like giving yourself perfect recall for names, conversations, and lost items. You can easily deploy this setup to chat with your own history and never forget a detail again.

🆔 @hackernewsgithubprojects

📦 frostlinx/searcheyes

SearchEyes

Build intelligent agents that can browse, search, and reason across both images and text by simulating an entire search world. While typical training pipelines struggle because they treat training data, search environments, and rewards as separate pieces, this project unifies them using a single knowledge graph. It connects data synthesis with a self-contained search engine and introduces a smart reward system to optimize how agents search. By keeping structural metadata intact, it helps smaller models match the search capabilities of models more than three times their size. It is the perfect setup for building next-generation visual search assistants.

🆔 @hackernewsgithubprojects

📦 filippawlicki/nanovsr

NanoVSR

NanoVSR is the video super-resolution model that actually runs in real time on small, low-power edge devices. Up-scaling blurry footage normally requires massive, power-hungry graphics cards, but this project solves that by ditching heavy transformers and complex optical flow algorithms. Instead, it uses a clever mathematical trick to collapse multiple network branches into a single, highly efficient stream during playback. This means you can get crisp, high-definition video at nearly thirty frames per second on a small, twenty-five watt hardware board. It is a brilliant, lightweight way to bring high-quality video enhancement to smart cameras and portable devices without draining their batteries.

🆔 @hackernewsgithubprojects

📦 vibedrift/vibedrift

VibeDrift

Keep your AI coding agent from making a mess of your codebase as it grows. AI assistants write logical code, but they have no memory of the custom design patterns you already settled on. One file gets a clean repository pattern while the next gets raw SQL, slowly turning your project into a chaotic mix of conflicting styles. This tool learns the dominant coding patterns your project already uses by taking a majority vote of your files, then automatically flags any new code that deviates. It stops style drift in its tracks right on your machine.

🆔 @hackernewsgithubprojects

📦 harmont-dev/hyper

Hyper Distributed MicroVMs

Spin up secure, isolated virtual machines in seconds without the bloat of traditional virtualization. Built on the Erlang virtual machine, hyper is a distributed orchestrator that manages Firecracker microVMs across multiple host nodes. Instead of relying on slow, full disk snapshots, it implements copy-on-write disk layering to let you fork running virtual machines instantly with zero performance penalty. You can load standard container images and run them inside isolated sandboxes while scale scheduling optimizes where your workloads run based on shared resources. It is the perfect tool for building secure, multi-tenant cloud platforms with raw bare-metal performance.

📰 https://news.ycombinator.com/item?id=48849161

🆔 @hackernewsgithubprojects

📦 ahekot/vnccs_easy-install

vnccs_easy-install

Build your own fully customized visual novel character sprites without touching a single line of messy configuration code. The vnccs_easy-install repository packages up a complete character production pipeline inside a portable Windows installer. It bundles ComfyUI with special tools to let you design outfits, swap poses in a 3D studio, generate natural emotion sheets, and even clone existing art. Instead of fighting python dependencies or downloading models manually, you just run one file to get a ready-made suite. Grab the package, run the setup script, and start building your own reusable character library today.

🆔 @hackernewsgithubprojects

📦 js-lee-ai/dart

DART

You can now dynamically adjust how much time an AI spend thinking before it answers, and you do not need to retrain a single model to do it. A clever project called dart lets you route questions between fast, cheap models and deep, reasoning models on the fly by checking if they agree on an initial draft. If the quick model nails it, you save money and time; if it struggles, the heavy-duty thinker automatically kicks in. It is basically a smart thermostat for your AI budget, keeping things fast without losing accuracy. It is a brilliant way to stop wasting brainpower on easy questions.

🆔 @hackernewsgithubprojects

📦 js-lee-ai/skin-deep

skin-deep

Test how easily an AI assistant will bypass its own safety rules before anyone even tries to attack it. While a model might block harmful requests during standard checks, its safety alignment is often surprisingly fragile and can break down completely after just a tiny bit of normal fine-tuning. This project, skin-deep, solves that problem by analyzing the internal mathematical activations of a language model. It calculates a single score showing if the model's safety is truly deep or just a temporary mask. Use this diagnostic tool to find and patch weak spots in your model before deploying it.

🆔 @hackernewsgithubprojects

📦 mjunaidca/polymarket-skills

Polymarket Skills

Polymarket-skills is the open-source trading toolkit that lets artificial intelligence agents safely navigate prediction markets using a strict paper-trading-first approach. Built as modular skills for AI assistants, it connects to live market data to scan for pricing inefficiencies, analyze momentum, and simulate trades without risking actual capital. The standout feature is its built-in safety constitution, which forces the system to run realistic paper trading sessions to prove a consistent mathematical edge before ever unlocking live execution. It translates complex blockchain market structures into clear, manageable steps so any curious developer can experiment with systematic trading safely.

🆔 @hackernewsgithubprojects

📦 harimoradiya/androidtvremote

Android TV Remote

androidtvremote is the Android application that rescues you when your physical TV remote inevitably slips between the couch cushions. It instantly transforms your smartphone into a fully functional remote control over your local Wi-Fi network. What makes this project stand out is how it effortlessly handles the heavy lifting of pairing protocols, secure handshake encryption, and network discovery right from your phone. You get smooth navigation, volume control, and even a synced keyboard that lets you type search queries directly on your phone instead of agonizingly clicking one letter at a time on the screen. It is completely free, privacy-focused, and keeps your living room smart.

🆔 @hackernewsgithubprojects

📦 reliefeai/browser-relay

browser-relay

Your AI agents can now work directly inside your everyday Chrome browser tabs, fully authenticated with your active logins, cookies, and extensions. Instead of spinning up a fresh, empty browser window that has none of your saved sessions, browser-relay connects your personal browser to local or remote AI agents over a simple command line, HTTP API, or Model Context Protocol. By using a lightweight Chrome extension and local server, agents can interact with your open tabs, click elements, capture network requests, and read page layouts safely. It is a fantastic local-first tool for developers who want their AI assistants to easily interact with real-world SaaS dashboards without annoying login hurdles.

🆔 @hackernewsgithubprojects