📦 openai/cdc-lean

cdc-lean

Researchers have fully verified a foundational graph theory conjecture using a computer assistant to ensure the proof has absolutely zero human errors. The project, called cdc-lean, uses the Lean programming language to mathematically guarantee that every simple, connected network without bottlenecks can be covered twice by a set of loops. By translating a complex flow theorem into computer-checked logic, they eliminated any reliance on guesswork or unproven assumptions. It is a fascinating peek into how mathematicians are using software to build an unbreakable foundation for the future of mathematical proofs.

🆔 @hackernewsgithubprojects

📦 requie/ai-red-teaming-guide

ai-red-teaming-guide

Your AI agents are one clever prompt away from sending your private customer database to a hacker. The ai-red-teaming-guide is a highly practical, open-source handbook packed with ready-to-use templates for stress-testing and securing AI systems. Instead of just listing abstract security concepts, it hands you concrete tools like threat-modeling workshop agendas, rules of engagement templates, and pre-built checklists for security reviews. It is incredibly useful for developers who need to find and patch vulnerabilities, like prompt injections or agent tool abuse, before their code goes live. Grab this guide and run a security check on your AI models today.

🆔 @hackernewsgithubprojects

📦 zimengxiong/hunyuan3d-swift

Hunyuan3D Swift

You can now generate and texture complete 3D models from a single flat image locally on your phone in under six gigabytes of RAM. This is possible because hunyuan3d-swift ports the popular Hunyuan3D shape and paint pipelines directly to Swift and MLX for Apple Silicon. Instead of relying on power-hungry cloud servers or massive graphics cards, this project runs the complex AI math entirely on device. It solves the massive memory bottleneck of 3D generation by optimizing the code for unified memory, letting you go from a 2D photo to a fully textured mesh on an iPhone. It is a massive milestone for mobile spatial computing.

🆔 @hackernewsgithubprojects

📦 sahir619/fable-method

Fable Method

Ordinary AI agents often claim success even when their code fails, but fable-method forces them to prove their work through a rigorous think, act, and prove workflow. This repository distills the problem-solving habits of Claude Fable 5 into a set of practical skills that any AI model can run alongside an adversarial evaluation suite that keeps them honest. By defining clear verification steps, gathering evidence from primary sources, and running strict post-work audits, it prevents common agent traps like silently fixing correct code to pass broken tests. It is a highly disciplined structure that helps developers get reliable, honest results from AI agents.

🆔 @hackernewsgithubprojects

📦 shik3i/koalasync

KoalaSync

Sync up your favorite video streams with friends without giving away your personal data. This clever tool lets you easily host watch parties across almost any site with a video player, from major streaming platforms to self-hosted media servers. The coolest part is how it handles show binges: it pauses playback for everyone until every single person has successfully loaded the next episode, so nobody gets left behind or spoiled. It runs entirely on a lightweight browser extension and a private local server, meaning no annoying tracking, no user accounts, and zero logs. Just generate a quick link, invite your friends, and enjoy the show together.

🆔 @hackernewsgithubprojects

📦 jenissimo/unfake.js

unfake.js

Clean up messy AI-generated pixel art and blurry vector images directly in your browser. When AI tries to make pixel art, it often spits out inconsistent pixel sizes, color bleeding, and weird blurry artifacts that ruin the retro aesthetic. This tool uses a clever Rust-powered WebAssembly engine to automatically detect the actual pixel grid, snap everything into perfect alignment, and downscale the image back to its sharp, original one-to-one scale. It even lets you vectorize rasters into clean SVGs. It is a brilliant way to turn messy machine-learning outputs into beautiful, usable game assets instantly.

🆔 @hackernewsgithubprojects

📦 notnotparas/pushcv-cli

pushcv-cli

Your entire job search can now run entirely from your terminal without a single byte of your personal data leaving your computer. An open-source tool called pushcv-cli acts like Git for your job hunt, keeping your application history inside a local database on your own machine. It lets you scrape job postings directly from platforms like LinkedIn and Greenhouse, tracks your progress on a retro terminal-based Kanban board, and even estimates salaries using public web data. Most impressively, it plugs into a local AI server to draft tailored resumes and cover letters using your master profile, completely offline. It is a private, local-first powerhouse that keeps your career search secure.

🆔 @hackernewsgithubprojects

📦 medoxisto/ad-blocker-chrome-extension

ad-blocker-chrome-extension

Websites are getting incredibly smart at detecting your ad blocker, but this clever extension beats them by running its code before the webpage's own scripts can even load. The ad-blocker-chrome-extension injects its blocking logic at the absolute earliest moment possible, making the site think everything is completely normal. By changing this timing, it skips past those annoying please disable your ad blocker walls that stop other extensions in their tracks. It handles YouTube ads, sketchy redirects, and trackers natively without a heavy performance hit or any creepy data collection. It is just a lightweight, open-source tool that keeps your browsing fast and entirely private.

🆔 @hackernewsgithubprojects

📦 lud1161/agentjail

Agentjail

Keep your coding assistant on a tight leash by intercepting its commands before they run. This project acts as a local security guard for tools like Claude Code and Cursor, checking every single tool call against local policies in just eight milliseconds. It prevents your AI from executing destructive commands like force-pushing to master, deleting files, or accidentally reading your secret credentials and uploading them to a third-party server. Everything is evaluated locally using Open Policy Agent rules, keeping your sensitive code and environment variables safe while you work. It is the ultimate insurance policy for developer peace of mind.

🆔 @hackernewsgithubprojects

📦 diet103/claude-code-infrastructure-showcase

Claude Code Infrastructure Showcase

Automatically load the right development guidelines exactly when you need them by using claude-code-infrastructure-showcase. This clever reference library fixes the biggest headache with Claude Code, which is that your custom instructions and development skills just sit there unless you manually remember to load them. By using a smart prompt-analysis hook, this system scans your input and automatically triggers the perfect coding guidelines for backend, frontend, or error tracking. It even supports optional AI-powered intent matching to keep your projects organized. Grab this setup to make your AI assistant work smarter so you can focus entirely on writing great code.

🆔 @hackernewsgithubprojects

📦 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