📦 0xohioism/polymarket-crypto-5m-15min-trading-bot

Polymarket Crypto Trading Bot

Polymarket Crypto Trading Bot is the public due-diligence overview that proves a live automated system actually works on short-term crypto markets. Instead of hiding behind backtests, this project shares real trading data from a live account that has traded over thirty thousand markets. It automates buying and selling on Polymarket for Bitcoin, Ethereum, and Solana price moves in five-minute windows. The most interesting part is the transparency. You can see the actual wins, the losing days, and the fees, so you know exactly what to expect. This isn’t a magic money printer, but it is a real, working system with verifiable results.

🆔 @hackernewsgithubprojects

📦 swufe-db-group/texlite

TexLite: The Self-Hosted LaTeX Editor

Write shared academic papers in your browser without handing your files to a cloud server. TexLite is a lightweight, self-hosted collaborative editor built for small research teams who want the live editing and commenting features of Overleaf, but with complete control over their data. The coolest part is how light it is; instead of running a massive, heavy container stack, it simply uses the LaTeX engine you already have installed on your computer. That means faster performance, zero external dependencies, and your documents stay safe on your own hard drive. It is the perfect fit for trusted groups who value privacy and speed.

📰 https://news.ycombinator.com/item?id=49450500

🆔 @hackernewsgithubprojects

📦 alchaincyf/huashu-excel

The Excel Audit Skill

Your AI agent is confidently lying to you about your sales numbers. The repository huashu-excel fixes this by making every single digit traceable to its exact source cell. It stops the common practice of blindly loading data into pandas, which silently mangles merged cells and duplicate rows. Instead, it performs a deep health check on the raw file to find dirty data. It then uses the totals rows already inside your spreadsheet as free checksums to verify every calculation. If your numbers do not match the original sheet, it flags the error immediately. This prevents the silent disasters where a wrong spreadsheet gets delivered as fact.

🆔 @hackernewsgithubprojects

📦 qufei1993/dsh-desktop

DSH Desktop: Zero Setup DeepSeek Harness

DSH Desktop removes the biggest hurdle to running the official DeepSeek Harness by bundling its own version of Node.js and a package manager directly inside the installer. This means you never have to hunt down the right runtime or configure your computer to get it working. The app launches the official interface in a secure, isolated window and includes a built-in manager to switch between different versions of the tool without touching your existing data. It is a clean, community-built wrapper for macOS and Windows that keeps the underlying software exactly as the developers intended, just in a package that is ready to run immediately.

🆔 @hackernewsgithubprojects

📦 flesymeb/harnessofharness

Harness of Harness: The AI That Builds Games Over Time

Harness of Harness is the autonomous framework that actually builds playable software over time. Instead of just writing code, it runs a multi-day process where an AI team plans, codes, and tests a project repeatedly. Each round improves the last one, letting the system fix mistakes and add polish gradually. It is cool because it produced real games, like a first-person shooter with a story and audio, entirely on its own. You watch the project grow from a rough idea into something you can actually play. It proves that AI can handle long, complex work, not just quick tasks.

🆔 @hackernewsgithubprojects

📦 2akouwu/reverify

Reverify: The AI That Doesn't Lie

When an A.I. analyzes a computer program, it usually just guesses what the code does, often inventing details that don't exist. Reverify fixes this by pairing a language model with a set of hard-working tools that act as a judge. The model proposes a theory about the binary, and the tools check that theory against the actual bytes. If the guess is wrong, the tools prove it is false. If it is right, the guess is verified. This creates a loop where the A.I. only reports facts that can be proven from the code itself, making the results trustworthy for real-world security work.

🆔 @hackernewsgithubprojects

📦 gbin/defragger

Defragger: The Linux Defragmenter You Actually Missed

Defragger lets you watch your Linux disk physically reorganize itself in real time, satisfying a deep itch for the old Windows block map. Built with Rust and Qt, it is not just a nostalgic wrapper, but a genuine tool that talks directly to the kernel to move file chunks. The coolest part? It runs the heavy lifting through a secure helper, so your main app never actually needs root access. It is a rare mix of visual satisfaction and serious utility for anyone curious about how files really live on your drive. If you want to see your storage breathe, this is the one to try.

📰 https://news.ycombinator.com/item?id=49438865

🆔 @hackernewsgithubprojects

📦 sharkspicy-nlp/ruleweaver

RuleWeaver: The New Standard for Testing AI Logic

RuleWeaver is the benchmark that finally tests whether AI truly follows complex rules in real-world scenarios. Most language model tests only check basic facts, but they miss the messy logic of actual life. This project solves that gap by weaving realistic situations from legal contracts and government reports, then asking models to navigate specific, tricky constraints. It does not just look for a correct answer; it verifies if the model used the right reasoning path to get there. This gives researchers a clear, honest way to measure if an AI is actually thinking or just guessing based on patterns.

🆔 @hackernewsgithubprojects

📦 sharkspicy-nlp/beyond-factual-knowledge

Teaching AI to Follow Rules

Teach a language model to actually follow rules, not just recite facts. That is exactly what Beyond Factual Knowledge does. It tackles a huge blind spot: models often ignore multi-step logic even when they have the right data. The team built a new benchmark and a training method that forces the AI to retrieve and apply specific procedural rules at the exact right moment in its thinking. Instead of just guessing, it learns to check a rule library step-by-step to solve complex problems correctly. It is a fascinating look at how we might push machines past simple trivia toward genuine, structured reasoning.

🆔 @hackernewsgithubprojects

📦 anthropics/commerce-agents

Commerce Agents: How to Build Smarter Store AI

Commerce Agents is the open blueprint that finally gives your business a smart digital front desk and a helpful back office manager. It is a collection of ready-made instructions for Claude that teach it how to help customers browse products and how to help staff manage inventory without breaking anything. The coolest part is that it shows you exactly how to build these assistants for different industries like travel or tickets, all using the same safe, proven code. It handles the tricky stuff like remembering what customers like and making sure no accidental orders get placed.

📰 https://news.ycombinator.com/item?id=49541574

🆔 @hackernewsgithubprojects

📦 mooreneural/lacuna

Find Hidden Protein Pockets

Find hidden binding pockets in proteins that appear completely flat. Lacuna solves a major hurdle in drug design by looking beyond a single static image of a protein. Many targets are called undruggable because no pocket is visible in their resting state, but they actually open up briefly. This tool generates a group of different shapes, or conformers, and scans each one to find temporary cavities. It then clusters these fleeting spots into stable sites and ranks them by how well they might bind a drug. The best part is that it runs in seconds on a standard computer without needing a powerful graphics card.

📰 https://news.ycombinator.com/item?id=49543481

🆔 @hackernewsgithubprojects

📦 hyacinthe-primus/file_converter_pro

File Converter Pro: Your Files Stay Home

File Converter Pro turns your Windows computer into a private, offline hub that changes any document, image, audio, or video file into a different format without ever touching the internet. This matters because your personal and professional files never leave your machine, meaning no uploads, no cloud servers, and no data breaches. It handles everything locally, so a Word document can become a PDF or a video can switch formats instantly, all on your hardware. The app runs entirely offline, ensuring total privacy for sensitive documents. You get full control over your data without sacrificing convenience.

🆔 @hackernewsgithubprojects

📦 msnightmare/falconflank

FalconFlank: The Office Macro Bypass

FalconFlank is the security research project that exposes a hidden gap in CrowdStrike’s endpoint protection. It proves that the software meant to automatically strip malicious macros from office files actually leaves a tiny opening for attackers to slip through and grab full control of a computer. The code shows how a standard office document can be used to run dangerous code that the sensor completely misses, even on the latest versions of Windows. It is a real example of how well-intentioned security features can accidentally create new risks. If you care about digital safety, remember that no system is perfect and testing these weaknesses helps us all stay safer.

🆔 @hackernewsgithubprojects

📦 davidmosiah/google-health-mcp

Google Health MCP: Your AI Agent's Private Health Access

Google Health MCP lets your AI chatbot read your actual Fitbit or Pixel Watch data right on your own computer, without ever sending your private login tokens to the cloud. Most health apps keep your stats locked away, so this tool acts like a private bridge that lets your local assistant check your sleep, heart rate, and daily movement safely. It works by running a secure, local connection that strips away any identifying details before your AI even sees the numbers. The coolest part is that you get personalized insights without sacrificing your privacy to a third-party server.

🆔 @hackernewsgithubprojects

📦 tstanczyk95/mcbyteplusplus

McByte++: Tracking Sports Without Training

McByte++ is the tracking tool that follows athletes without ever needing to train on their specific game. This project is the official code for a research paper that solves a huge headache in sports video analytics. Normally, you have to spend ages teaching a computer who is who, but this method just works right out of the box. It keeps track of every player on the court, and if they leave the frame and come back, it remembers exactly who they are. It is built by researchers at Inria and offers a smarter, faster way to analyze sports video without the usual heavy lifting.

🆔 @hackernewsgithubprojects

📦 lmqfly/agentfold

AgentFold: AI-Driven Protein Folding Discovery

A computer program now independently designs better protein folding models by writing its own code, fixing its own bugs, and training its own variants. AgentFold is a multi-agent framework that automates the entire scientific discovery loop for protein structure prediction. It starts with an existing model, proposes specific architectural changes, implements the code, runs the training, and evaluates the results using structural metrics. The system then analyzes what worked and what failed, storing these lessons to guide its next attempt. This creates a self-improving cycle where the AI refines the model based on real performance data, not just guesswork.

🆔 @hackernewsgithubprojects

📦 funinkina/openeffects

OpenEffects: Linux Webcam Effects

OpenEffects is the Linux webcam tool that finally puts professional camera tricks right on your desktop. It acts like a smart filter for your webcam, letting you blur your messy room, swap in a new background, or let the camera automatically zoom in on your face so you always look centered and professional. The coolest part is that it runs entirely on your computer, so your video calls stay private and snappy without needing a separate app to run in the background. It works with any program you use, meaning you get these fancy effects without ever leaving your meeting or streaming software.

📰 https://news.ycombinator.com/item?id=49547949

🆔 @hackernewsgithubprojects

📦 opentslm/timerlm

How TimeRLM Finds Tiny Errors in Giant Data

Spotting a glitch in a million data points sounds impossible, but TimeRLM makes it routine by letting an A.I. explore your data like a detective instead of just staring at a chart. Instead of squishing a huge time series into a tiny summary, the model opens a live code window to zoom in, run calculations, and hunt down the exact moment something broke. This is brilliant because it catches minute errors that would vanish in a standard snapshot, turning a massive, messy signal into a solvable puzzle. It is a clever way to give A.I. real investigative tools rather than just raw numbers.

🆔 @hackernewsgithubprojects

📦 lanrhyme/micyou

MicYou: Use Your Phone as a PC Microphone

MicYou turns your Android phone into a high-quality microphone for your computer by streaming audio over Wi-Fi or USB. It solves the problem of poor built-in PC mics by using your phone's superior hardware for calls and recording. The software routes this audio through a virtual device so any application can use it as if it were a physical plug-in microphone. It even includes AI noise suppression to clean up the sound. This is a simple way to get broadcast-quality audio without buying new equipment. It is a great tool for streamers and anyone needing better voice input.

🆔 @hackernewsgithubprojects

📦 qufei1993/skills-hub

Skills Hub: One App for All AI Coding Tools

A single desktop application now manages skills for over forty different AI coding tools simultaneously. This solves the messy problem of keeping instruction files updated across Cursor, Claude Code, and other assistants, where manual copying leads to version conflicts and wasted effort. The app installs every skill into one central folder, then automatically links them to whichever tools you have active, so you update a capability in one place and see it appear everywhere instantly. This centralized approach removes the need to track down every hidden configuration folder on your computer. It is the definitive way to organize your AI toolkit without the clutter.

🆔 @hackernewsgithubprojects

📦 shopify/claude-for-commerce-examples

Claude for Commerce Examples: The AI That Shops and Sells

Claude for Commerce Examples is the practical blueprint that finally makes AI shopping agents work on real Shopify stores. It connects a customer-facing chatbot to your live catalog, letting buyers search, build carts, and ask policy questions without leaving the page. The real magic is in the merchant side, where the AI reads your inventory and proposes price changes or restocks, but only applies them after you explicitly hit approve. It is the perfect starting kit if you want to build custom AI agents that actually touch your store data, giving you full control over what gets changed and when.

🆔 @hackernewsgithubprojects