📦 patrickmgarrity/anthropic-credited-cves

The Anthropic Cve Tracker

Keep a close eye on the Anthropic Cve Tracker, a living list that documents every security flaw publicly credited to Anthropic and its Project Glasswing research team. It isn't just a random collection; it is a massive, organized table that maps out the real-world impact of this specific AI-driven vulnerability hunt. The repository currently tracks two hundred and twenty-five distinct issues, ranging from minor bugs to critical exploits found in the wild. It highlights exactly which software components are being cracked open and who is responsible for the fixes.

🆔 @hackernewsgithubprojects

📦 jerryjliu/docjev

DocJev: The Fast Document Splitter

DocJev identifies and separates distinct documents hidden inside large multi-file PDFs. It uses natural language rules to classify content and pinpoint exact page boundaries, even when adjacent sections look nearly identical. For example, it correctly splits a fifteen-page government packet containing two separate Treasury auction results that share the same category, while keeping a dense ten-page economic report intact. The system processes real publications from the IRS and SEC, delivering precise segmentation results in under half a second. It runs locally for text extraction and uses a hosted service for final decisions.

🆔 @hackernewsgithubprojects

📦 kharmanskyi/open-steps

Open Steps

A coding agent just finished fixing a critical bug, but instead of a clear answer, it handed back a wall of technical jargon and commit hashes. This is exactly the problem Open Steps solves. Created by a product builder who doesn't read code, this project teaches AI agents to communicate in plain, human language. It replaces confusing technical details with simple reports that clearly state what is finished, what is broken, and what needs your next action. It’s like having a translator who ensures you actually understand the status of your project without needing a computer science degree.

🆔 @hackernewsgithubprojects

📦 agenta-ai/awesome-ai-agent-platforms

Awesome AI Agent Platforms

Map the sprawling world of open-source AI tools with this single, curated directory. The project, called awesome AI agent platforms, solves the confusion of finding reliable software by listing every major open-source agent tool in one place. It groups these projects into five clear categories, from digital coworkers that handle your daily tasks to frameworks developers use to build their own. The most surprising part is how it tracks the license and hosting model for every single entry. This lets you instantly know if you can self-host a tool or if you need a cloud service. It removes the guesswork from choosing an AI teammate.

🆔 @hackernewsgithubprojects

📦 smixs/creative-director-skill

Creative Director Skill: 571 Legendary Campaigns

A single project packs five hundred and seventy one of the most famous advertising campaigns in history into a practical toolkit for generating new ideas. Known as Creative Director Skill, this repository functions like a digital brain for brainstorming, combining proven thinking frameworks with a rigorous scoring system based on actual industry awards. It solves the common problem of creative blocks by providing structured methods to analyze emotions, insights, and storytelling patterns. Instead of guessing what works, users can apply the exact logic used to create iconic ads for global brands. It turns abstract creativity into a repeatable process grounded in real world success.

🆔 @hackernewsgithubprojects

📦 gefsikatsinelou/metasearchmcp

MetaSearchMCP: The Search API Built for AI Agents

MetaSearchMCP is the search gateway that speaks fluent agent instead of human. It fires off one request to dozens of sources at once, from Google to Wikipedia to Stack Overflow, then shreds all those messy results into one clean, predictable list of data. This solves the headache of writing separate scrapers for every site and worrying about which API might fail today. It’s built for your A I tools to grab facts, code, or papers without breaking their flow. If you’re building agents that need real-world answers, this is the simple way to get them.

🆔 @hackernewsgithubprojects

📦 amap-ml/dreamx-rec

DreamX Rec: The Travel AI That Predicts Your Journey

DreamX Rec is the travel research suite that finally connects the dots of where to go, how to travel, and what to visit along the way. Instead of treating recommendations as isolated clicks, this project unifies a massive dataset of real-world trips into a single system that understands the context of your journey. It predicts your destination, preferred travel mode, and departure time by analyzing the flow of your past experiences. This is fascinating because it moves beyond simple lists to model the actual logic of a trip. By connecting these different parts of travel, it offers a clearer view of how personalized systems can understand complex, multi-step human decisions.

🆔 @hackernewsgithubprojects

📦 wink-run/tokenbank

Token Bank: Your AI Spending Accountant

Token Bank acts as a secret middleman between your coding tools and the expensive AI models they use. It sits quietly on your computer, catching every request to see exactly where your money is going. The real magic happens when it starts saving you money. Instead of always paying full price for top-tier models, it automatically routes your routine tasks to free or local options that are still good enough for the job. You don’t have to change how you type or which tools you use. It just makes your AI cheaper without you noticing.

📰 https://news.ycombinator.com/item?id=48103934

🆔 @hackernewsgithubprojects

📦 youdotcom-oss/agent-skills

agent-skills: Give Your AI Agent Live Web Context

Give your coding agent live access to the current web without writing custom code. The agent-skills repository connects popular development tools directly to You.com services, allowing your AI to search for fresh information, read specific pages, and find accurate financial data. It acts as a ready-made bridge, so your agent knows exactly how to fetch and cite real-world facts instead of relying on outdated training data. You install it once, and your agent instantly gains the ability to ground its answers in up-to-date sources. If you build with AI agents, this is the easiest way to ensure they are always working with the truth.

🆔 @hackernewsgithubprojects

📦 easyeda/eext-run-api-gateway

EasyEDA Pro Extension Run API Gateway

Let your AI coding assistant draw actual circuits right on your screen. This tool plugs directly into EasyEDA Pro, creating a secure bridge that lets AI tools like OpenCode or Claude Code talk to your schematic editor in real time. Instead of just generating text, the assistant can now inspect your project, understand your layout, and execute commands to manipulate your design. It automatically finds the connection, verifies the handshake, and keeps things running smoothly even if your network hiccups. It is the missing link for engineers who want their coding agents to do more than just write code.

🆔 @hackernewsgithubprojects

📦 elevenlabs/skills

ElevenLabs Skills: AI Coding Superpowers

ElevenLabs just dropped a toolkit that lets your AI coding assistant generate professional voice applications from a simple text prompt. It is a collection of specialized instructions that teach tools like Cursor how to call ElevenLabs services correctly. Instead of reading endless documentation, you just tell your AI to build a voice agent or dub a video, and it writes the right code. This solves the problem of complex setup by handling API keys and SDK versions automatically. It is the difference between struggling with syntax and actually shipping a product. Your editor now speaks fluent audio, making development faster and less frustrating.

🆔 @hackernewsgithubprojects

📦 elevenlabs/cli

ElevenLabs CLI: Voice Agents as Code

Turn text into speech and manage voice agents directly from your terminal. The ElevenLabs CLI lets you type a command to hear a voice speak your words instantly, or treat your AI agents like software code by saving them as files on your computer. This approach is surprising because it allows you to version control your voice characters and sync changes to the cloud just like you would with standard text files. You can push updates, pull changes, and test your agents without leaving the command line. It is a simple way to build and manage conversational AI without needing a separate web dashboard.

🆔 @hackernewsgithubprojects

📦 aaditya-v-more/claude-graft

Claude Graft: Run Multiple Claude Accounts Side-by-Side

Run several Claude Desktop accounts side by side on your Mac, each with its own login, shortcut, and shared chat history. It solves the problem of having only one Claude login when you actually need multiple accounts at once. You can create shortcuts for extra accounts, copy chats over from a previous login, and keep your pins and sidebar order in sync across all of them. It’s useful if you juggle different Claude accounts for work, personal projects, or just want more room to experiment without losing your history.

🆔 @hackernewsgithubprojects

📦 anotiawang/awesome-jev

Awesome Jev: The Ultimate Resource Guide

Awesome Jev is the central hub that finally maps the entire ecosystem of TypeSafe System One. It solves the problem of scattered information by curating a massive, organized list of every application, library, and tool built for this specific AI framework. The real surprise is seeing just how wildly creative people have become with it, from browser agents that book flights in seconds to bots that play classic video games like Doom and Tetris. This collection proves that this technology is far more than a simple text generator, offering a clear window into how developers are building smart, decision-focused agents today.

🆔 @hackernewsgithubprojects

📦 juneyaooo/social-account-doctor

Social Account Doctor: The Ultimate Content Audit

Social Account Doctor is the diagnostic tool that finally explains why your content gets ignored. It takes a deep look at viral hits in your specific niche to figure out exactly which hooks and editing styles are working, then translates those mechanics into a simple, copy-paste draft for your next video. It’s basically a cheat code for creators who are posting consistently but seeing zero growth. Instead of guessing what’s wrong, you get a clear roadmap for what to film next. Stop posting into the void. Get your account a real health check, find the winning formula, and start actually getting seen.

🆔 @hackernewsgithubprojects

📦 omarroth/doubletake

Doubletake: AirPlay for Linux

Doubletake turns any Linux desktop into a screen that Apple TV can mirror, filling a gap where macOS and Windows users get this for free but Linux users were left behind. It handles the complicated handshake, encryption, and video encoding in the background, so you can just cast your screen to a TV or Mac without installing heavy, unstable workarounds. The coolest part is that it works with both X11 and Wayland, meaning it adapts to your specific setup automatically. If you want to watch your code or movies on the big screen without juggling cables or buying extra hardware, this is the tool that makes it happen.

📰 https://news.ycombinator.com/item?id=49209939

🆔 @hackernewsgithubprojects

📦 maanhimself/opendlss-nr

OpenDLSS NR: The AI Image Generator That Runs Locally

NVIDIA just showed that AI can invent new details in your game, and someone built the exact math to run it on your own computer. This project is a Vulkan reimplementation of the DLSS 5 Neural Rendering network, meaning it takes a blurry frame and generates sharp new pixels from scratch. The crazy part is that it matches the original output perfectly, down to the single byte. It is not just a filter that makes things look nicer. It is a heavy math puzzle solved on your graphics card to make a 4K image from a 1080p input.

🆔 @hackernewsgithubprojects

📦 meodai/skill.color-expert

Your AI's Secret Color Expert

Turn your coding agent into a color science expert with the color expert skill. It solves the problem of AI giving generic or wrong color advice by feeding it a massive, curated library of real research. Instead of guessing, it accesses nearly three hundred thousand words covering everything from historical paint mixing to modern screen accessibility standards. The coolest part? It actively corrects common myths, teaching your agent why standard color models often fail and how to pick palettes that actually look good. It’s not just a note file; it’s a brain upgrade for any AI you use.

🆔 @hackernewsgithubprojects

📦 frontier-harness-eval/eval

The 17x Cost Gap in Coding Agents

The same AI model can solve a coding task for one dollar or nearly twenty, depending entirely on the software wrapper used to run it. This benchmark, called Eval, tested a single AI model across nine different coding tools on thirty identical software problems. While the pass rates stayed surprisingly close, the cost difference was massive. The cheapest tool spent just over a dollar per solved task, while the most expensive spent nearly eighteen dollars for the same result. The repository publishes these public results and provides a workflow for anyone to test their own tool against these exact tasks.

🆔 @hackernewsgithubprojects

📦 qdrant/skills

Qdrant Skills for AI Agents

Qdrant released a toolkit that teaches AI coding agents how to act like senior database engineers. Instead of just reading code, these agents now possess specialized knowledge on complex topics like scaling, performance tuning, and migrating data between models. The most surprising part is that the system doesn't rely on static tutorials. It uses a live advisor that fetches the most current guidance directly from the official documentation every time you ask a question. This means your coding assistant always gives advice based on the latest best practices, rather than outdated training data.

🆔 @hackernewsgithubprojects

📦 zefan-cai/open-jev

Open-Jev: AI Decisions Without the Guesswork

This project skips the usual AI guessing game. Instead of watching a model invent an answer and then parsing that text, Open-Jev gives you actual numbers. You feed the model your context and your specific questions, and it spits out typed probabilities directly. It is a clean way to make decisions without the messy business of reading generated sentences. This repository is an open implementation of that idea, built on Qwen models. It handles everything from routing customer service tickets to playing simple games. The best part is you get the raw confidence scores right away. No more hoping the AI wrote the right words.

🆔 @hackernewsgithubprojects