📦 rgem227/knoweldge-base

Knowledge Base: The MCP Powerhouse

The knowledge base that finally lets your AI agents read your actual files is called Knowledge Base. It is a self-hosted hub where you upload documents, organize them into folders, and manage team access, all from a single web interface. The standout feature is its built-in support for Model Context Protocol calls. This means your AI assistants can directly connect to this repository, search through your PDFs and Word docs, and pull up specific information on demand. It turns a static file storage system into a living, queryable brain for your AI tools. If you want your agents to know exactly what you know, this is the bridge you need.

🆔 @hackernewsgithubprojects

📦 riba2534/claude-opus-5-5-demo

Claude Opus 5.5 Built Three 3D Games From One Sentence Each

Claude Opus 5.5 Demo is the code generation stress test that proves an AI can build playable, polished 3D games from just a single sentence of instruction. The creator challenged the model to build three distinct web experiences, a pelican riding a bike, a classic first-person shooter map, and a racing game, with zero human edits to the source code. The model handled everything, from researching map layouts to writing the graphics engine and even deploying the live sites itself. This isn't just a demo; it's proof that AI can now handle complex, end-to-end creative tasks without being held by hand, marking a massive leap in autonomous software development.

🆔 @hackernewsgithubprojects

📦 rizzo-ai-academy/rizzo-flow

Rizzo Flow: AI Decisions Without Text

Rizzo Flow is the local AI tool that returns typed decisions without writing a single word of text. Usually, large language models generate slow sentences that you have to parse, but this project reads the hidden probabilities directly from the model’s internal math. It turns messy inputs into instant, structured answers like a clear yes or no, or a specific score. This means you get the judgment of an AI without the lag or format errors of standard text output. It runs entirely on your own machine, making it perfect for private, real-time automation.

🆔 @hackernewsgithubprojects

📦 saragordic/rooms

Rooms

Rooms is the menu bar app that finally tames your chaotic Mac desktop by turning your projects into dedicated virtual workspaces. Instead of drowning in a sea of overlapping windows, you just press option space, type a project name, and your custom layout instantly snaps into place. It hides everything else without actually closing a single app, and it even remembers different layouts for your laptop screen versus your external monitor. When you switch projects, your previous windows are safely parked in the background, ready to return exactly how you left them. It is a brilliant, completely offline way to stay focused.

🆔 @hackernewsgithubprojects

📦 kloxeld/xscrape

xscrape: The Smart Twitter Data Collector

Xscrape is the Python library that finally makes collecting Twitter data feel effortless. It solves the headache of getting blocked by automatically rotating through your account pool and adjusting its speed to stay under the radar. Instead of writing fragile scraping code from scratch, you just tell it what to look for, and it handles the complex background work of managing connections and organizing your results. The coolest part is how it reconstructs entire conversation threads into neat, exportable files, turning messy social feeds into structured data you can actually analyze.

🆔 @hackernewsgithubprojects

📦 v-modal/awesome-jev-tools

One Model for Every Decision

A browser extension uses Jev to detect sponsor reads in YouTube videos with just one dollar per thousand videos. It skips generating text and instead asks a direct question: is this ad or content? The tool returns a simple yes, no, or score, making it fast and cheap for live software. A repository called awesome Jev tools collects these real projects to show how this model works in the wild. It tracks live deployments where Jev handles routing, safety checks, and scoring. This is not a chatbot; it is a decision engine.

🆔 @hackernewsgithubprojects

📦 tianyucodings/jevharness

JevHarness: The AI That Plays Pokemon Better Than You

Take a slow, thoughtful AI and a fast, instinctive one, and let the smart one build a custom program that uses the quick one to win. That is the core trick behind JevHarness. It solves the problem of high cost and slow speed in artificial intelligence. The project uses a large model to write specific code for a task, like playing a battle. It then freezes that code, so a smaller, cheaper model can make rapid decisions without thinking deeply every time. The result is an agent that acts with the speed of a reflex and the strategy of a plan.

🆔 @hackernewsgithubprojects

📦 tencentarc/gamehorizon

GameHorizon: Measuring AI in AAA Games

Tencent ARC just built a benchmark that grades AI models on how well they actually play AAA games, not just on static images. The project is called GameHorizon, and it solves a big problem: figuring out if a model can truly understand complex, long-term strategy in real-time gameplay. It uses five thousand hours of actual game footage to test if AI can plan ahead or just react to what's on screen right now. The results are already out, and the best model barely scored eighty percent. So if you're building agents that need to think several steps ahead, this is the yardstick you need to know where the line is.

🆔 @hackernewsgithubprojects

📦 yinsongxu/llm2jev

How LLM2Jev Answers Questions Instantly

Take a standard local language model and turn it into a rapid decision engine that answers complex questions without writing a single new word. The project called LLM2Jev reads the initial signal from your model to pick an answer or score an image, completely skipping the slow step of generating text token by token. This makes it incredibly fast for structured tasks like choosing between options or evaluating a visual scene. By relying on this prefill-only method, you get precise results in milliseconds rather than seconds. It is a clever way to get smart, structured answers from local hardware without the usual wait.

🆔 @hackernewsgithubprojects

📦 onlistteam/ai-manager

AI Manager: Your Calm Control Center for AI Coding Tools

AI Manager is the desktop app that finally stops the chaos of managing multiple AI coding tools by giving you one calm place to install, update, and configure them all. Instead of jumping between different terminals or config files for every single assistant, this application acts as a unified dashboard that checks which tools are installed, handles their updates, and manages your API connections in one clean interface. It solves the headache of juggling different versions and settings by keeping everything organized locally on your machine.

🆔 @hackernewsgithubprojects

📦 yukitorido/short-video-generator-ai

Short Video Generator AI: Turn Long Videos into Viral Shorts

Short Video Generator AI takes a long YouTube link and automatically turns it into ready-to-post vertical shorts. The most surprising part is that it uses artificial intelligence to listen to the entire video, find the most exciting moments like emotional peaks or big reveals, and cut them out for you. This solves the tedious problem of manually scrolling through hours of footage to find the best clips. It handles transcription, translation, and even adds a catchy AI-written hook at the start of each clip to grab attention. You get clean, vertical videos with no watermarks or paid subscriptions required.

🆔 @hackernewsgithubprojects

📦 tobi/disktree

See Exactly What Is Eating Your Hard Drive

Stop guessing why your storage is full. disktree scans your computer and draws a visual map where every folder is a colored block sized by its actual cost on disk. It highlights the specific junk you can safely delete, like old caches or build files, while keeping your important data protected. You can zoom into the mosaic to find the space hogs, mark them for removal, and watch your free space update in real time. It is a safe, visual way to clean up your drive without accidentally deleting something important. If you are running low on space, this tool makes the cleanup process simple and confident.

📰 https://news.ycombinator.com/item?id=49841155

🆔 @hackernewsgithubprojects

📦 dbt-labs/dbt-charts

Describe Data, Get a Chart

Describe what you want to see in plain English, and an AI agent writes the exact chart for you. Dbe Charts turns your data into a visual dashboard using a simple text file. This means your AI assistant can build the chart for you, while you keep full control to read and edit the code. It’s a fresh way to turn raw numbers into clear pictures, without needing to learn a complicated coding language. Perfect for anyone who wants smart, automated visuals. Try it out and see how easy data can be.

🆔 @hackernewsgithubprojects

📦 gmgnai/gmgn-skills

gmgn-skills

gmgn-skills lets your AI agent trade meme coins like a pro. It pulls live data from Solana, BSC, and Base to spot smart money moves before the crowd does. Instead of you staring at charts, your agent scans for new tokens, checks if insiders are dumping, and executes trades in under a third of a second. It even sets your take-profit and stop-loss orders automatically so you don't have to guess. If you want your AI to watch the market for you, this is the tool that makes it happen. Now you can let your agent do the heavy lifting while you just watch the numbers go up.

🆔 @hackernewsgithubprojects

📦 localai-org/motion-bricks.cpp

Motion Bricks: Neural Animation on Your CPU

Motion Bricks is the local neural engine that generates real-time robot animations from simple keyframes without a GPU. It ports a complex model from NVIDIA to standard C++, allowing you to steer a thirty-four joint digital skeleton directly on your computer using just a keyboard. This means you can drive lifelike movement for games or physical robots on everyday hardware, bypassing the need for expensive cloud servers. It is a powerful tool for creators who want full control over motion generation. The takeaway is clear: advanced AI animation no longer requires a data center, just your machine.

🆔 @hackernewsgithubprojects

📦 sno-ai/sno-station

Sno Station: Your AI Agents' Night Shift

Sno Station is the local toolkit that turns your separate AI coding agents into a single, self-improving squad. Instead of juggling different tools, it gives them shared, encrypted memory so they can pick up exactly where the other one left off. The coolest part? Every night, the system reads through their recent work, finds their mistakes, and drafts updates to their own instruction files. You just review and accept, so they get smarter daily without touching the cloud. It is all open source and runs entirely on your machine, proving that two heads really are better than one.

🆔 @hackernewsgithubprojects

📦 omacom/ttfx

ttfx

This terminal tool renders animated text effects with a startup time of less than one millisecond. Known as ttfx, it transforms plain shell output into visual animations like lasers and rain using a single static binary. Unlike the original Python version, this Rust port eliminates interpreter delays and heavy dependencies. It runs thirty seven distinct effects directly from your command line. The result is a snappy, dependency free tool that fits perfectly into any text pipeline. No installation steps or slow imports. Just pipe your data in and watch it move. It is the fastest way to add visual flair to your terminal workflow without any performance penalty.

🆔 @hackernewsgithubprojects

📦 vibeforge1111/dexscreener-cli-mcp-tool

Dexscreener CLI

Scan the hottest crypto tokens across every major chain right from your terminal. This free tool gives you a live dashboard that scores tokens by real momentum and volume, so you stop guessing which ones are actually moving. You can also hook it up to an AI agent to ask questions in plain English instead of typing complex commands. It is a simple, powerful way to track market signals without needing a paid API key. If you want to catch new tokens before they blow up, this is your ticket.

🆔 @hackernewsgithubprojects

📦 tarwin/tinyjsapp

tinyjsapp: Write One Codebase, Run Anywhere

Your JavaScript code runs directly inside your computer, skipping the heavy browser engine that usually slows things down. This project, called tinyjsapp, gives you a tiny five megabyte tool that turns your scripts into real desktop software for Mac, Windows, and Linux. It solves the problem of app size by letting you build a single project that feels native on every screen. You can even use your phone as a remote control for the app, which is a surprisingly handy trick. It is not a web page in a box; it is a lightweight bridge that lets code talk to the machine itself.

🆔 @hackernewsgithubprojects

📦 penso/herdr-gpui

Herdr: The Native App for Your Terminals

Herdr is the native Mac app that finally lets you see every terminal session and workspace on your computer in one fast window. Built with Rust, it connects directly to your local Herdr server, painting the actual terminal cells without running a separate emulator or wrapping your existing tools. The coolest part is that it tracks what your coding agents are actually doing in real time, so you can watch them work without staring at raw logs. It is not a replacement for your shell, just a smart viewer that keeps everything organized and visible.

🆔 @hackernewsgithubprojects