142 subscribers
10.2K videos
10.8K links
Download Telegram
This media is not supported in your browser
VIEW IN TELEGRAM
πŸ“¦ chrissotraidis/bluewake

BlueWake: The Wind Waker on iPhone

Play The Legend of Zelda: The Wind Waker directly on your iPhone, iPad, or Windows computer without an emulator. This project takes the original GameCube game code and translates it into native instructions for your device, so it runs at the game’s native speed without slowing down your phone. The most impressive part is that it runs at a steady thirty frames per second on an iPad Pro, matching the original console’s performance. It handles touch controls, external game controllers, and high-resolution texture packs, all while using your own legally purchased disc. Since it translates the code ahead of time, it feels like a genuine app rather than a simulation.

πŸ†” @hackernewsgithubprojects
This media is not supported in your browser
VIEW IN TELEGRAM
πŸ“¦ remocn/remocn-studio

Remocn Studio: The Video Editor for AI

Edit video by talking to an AI agent instead of dragging clips on a timeline. Remocn Studio is a desktop app built on Remotion where you describe what you want in plain language, and an AI assistant writes the code to build the animation for you. It comes pre-loaded with motion design rules and templates for product demos, so your AI editor actually understands pacing, easing, and how to make things look professional. You can preview your video in real-time inside the app, and even point at specific elements to tweak them.

πŸ†” @hackernewsgithubprojects
This media is not supported in your browser
VIEW IN TELEGRAM
πŸ“¦ yusuke710/manim-skill

Manim Skill: AI Video Generation

manim-skill is the coding agent extension that turns plain text prompts into fully produced educational videos with synchronized voiceovers. It solves the problem of complex video production by having the AI agent handle every step, from writing the narration script to generating local audio and coding the final animation. This is useful because it removes the need to manually sync timing between voice and visuals, allowing you to simply describe a concept and receive a polished, explainer-style video that you can easily refine by giving specific feedback on individual scenes.

πŸ†” @hackernewsgithubprojects
This media is not supported in your browser
VIEW IN TELEGRAM
πŸ“¦ syncso-inc/syncso

SyncSo: Live City Data for AIs

SyncSo plugs your AI assistant into a live feed of actual events happening right now in New York City. Instead of guessing based on old training data, it scans thousands of real listings for live music, comedy shows, and local classes, returning precise times, prices, and direct booking links. You can ask for a quiet first date spot or a free outdoor activity, and the system filters the entire city to find what fits that exact moment. It turns vague questions into bookable plans with real-world details. So next time you ask your chatbot for date ideas, you get fresh answers, not recycled guidebook entries.

πŸ“° https://news.ycombinator.com/item?id=49950236

πŸ†” @hackernewsgithubprojects
This media is not supported in your browser
VIEW IN TELEGRAM
πŸ“¦ gesta-run/subpool

Subpool: One Key for Every Team AI Subscription

Subpool is the self-hosted manager that finally lets one API key access every AI subscription in your company. It solves the chaos of juggling separate logins for tools like Codex and GitHub Copilot by pooling those accounts behind a single, secure endpoint. Instead of every employee managing their own access, administrators create shared pools and hand out unique keys that automatically route requests to healthy accounts. The system tracks remaining usage so you never hit a wall mid-project, and it never stores your actual conversation data. You get centralized control, clear auditing, and a simple way to share expensive AI licenses without exposing raw credentials to individual users.

πŸ“° https://news.ycombinator.com/item?id=49535569

πŸ†” @hackernewsgithubprojects
This media is not supported in your browser
VIEW IN TELEGRAM
πŸ“¦ ythx-101/live-panel-skill

Live Panel Skill: Animated Architecture Diagrams

Turn a single text file into a living system map that actually runs. This project generates moving infographics where data packets travel along wires, counters tick upward, and status bars flip colors as states change. It solves the problem of static diagrams by creating a video that looks like a live monitoring dashboard. Every frame is a complete picture, so you can pause it anywhere and still understand the whole system. The result is a short video file or a webpage that loops forever. You just describe your setup in a simple config file, and the tool handles the rest.

πŸ†” @hackernewsgithubprojects
This media is not supported in your browser
VIEW IN TELEGRAM
πŸ“¦ adityajha2005/yc-outreach

YC Outreach: The 80 Percent Email Trick

Turn any Y Combinator batch into a ready-to-send list of personalized cold emails, all from your browser. This project scans public company pages to pull founder names and websites, then guesses their professional email addresses using common naming patterns. The surprising part is that this simple guesswork is right about eighty percent of the time. You write your email once in a single template, and the tool fills in every founder’s name and company details automatically. It’s free, requires no server setup, and keeps your data private in your browser, making it a surprisingly effective way to reach out to startups without paying for expensive lead generation tools.

πŸ†” @hackernewsgithubprojects
This media is not supported in your browser
VIEW IN TELEGRAM
πŸ“¦ zoolapp/aime

AIME: The Open Source Chinese Input Method for macOS

Type Chinese on your Mac with a tool that respects your privacy. AIME is an open-source input method built on the RIME engine, meaning your daily typing happens entirely on your device without any hidden data collection. The standout feature is its optional AI layer. You can invoke translation or text polishing directly from your keyboard using a simple shortcut, letting you refine sentences instantly while keeping full control over what gets processed. It blends the flexibility of a traditional engine with modern, on-device intelligence.

πŸ†” @hackernewsgithubprojects
This media is not supported in your browser
VIEW IN TELEGRAM
πŸ“¦ ymuskrat/arcticdb_mcp

arcticdb_mcp: Your AI's New Data Sidekick

arcticdb_mcp gives your AI assistant direct hands-on control over your financial data, turning complex database tasks into simple conversation. You can ask your bot to check stock prices, update records, or manage versions, and it will just get the work done. This project solves the problem of needing to write manual scripts for every small data change, letting you automate your workflow with built-in safety features like versioning. It is basically a bridge that lets smart assistants talk directly to your data store without breaking anything. If you are tired of writing repetitive code for data tasks, this is the tool that lets you just talk to your database instead.

πŸ†” @hackernewsgithubprojects
This media is not supported in your browser
VIEW IN TELEGRAM
πŸ“¦ jayleaton/glm53-tensorfold-spark

GLM53 Tensor Fold Spark: 2x Faster AI on Spark

GLM53 Tensor Fold Spark is the inference engine that makes two small computers outperform big servers. It runs a massive AI model on two NVIDIA DGX Sparks, splitting the math between them to answer questions much faster than standard tools. The coolest part is its warm replay feature. If you send the same prompt again, it instantly jumps back to where it left off, answering in a fraction of a second instead of reprocessing everything. It feels like the computer has perfect memory. This proves you do not need a data center to get fast, local AI. Just two sparks and this engine give you serious power.

πŸ†” @hackernewsgithubprojects
This media is not supported in your browser
VIEW IN TELEGRAM
πŸ“¦ nand2mario/z486_mister

z486 MiSTer

A small FPGA board now runs Doom at nearly thirty frames per second using a processor design that never shipped in a box. The z486 MiSTer core is a digital brain written in code that runs on a tiny chip, turning a handheld device into a retro computer capable of handling 1990s graphics. It solves the problem of running old software on modern hardware without needing a bulky desktop tower. The result is a compact, battery-powered PC that handles classic games with surprising speed. It proves that modern electronics can recreate the muscle of machines from thirty years ago. The takeaway is simple: you can own a pocket-sized Windows computer.

πŸ†” @hackernewsgithubprojects
This media is not supported in your browser
VIEW IN TELEGRAM
πŸ“¦ heise3/academic-deai

Academic DeAI: Write Like Yourself, Not an Algorithm

Academic DeAI strips away the robotic, formulaic tone from research papers while keeping every citation, number, and argument exactly where you put it. Instead of just swapping words, it spots the repetitive sentence structures that make AI writing feel generic and smooths them out so the text sounds like a real human scholar. It works for both English and Chinese, helping you preserve your unique voice and the actual evidence behind your claims. It is not a magic fix for detectors, but it is a smart editing guide that helps you sound natural and credible.

πŸ†” @hackernewsgithubprojects
This media is not supported in your browser
VIEW IN TELEGRAM
πŸ“¦ telepath-computer/television

Television: The Missing GUI for Personal Agents

Television is the visual workspace that finally lets your AI agent build actual interfaces instead of just text. It solves the problem of agents getting stuck in chat boxes by giving them a real screen to work on. You talk to your agent normally, but when it creates a document, a chart, or a live app, it places those artifacts directly on your Television. These items stay on screen, update in real time, and can even be interactive.

πŸ“° https://news.ycombinator.com/item?id=49946919

πŸ†” @hackernewsgithubprojects
This media is not supported in your browser
VIEW IN TELEGRAM
πŸ“¦ bquantfinance/administracion-fuentes-publicas

Fuentes PΓΊblicas: The Secret to Spanish Open Data

Administracion fuentes publicas cuts hours of debugging by documenting exactly where Spanish government data lives and how to access it without crashing. The project catalogs ninety-five data sources, from energy prices to public tenders, and reveals the silent traps that official guides ignore. For instance, one API returns only fifty rows unless you pass a specific limit, while another uses internal codes that look nothing like standard municipality numbers. By verifying every endpoint with real calls, this open-source map turns chaotic public data into a reliable foundation for developers, startups, and AI agents building the next generation of civic tools.

πŸ†” @hackernewsgithubprojects
This media is not supported in your browser
VIEW IN TELEGRAM
πŸ“¦ zhangweihui666/silver-tourism-digital-twin

Simulating 500 Virtual Seniors in a 3D Historic District

Silver Tourism Digital Twin lets you build a full three dimensional replica of a historic city district and drop five hundred virtual seniors into it to see how they move. You can feed it a place name like a famous old alley in China, and it pulls real map data to reconstruct the buildings, streets, and benches. Then, you run a simulation where these agents walk around, avoiding cars, checking signs, and finding places to rest. It is a clever way to test if a space is actually safe and usable for older people before anyone ever sets foot there.

πŸ†” @hackernewsgithubprojects
This media is not supported in your browser
VIEW IN TELEGRAM
πŸ“¦ deepbeepmeep/ltx-desktop-wangp

Generate AI Videos on 6GB VRAM: LTX Desktop

LTX Desktop lets you generate AI videos locally on a graphics card with just six gigabytes of video memory. This open source app uses the LTX models to turn text, images, or audio into video clips without sending your data to the cloud. It solves the problem of needing massive, expensive hardware for local video generation by optimizing the process for standard consumer GPUs. The project is particularly interesting because it bridges the gap between high quality AI video tools and accessible hardware, giving creators full control over their workflow. It also includes a built-in editor for refining your clips.

πŸ“° https://news.ycombinator.com/item?id=47404744

πŸ†” @hackernewsgithubprojects
This media is not supported in your browser
VIEW IN TELEGRAM
πŸ“¦ otter-sec/rctf

rCTF: The Flexible Platform for Cyber Competitions

R C T F is the cybersecurity competition platform that lets organizers run their own event without getting locked into a single cloud provider. Instead of forcing you to use specific services for emails, storage, or hosting, it gives you a simple way to swap out the parts you need while keeping everything else the same. This means you can host a small local contest or a massive global tournament using the same core software, changing only the backend services that fit your budget and infrastructure. It solves the headache of rewriting your setup every time you switch hosting providers.

πŸ“° https://news.ycombinator.com/item?id=49951908

πŸ†” @hackernewsgithubprojects
This media is not supported in your browser
VIEW IN TELEGRAM
πŸ“¦ casys-ai/mcp-erpnext

MCP ERPNext: Give AI Hands for Your ERP

Hand your AI agent the keys to your company’s entire back office. That is exactly what MCP ERPNext does. It plugs directly into your ERPNext or Frappe instance, turning every invoice, inventory count, and sales order into data an AI can read and act on. But here is the part that actually gets me. Instead of just returning a wall of raw text, it draws interactive visual dashboards right inside your AI chat. You get live kanban boards, clickable charts, and document viewers that look just like the real software. It is like giving your AI assistant a proper monitor instead of a text file.

πŸ“° https://news.ycombinator.com/item?id=47525863

πŸ†” @hackernewsgithubprojects
This media is not supported in your browser
VIEW IN TELEGRAM
πŸ“¦ feiyuaq/zcfsrf

Zcubed: Learn English While Typing

Your phone keyboard can teach you English while you type. Zcubed is a mobile input method that displays real-time English translations right above the keys as you write in Chinese. It solves the problem of needing separate study time by turning everyday texting into a learning session. When you type, you see the meaning, listen to pronunciation, and check example sentences instantly. This passive approach helps you build vocabulary naturally through daily chats and searches, rather than drilling flashcards. It is a simple, effective tool for anyone wanting to learn English without extra effort.

πŸ†” @hackernewsgithubprojects
This media is not supported in your browser
VIEW IN TELEGRAM
πŸ“¦ pruefsumme/widemelon

WideMelon: Widescreen DS Emulation

WideMelon is the Nintendo DS emulator that finally lets you play three-dimensional games on a modern widescreen monitor. The problem is that the original handheld has two small square screens, but your computer monitor is wide. Standard emulators just stretch the image, which makes characters look fat and breaks the proportions. Instead, WideMelon expands the viewports for the three-dimensional games while keeping the two-dimensional menus and the touchscreen controls at their native size. This means you get a bigger field of view without any distortion. It is a clever tweak that makes older games feel comfortable on today's hardware.

πŸ“° https://news.ycombinator.com/item?id=49773400

πŸ†” @hackernewsgithubprojects
This media is not supported in your browser
VIEW IN TELEGRAM
πŸ“¦ monte-carlo-data/mc-agent-toolkit

MC Agent Toolkit: The Data Guardian

MC Agent Toolkit is the data observability bridge that lets your coding assistant actually see what’s happening in your databases. Think of it as giving your AI editor a pair of eyes, so it stops guessing and starts knowing if a table is fresh, if a query is broken, or if a pipeline is about to fail. It plugs directly into popular tools like Claude Code and Cursor, turning your daily coding environment into a live diagnostics center. Instead of just writing code, it validates your changes against real-time data health, catching expensive mistakes before they hit production.

πŸ†” @hackernewsgithubprojects