194 subscribers
12K videos
12.6K links
Download Telegram
This media is not supported in your browser
VIEW IN TELEGRAM
πŸ“¦ rafaelpta/dupehound

dupehound

Your AI assistant just wrote the same function for the third time under a new name, and you probably missed it. dupehound fixes this by looking at the shape of your code rather than the words, so it catches duplicates even after you rename every single variable. It scans your project in under a second, works completely offline, and tells you exactly which copy to delete so you can stop maintaining identical logic in five different places. No expensive API calls, just a fast check that keeps your codebase clean and honest. If you build with AI, this tool is your safety net against silent clutter.

πŸ“° https://news.ycombinator.com/item?id=48502793

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

StarryKit: Your AI Agent Makes Slides Now

Your AI coding agent can now build professional, fully editable presentations directly inside your terminal. StarryKit plugs into tools like Cursor and Claude Code so you can generate polished slide decks and social graphics using plain text prompts. The best part is that these designs are not just images; you can actually open them and move every single element around. It exports cleanly to PowerPoint or PDF, turning a simple chat request into a real, usable design file. If you want to stop hunting for templates and start creating directly with your code assistant, this is the bridge you have been waiting for.

πŸ“° https://news.ycombinator.com/item?id=49276368

πŸ†” @hackernewsgithubprojects
This media is not supported in your browser
VIEW IN TELEGRAM
πŸ“¦ lotus0614/moss-manga-studio

Moss Manga Studio: AI Manga Editor

Moss Manga Studio is the creative editor that turns a single JSON file into a complete comic page. Instead of drawing every panel by hand, you define the layout and dialogue in a simple data structure, and the software handles the rest. This is great because it lets you focus on the story while an AI model does the heavy lifting for the artwork. The most surprising part is how easy it is to fix mistakes. If a character has too many fingers or a speech bubble looks messy, you can just type a quick instruction to correct that specific spot.

πŸ†” @hackernewsgithubprojects
This media is not supported in your browser
VIEW IN TELEGRAM
πŸ“¦ sp8esa/esp32-datv

ESP32-DATV: Your $5 Wi-Fi Chip is a TV Transmitter

A five-dollar microchip is literally broadcasting actual television video from its internal Wi-Fi hardware. The ESP32-DATV project turns a standard ESP32-C3 board into a functioning satellite TV transmitter without needing any extra radio hardware. It squeezes high-speed digital video signals straight out of the chip’s built-in digital-to-analog converter. You feed it a video file on your computer, and the chip mathematically shapes the data into a broadcast signal. This lets hobbyists beam live video over the airwaves using nothing but a tiny, cheap microcontroller. It proves that powerful signal processing doesn’t require expensive, dedicated hardware.

πŸ†” @hackernewsgithubprojects
Media is too big
VIEW IN TELEGRAM
πŸ“¦ jayleaton/deepseek-v41-tensorfold-spark

DeepSeek V41 TensorFold Spark: 3x Faster AI on Two Chips

DeepSeek V41 TensorFold Spark is the inference engine that runs a massive AI model on just two consumer-grade chips. Most people assume you need a rack of expensive servers to run this level of intelligence, but this project proves otherwise. It uses a clever technique called speculative decoding to guess words and verify them instantly, which makes the system up to three times faster than standard setups. This means you get lightning-fast, accurate AI responses without the massive power bill or hardware costs. It is still work in progress, but the speed gains are already impressive.

πŸ†” @hackernewsgithubprojects
This media is not supported in your browser
VIEW IN TELEGRAM
πŸ“¦ drowzeys/imagination-studio-by-keys-wasserman

Imagination Studio: The Local AI Film Crew

A single Mac can now plan, shoot, and sound design a complete short film without ever touching the internet. Imagination Studio runs a full production crew locally, letting you type a sentence and receive a finished video clip with synchronized audio and music. It handles the heavy lifting of image generation and motion synthesis on your own hardware, meaning your creative data never leaves your desk. This is not just a picture maker; it is a working studio for people who want to direct their own visuals.

πŸ†” @hackernewsgithubprojects
This media is not supported in your browser
VIEW IN TELEGRAM
πŸ“¦ mk27mk/uxed

Stop Guessing: Edit Your Code Visually with uxed

Replace the slow back-and-forth of describing code changes in chat with a visual, interactive canvas that feels like editing a design file. The project uxed transforms how developers work with artificial intelligence by letting you pick, drag, and restyle user interface elements directly in a live browser window, rather than typing out vague instructions and hoping for the best. It turns your rough sketches into functional, tested software components in a fraction of the time, eliminating the frustration of miscommunication and repeated corrections. This tool bridges the gap between creative design and technical implementation, ensuring the final code matches your vision exactly.

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

Agentic Resource Registry: One Place for All Your Coding Agents

Agentic Resource Registry is the self-hosted hub that stops your team from building the same coding tools twice. It acts as a central library where developers can publish and discover skills, agents, and prompts for tools like Claude Code and Cursor, solving the mess of scattered files and unknown usage. The standout feature is its session replay capability, which records exactly how an agent handles a task so teams can see real failures and fix them instead of guessing. This turns silent errors into clear lessons, ensuring your internal tools actually improve over time.

πŸ“° https://news.ycombinator.com/item?id=50303291

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

BunPod: The Podcast App with Personality

BunPod turns your daily podcast listening into a visual experience. It is a mobile app built to feel alive, where shapes morph and colors shift as you navigate. Instead of static buttons, the interface reacts to your taps with playful, springy animations. You can sign in, follow your favorite shows, and manage downloads all within this dynamic environment. The code is open-source, so you can see exactly how these fluid interactions are built. It proves that a simple player can have real character. Give it a try and see how a podcast app can actually feel fun to use.

πŸ†” @hackernewsgithubprojects
Media is too big
VIEW IN TELEGRAM
πŸ“¦ soimy/c3rb3r-rescue

C3RB3R Rescue: Ransomware Recovery That Actually Works

A live ransomware process was stopped mid-encryption, and its memory still held the exact key needed to unlock thousands of files. This project, known as C3RB3R Rescue, turns that specific technical detail into a practical survival kit for Synology NAS systems. Instead of just telling you to panic, it gives you a precise, step-by-step playbook to freeze the malware before you accidentally reboot and lose the only chance to decrypt your data. It even explains how to pull keys from physical RAM or use file system quirks to restore files when no key is found.

πŸ†” @hackernewsgithubprojects
This media is not supported in your browser
VIEW IN TELEGRAM
πŸ“¦ molence/mol-1

Mol-1 Predicts Complex Molecular Shapes

Predict the precise three-dimensional shape of complex biological systems. Mol-1 is an open source tool that figures out exactly how proteins, DNA, and drug molecules fit together in space. It takes your biological sequences and calculates the atomic arrangement, which is the key to designing new medicines. The best part is that you can run this locally on your own graphics card. You get the full power of frontier research without relying on a black box service. This project is a massive step for accessible biology. If you are working on drug discovery, this is the toolkit you need to build accurate structural models yourself.

πŸ†” @hackernewsgithubprojects
This media is not supported in your browser
VIEW IN TELEGRAM
πŸ“¦ akil-x/r00tlib-catalog

The Free Tech Book Catalog

Rootlib Catalog is the open tech book index that finally puts hundreds of free textbooks in your pocket. Instead of hunting for scattered PDFs, this community project gathers verified copies of top titles in cybersecurity, artificial intelligence, and game development into one searchable list. It links directly to mirrors and discussion threads, so you can grab the knowledge without paying a dime. It is basically a massive, organized library built by developers for developers. If you are studying systems or security, this is your shortcut to serious reading material. Check it out and see what you have been missing in your study rotation.

πŸ†” @hackernewsgithubprojects
This media is not supported in your browser
VIEW IN TELEGRAM
πŸ“¦ andyhuo520/vibe-knowledge

Vibe Knowledge: Turning Facts Into Cinematic Videos

Transforming a single fact into a polished, cinematic video is the core magic of Vibe Knowledge. This project acts as a specialized instruction set for artificial intelligence, guiding it through the entire process of creating short educational films. It handles everything from researching and scripting to voice generation and visual rendering, ensuring every visual element is drawn in code with precise sources for every claim. The standout feature is its library of forty-four distinct visual styles, allowing creators to instantly switch between aesthetics like pixel art, blueprint diagrams, or traditional ink painting without changing the underlying script.

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

OpenCode Quota: Your AI Token Meter

Check exactly how much of your AI coding quota you have left right now. OpenCode Quota plugs into your terminal editor to track your token usage and remaining limits across dozens of different AI providers like Anthropic, OpenAI, and Google. It solves the confusing problem of switching between tools without knowing when you will hit a paywall or rate limit. The best part is that it runs completely outside the main chat, so it never slows down your prompts or eats up your valuable context window. You just type a simple command to see a clean breakdown of your spending and limits.

πŸ†” @hackernewsgithubprojects
This media is not supported in your browser
VIEW IN TELEGRAM
πŸ“¦ changhaoting1998-star/manufacturing-wechat-miniapp-starter

Manufacturing WeChat Mini Program Starter: The Shop-Floor Fix

Turn your factory floor into a live data stream without forcing workers to install another app. This starter uses the WeChat Mini Program to let employees log shifts, confirm pay, and report quality checks right from the phone they already use. It solves the messy problem of paper reports and delayed updates by sending verified data directly to your manufacturing system. The coolest part is how it protects everyone: it ensures only the actual person can clock in and keeps a clear, auditable trail of every single event. It is not a full system, but a clever bridge that makes your data honest and immediate.

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

Douyin Comments

Douyin Comments is the agent skill that captures the entire comment section of a single video by using your actual browser session to handle the tricky security signatures. Instead of trying to reverse engineer complex encryption or using fake data, it simply copies the real requests your page is already making to fetch data. This lets you pull every top-level comment and nested reply into a clean, readable text file without needing special software or risking your account getting blocked.

πŸ†” @hackernewsgithubprojects
This media is not supported in your browser
VIEW IN TELEGRAM
πŸ“¦ win4r/video-director

video-director

Your AI agent can’t watch a video, but video-director forces it to measure every frame. This Claude skill turns coding tools into a full film production pipeline. You write the animation in HTML or Canvas, and the system renders it to MP4. The real magic is the quality check. Two scripts scan your final file for invisible mistakes like a black first frame, unreadable text, or audio that is too quiet. It even verifies your data matches your source files. It’s a strict director that ensures your code looks exactly right before you publish. No more guessing if your animation looks good. You get verified, polished visuals from plain code.

πŸ†” @hackernewsgithubprojects
This media is not supported in your browser
VIEW IN TELEGRAM
πŸ“¦ wzc520pyfm/gen-ai-pose-image

Lanpose: Generate Whale Girl Art

Generate consistent character art by mixing and matching pose sketches and clothing from a massive library. Lanpose is a web tool that lets you pick a body pose and a costume, then uses an image model to render your chosen character in that exact outfit and stance. It is designed for the community whale-girl model Dafeiyu, but you can import other photos to change the face or clothes. The best part is that it plugs directly into the DeepSeek Harness, letting you command the AI to search and generate images without leaving your workflow.

πŸ†” @hackernewsgithubprojects
This media is not supported in your browser
VIEW IN TELEGRAM
πŸ“¦ keoyyo85/foundphone-studio

FoundPhone Studio: The AI Phone Story Builder

FoundPhone Studio is a browser-based framework that lets you build interactive, branching stories that play directly inside a realistic virtual smartphone interface. The project’s most interesting feature is that you can feed natural language descriptions, chat logs, and images to an AI tool, which then converts them into a structured, playable narrative without you having to manually code the phone’s UI. It solves the problem of creating complex, multi-ending mobile story experiences by providing a ready-made runtime with over forty app templates, including simulated messaging, calls, and social media.

πŸ†” @hackernewsgithubprojects
Media is too big
VIEW IN TELEGRAM
πŸ“¦ lzyang2000/morphmimic

MorphMimic: One Brain for Many Robots

MorphMimic is the robotics framework that trains one shared brain to control three different humanoid robots at once. Instead of building separate software for every machine, it uses a single policy and world model that adapts to the unique physical traits of each body, from the Unitree G1 to the AgiBot X2 and the Booster T2. The coolest part is the direct VR teleop, where a headset tracks your movement and the robot copies it in real time without complex motion capture setups. It also handles hardware delays so the robots don’t stumble.

πŸ†” @hackernewsgithubprojects