📦 openvdn/vdn-minimax-h3

VDN Minimax H3: Video Generation That Outpaces Playback

A machine can now generate a fourteen-second video clip in just eleven seconds, meaning the computer renders the footage faster than you would watch it. That is the core capability of VDN Minimax H3, an open-source model that makes high-quality video generation significantly faster without sacrificing visual quality. It solves the problem of slow rendering times by using a clever hybrid architecture that mixes two different types of neural network attention, allowing it to process frames much more efficiently than standard models. The project is fully open-source, releasing both the optimized code and the training data recipes so anyone can reproduce or improve upon it.

🆔 @hackernewsgithubprojects

📦 comfy-org/comfy-mcp

comfy-mcp: Let AI Agents Run Your Local ComfyUI

comfy-mcp is the local bridge that lets AI agents drive your own ComfyUI without touching the cloud. Instead of relying on remote servers or complex APIs, this lightweight tool acts as a thin wrapper over the Comfy command line interface, allowing agents to directly run workflows, manage models, and handle installations on your own machine. The real surprise here is how it keeps things secure and honest by only passing commands to the underlying engine, ensuring that any actions involving costs or dangerous changes require explicit permission from you.

🆔 @hackernewsgithubprojects

📦 warmbly/warmbly

How to keep your cold emails out of the spam folder

Warmbly is the open source email platform that actually warms up your inbox before you start blasting. If you send cold emails, you know the pain of having your messages land in the junk folder, but this tool solves that by pairing your own mailboxes with a network of other accounts that interact with your mail to build a solid reputation. It is not a black box service where you lose control; instead, it runs entirely on your own hardware using standard tools, giving you total privacy and ownership over your outreach. You can self-host the whole system with a single command, meaning no cloud fees or vendor lock in.

📰 https://news.ycombinator.com/item?id=48771562

🆔 @hackernewsgithubprojects

📦 saganaki22/comfyui-vdn-h3

ComfyUI VDN H3

ComfyUI VDN H3 lets your personal graphics card render long videos in seconds instead of minutes. It replaces the heavy math that slows down video generation as clips get longer with a clever shortcut called hybrid attention. While the original model needed a massive cluster of server-grade GPUs to run quickly, this tool port that speed to any computer using ComfyUI. It works by keeping nearby frames perfectly detailed while using a lightweight method for distant context, which saves time without ruining quality. This means you can generate complex video sequences on your own hardware without needing a datacenter.

🆔 @hackernewsgithubprojects

📦 saganaki22/comfyui-vdn-h3

ComfyUI VDN H3

ComfyUI VDN H3 lets your personal graphics card render long videos in seconds instead of minutes. It replaces the heavy math that slows down video generation as clips get longer with a clever shortcut called hybrid attention. While the original model needed a massive cluster of server-grade GPUs to run quickly, this tool port that speed to any computer using ComfyUI. It works by keeping nearby frames perfectly detailed while using a lightweight method for distant context, which saves time without ruining quality. This means you can generate complex video sequences on your own hardware without needing a datacenter.

🆔 @hackernewsgithubprojects

📦 r44vc0rp/superlocal

Superlocal: One Inbox, Many Accounts

Superlocal merges every email account you own into a single, fast desktop interface. Instead of juggling separate tabs for Gmail, iCloud, or other services, you connect them all through one central gateway that keeps your passwords private while mixing your messages into one clean list. The coolest part is that it works right away with fake demo mail, so you can test the unified search and keyboard shortcuts without typing in a single real password. It treats your inbox like a local, secure hub where you control exactly which accounts show up and how they sync.

📰 https://news.ycombinator.com/item?id=49559198

🆔 @hackernewsgithubprojects

📦 obedience-corp/festival

Plan Once, Code Forever: The Memory for AI Agents

Hand your coding assistant a map that never fades. Festival solves the frustrating problem where AI agents forget exactly what they were doing the moment a session ends or a tab closes. Instead of starting from scratch every time, you define a structured plan once, and any agent picks up right where you left off, keeping the full context of your project alive across days or weeks. It turns fleeting chats into a persistent workflow that actually remembers the details. You stop re-explaining your architecture and start letting the bot execute the vision. Give your code a memory that lasts.

🆔 @hackernewsgithubprojects

📦 engneer-hamachan/area512

Area512

A tiny pocket computer with only five hundred and twelve kilobytes of memory now runs full Ruby and Python scripts compiled directly on the hardware. Area512 is a self-contained operating system for the M5Stack Cardputer that bundles a file manager, code editor, and terminal into one seamless environment. You can write code, compile it to bytecode, and execute it entirely on the device without needing a laptop. The project ships with practical tools like a spreadsheet and a word processor, alongside retro games, all optimized for the device’s limited resources.

📰 https://news.ycombinator.com/item?id=49399476

🆔 @hackernewsgithubprojects

📦 rootprint/rootprint

Rootprint: Own Your Logs

Keep your server logs on your own hardware with full-text search. Rootprint solves the problem of handing over your system data to expensive third-party services for basic tracking. It ingests your application logs and traces, then lets you dig through them with a fast, searchable interface. You get a clean dashboard to spot errors and understand exactly what broke, without any outside company reading your data. It’s a self-hosted, open-source tool that puts control back in your hands. If you want to see your own logs without renting someone else’s software, this is the tool to try.

📰 https://news.ycombinator.com/item?id=48368810

🆔 @hackernewsgithubprojects

📦 qiannianhuanxiang/dsha

Run a Full Linux Server in Your Pocket

Transform your smartphone into a full-fledged Linux server without needing root access or command line expertise. DSHA packages a complete Ubuntu operating system directly inside an Android app, allowing you to run complex AI coding agents right from your screen. The most surprising aspect is that this entire environment functions without the typical performance drag found in other phone-based solutions, delivering speed improvements comparable to dedicated hardware. It handles everything from file management to running native applications, ensuring your data remains safe even if the app is removed. This project turns a simple phone into a powerful, portable workspace.

🆔 @hackernewsgithubprojects

📦 morten-buur/nordef-matrix-open-control

Nordef Matrix Open Control

Nordef Matrix Open Control acts as a mechanical speed bump for artificial intelligence agents, ensuring they cannot drive themselves off a cliff. Built by Morten Büür and Eirik, this tool sits outside the model itself, meaning the A I cannot talk its way out of its own leash. It checks every action against a strict list, requiring a cryptographic human signature to proceed with anything risky. If the signature is missing or expired, the system simply stops. It also keeps a tamper-proof log of every decision, so nobody can quietly change the rules later. It is not a magic shield, but a clear, honest boundary.

🆔 @hackernewsgithubprojects

📦 ethanfel/comfyui-minimaxh3-context-loop

ComfyUI MiniMax H3 Context Loop

ComfyUI MiniMax H3 Context Loop is the ComfyUI pack that actually keeps motion and sound going across video joins. It builds longer stories by stitching separate generated clips together so they feel like one continuous take, not a jarring slideshow. The magic is in how it uses the ending of one clip to guide the start of the next, ensuring characters keep moving and audio flows naturally without breaking. This solves the biggest headache in AI video editing: making multi-scene projects that don't feel chopped up.

🆔 @hackernewsgithubprojects

📦 bam-bam-2/solo-skills

Solo Skills: AI Agents for Solo Founders

Solo Skills is the open-source kit that gives solo founders a full team of AI agents without hiring anyone. Built by a community leader who automated forty-nine solo tasks, this repository shares twenty-six ready-to-use agent skills that handle everything from generating product demo videos without screen recording to turning meeting transcripts into structured notes. Each skill acts as a step-by-step procedure that AI coding assistants can read and execute, turning repetitive busywork into automated workflows. If you run a one-person business, this is a practical way to reclaim your time by letting AI handle the operational grind so you can focus on growing your work.

🆔 @hackernewsgithubprojects

📦 openai/primegaps186

Primegaps 186

OpenAI has formalized the proof that prime numbers eventually get closer than one hundred eighty-six units apart in a machine-verifiable logic system. The project, called Primegaps 186, encodes a major number theory result in Lean four, a language designed so computers can check mathematical logic. It relies on a Python script that independently verifies the heavy computational parts, ensuring the proof is not just hand-wavy but rigorously checked. While the proof assumes a few deep results as starting points, the logic connecting them to the final gap bound is fully verified. It is a fascinating look at how we use code to audit high-level math.

📰 https://news.ycombinator.com/item?id=49555257

🆔 @hackernewsgithubprojects

📦 bernardogiordano/rewind

Rewind: Your Personal Spotify Wrapped

Rewind is the self-hosted listening recap that turns your Navidrome history into a shareable visual story. It reads directly from your own music server’s database to generate a slideshow of your top songs, artists, and late-night favorites. The standout feature is its ability to export every stat card as a high-quality image, so you can post your yearly review to social media without relying on a big tech company’s data. It works right out of the box with Docker, giving you full control over your private music analytics. If you run your own music server, this is the missing piece for celebrating your listening habits in style.

📰 https://news.ycombinator.com/item?id=47702944

🆔 @hackernewsgithubprojects

📦 osfv/bravedebloater

BraveDebloater: The Safe Way to Strip Bloat

Silently strip out Brave Browser's built-in extras by applying official enterprise policies. This project tackles the messy reality that most debloating scripts hack system files or break your browser. Instead, it uses the same policy system that companies use to manage browsers, ensuring every change is official, reversible, and safe. You get a dry-run preview by default, so nothing changes until you explicitly approve it. It also creates a backup before writing anything, meaning you can restore your browser to exactly how it was if you change your mind. It refuses to disable Shields or updates, so you keep your security while losing the noise.

📰 https://news.ycombinator.com/item?id=48530920

🆔 @hackernewsgithubprojects

📦 zhaoyx239/x-translator

X-Translator: Real-Time Voice Translation

Speak in one language and hear instant translation in another without typing a single word. X-Translator bridges the gap between hearing and understanding by piping live audio into a smart pipeline that recognizes speech, converts the meaning, and synthesizes a new voice. It doesn't just read out text; it keeps track of who is speaking so the translated audio maintains distinct vocal identities for each person. You get to see the original words, the translated text, and listen to the synthesized speech all at once in your browser. It’s a neat peek into how real-time multilingual conversation is actually built.

🆔 @hackernewsgithubprojects

📦 ryze-ai-adgent/open-seo-mcp-skills

Open SEO MCP Skills: Real Data, No Estimates

Hand your AI assistant the keys to your actual Google Search Console and Analytics, and watch it run a professional SEO audit without guessing a single number. Open SEO MCP Skills connects Claude directly to your real ranking data and keyword volumes, so you get precise insights on where you are losing traffic or overpaying for ads. The most fascinating part is its ability to track exactly which pages AI engines like ChatGPT are sending people to, giving you a clear look at your visibility in AI search. It is completely free and open source, meaning you own the code and the data.

🆔 @hackernewsgithubprojects

📦 sh1nzzz/on_the_fly3r

On-the-Fly3R Builds Maps Live From Drone Videos

On-the-Fly3R builds detailed three-dimensional maps from drone video streams in real time, processing new images as they arrive without needing to re-analyze the entire footage from scratch. This framework solves the massive computing problem of scanning huge, ever-growing scenes by intelligently picking only the most relevant images to process at any given moment. It uses modern artificial intelligence models to stitch these snippets into a consistent global map, ensuring accuracy even over long distances. This makes it possible to monitor vast areas with live spatial awareness rather than waiting for a slow batch process after the fact.

🆔 @hackernewsgithubprojects

📦 facebookresearch/midtraining-distillation

Midtraining Distillation: The Logic Trick

Standard knowledge distillation during mid-training makes models better at reasoning but worse at remembering facts. Meta’s midtraining distillation project introduces a method called Switch Distillation that solves this tradeoff. It only uses the teacher model to guide the student on the hardest, most uncertain words, leaving the rest to learn normally. This keeps the reasoning gains without sacrificing factual recall. If you are building language models, this is the fix for a problem you did not know you had.

🆔 @hackernewsgithubprojects

📦 lnkiai/m3e-canvas

M3E Canvas: The Browser Sketchpad for AI Coding Prompts

Drag buttons, cards, and sliders onto a canvas to sketch out a full mobile app interface right in your browser. M3E Canvas is a design tool that lets you arrange Material Design components, link screens together, and preview the user flow before you write a single line of code. The magic happens when you are done sketching: the app translates your entire design into a concise, natural-language prompt. You copy that text, paste it into an AI coding tool, and the AI builds the actual application for you. It is a clever bridge between visual design and AI development, turning your rough ideas into working code without the usual back-and-forth.

🆔 @hackernewsgithubprojects