69 subscribers
7.59K videos
8.2K links
Download Telegram
This media is not supported in your browser
VIEW IN TELEGRAM
πŸ“¦ philolabs/fable51-worlds

Fable 51 Worlds: Anime Streets in Your Browser

Fable 51 worlds is the code-based tool that turns a simple text prompt into a fully walkable, anime-styled 3D environment. Instead of downloading heavy game assets, this project generates every building, tree, and street detail directly through code using Three.js. The most surprising part is how it creates places like Kyoto’s Higashiyama district without using any pre-made 3D models. It builds the entire scene from scratch, drawing every texture with canvas code so it looks like a hand-painted animation background. You can walk through these digital streets right in your web browser. It is a fascinating look at how code can replace traditional 3D modeling pipelines.

πŸ“° https://news.ycombinator.com/item?id=49541458

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

Cotal: The Shared Space for AI Agents

Cotal is the open standard that lets any number of AI agents coordinate in a shared space where you define the structure. Most tools force a rigid hierarchy, but Cotal lets you build flat teams, supervisor trees, or complex swarms using a simple configuration. The real magic is that every agent can see who else is online and message them directly, whether broadcasting to a group or sending a private note that waits until the recipient is ready. This turns isolated bots into a collaborative team that works across different machines and providers.

πŸ†” @hackernewsgithubprojects
This media is not supported in your browser
VIEW IN TELEGRAM
πŸ“¦ xiaopu-ai/web-design

Web-Design: AI Web Design That Actually Works

Web-Design is the AI coding skill that forces your design decisions to happen before the code does. Instead of blindly generating random interfaces, it extracts a clear, editable design document from a product spec, a website link, or even a single screenshot. This file locks in your colors, typography, and motion rules so the code follows a strict plan rather than guessing. The result is a web page that stays consistent across every page you build, while remaining easy to tweak by hand. It turns the unpredictable nature of AI coding into a controlled, professional design process that you can actually read and own.

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

OpenCode Meets Command Code: The Provider Plugin

Connect your favorite coding assistant to every Command Code plan using a single, simple plugin. This tool plugs directly into OpenCode, giving you instant access to a wide variety of models without needing to juggle multiple subscriptions or complex manual configurations. The real surprise here is how it handles pricing; it automatically pulls in detailed deal intelligence, showing you exactly what you are getting, from peak discounts to monthly allowances. It even works entirely offline, ensuring your setup never breaks just because a website is down. You get a clean, unified experience that keeps your costs transparent and your workflow smooth.

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

sanoTTS: A Voice That Lives On A Chip

Turn plain text into a natural human voice right on a three dollar microcontroller or in your web browser without sending anything to the cloud. sanoTTS is a family of tiny neural networks that fit in just a few megabytes, allowing you to build speaking devices that work completely offline. The real magic here is how small it gets; the heart nano model uses only two hundred and ninety four thousand parameters, packing an entire text to speech system into three hundred and thirty seven kilobytes. This means you can get high quality audio synthesis on hardware that costs less than a sandwich.

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

Khora: The Smart Memory for AI Agents

Khora is a Python library that gives AI agents a proper brain, not just a notebook. It takes messy data from different sources, breaks it down into people, places, and events, and stores it in a connected knowledge graph. Instead of just searching for matching words, it answers questions by walking through those connections to find the real answer. This is perfect for support bots or research assistants that need to remember context over long conversations. It plugs into popular frameworks like LangGraph and LlamaIndex, so you can drop it into your existing agent setup.

πŸ“° https://news.ycombinator.com/item?id=48465131

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

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

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

πŸ“° https://news.ycombinator.com/item?id=48771562

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

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

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

πŸ“° https://news.ycombinator.com/item?id=49559198

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

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

πŸ“° https://news.ycombinator.com/item?id=49399476

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

πŸ“° https://news.ycombinator.com/item?id=48368810

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

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

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

πŸ†” @hackernewsgithubprojects
πŸ‘Œ1
This media is not supported in your browser
VIEW IN TELEGRAM
πŸ“¦ 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.

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

πŸ“° https://news.ycombinator.com/item?id=49555257

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

πŸ“° https://news.ycombinator.com/item?id=47702944

πŸ†” @hackernewsgithubprojects