📦 jxy333967/jianxunyun

Jianxunyun: Your Guide to Stable Access

Keep your online access stable and private with Jianxunyun, a dedicated virtual private network service. Instead of guessing which server works, this repository serves as your personal cheat sheet for every official entry point. It lists the main websites and specific backup domains you need if the primary links get blocked. This is incredibly useful because digital services change addresses frequently, and having a static reference means you never lose your account or subscription data. You can switch between these addresses instantly to bypass regional restrictions. It is a simple, practical tool for anyone needing reliable, secure connectivity without the hassle of digging through forums.

🆔 @hackernewsgithubprojects

📦 sandflow-ai/sand3d

sand3d: 3D Modeling in Python for AI

sand3d is the 3D modeling library that lets AI build complex objects with surprisingly short code. It turns Blender into a text-based toolkit where a language model writes a few simple lines to create a whole machine, like a washing machine, in under forty lines. This is powerful because the entire instruction set fits inside an AI prompt, meaning a model can generate and explain a 3D design in plain, readable Python. It is not just for static shapes; it handles moving joints and parts, making it perfect for building robotic assets and game-ready models.

🆔 @hackernewsgithubprojects

📦 livliv-dev/player

LivLiv Player: Your Webcam Avatar

Drop an animated character onto your website with just a few lines of code. This is LivLiv Player, a tiny tool that brings two dimensional avatars to life right in your browser. The coolest part is that you can plug in your webcam, and the character mirrors your real-time facial expressions. It tracks your face locally on your device, so your avatar smiles, blinks, and talks just like you do. It is incredibly lightweight, with no heavy dependencies, making it perfect for adding a personal touch to stream overlays or interactive pages. No need for expensive software.

🆔 @hackernewsgithubprojects

📦 kingdaswinx/templum

Templum: Your AI Agents on One Canvas

Templum turns your computer screen into a giant digital whiteboard where you can pin down as many terminal windows as you want. You can drag them around, zoom out to see the big picture, or snap them together like a puzzle. The coolest part is that it acts as a bridge for your artificial intelligence coding tools. You can literally draw a cable from an AI agent to a to-do list or a note, allowing the robot to read your plan and start typing code into a terminal next to it. It is built with Rust and runs directly on your graphics card, so it feels snappy and native.

🆔 @hackernewsgithubprojects

📦 sawyerhood/do-computer

Do Computer: Your Own Personal AI Agent

Give your AI assistant a real computer to work on. Do Computer is an open-source project that lets you host your own always-on personal agent, called a Dood. Unlike standard chatbots that forget everything when you close the tab, this agent keeps running, remembers your preferences, and can even execute code on a machine you control. It is fascinating because it puts the power of a persistent, self-hosted AI worker directly in your hands without relying on a single corporate cloud. You get a customizable agent that learns skills, manages schedules, and connects to your favorite tools. It is your own digital partner, ready to work whenever you need it.

🆔 @hackernewsgithubprojects

📦 athei/mtld3d

Play Windows Games on Mac with Metal

mtld3d lets you run older Windows games directly on macOS by translating their legacy graphics code into Metal, Apple’s native language for high-speed rendering. It swaps out the standard compatibility layer with a custom engine that handles the heavy lifting right on your Mac’s hardware, bypassing the usual slowdowns. The most exciting part is how it runs these programs without needing a full virtual machine, keeping everything fast and responsive. You get true performance improvements rather than just running old software in a box. This project is a great example of how much further we can push cross-platform gaming.

🆔 @hackernewsgithubprojects

📦 kanapitsas/portal2-recomp

Portal 2 on iPhone

Play Portal 2 natively on your iPhone and Apple Silicon Mac without an emulator. This project rewrites the game’s original computer instructions into code your device runs directly, eliminating performance penalties from translation layers. The most surprising feature is firing portals by tapping the back of your phone, turning your device's physical shape into part of the puzzle-solving experience. It handles graphics and networking directly on your hardware, allowing smooth gameplay and local multiplayer with another phone or computer. You simply need your own copy of the game to build this. If you love classic puzzles, this is a fascinating look at running old games on modern hardware.

🆔 @hackernewsgithubprojects

📦 majorminorlabs/hermes-voice

Hermes Voice: Talk to Your AI Agent

Hermes Voice is the home integration that lets you talk to your personal AI agent using just your voice. Instead of typing into a chat box, you simply say Hey Hermes to an old Amazon Echo, and your custom agent responds out loud. It connects Home Assistant to your specific AI profile, meaning the assistant remembers your preferences and keeps the conversation flowing naturally. You can even set it up so your agent controls your lights or searches the web while you speak.

📰 https://news.ycombinator.com/item?id=50381927

🆔 @hackernewsgithubprojects

📦 cvg/flexglue

FlexGlue: The Image Matcher That Knows When to Stop

FlexGlue is the image matching model that knows when two pictures are actually the same place. It solves a tricky problem where look-alike buildings or repeated patterns fool standard software into thinking they match when they do not. Instead of blindly connecting points, this tool predicts if the images show the same scene and stops working early if they do not. This saves time and prevents false connections. It handles tricky lighting and angles with ease. You get a cleaner result without the extra noise. This is a smart way to handle complex visual data. It is built for real world reliability. Trust your results more.

🆔 @hackernewsgithubprojects

📦 tradertanmay/ai-agents-zero-to-hero

AI Agents: Zero to Hero

AI Agents: Zero to Hero is the Python curriculum that strips away framework magic to show you exactly how autonomous agents work from first principles. It replaces opaque black-box tools with a clear, code-first path that walks you through the observe-decide-act loop using only standard Python. The surprising strength here is its zero-dependency approach, meaning you can build, run, and debug a complete agent loop without installing heavy packages or managing API keys. This gives you a deep, framework-independent understanding of memory, tool calling, and safety before touching real production systems. It is the clearest way to move beyond buzzwords and actually build intelligent software you can trust.

📰 https://news.ycombinator.com/item?id=49973196

🆔 @hackernewsgithubprojects

📦 tiptreesystems/lacuna-research-mcp

Lacuna Research MCP

Lacuna Research MCP is the knowledge bridge that turns your coding agent into a full-time research assistant. It plugs into your favorite editor to search through millions of machine learning papers, authors, and venues. The coolest part is that it traces code repositories back to their original academic papers, so you know exactly where every tool came from. It also surfaces AI generated research proposals, giving you fresh ideas before you start coding. It is a map of the entire field, making it easy to find prior work and avoid reinventing the wheel.

🆔 @hackernewsgithubprojects

📦 giveen/decomp.anything

Turn Any Binary Into Readable Code

Reverse engineer any software by letting an AI agent write C code that compiles to the exact same bytes as the original program. The tool splits a binary into small pieces, then has the agent guess the source code for each part. It uses the original compiler to build the guess and compares the output byte by byte until they match perfectly. If they do not match, the agent sees the difference and tries again. This works for old games, Windows apps, and Linux tools. It runs entirely on your own computer, so your files never leave your machine. No account needed, no cloud, no privacy trade-offs.

🆔 @hackernewsgithubprojects

📦 bytedance/axion1_0

Axion 1.0: The Simple Agent Recipe

Axion 1.0 shows you how to build a top-tier AI agent using just two training steps and high-quality data, skipping all the complicated middle stages that usually make these projects messy. It turns out that if you give the model really good problems and let it learn from its own success, you get a system that can handle complex science and tool use just as well as the biggest closed models out there. The team released the entire recipe so you can see exactly how they did it without any hidden tricks. It proves that you don't need a massive, opaque pipeline to create something powerful.

🆔 @hackernewsgithubprojects

📦 jdx/mr-boxington

mr boxington

Your Rust build cache now works across different folders. The tool called mr boxington remembers what your compiler finished so you never have to compile the same code twice. Usually, if you copy a project into a new folder, your computer starts over from scratch. mr boxington fixes this by keeping a shared library of finished work. It fits right into your normal build process, so you just run your usual commands and wait less. It also cleans up old files automatically to save space. If you build many projects at once, this tool stops them from fighting over your computer’s resources.

📰 https://news.ycombinator.com/item?id=50382046

🆔 @hackernewsgithubprojects

📦 beipo-ai/northcua

NorthCUA: The Agent That Actually Works

Run real computer tasks on your desktop and in the browser, then actually verify the result. NorthCUA is an open-source harness that gives an AI agent the tools to click, type, and navigate, but the real kicker is the built-in evaluator. It doesn't just trust the agent’s word that the job is done; it independently inspects the live workspace and the final artifacts to check the work. It even remembers context across long tasks and lets you recover a whole batch of jobs if one step fails. It turns a brittle, one-off script into a reliable, auditable workflow.

🆔 @hackernewsgithubprojects

📦 direct-img/vibegif.direct-img.link

The Zero-Click Public Domain GIF Library

A single repository serves as the source code for a gallery of thousands of animated images that are completely free to hot-link. No copyright claims, no attribution requirements, and no hidden terms. The most surprising capability is that you can copy the direct link to any specific animation and paste it straight into your own project, blog, or chat window. It works instantly without needing to download or host the file yourself. This solves the endless headache of searching for safe, usable graphics that won’t get taken down. You get a reliable, permanent resource for quick visual communication.

🆔 @hackernewsgithubprojects

📦 millillion/lasm

Lasm: Lean on the Web

lasm is the runtime that finally runs Lean code right inside your browser and Node.js. It bridges the gap between a rigorous mathematical programming language and the fast, sandboxed world of WebAssembly. Imagine writing a web server or a complex calculation in Lean, then deploying it to Cloudflare Workers without needing a heavy C compiler or native dependencies. It handles file systems, networking, and even HTTP requests directly from Lean, giving you the safety of formal proofs with the portability of the web. If you have ever wanted to run trustworthy, verifiable logic in a serverless environment, this project is your ticket to a safer, more precise JavaScript stack.

📰 https://news.ycombinator.com/item?id=50299004

🆔 @hackernewsgithubprojects

📦 auryg/krea-2-two-stage-sampler

Krea 2 Two Stage Sampler

Krea 2 Two Stage Sampler lets you mix two different AI models in the middle of an image generation. Usually, you pick one model and run with it. Here, you run a raw, base model for the first few steps to get a wild, varied sketch, then hand off to a turbo model for the final steps to sharpen the details. It’s like drafting in pencil and then inking in pen, all in one seamless pass. This saves time and often boosts quality, since you get the creative chaos of the raw model and the speed of the turbo finish.

🆔 @hackernewsgithubprojects

📦 snarktank/ralph

Ralph: The AI Loop That Finishes Your Code

Ralph is the autonomous coding loop that finishes your project by itself. Instead of a single chat session that forgets everything, Ralph spins up a fresh AI worker for each small task, letting them pick up exactly where the last one left off. It reads your requirements, writes the code, runs the tests, and only moves on when the work is actually done. If it gets stuck or needs to learn something new, it saves those notes to a file so the next iteration can use them.

🆔 @hackernewsgithubprojects

📦 sksarvesh007/antiglaude

Antiglaude: Run Claude Code on Gemini

Plug Claude Code directly into Google Gemini models using Antiglaude. This local bridge speaks the exact language your coding assistant expects, translating every request into a format Google can process instantly. It handles the messy parts like token refreshes and connection drops so you don't have to think about them. You get a live terminal dashboard to track your usage and switch models on the fly with a single command. It is the perfect way to test powerful reasoning models without changing your existing setup. If you want to mix and match AI engines without the headache, this is your gateway.

🆔 @hackernewsgithubprojects