📦 mateussmeneses/theorder1886-port

The Order 1886 PC Native Port

Run a PlayStation game directly on your Windows PC without any CPU emulation. The Order 1886 PC Native Port lets you play this exclusive title natively, meaning the processor executes the original game code exactly as it was designed for the console. Since the PlayStation hardware uses the same architecture as modern computer chips, the game runs at full speed without the usual performance penalties of traditional emulators. The only translation needed happens in the graphics engine, which converts visual instructions so your modern graphics card can display them.

🆔 @hackernewsgithubprojects

📦 agent2api/agent2api

Agent2API: One Key for Every AI

Your computer already holds the login credentials for multiple artificial intelligence clients, but those sessions are locked away inside separate apps that talk to each other in different languages. Agent2API changes that by running locally on your machine and turning those existing logins into one standard, universal interface. It acts like a smart translator, allowing any tool you use to connect to all those services at once without needing new accounts. The most surprising part is that it strips away identifying details from your requests, so you can use your subscriptions freely while keeping your digital footprint private.

🆔 @hackernewsgithubprojects

📦 soumatheusgomes/editonny

Edit Video By Talking: Editonny

Editonny is the local video editor that edits your clips just by listening to you. It plugs directly into your AI coding agent, meaning you stop clicking through timelines and start describing your vision in plain English. The coolest part is that it runs entirely on your own machine, keeping your private footage safe while handling the heavy lifting like cutting awkward pauses and adding crisp captions. It even turns your spoken words into animated motion scenes, giving your video a professional rhythm without touching a single slider. No cloud uploads, no complicated timelines, just a conversation. If you want to edit faster, this is the tool that actually listens.

🆔 @hackernewsgithubprojects

📦 llamaboi55/dragshift

DragShift: The Glassy Drag-and-Drop Menu

Drag any file, press Shift, and a glowing, liquid-glass radial menu pops up right under your cursor. DragShift turns that simple gesture into a full editing suite for Windows, Mac, and Linux, letting you convert images to PDFs, compress files, or annotate documents without opening a single app. The coolest part is the visual effect; the menu actually refracts the screen behind it, bending light like real glass. It’s a slick, free tool that makes file handling feel like magic. Give it a spin and your file management just got a whole lot more fun.

🆔 @hackernewsgithubprojects

📦 harkhowalia-1/macsubsystemforandroid

Mac Android Subsystem for Mac

Double-click an APK file and watch a full Android app open in its own Mac window with a real Dock icon. Mac Android Subsystem makes this happen on Apple silicon by quietly running Android in the background at near native speed. You get Mac-style notifications, copy-paste, and game controller support, making it feel like a true part of your Mac. It is free and open source, built on LineageOS, QEMU, and scrcpy. This is a fascinating look at how a Mac can host a whole Android world without the usual emulator slowdown.

🆔 @hackernewsgithubprojects

📦 zjwfufu/smd

SMD: 4-Step AI Generation

SMD is the diffusion toolkit that makes high-end AI generation run in just four steps. Typically, creating a single image or video requires dozens of calculations, but this project uses a technique called on-policy distillation to teach a smaller model to match the quality of a larger one. It works across text-to-image, video, audio, and three-dimensional assets, meaning you can generate complex media without the usual computational wait. This is useful for developers who need speed and efficiency without sacrificing output fidelity. The result is a faster, lighter way to create digital content that looks and feels just as good as the heavy original models.

🆔 @hackernewsgithubprojects

📦 seacen/meetcap

MeetCap: The Private AI Meeting Assistant

MeetCap is the free meeting assistant that keeps your conversations entirely on your computer. It listens to calls, records audio locally, and uses artificial intelligence to write clear meeting notes without sending your data to a cloud server. The standout feature is that it lets your AI agent drive the process, so you can ask your assistant to record a call or search past meetings for specific details like supplier prices. It even explains new terms as they come up so you never miss a beat.

📰 https://news.ycombinator.com/item?id=50147993

🆔 @hackernewsgithubprojects

📦 heyongjun666/aicu-graph

AICU Graph: The AI Team That Builds Itself

Turn a messy goal into a living map of AI workers. AICU Graph analyzes your task and instantly builds a team of different roles to handle it together. It does not just guess; it creates a visual graph where every step is a real, running agent. You can watch them collaborate, fix errors, and deliver actual results. It is like hiring a whole department in seconds, just to get complex work done. This is how you scale your ideas without hiring another human.

📰 https://news.ycombinator.com/item?id=50054253

🆔 @hackernewsgithubprojects

📦 jize-w/awesome-world-model-interpretability

Awesome World Model Interpretability

Researchers just released a comprehensive guide to understanding the inner workings of the most advanced predictive AI systems. The repository Awesome World Model Interpretability collects every key paper on how we can look inside these models to see how they learn to predict the future. It focuses on a specific type of architecture called Joint-Embedding Predictive Architectures which learn abstract internal maps of the world instead of just copying raw data. The collection includes a new perspective paper that argues simply looking at the output is not the same as understanding the model.

🆔 @hackernewsgithubprojects

📦 flashrt-project/flashrt

FlashRT: Run AI Robots in Real Time

FlashRT lets robotic arms move in real time by running AI brains on tiny, fast chips. Standard software is too slow for physical robots, causing hesitation and failure. This engine uses hand-written code to squeeze maximum speed out of hardware like NVIDIA GPUs and AMD processors. It turns a slow twenty-six-hundred-millisecond decision into a snappy twenty-two-millisecond one. This allows a robot to react to the world instantly, making it safe and practical for real use. If you are building physical AI, this is the engine that makes it possible.

🆔 @hackernewsgithubprojects

📦 openchamber/opencode-claude

Use Claude Pro in OpenCode

Plug your existing Claude Pro or Max subscription directly into OpenCode and OpenChamber. Instead of juggling a separate API key, this tool turns your local Claude Code terminal login into a provider that sits right inside your editor. It works by quietly running the official agent software beneath the surface, so you get full access to powerful models like Opus and Sonnet without buying extra credits. The best part is that it keeps your login secure and never touches your password. You just pick a model from the list and start coding. If you are tired of paying twice for AI access, this is the clean fix you need.

🆔 @hackernewsgithubprojects

📦 storytold/artcraftx

One App, Every AI Model

ArtCraft-X is a desktop application that connects you directly to a wide variety of AI generation services without needing separate accounts for each one. Instead of juggling different websites for images, videos, or 3D models, this tool brings them together into a single, clean interface. It handles the technical complexity of connecting to these providers in the background, letting you focus purely on your creative prompts and output. By unifying these tools, it simplifies the workflow for creators who want to experiment with different AI styles and formats. If you have ever wanted to switch between models without switching apps, this project is built exactly for that.

🆔 @hackernewsgithubprojects

📦 victortaelin/uniichat

UniiChat: The Chat That Never Ends

UniiChat is the single-thread AI assistant that finally solves the problem of context rot. Instead of starting fresh every time, it stores every message you send into a permanent memory tree that compresses older details into broad summaries while keeping recent thoughts sharp. This means the agent can remember specific things you asked about years ago without losing its place in the current conversation. The system runs on your own hardware using standard model providers, letting you build a personal AI that grows with you over time.

🆔 @hackernewsgithubprojects

📦 hybirdss/hycli

Hycli: Turn Websites into AI Tools

Hycli is the website tool that makes your entire web presence available to your AI without risking your account. It works by quietly inspecting a site’s structure and your actual browser login to build a set of safe, typed commands for your assistant. The coolest part is how it handles writes. It figures out how to create or edit things on a site but refuses to actually do it until you explicitly say yes. This means your AI can search, read, and plan changes using your real data, while keeping your login secrets locked inside your computer so they never leak to the model.

🆔 @hackernewsgithubprojects

📦 ely-open-source/elyoffice

Ely Office: The Offline Desktop Suite

A full office suite written in Rust runs entirely on your computer without a single ping to a server. That is exactly what Ely Office provides. It is a collection of desktop applications for documents, spreadsheets, mail, and presentations, all built to work offline. The team chose Rust for speed and safety, pairing it with a custom graphics engine to make the apps feel native and fast. This means your work stays on your machine, protected from cloud outages and privacy concerns. It is a local-first alternative to the heavy web-based tools we all use every day.

🆔 @hackernewsgithubprojects

📦 hugo-dz/spritefusion-sprite-normals

Give Flat Sprites Real Depth with Sprite Fusion Sprite Normals

Take any flat pixel art sprite and instantly give it the illusion of three-dimensional depth. This tool, called Sprite Fusion Sprite Normals, solves a specific problem for game developers: it turns simple, two-dimensional images into normal maps that allow them to react realistically to dynamic lighting. The surprising part is how it works; the software analyzes the shape and painted shading of your artwork to calculate a fake surface relief, meaning your sprites can cast shadows and catch light just like physical objects do. It handles single images, sprite sheets, and animated sequences, keeping the original pixel resolution and transparency intact.

🆔 @hackernewsgithubprojects

📦 mnemon-dev/mnemon

Mnemon: Memory for AI Agents

Your coding bot forgets everything the second you close the tab. That is the biggest annoyance in modern development. Mnemon fixes this by giving your artificial intelligence a permanent brain that actually thinks. Instead of shoving every sentence into a massive, slow database, it stores facts as a connected web of ideas. When your agent works, it asks what it already knows before guessing. This means it remembers your project structure and past decisions across different tools. It is a single, local file with no cloud subscriptions or extra keys. It simply plugs into the bot you already use. The result is an assistant that actually knows your codebase.

🆔 @hackernewsgithubprojects

📦 miaai-lab/deepseek-v4.1-flash-1017-2x-dgx-sparks

DeepSeek on Two Sparks

DeepSeek V4.1 Flash is the dual chip setup that turns two small desktop units into a massive local server. Instead of buying one giant expensive machine, you link two compact devices with a direct high speed cable to share the heavy lifting. The coolest part is that you can run a full one million token window on this modest hardware. That means you can feed in huge documents or long conversations without the system forgetting what you said at the start. It handles images and complex tools right out of the box. You just run one simple script to start everything up.

🆔 @hackernewsgithubprojects

📦 deepclause/deepclause-sdk

DeepClause SDK: The Self-Modifying Agent

Build an artificial intelligence agent that writes its own source code. DeepClause SDK is a TypeScript library that runs an interactive terminal where you speak plain English to an AI. Instead of returning a static answer, the agent edits a live Prolog program that serves as the agent's own brain. This program defines every tool, memory, and logic rule the agent uses. Because the agent modifies its own underlying code, it can instantly learn new skills and adapt to your specific task. You can even watch it think, test its changes, and roll back mistakes with a single command.

🆔 @hackernewsgithubprojects

📦 da7-tech/mind

Mind: The Brain for Your AI Coder

Give your AI coding assistant a brain that actually remembers what you told it last week. Mind is a single Python file that acts as persistent memory for your agents, solving the annoying problem of them forgetting context or hallucinating old details. It automatically captures decisions, links related concepts, and even runs a nightly dream cycle to consolidate what matters while pruning the noise. The coolest part is that it runs entirely offline with zero dependencies, meaning your code and context never leave your machine. It is simple, private, and genuinely useful.

🆔 @hackernewsgithubprojects

📦 heychengc/wallstreet-explainer

Wallstreet Explainer

Turn any financial question into a polished, cinematic video. This project provides a complete toolkit for creating those high-end, Wall Street-style explainers, handling everything from sourcing real news footage to rendering the final frame. The coolest part? It uses code to build a three-dimensional visual stage where giant numbers and real people interact, making complex data actually make sense. You get scripts for finding assets, cutting out specific speakers from interviews, and mixing audio, all designed to keep the pacing tight and professional. It’s less about writing code and more about giving your AI assistant a strict creative brief.

🆔 @hackernewsgithubprojects