📦 kalcode/spaceprojectsim

Spaceprojectsim

Watch an entire galactic civilization run itself in a gorgeous, self-operating universe built with Rust and Bevy. Instead of playing a typical game, you act as a god-mode observer monitoring hundreds of autonomous ships that trade, mine, and accept contracts based on real-time AI planning. The most incredible part is the dynamic economy, where prices aren't fixed; instead, markets price thirteen different commodities using actual shortages and local demand. When supplies run low, prices skyrocket, and autonomous cargo haulers dynamically recalculate their flight paths to chase the profit. It is a living, breathing model of cosmic capitalism right on your screen.

📰 https://news.ycombinator.com/item?id=48996187

🆔 @hackernewsgithubprojects

📦 decrazyo/anes

anes

Anes is the hardware modding project that turns a classic Nintendo Entertainment System into a dual-chip graphical powerhouse. By desoldering chips from a donor console and combining them onto a custom daughterboard, this hardware modification wires two picture processing units into a single system. The second chip effectively doubles the visual capabilities of the retro console, unlocking deeper colors, many more simultaneous on-screen sprites, and actual hardware-driven parallax scrolling. While it requires serious soldering skills, the project opens up a fascinating look at what classic gaming hardware can do when pushed beyond its original design limits.

📰 https://news.ycombinator.com/item?id=48652997

🆔 @hackernewsgithubprojects

📦 lidge-jun/opencodex

OpenCodex

You can now run any AI model you want inside Codex and Claude Code. A tool called opencodex acts as a clever local proxy that translates the Codex API into the language of other providers. Instead of being locked into default models, you can instantly route your development tasks to Claude, Gemini, DeepSeek, or even your own local Ollama models. It supports streaming, tool calling, and complex reasoning on the fly, and you can manage everything from a simple web dashboard. It is the ultimate way to bring your favorite AI brain to your existing coding workflow.

📰 https://news.ycombinator.com/item?id=49012330

🆔 @hackernewsgithubprojects

📦 owasp/www-project-agent-memory-guard

OWASP Agent Memory Guard

Stop hackers from poisoning your AI agents by protecting their long-term memory. When an AI saves a conversation, an attacker can sneak in malicious instructions that hijack the agent on its very next run, even if you clear the chat history. To stop this, www-project-agent-memory-guard sits directly between your agent and its storage, scanning every single read and write. It blocks prompt injections, redacts leaked secrets, and prevents unauthorized system setting changes in just microseconds. Best of all, it runs completely locally with no external API calls, keeping your AI secure, compliant, and under your control.

📰 https://news.ycombinator.com/item?id=48342710

🆔 @hackernewsgithubprojects

📦 macpaw/cleanmymac-cli

CleanMyMac CLI

Reclaim gigabytes of wasted storage directly from your terminal by targeting bloated caches, old build artifacts, and heavy project dependencies in seconds. This clever command-line tool searches out developer junk from Xcode, Docker, package managers, and AI tools, gathering all those hidden digital leftovers into a clean interactive dashboard. You can easily hunt down massive folders like node_modules, analyze your overall disk usage, and even free up inactive RAM with simple commands. The best part is that nothing gets deleted without your explicit approval, meaning your actual source code remains completely safe. Install it with Homebrew to keep your environment running fast.

🆔 @hackernewsgithubprojects

📦 codedpro/mt5-trade-split-manager

MT5 Trade Split Manager

mt5-trade-split-manager is the MetaTrader 5 companion that finally bridges professional trading terminals with modern artificial intelligence. Instead of manually clicking through complex trade panels, you can let an AI agent like Claude parse your simple text signals and execute trades for you. Its best trick is intelligent order splitting, which automatically divides a single trade into up to ten distinct positions, each with its own target. This means you can lock in majority profits early while keeping your remaining positions running completely risk-free. It is a brilliant way to make advanced money management entirely hands-free.

🆔 @hackernewsgithubprojects

📦 donkruger/kanban

Kanban

Your project management board can live entirely on your own hard drive as plain Markdown files. Kanban is a local-first desktop application that bypasses servers, accounts, and cloud databases altogether. It gives you complete sovereignty over your data, storing your entire board history in readable, portable local files. Because it is completely offline by default, there is no telemetry tracking your work. It even features an embedded terminal designed to work with local AI coding agents without ever storing or uploading your API keys. It is the perfect, secure tool for developers who want to organize their workflow privately and keep total control over their files.

🆔 @hackernewsgithubprojects

📦 suvitruf/unity-arcanum

Unity Arcanum

Bring classic isometric role-playing games back to life on a modern engine. This project is a brilliant, clean-room reimplementation of the legendary engine behind Arcanum, built entirely from scratch in Unity six. Instead of modifying or redistributing copyrighted files, this clever system reads the original game's data files directly at runtime to stream maps, render dynamic day-night lighting, handle turn-based combat, and build composite character sprites on the fly. It is a massive love letter to classic RPGs that makes the original game fully moddable and ready for modern hardware. Grab your original game files, and let the magic begin.

🆔 @hackernewsgithubprojects

📦 gnhen/midscroll

Midscroll

Linux users can finally have the fluid, click-and-drag page scrolling that Windows users have taken for granted for decades. A clever utility called midscroll brings that exact middle-mouse autoscroll behavior to your Linux desktop. By capturing mouse inputs at the kernel level, it works smoothly across both Wayland and X11 in every single app you run. It uses Chromium's actual scrolling formula, meaning tiny drags crawl while a quick tug flies down the page. It even pauses itself automatically when you switch to games or CAD software that rely on native middle clicks, giving you the perfect, seamless navigation experience Linux was missing.

🆔 @hackernewsgithubprojects

📦 chrisjz/universe

Universe

Scroll through forty-three orders of magnitude in one continuous zoom, flying from the edge of the observable universe straight down to a single proton. This interactive atlas maps the cosmos in true scale using high-performance browser graphics, combining real astronomical catalogs with street-level terrain data. You can watch constellations shift over thousands of years, track the International Space Station, or watch the moon shadow block out the sun during real-time eclipses. It solves the massive challenge of rendering cosmic distances alongside atomic structures on a single screen without loading screens. Open it up and enjoy a breathtaking, scientifically accurate tour of our entire reality.

🆔 @hackernewsgithubprojects

📦 harbor-framework/frontier-bench

frontier-bench

Artificial intelligence agents can write essays and generate images, but they still struggle with complex, multi-step computer tasks like debugging real codebase leaks, managing active database cutovers, or routing photonic waveguides. A project called frontier-bench solves this by creating an evolving suite of demanding, real-world computer tasks to measure exactly what these agents can get done. Instead of simple toy tests, it challenges digital assistants with highly technical, practical problems across software, physics, and operations to see where they fail. It gives developers a clear, objective yardstick to evaluate agent performance, helping us understand when AI is truly ready for complex office work.

🆔 @hackernewsgithubprojects

📦 prism-shadow/penguin-harness

penguin-harness

Build and optimize fully functional AI assistants from a single text prompt using penguin-harness. Instead of stitching together complex pipelines manually, this zero-code tool lets AI agents build other AI agents for you. You can type out a single sentence, and the system automatically generates the scaffold, code, and running instructions for a complete application in seconds. It even benchmark-tests and refines itself over time to boost accuracy, all while running on open models for a tiny fraction of the usual cost. It is a brilliant way to experiment with self-evolving AI apps without the massive development headache.

📰 https://news.ycombinator.com/item?id=49015242

🆔 @hackernewsgithubprojects

📦 mmlcourse4all/mml

Mathematics for Machine Learning Study Guide

Most people struggle with machine learning not because of the coding, but because the underlying math feels like an impenetrable wall of symbols. This community-driven study guide acts as a friendly map to help you conquer the essential mathematical foundations before you even touch an algorithm. It focuses strictly on the core concepts you actually need to understand what is happening under the hood, saving you from wasting months on irrelevant textbook chapters. It is essentially a shortcut to building real mathematical confidence, making your next steps in AI infinitely easier to understand.

🆔 @hackernewsgithubprojects

📦 qoery-com/pmxt

pmxt

pmxt is the unified tool that finally brings a single, standard interface to the fragmented world of prediction markets. Instead of fighting with unique APIs, strange data structures, and completely different workflows for every single prediction platform, you write your code once. It lets you query markets and execute trades across different platforms like Polymarket and Kalshi using a single, cohesive style in either Python or TypeScript. You can let their hosted service handle the complicated on-chain signing and transactions, or self-host the lightweight engine locally to keep full control of your private keys. It is the perfect universal adapter for developers building prediction bots or smart assistants.

🆔 @hackernewsgithubprojects

📦 aws-samples/sample-specship

SpecShip

AI coding agents are notorious for building fast but shallow software that lacks deep testing and error handling. The open-source project sample-specship solves this by forcing AI models to follow a strict engineering pipeline. Instead of letting an agent immediately write and approve its own code, this system introduces adversarial validation where independent subagents aggressively test and review the work against a pre-written contract. It even mandates test-driven development, blocking any new code from being merged until failing tests are written first. It turns fragile AI prototypes into thoroughly tested, production-ready software through disciplined, automated quality gates.

🆔 @hackernewsgithubprojects

📦 microsoft/mage

Mage

Microsoft just released a four-billion parameter model family called mage that matches the quality of AI systems five to eight times its size. Instead of throwing raw computing power at image generation and editing, this project co-designs its image tokenizer and model backbone to focus detail exactly where the visual signal is. This means you can generate high-resolution images or perform complex, instruction-based image edits with massive speedups on ordinary hardware, and it even renders clean bilingual text. It is a fantastic, lightweight setup for developers who want top-tier results without renting a massive server cluster. Check it out to run fast local generation.

🆔 @hackernewsgithubprojects

📦 tanishq-dubey/macos-laguna-s2.1

macos-laguna-s2.1

macos-laguna-s2.1 is the local benchmark harness that finally makes it easy to find the absolute fastest and most accurate way to run the massive Laguna coding model on your Mac. If you are experimenting with local code assistants, you know that picking the right model size and format is usually a guessing game. This tool automatically downloads, runs, and evaluates different compressed versions of the model against a suite of real-world python coding tasks. It tracks memory use, loading speed, and actual token output directly on apple silicon, revealing exactly which setup gives you the best performance without sacrificing intelligence.

📰 https://news.ycombinator.com/item?id=49001323

🆔 @hackernewsgithubprojects

📦 lspr98/conformer-stt-s3

Conformer STT S3

Run voice recognition directly on a tiny microcontroller without ever connecting to the internet. The conformer-stt-s3 project brings a compressed, thirteen-million parameter English speech-to-text model straight to the ESP32-S3 chip. Instead of sending your private voice data to a massive cloud server, this system processes and transcribes your speech completely on the device, ensuring total privacy. By using clever math shortcuts, custom processor instructions, and split-core processing, it squeezes a heavy deep-learning model into just a few megabytes of memory. It is a massive win for building secure, low-power, and battery-friendly smart home gadgets that work anywhere.

🆔 @hackernewsgithubprojects

📦 atomicbot-ai/atomic-agent

atomic-agent

You can now run a highly capable AI agent completely offline on your own device without sacrificing advanced reasoning or tool usage. Built specifically for local models, atomic-agent is a local-first companion that operates entirely on your hardware to ensure absolute privacy. Unlike standard setups that struggle with complex actions offline, this project introduces custom tool-calling grammars that force local models to use system tools, search the web, and manage files reliably. It features a built-in terminal interface, long-term memory consolidation, and deep integration with the Model Context Protocol. It is the perfect playground for building private, highly capable assistants that run anywhere.

🆔 @hackernewsgithubprojects

📦 dingwu1021/silent-failures-multimodal-agentic-search

Silent Failures in Multimodal Agentic Search

Expose the hidden errors in visual search assistants before they lead your applications astray. When advanced AI agents search the web using both text and images, they often produce correct final answers despite completely ignoring the image, hallucinating sources, or contradicting the visual evidence. The silent-failures-multimodal-agentic-search project introduces a diagnostic framework to catch these invisible blunders. By running full agent search paths through a specialized evaluation judge and stress-testing them with blank images, this tool measures true correctness rather than surface accuracy. It is a fantastic way to understand how your visual search models actually behave under the hood so you can build more reliable agentic systems.

🆔 @hackernewsgithubprojects

📦 happynessi/prefix_grpo

Prefix GRPO

Train small-model AI agents more effectively by slicing and reusing successful teacher trajectories rather than relying on basic imitation. The prefix_grpo repository introduces a clever approach to reinforcement learning by splitting a teacher's step-by-step rollout into replayable starting points, restoring those exact environmental states, and training the student model on how to continue successfully from those mid-game moments. By optimizing both the historical context tokens and the ongoing actions, the system helps smaller models learn complex reasoning tasks in environments like text games and grid worlds. It provides the experimental code, modified trainers, and validated datasets to help developers teach smaller models to act like expert agents.

🆔 @hackernewsgithubprojects