📦 bobliuuu/open-flapping-airplanes

open flapping airplanes

Launch a single command and watch one GPU kernel train a language model, stream live text responses, and play Doom at thirty-five frames per second simultaneously. This project, called open flapping airplanes, recreates a viral demo by writing one persistent worker that never stops. Instead of the computer constantly starting and stopping tiny tasks, which wastes time, this single worker stays active and pulls work from a queue. The most surprising part is that it actually runs the classic Doom engine right on the graphics chip while training. This proves that modern hardware can handle mixed workloads without constant overhead.

🆔 @hackernewsgithubprojects

📦 color-ide/coloride

Coloride: The Local-First IDE for Mac

Coloride is a desktop editor that refuses to call home, meaning your code stays on your Mac without needing an account or cloud connection to start editing. It bundles a file explorer, live terminals, and even a built-in browser so you can test your work in one window. The most interesting part is the strict local-first design, where every action runs on your own machine by default. You get a complete development setup that respects your privacy, proving that a powerful tool does not require handing over your data to a server. If you value keeping your code private, this is the one to try.

🆔 @hackernewsgithubprojects

📦 ethany14/eregion-job-finding-agent

Eregion Job Finding Agent

Eregion Job Finding Agent fills out real job applications on your computer and stops right before you hit the submit button. It searches company boards and LinkedIn, reads every posting in full, and sorts the results by how well they fit your resume. The most surprising part is that it actually opens your browser, types in your details, and navigates through the forms page by page. It handles the tedious typing so you can focus on the decisions that matter. If a CAPTCHA or password field appears, it pauses and waits for you to take over. Since everything runs locally on your machine, your data never leaves your hands.

🆔 @hackernewsgithubprojects

📦 lxe/dsx

Run a 552B AI Model on Your Gaming PC

Run a massive five hundred and fifty billion parameter AI model on your own gaming desktop. dsx is a custom engine built in Rust and CUDA that squeezes this huge model into two twenty-four gigabyte graphics cards and one hundred twenty eight gigabytes of system memory. Usually, software this big needs a datacenter, but this project spreads the model’s experts across your graphics cards and processor so they can all work at the same time. The coolest part is that it actually follows your conversation in real time.

🆔 @hackernewsgithubprojects

📦 openselena/omniget

OmniGet: The One-App Download Suite

Your browser is quietly forgetting every video, article, and song you ever saved, and OmniGet fixes that by becoming your personal, offline library for everything you find online. It is a desktop application that acts like a universal grabber, pulling high-quality video, music, and even entire paid courses from over a thousand websites right onto your hard drive. The coolest part is that it isn't just a download button; it is a full workbench that lets you clean up audio, organize your files, and even keep a private chat client running all in one place. You stop worrying about links breaking or platforms changing their rules.

🆔 @hackernewsgithubprojects

📦 kkkkhazix/agent-autoloop

Agent Autoloop: The Silent Worker

Stop babysitting your terminal. Agent Autoloop turns your command line agents into a background worker that picks up tasks, does the heavy lifting, and then quietly waits for your input only when a human decision is required. The truly surprising feature is the zero cost wait. When the agent hits a critical choice, it shuts down completely. No process runs and no tokens are spent while you take your time. The system stores its state in a local database, so if you reply three days later, the agent instantly resumes exactly where it left off.

🆔 @hackernewsgithubprojects

📦 saos-3624/dsh-see-now

See Now: The Screen Watcher That Saves Money

See Now is the visual plugin that makes artificial intelligence watch your screen without burning through your budget. It solves the problem of feeding constant screenshots to a model, which is wasteful and often misses important details. Instead, this tool measures how much the picture actually changes on your display. It only sends a new image when something real happens, like a window switch or a video scene change. If your screen is still, it sends almost nothing, saving you from paying for blank frames. You get a clear picture of what your computer is doing, but only when it matters.

🆔 @hackernewsgithubprojects

📦 balanov/skein

Skein: The Emergency Stop for AI Swarms

Skein is the fail-closed orchestration tool that ensures your local agent swarm actually stops when you tell it to. It executes task graphs with a persistent epoch fence, meaning if you hit the emergency stop, it doesn't just ignore the signal. It actively rejects any late results from the old run and kills the underlying processes immediately. This is huge because it prevents zombie tasks from finishing work after you've already called it off. You get a single static binary with no database, just pure control. If you are running local AI agents, this is the safety net you need.

🆔 @hackernewsgithubprojects

📦 dev2ex/twig

Twig: Every File System In One Place

Your phone connects to your entire digital life at once. Twig is an Android file manager that displays your local storage, cloud drives, and remote servers in a single unified tree. It solves the problem of having to switch between different apps to reach files on a NAS, a backup archive, or a media server. The app uses plain Kotlin to keep the installation small, meaning it runs quickly without bloat. You browse through everything from a standard folder to a remote server as if it were on your phone. It turns your device into a central hub for all your data.

📰 https://news.ycombinator.com/item?id=50167416

🆔 @hackernewsgithubprojects

📦 mrsladoje/sweet-search

Sweet Search: Local Code Search for AI Agents

Your AI coding agent is spending way too much time and money just trying to find the right file. Sweet Search fixes this by giving tools like Claude Code a fast, local brain that understands your codebase without sending it to the cloud. Instead of the usual slow, line-by-line text matching, it uses semantic search to answer questions like where we handle user authentication in seconds. You run it once, and it builds an index right on your machine, meaning no API keys and no privacy leaks.

📰 https://news.ycombinator.com/item?id=50326635

🆔 @hackernewsgithubprojects

📦 reliant-labs/reliant

Reliant: Your AI Dev Team

Reliant lets you hand your code to AI agents that actually work while you sleep. It runs on always on machines that stay online even when your laptop is closed, so your agents can keep building and fixing apps in the background. The coolest part is Autopilot, which turns your GitHub into a team of reviewers, engineers, and on call workers that file issues and open pull requests for you. You get a full dev stack that handles the boring stuff, leaving you to just merge the good stuff. It is the closest thing to a tireless, digital engineering team you can plug in today.

🆔 @hackernewsgithubprojects

📦 ankushkun/sh23ds

Play Silent Hill 2 on a 3DS

Run the full Silent Hill 2 Director’s Cut on a Nintendo 3DS. This isn’t an emulator; it’s a native port that translates the PC game’s logic directly into code for the handheld. You need your own copy of the game, but once converted, you get the real experience with true depth on the top screen. It’s wild that a modern console can run this horror classic so smoothly. If you miss that fog and dread, this is how you bring it back to life in your pocket.

🆔 @hackernewsgithubprojects

📦 finic-ai/kairos

Kairos: The AI That Hires Itself

Kairos is the open-source fraud engine that lets your coding agent do the job of a human data scientist. Instead of manually tweaking rules, you connect tools like Claude Code or Cursor to the system, and they analyze your data, build new detection models, and test which version catches the most scams. When you send in a sign-up or a payment, the system instantly decides whether to approve it or block it, keeping every signal that led to that call. The most surprising part is that this agent can propose, train, and ship better models automatically, meaning your fraud detection gets smarter without you writing a single line of code.

📰 https://news.ycombinator.com/item?id=50358314

🆔 @hackernewsgithubprojects

📦 ant-intl/bizagentbench

BizAgentBench: Testing A.I. Payment Agents

BizAgentBench puts A.I. agents to work on fifty realistic payment service tasks to see if they can actually handle real business logic without breaking the bank. The surprising part is that it doesn’t use another A.I. model to judge the results; instead, it checks the exact state of the simulated database and execution history using strict, deterministic rules. This means you get a clear, unambiguous score on whether the agent hit the goal, followed the process, and protected the data from mistakes. It’s a crucial step toward figuring out if these tools can actually be trusted with money. If you are building or testing A.I.

🆔 @hackernewsgithubprojects

📦 fjaeckel/seriesoftubes

Series of Tubes

Series of Tubes is the browser game that actually teaches you how the internet works. It starts you with one lonely router in a single city and challenges you to build a global network that rivals the big telecom giants. The real hook here is the chaos; you are not just laying cables, you are fighting sharks, angry investors, and massive cyber attacks while trying to keep your customers happy. It forces you to understand the messy reality of global infrastructure without drowning you in jargon.

🆔 @hackernewsgithubprojects

📦 two-delta/dcoco

DCOCO: The Fastest Way to Speed Up AI

Make your language models generate text up to six times faster. DCOCO solves a tricky problem where AI tries to guess entire blocks of words at once but forgets that earlier words change the context for later ones. It fixes this by checking how every possible word fits with its neighbors in a single quick pass, ensuring the guess still makes sense. This makes the whole process dramatically faster than standard methods, even when serving many users at once. If you want your AI to talk without the wait, this is the tool that gets it done.

🆔 @hackernewsgithubprojects

📦 codician-team/diffinery

Diffinery: Run GitHub on Your Own Cloudflare Account

Diffinery lets you host code and run your existing GitHub Actions workflows entirely on your own Cloudflare account, meaning you get the speed of serverless containers without managing a single physical server. The coolest part is that it treats AI coding agents as real team members with strict safety rails, allowing them to open pull requests and fix bugs while humans retain final approval. It is open-source and self-hosted, so your data stays yours. If you want your AI tools to do the heavy lifting while you keep the keys, this is the setup for you. It is a smart way to modernize your workflow without the usual infrastructure headaches.

🆔 @hackernewsgithubprojects

📦 power-pudu/egg-of-time

Egg of Time: Native PC Port of Chrono Trigger

Play Chrono Trigger for Nintendo DS on your computer at native speed without using a standard emulator. This project, called Egg of Time, translates the handheld game's raw processor instructions directly into standard C code, which compiles into a high-performance native program. You supply your own game file, and the software builds the executable on your machine, resulting in smooth high frame rates and widescreen support. It is a fascinating look at static recompilation, turning a portable console experience into a modern desktop application with full controller support.

🆔 @hackernewsgithubprojects

📦 x0rro/xara

Xara: Open Source Radio Modem for Linux

A small open source project now lets a standard Linux computer act as a complete radio modem for amateur ham radio networks. Xara handles the heavy digital lifting of encoding and decoding voice and data signals, which means your computer can communicate directly with other stations using the same protocols as the expensive commercial software that has dominated this space for decades. It handles both high frequency and frequency modulation, letting you set up a station from scratch without paying for proprietary licenses. You plug in your audio interface, tell it your call sign, and it handles the rest.

🆔 @hackernewsgithubprojects

📦 andrew-babo/muse4ai

Muse4AI: Let Your AI Agent Make Pictures and Videos

Take control of visual creation by letting your favorite AI assistant generate images and videos directly from your own computer. Muse4AI acts as a private bridge on your Windows PC, connecting tools like ChatGPT or Claude to your personal Muse account. This means no cloud middleman, no subscription fees, and total privacy, as everything runs locally on your machine. The real magic is that your agent can actually talk to Muse, ask it to make a video, and then wait for the finished clip to appear in your local library. It turns your AI assistant into a creative partner that can produce visual content for you.

🆔 @hackernewsgithubprojects