📦 deepseek-ai/deepgemm-ascend

DeepGEMM Ascend: NPU Matrix Magic

DeepGEMM Ascend takes the painful, low-level mess of writing high-speed math kernels for Huawei Ascend chips and hides it behind a simple, clean interface. Normally, squeezing maximum speed out of this hardware means wrestling with confusing memory layouts and complex alignment rules, but this library wraps those headaches in a neat package. It lets you run heavy AI math, like matrix multiplications for large language models, at speeds that hit the absolute physical limit of the chip. Because it uses the same commands as the original DeepGEMM project, you can swap it in without rewriting your code.

📰 https://news.ycombinator.com/item?id=49903881

🆔 @hackernewsgithubprojects

📦 vivy-yi/awesome-agent-orchestration

Awesome Agent Orchestration: The Ultimate AI Agent List

Coordinate a whole team of A.I. workers to tackle complex jobs you could never handle alone. That is the power of the Awesome Agent Orchestration list, which maps out the entire landscape of frameworks like AutoGen and CrewAI. Instead of guessing which tool to trust, this curated guide organizes every major option from simple chat bots to massive swarm systems, along with the communication standards they all use. It turns a chaotic sea of options into a clear map, showing you exactly how these digital teams talk and work together.

🆔 @hackernewsgithubprojects

📦 antseed/antseed

Antseed: The P2P AI Network Without Gatekeepers

Antseed is the peer-to-peer network that turns AI inference into an open marketplace. Instead of routing every request through a single corporate server, this system lets users run their own nodes to sell AI services directly to others. You can plug in your own model or API key and share your spare computing power, while buyers automatically find the cheapest or fastest provider nearby. The result is a decentralized marketplace where you keep control over your data and your costs, removing the middleman entirely. If you want to own your AI infrastructure rather than renting it, this is the project to watch.

🆔 @hackernewsgithubprojects

📦 marspa73/atarijam

JAM: AI in 30 Kilobytes on an Atari 800

A working neural network language model now fits inside thirty kilobytes of memory on a 1979 Atari 800. This project, called JAM, proves that real generative artificial intelligence can run on ancient eight-bit hardware without needing a modern processor. It uses a deterministic neural network to generate text character by character directly on the machine, solving the problem of running complex AI on devices with almost no computational power. By squeezing a functioning brain into such a tiny footprint, it shows how far minimal computing has come. The result is a fascinating, albeit limited, demonstration of silicon intelligence running on a vintage gaming console.

🆔 @hackernewsgithubprojects

📦 hitheshkaranth/openterminalui

OpenTerminalUI: The Open Source Bloomberg Alternative

OpenTerminalUI is a self-hosted trading terminal that actually reads the company reports you are supposed to be reading, turning dense financial filings into verified, cited insights without hallucinating a single number. It works offline on your own hardware, giving you full control over your data and the AI models that crunch it. If you are tired of black-box algorithms that guess why a stock moved, this open-source tool lets you see exactly which quote in the annual report supports the claim. It is the difference between trusting a vibe and trusting a documented fact, all wrapped in a fast, keyboard-driven interface that respects your privacy and your setup.

🆔 @hackernewsgithubprojects

📦 echris6/motion-video-kit

The AI Video Quality Check

Motion Video Kit is the AI video toolkit that refuses to let you ship bad work. It packages a rigorous review loop where fresh critics grade every frame against strict quality standards, catching issues that automated tools miss. This prevents the common trap where AI video looks technically smooth but feels flat and generic. By forcing you to measure loudness, check for frozen frames, and verify motion physics, it ensures the final cut feels premium and intentional. You get a commercial that actually looks like it was made by a human studio. Stop guessing if your video is good. Let the critics tell you the truth before your clients do.

🆔 @hackernewsgithubprojects

📦 evilsheep/max-payne-2-vr

Max Payne 2 VR: Bullet Time in Headset

A two decade old noir thriller now features manual magazine reloading and physical grenade catching in virtual reality. Max Payne 2 VR is a free mod that lets you play as Max or Mona with tracked hands and room scale movement. It adds tactile combat where you physically swing weapons and catch live grenades mid-air. While it is a fan project for a classic PC game, it transforms the famous bullet time mechanic into a visceral, spatial experience. This is strictly for PC VR setups like Quest 3 or PSVR2. The takeaway is that even retro games can gain modern spatial depth through dedicated community mods.

🆔 @hackernewsgithubprojects

📦 iquestlab/modularrsi

Modular RSI: The Universal Test Harness for AI Agents

Modular RSI is a single command-line tool that lets you run the same AI coding agent on over sixty different real-world benchmarks. Instead of writing custom scripts for every new test suite, developers plug their agent into this universal harness. It handles the messy details like setting up secure sandboxes and checking if the code actually works. This means you can finally compare how well different AI models handle tasks like fixing bugs or writing new features, all using one consistent setup. It turns the chaotic process of testing AI agents into a simple, repeatable workflow.

🆔 @hackernewsgithubprojects

📦 private-garden-labs/garden-desk

Garden Desk: AI That Never Leaves Your Computer

Garden Desk runs powerful artificial intelligence entirely inside a locked virtual room on your own computer, meaning your files never touch the internet. It solves the privacy gap for people who need help organizing, reviewing, or analyzing their own documents without trusting a cloud server with their data. You simply pick a folder, describe what you need, and the software works inside that secure, offline bubble to produce results you can save wherever you like. This project proves that useful local automation is possible without sacrificing your control over your information. If you value your privacy, this is the tool to watch.

🆔 @hackernewsgithubprojects

📦 trevornk/ramblr

Ramblr: Dictate Anywhere on Android

Dictate text into any Android app with a single tap, completely offline if you choose. Ramblr is a voice input tool that transcribes your speech directly on your phone, so your data never leaves your device. The coolest part is the AI cleanup feature, which uses a local large language model to polish your messy dictation into clean, professional text before you even see it. It is not just a basic recorder; it actively fixes your grammar and tone right on your screen. This means you can talk naturally and let the software handle the editing, giving you total privacy and speed.

🆔 @hackernewsgithubprojects

📦 eifr/vigilo

Vigilo: Your Phone Is a Security Camera

Vigilo is the web app that turns your phone into a live security camera without any extra hardware. It works entirely in your browser, using computer vision to spot motion and track objects in real time, which means you do not need to install heavy software or connect to a private cloud. The coolest part is that you can set up alerts to send photos directly to your Telegram chat, so you get an instant snapshot every time something moves. It is a clever way to use the device already in your pocket as a simple, portable eye on your home or workspace.

🆔 @hackernewsgithubprojects

📦 opencoven/coven

Coven: The AI Runtime That Actually Remembers

Coven is the local-first runtime that finally gives your AI coding agents a real memory and a strict leash. Instead of letting a chatbot wander loose with your credentials, it keeps sessions locked to your specific project, ensuring the agent only does what you explicitly allow. The coolest part? It speaks every dialect. Whether you run Claude Code, Codex, or Copilot, Coven sits underneath them all, turning your scattered AI tools into one coherent, durable workflow that remembers your codebase context even after you close the terminal. It is less about flashy features and more about making sure your digital helpers actually stay in their lane.

🆔 @hackernewsgithubprojects

📦 menloresearch/isaac_asimov

Teach a Humanoid Robot to Walk

Train a real humanoid robot to walk by teaching it in a virtual playground. This project gives you the exact code to build walking brains for the Asimov one, a two-legged bot that looks like a tiny human. Instead of guessing how to balance, the software uses a clever trick to copy natural movement data, making the robot’s steps look smooth and lifelike rather than robotic. It handles the heavy math so you can focus on the fun part: watching your digital student stumble, recover, and eventually strut. Once it learns in the simulation, you deploy that same brain to the actual hardware.

🆔 @hackernewsgithubprojects

📦 fr3on/portkill

PortKill: The macOS App That Kills Dev Servers In One Click

PortKill is a tiny menu bar app for Mac that turns the annoying hunt for runaway development servers into a single click. Instead of digging through terminal logs to find out which project is hogging a port, it simply lists every active server, identifies the specific folder it belongs to, and lets you stop it immediately. It even figures out your project type by looking for files like package dot json or cargo dot toml. It’s a small, private tool that stays completely out of your way until you need it, making local development way less cluttered.

🆔 @hackernewsgithubprojects

📦 opencoredev/social-sdk

Social SDK: One Call, Every Platform

Your code now knows exactly what a social platform will actually accept before you even try to send it. Social SDK gives you a single, typed way to publish to Bluesky, Instagram, TikTok, and YouTube without rewriting your logic for every new feature or breaking change. The real win is the mock backend, which lets you test your entire posting pipeline offline using a fake, deterministic response instead of risking real API keys or accidental posts. It turns messy, unpredictable platform APIs into a clean, predictable flow you can trust. Stop guessing if your post worked, and start building with total confidence. That is the takeaway.

📰 https://news.ycombinator.com/item?id=49935999

🆔 @hackernewsgithubprojects

📦 jiaosiyuu/thinkgen

ThinkGen: AI That Thinks Before Painting

ThinkGen is the image generator that actually reasons about your request before painting it. Instead of just guessing what you want, it pauses to think through the details, refining your simple words into a richer, clearer picture in its head before drawing. This means the final image matches your intent much more accurately than standard tools. It works right in your terminal with open weights, so you can see exactly how it improves your prompt. If you want AI art that truly understands what you are asking for, this project shows a smarter way to generate visuals that look like they were planned, not just produced.

🆔 @hackernewsgithubprojects

📦 robbietilton/compositor

Compositor: Photoshop, But Free

Compositor lets your Mac's AI agent build photo projects while you watch the canvas update in real time. It is a free, open-source image editor built for Mac users who want Photoshop's workflow without the subscription. The app handles layers, masks, and advanced color adjustments, making it a serious tool for compositing. Because it is open source, you can modify the code to fit your exact needs. It even accepts files from Photoshop, so switching is easy. If you want professional editing power without the price tag, Compositor is a solid alternative to explore.

🆔 @hackernewsgithubprojects

📦 itsmostafa/system-one-connector

System One Connector: AI Agents Get Real Answers

System One Connector is the model connector that gives your AI agent actual numbers instead of vague guesses. It plugs into tools like Claude Code or Codex so your agent can ask a direct question and get a clear probability back, such as ninety-five percent urgency. Instead of reading a paragraph and hoping for the best, your agent gets a hard answer it can use in logic, like deciding if a ticket needs immediate help. This project solves the problem of AI hesitation by providing fast, cheap, and structured judgment calls, meaning your agent can act on facts rather than feelings.

🆔 @hackernewsgithubprojects

📦 ayanamislover/ayanamitaskmanager

Ayanami Task Manager: AI Memory Fix

Ayanami Task Manager solves the biggest headache in AI coding: agents forgetting everything between sessions. Instead of losing project context every time a chat window closes, this local-first tool acts as a shared memory bank for your coding agents. It stores tasks, decisions, and progress in one place so that when a new agent picks up the work, it doesn't have to guess. It’s not just a to-do list; it’s a continuous handoff system that lets different AI models like Codex or Claude read exactly where the last one left off.

🆔 @hackernewsgithubprojects

📦 internrobotics/internw0-delta

How InternW0-Delta Teaches Robots to Predict the Future

InternW0-Delta is the robot model that actually watches what happens before it moves its arms. It is a massive open project that teaches machines to predict how the world changes so they can act with better timing. It uses twenty thousand hours of video from humans and robots to build this skill. Instead of just memorizing movements, the system learns the cause and effect of every action. It sees a scene, predicts what will happen next, and then decides exactly where to move. This makes the robot far smarter and more adaptable than simple scripts. It is a huge step toward machines that truly understand their environment.

🆔 @hackernewsgithubprojects

📦 sqooky/optimizationlock

OptimizationLock: Max FPS for Deadlock

OptimizationLock is the configuration collection that keeps Deadlock running smooth without looking terrible. It provides a simple way to swap in a pre-tuned file that boosts your frame rate by adjusting the game’s internal settings, like reducing shadow quality or turning off heavy lighting effects. Instead of guessing which lines to change, you pick a preset that fits your computer, whether you want maximum speed or just a bit more performance while keeping the visuals sharp. It even includes an automatic tool that updates your settings whenever the game changes, so you never have to manually fix broken files again.

🆔 @hackernewsgithubprojects