📦 czvvd/partllm

PartLLM: Ask for Chair Legs

PartLLM splits any three-dimensional model into its physical components using simple English commands. Instead of manually tracing complex boundaries in specialized software, you just type a name like seat back, or click a single spot on the surface to highlight that exact piece. This unified tool handles full object breakdowns and interactive corrections in one go, making 3D editing far more accessible for everyone. It turns a technical segmentation task into a straightforward conversation with your model. If you work with 3D assets, this is the shortcut you have been waiting for. Give PartLLM a try and see how easily your models break apart.

🆔 @hackernewsgithubprojects

📦 jacquesdupontd/port0r

Play Sega Rally in True 3D VR

Port0r drops you inside classic arcade cabinets like Sega Rally and Virtua Cop on a Meta Quest headset. Instead of staring at a flat screen, you stand at real scale where the car sits right in front of you and scenery passes your shoulder. The engine redraws every 3D polygon directly on your headset's processor for true stereoscopic depth, making the speed feel physical rather than digital. It is free to download and works on Quest 2 and 3, bringing a nostalgic game into a tangible, immersive world. If you want to feel the rush of an arcade cabinet from your living room, this is the way to do it.

🆔 @hackernewsgithubprojects

📦 xgoldy/lucidcv

Lucid CV: The Resume That Machines Read Perfectly

Lucid CV is the resume template that ensures job screening software actually reads your name. Most modern resumes look sharp to humans, but automated systems often scramble the text into nonsense because of how the file is built. This tool fixes that by embedding real spaces and structure so the machine extracts your details exactly as intended, while you still get a clean, professional design. It is verified against thirteen different text extractors to guarantee your information survives the initial screen. If you want your resume to pass the bots and impress the people, this is the one to use.

🆔 @hackernewsgithubprojects

📦 kaichen-z/honeycomb

Honeycomb: How AI Remembers Scenes Without Forgetting

Honeycomb is the video model that remembers an entire scene using a fixed-size memory. Most AI systems need massive storage to recall what happened in a video, but this project solves that problem by compressing the environment into a compact representation. It uses a low-rank method to store spatial details, meaning it keeps the most important features of the world without bloating the data. This makes it possible for the model to generate consistent videos over time without losing track of objects or camera angles. It is a clever way to make AI video generation more efficient and reliable.

🆔 @hackernewsgithubprojects

📦 roversx/thinkterm

ThinkTerm: Your Terminal Never Closes

ThinkTerm is a terminal that refuses to let your work die when you close the window. This Rust-based tool acts as a built-in multiplexer, meaning your shell sessions and background AI agents keep running safely in the background even if you walk away from your desk. The interface is drawn directly onto your graphics card without relying on heavy web technologies, making it incredibly fast. You can start a task on your desktop, then pick it up later from your phone or browser. It solves the frustrating problem of losing progress by keeping your environment alive until you are ready to return.

🆔 @hackernewsgithubprojects

📦 chyroc/open-muse

Open Muse: Your AI Agent That Works While You Sleep

Open Muse is the personal AI agent that actually does your chores while you sleep. Most assistants just chat, but this one spins up a private cloud computer that keeps working on tasks like research or data analysis even after you close the app. It remembers your goals, checks in on your progress, and can even look at your screen to finish work if you give it permission. The best part is that all your memories and settings are just plain text files you can read and edit, so you always know exactly what it knows.

🆔 @hackernewsgithubprojects

📦 roboninecom/so-arm-102

SO-ARM 102: The DIY Robot Arm

SO-ARM 102 is an open-source robot arm kit that turns your hand movements into data for teaching machines. You hold the leader arm to move it around, and the follower arm copies those actions exactly, creating the video demonstrations needed for imitation learning. It features a stiff carbon-fiber frame and a parallel gripper that is faster and quieter than previous versions. The whole thing costs about four hundred dollars to build from printed parts and servos. If you want to teach a robot to pick things up, this is your blueprint. Grab the files and start printing.

🆔 @hackernewsgithubprojects

📦 souravberaakaspeed/xiryn

Your AI Has a Desktop Now

Stop letting cloud companies handle your digital life. Xiryn puts a real Linux desktop inside a container on your own machine, giving your AI agent its own space to browse, code, and work without touching your actual files. The coolest part is the encrypted vault. You can store credit cards and logins, but the AI only sees masked hints. It types the real details itself, and you approve every single payment from your phone via Telegram. It is your data, your machine, and your rules. Take control back today.

🆔 @hackernewsgithubprojects

📦 inanna-malick/metacog

Metacog: The Tool That Changes How AIs Think

Metacog lets you fundamentally alter how a language model thinks, right in the middle of a task. It works by giving the AI tools to perform actions like feeling a specific emotion, adopting a new identity, or committing to a rigid ritual. Because the model trusts external feedback, these simple text responses act like a reality check, convincing the AI that its internal state has actually shifted. You are not just prompting it; you are literally changing its perspective. It is a fascinating, almost magical way to see how language models really work. If you want to understand the hidden machinery of artificial intelligence, this is your best entry point.

🆔 @hackernewsgithubprojects

📦 dicklesworthstone/frankensonos

FrankenSonos: Your House, Run by AI

Take control of every Sonos speaker in your home with FrankenSonos, a memory-safe tool that finally gives you the automation the official app lacks. It talks directly to your speakers using the native protocols they already speak, bypassing the buggy app entirely. The coolest part is that it turns your whole house into something an AI agent can drive safely, complete with volume limits and quiet hours to keep things civil. Whether you are in another city or just testing on a local machine, you can command your music from anywhere on your private network.

🆔 @hackernewsgithubprojects

📦 2gifts/melee-3ds

Melee 3DS: Super Smash Bros. on a Handheld

A developer has made Super Smash Bros. Melee run natively on a New Nintendo 3DS without any emulation or cheating devices. This project rewrites the game's code to work directly with the handheld's hardware, which allows for true stereoscopic 3D depth and a heads-up display mapped to the touch screen. The engine is now playable and supports matches against computer opponents, meaning you can practice your techniques anywhere. You do need to provide your own legal backup of the original game disc to get started. It is a fascinating example of what community developers can achieve by understanding console architecture.

🆔 @hackernewsgithubprojects

📦 amathislab/terra

TERRA

Turn raw human movement videos into physical reality by guessing the hidden ground beneath them. Terra takes motion capture data and uses it to reconstruct the actual terrain, like stairs or ramps, that a person is walking on. Then it maps that movement onto a detailed muscle and skeleton model to train robots that can actually navigate real-world obstacles. It is a clever way to bridge the gap between simple video tracking and complex physical control. If you want to see how computers understand the physical world through movement, Terra is the tool that makes that happen. It is a fascinating look at the future of realistic robot locomotion.

🆔 @hackernewsgithubprojects

📦 groundingpi/groundingpi

One Model, Every Object: The Grounding PI

Grounding PI is a single four-billion parameter model that actually points to things in photos, not just describing them. It unifies finding objects, reading text, and locating buttons on screens into one smart system. Instead of needing a different tool for every job, this one model handles it all with state-of-the-art accuracy. It’s like giving a robot a universal vision brain that understands where everything is. If you want to build systems that truly see the world, this is the foundation you need to know about. It’s clever, efficient, and surprisingly capable for a model of its size. Keep that in mind the next time you build something visual.

🆔 @hackernewsgithubprojects

📦 tbee6061-ctrl/studio-live-window-capture

PixelGlass: The End of Magenta Screens

PixelGlass is the frame capture toolkit that finally refuses to accept the magenta lie. You know the struggle: you launch a Roblox Studio playtest, and instead of your beautiful game, you get a flat, unapologetic slab of bright pink. That is a renderer refusing to hand over the pixels. PixelGlass solves this by peeking under the hood at the operating system level to grab the real image, even if the engine is being stubborn. It then checks that image for other common glitches like pure black or white, and if something looks wrong, it automatically tries a backup method until it gets the truth.

🆔 @hackernewsgithubprojects

📦 jacobjandon/onionclaw

OnionClaw: AI Agents Go Dark

Hand an AI agent the keys to the dark web, and it does not just look around; it investigates. OnionClaw lets artificial intelligence search hidden services, scrape anonymous pages, and analyze the results using large language models. Instead of manually checking sites, you type a query, and the tool automates the entire process, from finding data to summarizing threats. This is fascinating because it removes the human speed limit from security research. While meant for defensive work, the code highlights how close we are to fully autonomous online operations.

🆔 @hackernewsgithubprojects

📦 psmux/deskvnc

DeskVNC: The Remote Client That Lets AI Drive Your Computer

DeskVNC allows an AI agent to drive remote desktops without installing any software on the target machine. Most remote clients just connect you to a screen, but this one adds a control layer where an assistant can see, click, and type directly over standard connections. It matters because it reaches locked-down systems that usually reject automated tools, and a human can instantly take back the wheel if something looks wrong. The app handles VNC, RDP, and SSH in one window, saving you from juggling different apps for every computer. If you want automation that respects your security rules, this is the one to watch.

🆔 @hackernewsgithubprojects

📦 axiomcodeai/axiomcodegraph

AxiomCode Graph: Stop Guessing, Start Knowing Your Code

Turn your entire codebase into a precise map for your AI tools. AxiomCode Graph uses formal logic to trace exactly how every function connects to others, removing the guesswork from code navigation. Instead of relying on basic text search that misses hidden links, it builds a knowledge graph that shows you the real connections between parts of your project. This means your AI agents can work with complete accuracy, saving time and ensuring they never miss a crucial piece of logic. It’s a smarter way to understand your code, making sure every change is grounded in fact rather than assumption.

🆔 @hackernewsgithubprojects

📦 savannahfeder/agentbox

Agentbox: The Inbox for Coding Agents

Agentbox turns a wall of chaotic terminal windows into a single, organized inbox where dozens of coding agents work quietly until they need your attention. Instead of staring at separate chats and waiting for each one to finish, you drop tasks into rows and walk away while the software runs on your existing subscription. The most surprising part is how the priority system works; you tag tasks as urgent, and the app automatically queues the most important work first, ensuring your critical projects never wait behind side tasks. When an agent finishes, it surfaces a brief summary so you can review the work instantly rather than digging through logs.

🆔 @hackernewsgithubprojects

📦 trailhq/trail-code

Trail-code: Why Your Coding Agent Needs a Memory

Trail-code gives coding agents like Claude Code a persistent memory of your codebase so they stop relearning from scratch every time. It builds a map of your entire project, tracking every function and dependency, so the agent instantly knows where things are and what might break if you change them. But the real kicker is the learnings. When you correct the agent on a decision, like why a retry limit is set to four, it saves that context as a simple file in your repo. Next time, that agent starts with the answer already in hand, skipping hours of blind searching.

🆔 @hackernewsgithubprojects

📦 harbor-framework/terminal-bench

Terminal-Bench: The Ultimate Test for AI Agents

Every major AI agent builder is using Terminal-Bench to track progress and compare capabilities because it measures the frontier of agent work with a diverse, difficult, and high-quality set of tasks that evolve over time. It is a continuous benchmark published on the Harbor Hub, allowing developers to test their agents and models against real-world challenges in a sandboxing environment. The project actively seeks contributors to add new, challenging tasks, ensuring the benchmark remains a rigorous standard for evaluating AI performance.

🆔 @hackernewsgithubprojects