📦 nvidia-nemo/automodel

NeMo AutoModel

Fine-tune and pretrain massive language and vision models across multiple GPUs with absolute ease. This project provides PyTorch-native distributed training that gives you out-of-the-box support for your favorite Hugging Face models. Instead of fighting with complex multi-node setups or spending days writing custom parallelization code, you can use ready-to-go recipes for the latest architectures like DeepSeek, Gemma, and Qwen. It handles the heavy lifting of splitting up these giant neural networks so they train incredibly fast without crashing your hardware. Check it out to scale up your AI training from a single workstation to a massive cluster in no time.

🆔 @hackernewsgithubprojects

📦 chatcut-inc/agent-plugin

ChatCut Agent Plugin

The ChatCut agent-plugin lets you edit entire video projects using artificial intelligence by connecting a helper agent directly to your timeline. Instead of clicking around a timeline to manually import media, trim clips, add captions, or generate voices, this clever tool translates your plain-text instructions into precise timeline edits. It even includes bundled media processors that handle high-performance video transcoding locally before uploading the assets to your cloud editor. It is like having a professional video editor living inside your chat window, ready to turn your rough ideas into finished, multi-track videos with a single prompt.

🆔 @hackernewsgithubprojects

📦 anubhav9/yellow-olive

Yellow Olive

Master the complexities of Kubernetes by playing a retro terminal adventure inspired by Pokemon Yellow. Instead of reading dry documentation, you spin up a local minikube cluster and capture and configure resources that are reimagined as quirky pocket monsters. For instance, containers are called Posemons, pods are Pokepods, and deployments are represented as harbor rosters. You will navigate a terminal map, interact with amusing mentors, and solve real, hands-on infrastructure challenges using actual command-line tools. It is a brilliant way to build muscle memory and turn stressful cluster configuration into an addictive, nostalgic gameboy-style quest.

🆔 @hackernewsgithubprojects

📦 hasenj/go-shirei

go-shirei

go-shirei is the cross-platform GUI framework that finally lets you build gorgeous desktop apps in pure Go without touching HTML or Javascript. It brings a true React-like immediate-mode API to desktop development, meaning you just describe what your interface should look like based on your data, and the framework handles the rest. Since it ships with its own custom platform backends, your application looks absolutely identical on macOS, Windows, and Linux. Even better, it renders everything in software, resulting in lightweight ten-megabyte binaries that consume virtually zero CPU when idle. It is the perfect weekend-project companion for building quick, native desktop tools.

📰 https://news.ycombinator.com/item?id=48882562

🆔 @hackernewsgithubprojects

📦 suvitruf/box3d-unity

Box3d for Unity

You can now run physics simulations up to three times faster than Unity's default engine using box3d-unity. This clever package brings Erin Catto's highly anticipated three-dimensional physics engine directly into Unity with a friendly C# layer that avoids messy pointers and annoying memory allocations. What makes it incredibly cool is the built-in replay tool. It lets you record a simulation and replay it frame-by-frame with guaranteed, identical results down to the last bit, even across different thread counts. It is a massive win for debugging physics glitches or building multiplayer rollback netcode.

🆔 @hackernewsgithubprojects

📦 vpalos/krbn

Krbn

Turn three-dimensional geometry into beautiful, hand-drawn vector art that looks like a human sketched it. This project is a TypeScript engine that rejects photorealism to capture the soul of a pencil drawing, converting technical and abstract scenes directly into clean SVG files. Instead of rendering pixels, it calculates exact mathematical silhouettes, handles transparency through cross-hatching, and intelligently ghosts hidden lines to maintain depth. Best of all, it features a clever, deterministic wobble effect that stays perfectly anchored between frames, meaning you can animate camera movements without the lines shimmering or boiling. It is the ultimate tool for turning math into art.

📰 https://news.ycombinator.com/item?id=48869159

🆔 @hackernewsgithubprojects

📦 ucsb-ai/gea

GEA

GEA is the evolutionary playground that helps groups of AI coding agents share their lived experiences to master complex tasks together. Instead of training one isolated assistant, this project allows a whole team of virtual developers to pool their knowledge, learn from each other's coding mistakes, and continuously upgrade their collective skills over time. By testing these agents on real-world software issues, the framework proves that AI can self-improve much faster when working as a community rather than struggling in isolation. It is an exciting glimpse into how cooperative networks will shape the future of software development.

🆔 @hackernewsgithubprojects

📦 ondreu/hearth

Hearth

Turn your Obsidian vault into a beautiful, personalized home screen that welcomes you every time you open your notes. Instead of starting with a blank page, you can now arrange a custom grid of interactive cards to build your ultimate personal dashboard. You can embed editable notes, track tasks on a kanban board, view a mini calendar, and even use a built-in calculator that converts currency on the fly. With modular layouts, smooth drag-and-drop resizing, and a fast search bar that quickly filters your files, everything in your digital workspace is suddenly right at your fingertips. Install the plugin today and design a cozy front page for your thoughts.

🆔 @hackernewsgithubprojects

📦 tonyd2wild/glm-5.2-quanttrio-200k-4x-dgx-spark

glm-5.2-quanttrio-200k-4x-dgx-spark

You can now serve the massive, unpruned GLM-5.2 model with all 256 experts intact at an incredible 200,000-token context window. This repository provides a complete, fully replicable recipe to run this high-fidelity setup across a four-node cluster of NVIDIA DGX Spark systems. By opting for a clever mixed precision checkpoint, the recipe fits the entire model into memory with actual room to breathe, completely avoiding the quality compromises of pruned models. It utilizes speculative decoding and optimized Triton kernels to achieve a blazing-fast speed of nearly thirty tokens per second. It is a massive win for anyone wanting top-tier open-source intelligence running locally at scale.

🆔 @hackernewsgithubprojects

📦 exxeta/exxperts

Exxperts AI

Control exactly what your AI remembers by running a local-first agentic runtime right on your computer. While typical AI tools silently build profiles or forget your conversations between sessions, this system keeps your persistent workspace rooms, knowledge bases, and files entirely on your own disk as plain files. The most exciting part is the approval-gated memory checkpoint system, meaning the AI must ask your permission before saving any new facts, decisions, or preferences about you. You can easily interact with your persistent rooms through a web dashboard or jump straight into your terminal with a command-line interface. It is the perfect way to get smart, personalized assistance without giving up...

📰 https://news.ycombinator.com/item?id=48884002

🆔 @hackernewsgithubprojects

📦 rasbt/llm-architecture-gallery

LLM Architecture Gallery

Most major language models are actually built on slightly different blueprints, and you can compare them all in one visual dashboard. The llm-architecture-gallery is a public metadata hub that powers a live visual gallery tracking the exact architectural differences between famous AI models. Instead of digging through endless research papers to find hidden technical details, this project catalogs the precise knobs, layers, and settings that make each model unique. It is a fantastic way to see how AI design is evolving without drowning in academic jargon. Check out the gallery to see how your favorite model is actually put together.

🆔 @hackernewsgithubprojects

📦 jinwoolee1230/poli

poli

Turn sparse, messy lidar point clouds into rich geometric understanding without relying on labeled data. Instead of using handcrafted rules or heavy supervised learning to clean up noisy 3D sensor scans, this self-supervised tool predicts a mathematical ellipsoid for every single point to map the surrounding surface shape. This means robots can understand their environments, track their own movements, and estimate object positions with much higher accuracy. It plugs directly into existing tracking and mapping systems without needing any changes to your neural network architecture. By modeling raw data as smooth mathematical shapes, you get clean, reliable 3D geometry instantly.

🆔 @hackernewsgithubprojects

📦 igorbarshteyn/jlens-gguf

jlens-gguf

You can now visually track and actively edit a language model's internal thoughts in real time using a standard quantized GGUF file. The jlens-gguf repository is an interactive visualizer and steering tool built directly on llama.cpp that lets you peer into the residual stream of a model at every layer. By mapping out how concepts form, it lets you pinpoint where the AI gets confused and actually edit those activations on the fly, allowing you to swap concepts or suppress specific tokens to instantly steer the generated text. It is an incredibly clever way to dissect and control local models with zero hassle.

🆔 @hackernewsgithubprojects

📦 sizhe-li/vera

Vera

Vera is the video-to-action model that finally lets robots control themselves by dreaming up their own future. Instead of trying to teach a robot physical actions directly, this clever setup lets a standard video-generating AI imagine a video of the task being completed successfully. Then, a specialized translating model reads that imagined video and calculates the exact physical joint movements needed to make that dream a reality. It completely separates dreaming from doing, making it incredibly easy to train robots for complex tasks without needing a massive supercomputer. You can even watch the robot think in real time through a live visual dashboard.

🆔 @hackernewsgithubprojects

📦 luckeyfaraday/athena-loops

Athena Loops

While AI coding agents are incredibly powerful, letting them run wild without supervision often leads to broken code and wasted API tokens. Athena Loops changes the game by turning the orchestrator, worker, and reviewer process into a deterministic control loop written in pure Python code. Instead of relying on a prompt to hopefully self-correct, this smart harness splits your goal into subtasks, delegates them to headless coding agents, and passes the output through a strict review gate that loops until success criteria are met. Because the control flow is handled by code rather than unreliable prompts, it prevents infinite agent loops using built-in budget guards. It even runs as an...

🆔 @hackernewsgithubprojects

📦 endee-io/endee

Endee Vector Database

Endee is a dedicated vector database written in C++ that can index and search up to one billion vectors on a single machine. Built to handle heavy AI retrieval workloads and RAG pipelines, it solves the problem of slow search times by optimizing its indexing directly for modern hardware. It compiles down to target specific CPU instructions like AVX512 or ARM's NEON to extract absolute peak performance. The coolest part is that it supports hybrid search, combining dense vector similarity with sparse exact matches and real-time metadata filtering. It is a incredibly fast, self-contained engine for giving your AI applications lightning-fast long-term memory.

🆔 @hackernewsgithubprojects

📦 rit3zh/expo-morphing-menu

expo-morphing-menu

Build sleek, fluid user interfaces in React Native by turning your standard chat composer into an interactive menu. Instead of letting a traditional pop-up sheet block your app design, expo-morphing-menu uses a spring physics engine to morph the input bar itself. The composer dynamically expands in height, width, and position to become the menu background. It stays perfectly aligned with the mobile keyboard while navigating multiple panels like photos, files, or custom integrations. It offers mobile developers a clean way to handle text inputs, media attachments, and options panels inside a single, unified interface.

🆔 @hackernewsgithubprojects

📦 hugecatlab/chattutor

ChatTutor

ChatTutor is the interactive learning assistant that finally gives your AI tutor a digital blackboard to sketch on. While standard chatbots get stuck explaining complex math and science using only dry text, ChatTutor gives the AI hands-on control over a dynamic math canvas and interactive mindmaps. When you ask a question, the AI actually draws out formulas, plots geometric shapes, and structures ideas visually, just like a real teacher writing on a whiteboard. It completely changes how you study technical topics. Check out the project to host your own visual AI classroom and make learning feel alive.

🆔 @hackernewsgithubprojects

📦 xiangyu-cas/codex-canvas

Codex Canvas

Edit images on a local infinite canvas directly inside your Codex conversation. This tool automatically pulls your generated visuals into a dedicated sidebar panel, keeping your workspace organized by project thread. The coolest feature is how you can isolate layers. It separates flat images into independent, movable elements like background, text, and objects, completing the hidden background behind them. You can rearrange these layers on the fly and export the entire canvas group as a Photoshop-ready PSD file. It makes visual asset organization incredibly easy. Give it a spin to bring layered, canvas-style image editing straight into your chat workflow.

🆔 @hackernewsgithubprojects

📦 adamlyttleapps/claude-skill-app-onboarding-questionnaire

claude-skill-app-onboarding-questionnaire

Build a high-converting, psychology-backed onboarding flow for your mobile app in minutes. The claude-skill-app-onboarding-questionnaire is a clever extension for your AI assistant that scans your codebase, figures out your app's core value, and automatically codes a gorgeous, multi-screen onboarding sequence. The absolute coolest part is that it doesn't just write basic questions. It actually builds a fully functional mini-demo of your core app experience right inside the onboarding, giving users a taste of your product before they even hit the paywall. It handles all the layout and copywriting automatically so you can watch your conversions skyrocket.

🆔 @hackernewsgithubprojects