📦 mtlab/pe-field

pe-field

pe-field is the open-source upgrade that takes traditional flat images and expands them into a fully structured three-dimensional space. While standard AI models struggle to understand depth when generating new angles of an object, this tool works by extending positional encodings into a volumetric field. It uses depth-aware and hierarchical structures to help diffusion transformers naturally reason about actual geometry. This means you can feed it a single flat picture and generate realistic new viewpoints or perform precise, spatially controlled image edits. It is a massive step forward for anyone trying to bridge the gap between flat 2D graphics and true 3D spatial awareness.

🆔 @hackernewsgithubprojects

📦 actava-ai/cura

Cura

Cura is a specialized one-trillion-parameter healthcare model that actually outperforms frontier systems like GPT-5.5 on demanding clinical benchmarks. Created through recursive self-improvement where AI training agents plan target capabilities and refine data based on observed failures, it excels at patient consultations, clinical reasoning, and interactive diagnoses. It even handles complex electronic health record tasks natively. What makes this project truly interesting is that the developers released the entire evaluation harness as an open-source, model-agnostic tool. This means you can plug in any OpenAI-compatible API or run local models with Ollama to run identical medical tests.

🆔 @hackernewsgithubprojects

📦 pixelcookie-zyf/taac-2026-serankmixer

taac-2026-serankmixer

Predict what users will actually buy or engage with after clicking an ad by using a highly optimized single-model ranking network. Built for the Tencent recommendation challenge, this project bypasses the need for massive, complex model ensembles to achieve a top-ten finish. It processes user behavior sequences and dense features using a specialized backbone combined with weighted-pair pooling to model data relationships more accurately. By implementing a dual-stream architecture with advanced training techniques like weight averaging and sharpness minimization, it delivers outstanding accuracy. It is a powerful, self-contained blueprint for building lightweight yet high-performing recommendation systems.

🆔 @hackernewsgithubprojects

📦 martindelophy/ai-video-editor

ai-video-editor

Edit full videos, generate AI voiceovers, and auto-transcribe subtitles entirely inside your web browser without uploading a single file to a cloud server. This clever tool brings a complete multi-track editor straight to your browser, keeping your media completely private. The coolest part is that it runs powerful machine learning models locally on your machine, letting you separate music tracks from vocals, crop videos automatically, and even generate talking digital avatars using your hardware. It is the perfect way to quickly slice clips, add natural-sounding voiceovers, and export your finished work securely without expensive subscription fees.

📰 https://news.ycombinator.com/item?id=48956143

🆔 @hackernewsgithubprojects

📦 qq456cvb/unipose9d

unipose9d

Track the exact 3D position, rotation, and actual size of absolutely any object in a photo without needing a pre-made 3D model or a category label. Normally, robots and cameras struggle to understand physical objects they have never seen before unless you feed them exact dimensions first. The unipose9d project changes that by estimating an object's full 9D pose from just a standard image and a simple point or text prompt. It figures out depth and alignment on the fly, making spatial tracking incredibly flexible. Grab the code and start tracking random objects instantly.

🆔 @hackernewsgithubprojects

📦 sagar-tamang/ultron-by-sagar-builds

ultron-by-sagar-builds

The browser interface that lets you rotate and zoom an Iron Man-inspired virtual orb using your webcam and hand gestures. Built on a Next.js and Three.js foundation, it uses modern artificial intelligence to track your hand joints on video, calculating the distance between your fingertips in real time. Pinching with one hand lets you grab and spin the beautiful orange wireframe globe, while squeezing both hands together or spreading them apart scales the view. It translates direct physical coordinates into smooth post-processed animations without complex accessories, giving you your own sci-fi setup right at home.

🆔 @hackernewsgithubprojects

📦 metareflection/formal-disco

Formal Disco

AI models can now automatically write, test, and self-correct mathematically proven software entirely on their own. While standard AI assistants frequently write buggy code, formal-disco uses a collaborative, multi-agent loop to generate complex programs that are guaranteed to work using rigorous verifiers like Dafny and Verus. It starts with an initiator agent that drafts a program, an automated verifier that tests it, and a specialized fixer agent that uses error feedback to patch up any flaws. By saving successful attempts, the system continuously fine-tunes itself to get smarter. It is a brilliant way to build ultra-reliable software datasets automatically.

🆔 @hackernewsgithubprojects

📦 no8d/comfyui-no8d-controls

ComfyUI NO8D Controls

The custom node pack comfyui-no8d-controls completely reshapes how you build workflows by packing complex sampler controls, image previews, and mask-based inpainting into a single, highly compact node. Instead of cluttering your workspace with a web of connected wires, it unifies your generation process with intuitive tools like an interactive brush, lasso, and eraser that trigger inpainting automatically when a mask is detected. It solves the headache of messy ComfyUI setups by streamlining LoRA stacking, visual style selection with responsive previews, and smart A/B image comparisons. It is the ultimate tool for keeping your canvas clean and your generation workflow fast.

🆔 @hackernewsgithubprojects

📦 mindlab-research/longstraw

LongStraw

Scale up reinforcement learning post-training to multi-million-token contexts without needing a massive GPU budget. Longstraw makes this possible by introducing a smart memory-saving technique called resident-prefix training. Normally, computing reward-based updates requires holding huge, complex autograd graphs for both the prompt and the response in memory at the same time. Instead, this system evaluates the shared prompt exactly once, locks that resident state in place, and then replays only the short trainable responses one at a time. It successfully processed a massive 2.1-million-token prompt workload, proving that we can train smarter on the hardware we already own.

🆔 @hackernewsgithubprojects

📦 kunkka19xx/look

look

This lightweight launcher runs searches in under one millisecond while keeping your data completely local. The project, called look, is an open-source, keyboard-first alternative to Spotlight and Raycast built for macOS, Windows, and Linux. It scans your local files, folders, and clipboard history instantly without sending any data to the cloud. You can also calculate math on the fly, kill system processes by port, and manage daily tasks directly from the search bar. Because it is built as a single native app with no background daemons, it consumes minimal system memory. It is the perfect, privacy-first productivity tool that stays out of your way.

🆔 @hackernewsgithubprojects

📦 openbmb/minicpm-robot

MiniCPM-Robot

Control your physical robots with an ultra-fast, local AI brain that fits on a single tiny chip. The openbmb/minicpm-robot repository provides a family of lightweight vision-language-action models designed specifically for real-world robotics. Its standout feature is an incredibly compact point-nine-billion parameter tracking model that runs fully on-device. It processes visual inputs and natural language commands locally on a quadruped robot at over five frames per second with just one hundred eighty milliseconds of latency. This means your robot dog can track targets and navigate complex environments dynamically without needing any external servers or internet connection. It is the perfect starting point for building responsive, intelligent machines.

🆔 @hackernewsgithubprojects

📦 oblien/openship

Openship

Openship is the self-hosted deployment platform that finally makes shipping code to your own servers feel like a premium cloud experience. You just point it at your repository, and it automatically detects your stack, builds your application, and handles the hosting. It completely eliminates the headache of complex configuration files, custom pipelines, and messy server management. The most exciting part is that it bundles your databases, domains, SSL certificates, backups, and even a fully featured mail server into one cohesive system. It gives you absolute control over your applications without sacrificing the convenience of modern push-to-deploy workflows.

🆔 @hackernewsgithubprojects

📦 microsoft/ontology-playground

Ontology Playground

Design and explore complex data relationships visually right in your browser without dealing with any messy database setup. This tool gives you an interactive, drag-and-drop canvas where you can build node-and-edge diagrams to map out how different concepts connect. You can load pre-built templates for industries like healthcare or finance, edit them on the fly, and instantly export your creations as standard data models. It is a brilliant way to wrap your head around structured data mapping. Grab a template, connect some nodes, and see how simple visualizing complex schemas can actually be.

🆔 @hackernewsgithubprojects

📦 praneybehl/llm-wiki-plugin

LLM Wiki Plugin

The second brain for AI agents that finally gives your digital assistants a shared, persistent memory. LLM Wiki Plugin is an open-source tool that turns your PDFs, articles, and meeting notes into a self-maintaining markdown knowledge base. Instead of starting every conversation from scratch, your coding agents can search, cite, and update this shared wiki directly inside your project directory. The absolute best part is that it requires no complex databases or embedding services, relying entirely on plain text files that you can easily read, edit, and track in git. Try it out to keep your projects organized.

🆔 @hackernewsgithubprojects

📦 manuxd32/ai-doomsday-toolbox

AI Doomsday Toolbox

Turn your pile of old, dusty Android phones into a fully functioning, offline AI supercomputer. With the ai-doomsday-toolbox, you can connect multiple phones over your home network to share the heavy lifting of running large language models, transcribing audio, and generating images completely offline. It is the ultimate way to rescue old hardware from the junk drawer and build a private edge-compute cluster right on your desk. You can even generate custom datasets or run an AI-powered virtual pet. Grab your old devices and start building your own independent, pocket-sized server farm today.

🆔 @hackernewsgithubprojects

📦 alexeygrigorev/ai-engineering-field-guide

ai-engineering-field-guide

Seven out of ten generative AI projects never actually make it past the pilot phase. To bridge this gap, the ai-engineering-field-guide provides a data-driven resource built entirely on real-world hiring and engineering data. Instead of relying on generic advice, this repository analyzes nearly five thousand actual job descriptions and over one hundred real interview experiences. It maps out exact learning paths for transitions from backend or data roles, lists real take-home assignments, and catalogs system design case studies from major tech companies. It is an incredibly practical blueprint for anyone trying to understand what modern companies actually look for when hiring.

🆔 @hackernewsgithubprojects

📦 0xk3vin/megamemory

MegaMemory

MegaMemory is the persistent knowledge graph tool that finally gives your AI coding agents a reliable long-term memory across development sessions. Instead of wasting time parsing raw code or generating noisy structural trees, this clever system lets your AI agent act as the indexer, writing down key architectural concepts, patterns, and design decisions in plain language. It runs a local SQLite database and generates in-process embeddings entirely on your machine without needing external API keys. Your agent simply queries its own memory to orient itself instantly, and can even merge conflicting memories when switching branches. You can even spin up a local web explorer to visually inspect your project's concept...

🆔 @hackernewsgithubprojects

📦 korroai/mue-x

Mue-x

Mue-x is the self-evolving AI assistant that actually rewrites its own source code in real-time as you watch. Instead of just running prompts, this autonomous assistant constantly reads its own Python files, generates and validates code mutations, and applies them directly to its own system. It even scans GitHub to clone relevant projects, autonomously absorbing new patterns and skills based on what you are talking about. With built-in safeguards to prevent errors and roll back bad code, it is a fascinating look at truly self-modifying software. It is a wild experiment showing how programs might write themselves in the future.

🆔 @hackernewsgithubprojects

📦 sneg55/pingcrm

PingCRM

Keep your personal and professional relationships from going cold by automatically pulling all your interactions into one private, self-hosted dashboard. This clever tool syncs with your Gmail, Telegram, Twitter, and WhatsApp, merging the same person across different networks into a single, unified timeline. It calculates a simple score to warn you when someone is sliding out of touch and even drafts personalized follow-up messages using AI so you know exactly what to say next. It is the perfect, private way to stay thoughtful without the manual tracking headache, leaving you with a perfectly organized digital Rolodex that practically runs itself.

📰 https://news.ycombinator.com/item?id=47423835

🆔 @hackernewsgithubprojects

📦 initializ/forge

Forge

Deploy portable, hardened AI agents right on your own infrastructure with Forge. This open-source runtime lets you run self-contained agents with custom skills next to your existing services, whether you are running on Kubernetes, on-premise, or even in air-gapped environments. What makes it incredibly interesting is how it secures these agents by default, using outbound-only connections, strict network controls, and detailed audit logging to keep everything safe. You can define specific agent skills in a simple markdown file, and the system compiles them into secure containers. It is the perfect, straightforward way to run reliable local agents without relying on third-party cloud connections.

📰 https://news.ycombinator.com/item?id=47323134

🆔 @hackernewsgithubprojects