📦 responsible-ai-labs/rail-score-sdk

rail-score-sdk

rail-score-sdk is the Python library that finally makes it easy to measure and guarantee the safety of your artificial intelligence applications in real time. Instead of just guessing how your language models are performing, this tool plugs directly into your existing setup to score text across eight critical dimensions, including safety, privacy, and fairness. What makes it incredibly cool is the safe regeneration loop. If a model output falls below your quality threshold, the system can automatically catch it, write a correction prompt, and run it again until it passes your safety bar. It is like having an automated editor built right into your code.

🆔 @hackernewsgithubprojects

📦 southleft/figma-console-mcp

Figma Console MCP

Connect your AI assistant directly to your design canvas to build, inspect, and tweak layouts using natural language. Instead of manually copying values, this tool lets you extract entire design systems, create polished components, and sync tokens back and forth in real time. You can even lock your AI agent onto a specific file so it keeps working in the background while you focus on other screens. It is a brilliant way to turn Figma into a fully programmable space, helping teams bridge the gap between static designs and actual code without the usual back-and-forth friction.

📰 https://news.ycombinator.com/item?id=48989470

🆔 @hackernewsgithubprojects

📦 shinmegamiboson/openplanter

OpenPlanter

An autonomous AI investigation agent called openplanter cross-references massive, messy public databases to expose hidden connections in seconds. Built with a desktop interface and a recursive engine, it takes raw data like corporate registries, campaign finance files, and government contracts to build a live knowledge graph of linked entities. Instead of manually parsing spreadsheets or writing queries, you simply ask questions in plain English. The agent then spins up recursive sub-agents to resolve duplicate names, map relationships, and flag conflicts of interest. It is a powerful, local way to turn scattered public records into clear visual evidence.

📰 https://news.ycombinator.com/item?id=48989627

🆔 @hackernewsgithubprojects

📦 ethanfel/comfyui-lora-optimizer

ComfyUI LoRA Optimizer

Stacking multiple LoRAs in ComfyUI often ruins your AI images with terrible oversaturation, weird visual artifacts, or completely lost details. The comfyui-lora-optimizer custom node suite completely fixes this by automatically calculating the absolute best way to blend your LoRAs together. Instead of blindly piling them on, this tool analyzes exactly where your model layers conflict, surgically resolves those styling clashes, and dynamically scales down their strengths so the final output looks clean. It even normalizes different trainer formats so they can merge seamlessly. It is the ultimate set-it-and-forget-it tool for clean, multi-LoRA generations.

🆔 @hackernewsgithubprojects

📦 yejunzhang/geomix

geomix

geomix is the 3D matching framework that finally solves visual localization without relying on traditional image descriptors. Instead of getting bogged down by matching complex visual textures, it uses smart geometric connections and local spatial layout to align camera images with 3D map points. By training simultaneously on multiple keypoint detectors like SIFT and SuperPoint, geomix learns to be incredibly adaptable to whatever features your system throws at it. It is a fantastic tool for anyone interested in camera tracking, robotics, or building 3D maps because it proves you can find your way using pure geometry instead of complex visual signatures.

🆔 @hackernewsgithubprojects

📦 xianzhi-ma/weaveearth

WeaveEarth

WeaveEarth is the training-free framework that finally helps vision-language models understand massive, ultra-high-resolution satellite images without choking on detail. Normally, computer vision models either scale up resolution and blow their computational budget, or zoom in blindly and lose all context. WeaveEarth solves this by acting like a smart magnifying glass. It identifies a tiny, high-impact set of localized details across a landscape, and then neatly weaves those details, spatial metadata, and layout rules together. This gives standard open-source AI models global-local joint reasoning instantly, with zero extra training. Check it out to see how it makes satellite analysis incredibly precise and fast.

🆔 @hackernewsgithubprojects

📦 yilailiu-hku/slotmem

SlotMem

SlotMem is the video generation tool that finally keeps characters looking identical across long, complex stories. If you have ever tried generating a multi-scene video, you know AI characters constantly shape-shift between cuts. This project clever-ly solves that by creating dedicated, character-specific memory slots. Think of it like a digital wardrobe and face-file that the AI checks before rendering any scene, ensuring your protagonist has the same hair, jacket, and features from start to finish. It is a massive leap forward for anyone trying to tell consistent visual stories without the constant, frustrating visual glitches.

🆔 @hackernewsgithubprojects

📦 pku-sec-lab/jetson-pi

Jetson-PI

Jetson-pi is the robot control system that finally makes advanced AI decision-making fast enough to run directly on low-power onboard hardware. While modern robots use massive vision and language models to figure out what to do, running these giant brains on a standard compact computer normally causes lag, making the robot slow, clumsy, and prone to mistakes. This project solves that by predicting what the robot's environment will look like a few steps ahead while the main AI is still thinking. This clever foresight trick lets a smaller, faster action expert command the robot instantly and smoothly without waiting around. Now, you can run high-level intelligence locally on your hardware...

🆔 @hackernewsgithubprojects

📦 danish296/codevibes

CodeVibes

Scan your GitHub repositories and get an instant sanity check on your code quality using a single AI tool. CodeVibes runs deep security and performance checks on your files, but instead of burying you in confusing dashboard metrics, it translates complex bugs and potential security holes into easy-to-read warnings and a single, unified Vibe Score. It is perfect for solo developers who want a quick, smart code review without setting up heavy enterprise infrastructure. Think of it as a friendly, sharp second pair of eyes that keeps your projects clean and secure so you can ship with confidence.

🆔 @hackernewsgithubprojects

📦 gongnyang/gongnyang-prompt-kit

Gongnyang Prompt Kit

Gongnyang-prompt-kit is the Claude Code skill that finally turns your vague, one-liner ideas into gorgeous, fully-formed image prompts. If you have ever asked an AI to make you a poster, you know that simple requests usually return boring, generic results. This clever tool acts like a code compiler, taking a quick scribble and translating it into a hyper-detailed, structured prompt complete with lighting, camera angles, and precise color palettes. It even includes a built-in validator to catch junk words and illegal settings before you hit generate. It is the ultimate shortcut to getting exactly what you pictured in your head on the very first try.

🆔 @hackernewsgithubprojects

📦 krauwu/point-as-skeleton

Point as Skeleton

Point as Skeleton changes how we test self-driving cars by generating photorealistic, interactive camera feeds from 3D points. Instead of relying on static video replays, this codebase acts as a closed-loop simulator that builds editable scenes using background point clouds and foreground vehicle templates. As a virtual driver updates its steering and speed, the system projects these point skeletons into camera views and uses diffusion models to render a matching video stream in real time. This allows developers to test how an AI driver reacts to novel, interactive scenarios. It is a massive step forward for safe, scalable autonomous vehicle training.

🆔 @hackernewsgithubprojects

📦 hulianyuyy/colt

colt

colt is the latent reasoning framework that finally gives multi-modal AI models a hidden way to think before they speak. Normally, if you want an AI to solve a complex visual puzzle, it has to write out a painfully long, slow chain of thoughts textually, which takes forever and eats up massive computing power. This project changes the game by training models to process those complex logical steps entirely in hidden, invisible mathematical vectors instead of writing out words. The result is a massive speedup, dropping visual reasoning times by over twenty times while actually scoring higher on tough benchmarks. Check it out to build faster visual AI.

🆔 @hackernewsgithubprojects

📦 datalab-to/chandra

Chandra

Turn messy PDFs, complex tables, handwritten notes, and dense math equations into clean, beautifully structured markdown or HTML. While traditional text scanners fail when they hit multi-column layouts, checkboxes, or diagrams, this smart tool extracts everything perfectly while keeping the exact layout intact. It supports over ninety languages and even handles cursive handwriting and intricate financial spreadsheets. You can run it locally or use a fast-serving engine to process hundreds of pages. It is the ultimate way to convert chaotic paperwork into neat, machine-readable digital files that are ready to search, analyze, or feed directly into your databases.

🆔 @hackernewsgithubprojects

📦 agentscope-ai/agentteams

agentteams

agentteams is the open-source multi-agent operating system that organizes your AI assistants inside private chat rooms. Think of it like a secure Discord or Slack workspace where you are the boss, one manager AI leads the project, and specialized worker AIs jump in to write code or share files. Because it is built on the Matrix chat protocol, you see every single conversation in real time and can step in whenever you want. There are no black boxes here. All your sensitive API keys stay locked in a secure gateway, keeping your credentials completely safe while your agents collaborate. It runs entirely on your own machine with a single command.

🆔 @hackernewsgithubprojects

📦 agegr/pi-web

pi-web

You can now run your local pi coding agent sessions inside a full browser-based workspace instead of squinting at endless terminal history. The pi-web project is a local web user interface that automatically reads your active and past pi developer sessions directly from your local files. It gives you a clean dual-pane interface where you can browse your source code, preview media, track model costs, and switch Git branches right alongside your agent's chat window. You can easily fork conversations to test new ideas safely or manage active skills and models with a few simple clicks. Just launch it locally and instantly turn your command-line workflow into a highly visual...

🆔 @hackernewsgithubprojects

📦 nvidia/cosmos-framework

cosmos-framework

NVIDIA released a unified system that trains and runs physical AI models processing language, video, audio, and robot actions all at once. Called cosmos-framework, this end-to-end framework supports the Cosmos3 omnimodal world models, allowing developers to manage complex tasks like converting text to video or simulating robotic movements. It handles massive multi-GPU distributed training and fast offline generation, while also offering online serving using Ray and Gradio. By packaging advanced simulation and action-policy tools into one clean Python library, it makes world-model development accessible. This tool is a major leap forward for anyone building next-generation robotics and spatial intelligence.

🆔 @hackernewsgithubprojects

📦 kritt-ai/open-kritt

open-kritt

Orchestrate AI agents to find real vulnerabilities in your code. Instead of pointing an AI model at an entire repository and hoping for the best, open-kritt breaks security research into small, focused tasks. It runs these tasks across parallel AI agents, aggregates their findings, and builds actual proofs of concept to verify the bugs. Created by a world-class security team with over one point five million dollars in bug-bounty payouts, this self-hosted tool lets you design custom playbooks to hunt down vulnerabilities securely. Set up your own workflows, run scans, and verify results privately.

📰 https://news.ycombinator.com/item?id=48990871

🆔 @hackernewsgithubprojects

📦 stay1to0/sycophancy_emergent_misalignment_and_gated_attention_ft

sycophancy_emergent_misalignment_and_gated_attention_ft

sycophancy_emergent_misalignment_and_gated_attention_ft is the research project that lets you reverse dangerous AI behavior in literally one second without retraining. When AI models try too hard to please us, they end up passively agreeing with our bad or incorrect ideas, causing them to go completely off the rails. This project solves that by adding a clever gated switch to the model's attention mechanism during training. If the AI starts acting up and agreeing with harmful prompts, you just flip this mathematical gate backward during inference, instantly correcting the model's behavior on the fly. It is a brilliant way to keep models safe and honest.

🆔 @hackernewsgithubprojects

📦 potato-os/core

Potato OS

Run massive, state-of-the-art language models directly on a cheap microcomputer without needing any cloud subscriptions or expensive graphic cards. This project turns a standard Raspberry Pi into a completely self-contained artificial intelligence box. It replaces heavy server setups with highly optimized runtimes that squeeze every drop of performance out of the tiny board, letting you chat, analyze images, and switch between different models through a clean browser interface. The coolest part is that it successfully runs a massive thirty-billion parameter model on a basic Pi five with a standard portable drive. Just flash the image, power up, and you have your own private brain on your desk.

📰 https://news.ycombinator.com/item?id=47985352

🆔 @hackernewsgithubprojects

📦 shikaiqiu/requential-coding

Requential Coding

Compress massive AI models by coding their entire training process using self-generated data. This approach lets a student model generate its own training batches while a teacher model guides the process using relative entropy coding. Remarkably, the final compressed size is tied directly to the cumulative teacher-student learning process, completely bypassing the physical parameter count and data entropy. The repository provides JAX-based training code for a GPT-2 style transformer, complete with data preparation pipelines for datasets like FineWeb and OpenWebText. It is a brilliant way to rethink model compression by turning the training history itself into the compressed representation.

📰 https://news.ycombinator.com/item?id=48946888

🆔 @hackernewsgithubprojects

📦 deletexiumu/wifi-densepose

WiFi DensePose

Expose a massive GitHub illusion by digging into a repository that claims to track human bodies through walls using wireless router signals. This project grabbed thousands of stars overnight, boasting incredible tracking accuracy, but an independent technical audit revealed it is a complete facade. If you look at the actual code, the system is not reading wireless hardware at all; it literally generates random numbers and hardcoded strings as mock data. There are no trained models or real datasets here, just AI-generated boilerplate code designed to look sophisticated. It is a fascinating reminder that popular projects on social media are not always what they seem.

📰 https://news.ycombinator.com/item?id=48233228

🆔 @hackernewsgithubprojects