📦 bevibing/socrates-skill

Socrates Skill

Turn your artificial intelligence assistant into a personal tutor that refuses to give you the answers. By installing socrates-skill, you add a teaching mode to your developer tools. When you ask it about a complex codebase, an architecture diagram, or a document, the system will never hand over a direct solution. Instead, it guides you to the answer yourself through five levels of targeted questioning, from clarifying your initial assumptions to presenting hypothetical scenarios. If you get stuck or demand a hint, it simply breaks the problem down into smaller pieces, ensuring you actually learn how your systems work.

📰 https://news.ycombinator.com/item?id=47657874

🆔 @hackernewsgithubprojects

📦 unicity-aos/aos-ce

aos-ce

Build and run intelligent software in an open, highly secure sandbox. With aos-ce, you can run a lightweight, community-driven operating system designed specifically for managing autonomous agents. Instead of letting programs run wild, this system isolates tasks into individual, secure sandboxes called capsules that communicate over a protected event bus. The most exciting part is its self-building tool, which actually teaches agents to inspect their own environment, identify missing features during real tasks, and safely write and compile new capsules to expand their own capabilities. It is a completely modular, inspectable playground that turns agents from simple chat programs into self-improving tools.

🆔 @hackernewsgithubprojects

📦 boona13/mykonos-island-voxels

Mykonos Island Voxels

mykonos-island-voxels is the browser-based world builder that wraps the sun-bleached look of a Mediterranean holiday into a zero-install creative toy. Instead of grinding for resources or stressing over high scores, you get to drop beautiful, hand-painted blocks onto a tiny grid and watch a picturesque Greek village assemble itself right in front of your eyes. It is loaded with over seventy-five gorgeous, tiny assets like whitewashed cottages, cobalt-blue domes, and flowering bougainvillea. Best of all, it runs on pure JavaScript with no modern bundler bloat, letting you sculpt your own private coastal paradise on any device.

🆔 @hackernewsgithubprojects

📦 disler/fusion-harness

Fusion Harness

Combine the unique strengths of different frontier models simultaneously instead of constantly trying to pick a single winner. This clever extension harness lets you run a two-model agentic engineering team right from your coding workspace. It orchestrates roles, letting a planning model act as an architect while a building model writes the code, merging their independent output into one unified result with clear attribution. It even features a self-correcting validation loop where an automated gatekeeper tests the work and feeds failures back to the builder until the code is proven to work. Stop compromising on a single AI brain and put a coordinated, self-testing team to work on your next...

📰 https://news.ycombinator.com/item?id=48981521

🆔 @hackernewsgithubprojects

📦 xuefeng-cvr/depthart

depthart

depthart is the lightweight visual computer model that finally brings high-quality depth sensing to compact, everyday hardware. It takes a standard flat photo and accurately calculates the distance of everything in the frame down to the exact meter. While massive artificial intelligence models usually require giant servers to run these calculations, this clever project shrinks the math down so it runs directly on normal desktop graphics cards and tiny, portable microcomputers. It is perfect for robotics, smart cameras, or anyone wanting to build real-time spatial awareness into a small device without melting their hardware.

🆔 @hackernewsgithubprojects

📦 openlanguagemodel/openlanguagemodel

OpenLanguageModel

Build and experiment with custom transformer architectures without the headache of writing training pipelines from scratch. When you want to design a new neural network, you are usually forced to choose between massive frameworks that hide all the math, or writing thousands of lines of boilerplate code just to handle multi-GPU training and data loading. This library sits right in the middle, giving you readable PyTorch-native blocks for attention, norms, and feedforward layers while quietly managing the complex training loops behind the scenes. It is perfect for testing new ideas or learning how these networks actually tick. Check it out and start designing your own models today.

🆔 @hackernewsgithubprojects

📦 alibaba-damo-academy/rynnbrain

RynnBrain

Researchers just trained a new brain for physical robots that lets them handle complex real-world tasks with incredible agility. Developed by Alibaba's DAMO Academy, rynnbrain is an open embodied foundation model designed to give robots a smarter, highly generalizable way to perceive and interact with the physical world. Instead of hardcoding specific movements, this model acts as a general-purpose brain that translates sensory data into direct physical actions. It helps robots adapt to completely new environments and handle objects they have never seen before, bringing us much closer to having helpful, multi-purpose robotic assistants in our everyday lives.

🆔 @hackernewsgithubprojects

📦 ayghri/i-have-adhd

i-have-adhd

i-have-adhd is the coding assistant plugin that finally stops AI models from burying your answers in corporate fluff. Instead of making you scroll through polite small talk, vague explanations, and friendly closers, this tool forces coding agents like Claude Code and Cursor to give you action-first, highly structured responses. It enforces strict rules like leading with immediate commands, numbering multi-step tasks, and capping list items. You get a direct route to your next move, with zero conversational filler. It is a brilliant way to keep your developer workflow fast and completely distraction-free.

📰 https://news.ycombinator.com/item?id=48184192

🆔 @hackernewsgithubprojects

📦 hyscaler/hycanvas

HyCanvas

Design stunning graphics, social posts, presentations, and even videos in your browser without ever worrying about monthly subscriptions, paywalls, or forced watermarks. This project gives you a completely free, self-hostable design platform that runs entirely on your own terms. Instead of relying on closed ecosystems, you can run this whole suite from a single, lightweight binary on your own server or desktop, keeping every template and export completely private. It even supports a bring-your-own-key setup for integrating your favorite artificial intelligence tools securely. Self-host it today to reclaim absolute control over your digital creative studio.

📰 https://news.ycombinator.com/item?id=48988317

🆔 @hackernewsgithubprojects

📦 zli12321/lhtb

Long Horizon Terminal Bench

Test how well artificial intelligence actually handles real, grueling work by dropping it into a terminal for hundreds of steps. Instead of letting agents write one quick script and brag about it, lhtb forces them to operate in a live container where their work is graded by hidden, objective verifiers. They cannot just say they are finished; they have to keep working and adapting to feedback until they truly pass or run out of time. Even the best models only solve about a quarter of these tasks, and half are completely unsolved. It is the ultimate reality check for AI agents.

🆔 @hackernewsgithubprojects

📦 w3cj/how-llms-work

how-llms-work

You can train a decoder-only GPT transformer entirely from scratch in your web browser with zero machine learning libraries. An interactive web application called how-llms-work runs a complete educational pipeline locally using raw TypeScript. Instead of hiding the math inside complex frameworks, it implements every single step of modern language models by hand, from simple pattern matching and backpropagation to subword tokenizers and word embeddings. You can inspect active neural network layers, watch word vectors cluster together in real time, and trigger multi-threaded training operations inside a clean interface. It makes the actual mechanics behind generative artificial intelligence transparent and accessible.

🆔 @hackernewsgithubprojects

📦 inferock/inferock-bench

Inferock Bench

Audit your AI bills and track actual token costs locally by routing your LLM traffic through a secure, self-hosted proxy. Instead of blindly trusting monthly invoice totals, inferock-bench acts as an independent observer that sits between your app and major providers like OpenAI, Anthropic, Gemini, and OpenRouter. It generates precise, per-call receipts that capture exact token usage, latencies, and silent errors, calculating exactly how much cash you lose on responses that timed out, cut off mid-sentence, or failed entirely. Set it up in minutes, swap two SDK lines, and start keeping your AI vendors completely honest.

📰 https://news.ycombinator.com/item?id=48868354

🆔 @hackernewsgithubprojects

📦 blaizzy/nativ

Nativ

Run frontier artificial intelligence models completely locally on your Apple Silicon Mac without any cloud subscriptions or account signups. This open-source macOS app bundles an optimized machine learning server to let you download, manage, and run highly efficient local models for chat, vision, and coding. You can use it as a private, secure desktop assistant or turn your machine into a local API server compatible with popular developer tools. It provides live performance metrics directly on your dashboard, showing memory pressure and decoding speeds. Grab this free desktop workspace to unlock your hardware's true offline intelligence.

🆔 @hackernewsgithubprojects

📦 avasol/galadriel-public

galadriel-public

Imagine having an AI assistant that actually remembers every single decision, bug, and conversation it has ever had, and can even edit its own code to fix its own bugs. Meet galadriel-public, a self-hosted Claude agent harness that builds a local, verbatim memory palace on your own machine. Unlike other agents that run up massive API bills re-reading past conversations, this project stores your history locally to query it for absolutely zero token cost. Even better, it exploits prompt caching to slash your overall Claude API costs by ninety percent. It is the ultimate playground for running a truly continuous, self-improving assistant.

🆔 @hackernewsgithubprojects

📦 wzk1015/worldcuparena

WorldCupArena

WorldCupArena is the benchmarking suite that finally puts artificial intelligence and deep-research agents to the ultimate real-time test of football prediction. Instead of evaluating models on static, outdated knowledge bases, this project challenges them to predict actual future matches before kickoff, scaling from Champions League games to the entire World Cup. The most fascinating aspect is how it measures a model's ability to research, forcing agents to browse current injury news, tactical setups, and market odds while strictly checking for information leakage. By evaluating everything from final scorelines to the exact minute of a substitution, it provides a fascinating, objective scoreboard of machine intelligence.

🆔 @hackernewsgithubprojects

📦 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