📦 mgechev/skillgrade

skillgrade

You can now run unit tests on AI agents to see if they actually know how to use your custom tools and instructions. A lightweight utility called skillgrade makes this incredibly easy by orchestrating simulated work environments inside Docker containers. It sends instructions to your agent, lets it perform tasks, and then scores the outcome. You can write simple deterministic scripts that verify files or run an automated AI rubric to grade the agent's workflow quality. Best of all, it works locally or in your CI pipeline, and you can preview the results in a clean browser dashboard. It is the perfect tool for proving your agents actually work before...

📰 https://news.ycombinator.com/item?id=48864778

🆔 @hackernewsgithubprojects

📦 esi-bench/esi-bench

esi-bench

esi-bench is the spatial intelligence benchmark that finally treats AI observers as active physical agents. Instead of feeding models a static set of images and asking them to guess what is happening in a room, this project lets them drive. Built on a physics simulator, the system forces models to actively navigate, look under objects, and sequence physical actions to answer complex questions about their surroundings. It turns out that when models can move around to investigate, they easily outperform passive vision, but they still struggle with choosing smart actions and knowing when their information is incomplete. It is a fascinating look at the future of robotic common sense.

🆔 @hackernewsgithubprojects

📦 tencent-hunyuan/hils-attention

HiLS-Attention

Train language models to handle virtually infinite text length without slowing to a crawl. The hils-attention repository introduces a smart way to manage computer memory during long chats or massive document reading. Normally, artificial intelligence gets bogged down because it tries to look at every single word at once. This project solves that by compressing large blocks of text into smaller summaries, letting the model instantly pick only the most relevant sections to focus on. This means you get lightning-fast processing and much better memory extrapolation. Give hils-attention a look to see how it makes ultra-long AI context incredibly efficient.

🆔 @hackernewsgithubprojects

📦 kacper-daftcode/vllm-moet

vLLM-Moet

Serve massive frontier models like GLM-5.2 and DeepSeek-V4-Flash directly on consumer Blackwell graphics cards without running out of memory. While these massive models normally require enterprise data centers, vllm-moet uses custom-written machine code kernels to compress the massive mixture-of-experts layers down to just two bits, while keeping a clever four-bit cache to restore original quality on the fly. When a model is still too big, it seamlessly turns your graphics card into a cache, keeping the active parts on the card and streaming the rest from your system memory or SSD with zero loss in output quality. Grab the code, boot up a model, and run massive AI on your...

🆔 @hackernewsgithubprojects

📦 majidmanzarpour/threejs-game-skills

Three.js Game Skills

Build fully playable, high-quality browser games using artificial intelligence assistants that act as your professional game development team. This repository installs custom skills into agents like Claude Code, allowing them to autonomously write gameplay logic, generate three dimensional models, compose sound effects, design slick user interfaces, and run automated playtests. Instead of writing boilerplate code, you simply tell your helper to construct a game from scratch, and it coordinates specialized workflows to make it happen. It is an incredibly powerful way to bring complex interactive ideas to life in your browser instantly.

🆔 @hackernewsgithubprojects

📦 cpp2rust/cpp2rust

cpp2rust

cpp2rust is the compiler tool that automatically translates old C++ codebases into fully safe Rust. Moving away from C++ usually means rewriting everything by hand to satisfy Rust's strict safety rules, but this tool takes a different path. It parses your existing code, maps out how the data flows, and outputs clean Rust files. To keep things safe without breaking how your code behaves, it uses a clever helper library that manages complex C++ pointers behind the scenes. This gives you a fast, automated way to upgrade legacy software to a modern language without starting from scratch.

📰 https://news.ycombinator.com/item?id=48862086

🆔 @hackernewsgithubprojects

📦 ather-techie/rag-interview-system

rag-interview-system

Preparing for AI developer interviews just got much easier with rag-interview-system, a massive open source handbook featuring over five hundred real-world questions and answers covering forty-one different retrieval-augmented generation architectures. Landing a modern AI job requires knowing more than just basic document search, and this guide walks you through complex setups like knowledge graphs, self-correcting retrieval pipelines, and speculative generation. It goes beyond theoretical concepts to prepare you for realistic system design rounds by analyzing critical production failures like semantic cache leakage and conversational drift. Check it out to level up your engineering skills before your next big interview.

🆔 @hackernewsgithubprojects

📦 utahmobl/opencap-monocular

OpenCap Monocular

You can now extract full 3D human biomechanics and skeletal motion from a single smartphone video. The opencap-monocular repository achieves this by combining 3D pose estimation, camera optimization, and biomechanical modeling. Traditionally, capturing physics-grade joint angles and muscle forces required expensive multi-camera labs, but this project processes a single-camera feed to generate accurate files compatible with OpenSim. It even integrates with an activity classifier to automatically recognize movements like squats or walking and optimize the calculations. It is a massive win for sports science and physical therapy, turning any phone into a portable biomechanics lab.

🆔 @hackernewsgithubprojects

📦 sazardev/goca

Goca

Build perfectly structured Go applications in seconds without writing any boilerplate code. If you are starting a new Go service, this tool scaffolds an entire Clean Architecture setup with one command. Instead of manually creating domain entities, use cases, database repositories, and HTTP or gRPC handlers, you just tell it what fields you need. It generates clean, decoupled layers, hooks up dependency injection, and even writes your integration tests automatically. It even includes safety guards like dry-run previews and automatic file backups so you never accidentally overwrite your work. Grab goca and start writing clean Go code today.

🆔 @hackernewsgithubprojects

📦 rodiun/frugon

Frugon

frugon is the local command-line tool that finally shows you how to slash your artificial intelligence bills without sending your private data anywhere. It runs entirely on your own machine, analyzing your raw API logs to calculate exactly how much cash you would save by swapping out expensive models for cheaper alternatives. You can set up its local proxy shim to capture your traffic, and the tool immediately highlights which simple requests can be routed to budget-friendly models and which complex ones need the premium tier. It is the ultimate way to stop overpaying for token usage and optimize your setup today.

📰 https://news.ycombinator.com/item?id=48816724

🆔 @hackernewsgithubprojects

📦 markfulton/claude-antigravity-agents

claude-antigravity-agents

The claude-antigravity-agents skill is the Claude Code extension that finally lets you run heavy background coding tasks in parallel without burning your subscription tokens. It turns Claude into an active orchestrator that delegates massive jobs like full-repo audits, security reviews, and large refactors to Google's Antigravity CLI. While you and Claude keep building your main features, a secondary model runs the grind work in an isolated background sandbox. Once the sub-agent finishes, Claude automatically runs build checks and reviews the code changes before merging them, giving you a safe, multi-model workflow that multiplies your coding speed.

📰 https://news.ycombinator.com/item?id=48817248

🆔 @hackernewsgithubprojects

📦 gokapso/whatsapp-cloud-inbox

WhatsApp Cloud Inbox

Manage multiple corporate chat accounts from a single dashboard using an elegant web interface. This project handles the official chat network API, giving you a shared interface that mimics the familiar messaging experience. The coolest part is how it automatically solves API limitations, like checking if your last customer interaction was within twenty-four hours and switching to authorized messaging templates if it has been longer. It handles custom interactive buttons, documents, and live media while tracking read receipts across different business numbers. Try running this simple self-hosted setup to keep all your customer chats organized in one place.

🆔 @hackernewsgithubprojects

📦 op7418/guizang-material-illustration

guizang-material-illustration

guizang-material-illustration is an AI assistant skill that creates high-quality explanatory diagrams and material-style charts featuring integrated Chinese text labels. Instead of generating generic decorative images, it translates complex ideas, data, or concept drafts into clear visual guides like flowcharts, mechanism diagrams, and beautiful 3D charts. By focusing on the central illustration layer, it cleanly extracts data from messy screenshots or raw text, packages the visual metadata, and renders readable diagrams perfect for slides, documentation, or social media cards. It is an incredibly clever tool for transforming abstract explanations into instantly understandable visual summaries.

🆔 @hackernewsgithubprojects

📦 anomalyco/terminal-control

terminal-control

Terminal-control is the terminal testing tool that lets AI agents and developers drive complex terminal applications with actual screen-based feedback. Instead of blindly guessing from raw text logs, this tool creates a real virtual terminal, allowing you to start background sessions, send precise keystrokes, and read the visible screen exactly as a human sees it. You can write robust automated tests, wait for specific on-screen text, and even capture screenshots or record MP4 videos of terminal sessions. It takes the guesswork out of terminal automation by providing a stable, reliable way to control, inspect, and test interactive terminal apps.

📰 https://news.ycombinator.com/item?id=48867841

🆔 @hackernewsgithubprojects

📦 dicklesworthstone/destructive_command_guard

Destructive Command Guard

AI coding assistants are incredibly productive until they accidentally run a rogue command that wipes out your entire database or deletes your git history. That is why destructive_command_guard is such a clever project: it acts as a high-speed firewall specifically designed to intercept and block dangerous terminal commands before an AI agent can execute them. Built in Rust for blazing speed, it parses incoming tool requests, runs them through a modular safety checklist, and instantly stops destructive operations while offering safe alternatives. It is a simple, brilliant way to let autonomous agents write your code without worrying they will accidentally destroy your entire workspace.

🆔 @hackernewsgithubprojects

📦 gostonx/uninstally

Uninstally

Uninstally is the native macOS uninstaller that finally cleans up the hidden junk other apps leave behind when you throw them away. Instead of just dumping an app in the Trash, it uses smart bundle detection to hunt down orphaned caches, logs, and support files buried deep in your system. You get a built-in safety score to preview exactly what is being deleted, batch uninstall tools, and even a right-click Finder menu to wipe apps instantly. It runs entirely on your Mac with zero trackers. Next time you clean house, let this app do the deep scrubbing.

🆔 @hackernewsgithubprojects

📦 jbarrow/commonforms

Commonforms

Static PDF documents can now be automatically transformed into interactive, fillable forms using open-source machine learning models. A new tool called commonforms analyzes the layout of any standard PDF to detect where empty spaces, text boxes, and signature areas should go, instantly embedding functional input fields. Instead of manually drawing boxes in expensive editing software, developers can run a single command in their terminal or write a few lines of Python code to update their files. It uses specialized lightweight models trained on a massive custom dataset to accurately pinpoint form fields, making digital paperwork dramatically easier to handle.

🆔 @hackernewsgithubprojects

📦 nebusec/cybermeowfia

cybermeowfia

A security vulnerability called GhostLock has quietly lingered inside every single Linux distribution for fifteen years, and researchers just released the code to prove it. The cybermeowfia repository gathers real-world proof-of-concept exploits for critical vulnerabilities discovered by the security team at Nebula. Its main focus is a sophisticated memory flaw in the Linux kernel where timing-based lock requests are forced into a state of confusion. By carefully coordinating background threads and manipulating process scheduling, the exploit bypasses kernel protections to gain complete control. It is a fascinating look at how tiny, decades-old code oversights can eventually lead to complete system takeovers.

🆔 @hackernewsgithubprojects

📦 vinhhien112/three.js-object-sculptor-codex-plugin

Three.js Object Sculptor

You can now transform flat images into interactive, animation-ready 3D models using pure code. Instead of relying on heavy mesh files or photogrammetry, the three.js-object-sculptor-codex-plugin uses a brilliant AI-guided workflow to analyze an image, plan the structure, and write a procedural Three.js factory in TypeScript. It blocks out the shapes, layers realistic physical materials, and sets up real pivots and joints so the object is ready for physics and motion. It even compares browser screenshots against the original image to auto-correct itself, giving web developers lightweight, highly customizable 3D assets directly from a reference photo.

🆔 @hackernewsgithubprojects

📦 robtand/prismaquant

PrismaQuant

Most mixed-precision tools guess how to compress artificial intelligence models, but PrismaQuant actually measures end-to-end performance to find the perfect fit. Instead of forcing every part of a massive language model into the same restrictive format, this clever allocator analyzes each individual layer to see exactly how sensitive it is. It assigns higher precision to the critical parts and compresses the rest using a fast mathematical knapsack solver. By validating every decision against real performance metrics, it produces incredibly light models that run natively on standard engines like vLLM with zero custom software required. It is the ultimate way to shrink your models without sacrificing their intelligence.

🆔 @hackernewsgithubprojects