📦 benjiyaya/minimax-h3-prompt-agentskill

MiniMax H3 Prompt Agent Skill

Transform your messy video ideas into professional-grade prompts with the MiniMax H3 Prompt Agent Skill. This clever tool takes your rough concepts and attached media, then automatically structures them into the exact format needed for MiniMax H3 video generation. It handles five different modes, from text-to-video to image-anchored sequences, and enhances your brief with cinematic details like camera movement, lighting, and sound design. You get a clean, ready-to-paste prompt that preserves your dialogue and maintains character consistency across shots. It is a massive time-saver for anyone using ComfyUI or Hermes Agent. Stop guessing how to format complex video instructions and start generating precise, high-quality scenes with confidence and ease.

🆔 @hackernewsgithubprojects

📦 v4bel/zapscape

Zapscape: KVM Escape

Zapscape is the security research that finally breaks the virtual machine prison on x86 processors. It is a detailed documentation of a vulnerability that allows a guest operating system to escape its sandbox and execute code with full administrative privileges on the host machine. This works by exploiting a tricky memory management bug where the system accidentally reuses a corrupted piece of memory during a cleanup process. The creator provides a proof of concept that demonstrates how a single virtual machine can take over the physical server running it. This matters because it shows that even with nested virtualization enabled, the isolation between cloud tenants is not guaranteed.

📰 https://news.ycombinator.com/item?id=49198843

🆔 @hackernewsgithubprojects

📦 agricidaniel/skill-forge

Skill Forge: Build AI Agents for Claude Code

Build production-grade AI agent skills from scratch without wrestling with complex documentation. Skill Forge lets you design, scaffold, and publish high-quality Claude Code skills using a simple, structured workflow. It solves the headache of creating reliable, reusable AI tools by guiding you through planning, building, and reviewing your skill with clear templates and automated checks. You get to turn vague ideas into structured, functional skills that actually work well, complete with quality scores and easy publishing steps. It is a clever way to standardize how you create these powerful AI assistants, making the whole process much less chaotic and far more repeatable.

🆔 @hackernewsgithubprojects

📦 nikodemon80/comfyui-h3-motion-context

ComfyUI H3 Motion Context

Chain MiniMax H3 video clips so motion and audio genuinely continue across joins instead of restarting from scratch. This project patches ComfyUI to let your next clip pick up exactly where the last one left off, keeping the same direction, speed, and even the exact same audio waveform rather than generating a similar sound. It solves the annoying problem of disjointed cuts by lifting a technical restriction in the original code that blocked intermediate frames. The real magic is in the audio handling, which forces the model to continue the actual recording rather than imitating it, creating seamless transitions that feel natural.

🆔 @hackernewsgithubprojects

📦 gen-verse/skill-entropy-rl

Skill-Entropy RL

Skill-Entropy RL is the open-source toolkit that finally trains large language models to switch between different thinking styles without breaking a sweat. Most AI models struggle when a task requires hopping from coding to logic or math in one go, because they learn to treat every problem as a single, flat skill. This project solves that by teaching the model to recognize when it is switching skills and rewarding it for planning that transition smoothly. It uses a special reward system that scores the model’s ability to juggle these changes, not just the final answer.

🆔 @hackernewsgithubprojects

📦 zhouhao1024/awesome-self-evolving-coding-agents

Awesome Self-Evolving Coding Agents

Awesome Self-Evolving Coding Agents is the curated research library that maps how artificial coders are learning to fix their own mistakes without human help. Instead of just writing code once, these systems analyze their errors, adjust their own logic, and grow smarter with every attempt. This repository gathers the latest academic papers, testing benchmarks, and foundational studies that make this possible. It is a vital guide for developers wanting to understand the shift from static tools to autonomous engineers that improve over time. Check it out to see the future of self-improving software in action.

🆔 @hackernewsgithubprojects

📦 zethwang/agentopsd

AgentOPSD: Smarter AI Learning

AgentOPSD is a reinforcement learning trick that finally helps AI agents learn from their own mistakes without needing extra help. Most AI models struggle when playing long games because they only get a final score, leaving them confused about which specific moves actually mattered. This project solves that by tracking the difference between what the AI thought it knew and what it actually did at every single step. It recursively updates a belief state to pinpoint exactly those pivotal turns that changed the outcome. This turns sparse feedback into dense, useful lessons.

🆔 @hackernewsgithubprojects

📦 xoreaxeaxeax/asm-hall-of-shame

The Slowest CPU Instruction Ever Measured

Make a single line of code take over a minute to finish. This repository is a quirky leaderboard that tracks the absolute slowest possible CPU instructions on modern processors. Instead of optimizing for speed, it intentionally engineers catastrophic slowdowns to see just how terrible performance can get. The number one spot uses a trick where one processor core tries to load a massive chunk of data from a surprisingly slow piece of hardware memory while several other cores aggressively pound on different parts of that same hardware to create a massive traffic jam.

📰 https://news.ycombinator.com/item?id=49214098

🆔 @hackernewsgithubprojects

📦 within-yao/envace

EnvACE: AI World Rehearsal

EnvACE lets an AI model practice solving problems by imagining the entire interaction before actually taking action. Instead of relying on an external simulator or real-world tool calls during training, this framework teaches the model to play two roles at once. First, it acts to generate a response. Then, it rehearses by predicting exactly how the environment would react to that specific action. By training this internal world model, the AI learns to predict its own future consequences, allowing it to run multiple imagined trial runs in parallel, summarize the best approach, and then commit to a single real execution.

🆔 @hackernewsgithubprojects

📦 veris-ai/riley-agent

Riley Agent: Test Voice AI with Real Banking Data

Riley Agent is the open-source benchmark that finally lets you compare every major voice AI platform using the same realistic banking support scenario. It solves the messy problem of testing voice assistants by giving you a consistent, simulated customer service workflow where an AI agent named Riley helps users manage fake credit cards. Instead of wrestling with different setups, you can drop in implementations from giants like OpenAI, Google, or AssemblyAI and watch them handle the exact same conversations with synthetic bank data.

🆔 @hackernewsgithubprojects

📦 gen-verse/past-bench

How Agents Actually Learn From Mistakes

PAST-Bench tests if personal AI agents can genuinely improve over time by learning from past mistakes. Instead of grading isolated tasks, it runs agents through long sequences where early experiences are supposed to help them handle later challenges better. The repo includes a clever framework called Hermes+ that adds specific memory and routing tools to help agents remember and reuse what they have learned. It essentially asks whether an AI remembers its previous failures and uses that knowledge to act smarter next time, rather than starting from scratch every time you talk to it.

🆔 @hackernewsgithubprojects

📦 msp-xen/ae-uav

AE-UAV: The First Air-to-Air Event Camera Drone Dataset

AE-UAV is the first air-to-air event camera drone dataset that turns jagged tracking labels into smooth, continuous motion paths. Most video datasets only check if an object is inside a box every few frames, but AE-UAV captures billions of raw sensor events and maps a perfect, curve-fitted trajectory across every single microsecond. This means researchers can evaluate drone tracking systems at any speed without guessing what happened between frames. It features nearly two hundred flight sequences captured from one drone chasing another, complete with thermal and RGB video for extra context.

🆔 @hackernewsgithubprojects

📦 aweai-team/calibforge

CalibForge: AI Terminal Calibration

CalibForge transforms how artificial intelligence learns to use command lines by filtering out tasks that are either too easy or impossible to solve, leaving only the perfect middle ground for training. Instead of dumping thousands of random coding challenges on a model, this project uses an adversarial process where different AI agents try each task and only the ones with mixed results survive. This creates a curated dataset of five thousand precise terminal exercises that force the learner to actually think, rather than guess. By training on this calibrated data, models see massive performance jumps on software engineering benchmarks because they are learning from genuine difficulty.

🆔 @hackernewsgithubprojects

📦 fudan-generative-vision/dynetrion

Dynetrion: The AI That Simulates Protein Movement

DyneTrion is the generative model that finally captures how proteins move and change shape over time. Most AI tools only guess what a static molecule looks like, but this project simulates the actual physical dance of atoms across different time scales. It solves the headache of predicting how complex biological structures shift and flex in real life. By training on massive datasets of molecular dynamics, it creates smooth, realistic animations of these tiny machines working. This matters because seeing the motion helps scientists understand diseases and design better medicines. It turns confusing data into clear, playable video clips of biology in action.

🆔 @hackernewsgithubprojects

📦 mbbill/mind-expander

Mind Expander

AI coding tools write fast code but explain it through exhausting walls of text. Mind Expander changes that by instantly turning your Rust or TypeScript codebase into an interactive, infinite-canvas browser diagram. Instead of reading long markdown summaries, you and your AI agent work on the exact same visual graph of modules, dependencies, and refactoring plans. It translates complex relationships and system architecture into a clear, source-backed visual tour you can click through. It is like having a GPS map for your system architecture that actually links back to your live files, making code reviews and refactoring plans incredibly simple to verify.

📰 https://news.ycombinator.com/item?id=48281337

🆔 @hackernewsgithubprojects

📦 derec4/internships-and-newgrad

Internships and New Grad

Save hours of searching by using a tool that automatically aggregates and deduplicates tech internship and new grad positions into one clean list. This project runs a Go program that fetches data from multiple popular job boards, parses the results, and merges them to remove duplicates while sorting by posting date. It creates a master spreadsheet you can actually use, turning scattered listings into a single source of truth for your job hunt. It is a practical way to stay ahead without manually copying and pasting from ten different sites. Grab the code, run it, and let the automation handle the busy work for you.

🆔 @hackernewsgithubprojects

📦 oil-oil/oil-motion

How to Make AI Video Respond to Your Scroll

Oil Motion turns AI video from a passive clip into an interactive tool that follows your scroll, mouse, or touch. It does this by first locking down key start and end frames to keep the subject consistent, then using AI to fill in the smooth motion between them. The system cleans up the video by removing awkward pauses and compressing it into efficient web assets. Instead of just playing from start to finish, the code maps your physical actions—like dragging a slider or scrolling down the page—directly to specific frames in that animation. This means you can pause, rewind, or scrub through the video naturally while watching it.

🆔 @hackernewsgithubprojects

📦 hakanseven12/opencadstudio

Open CAD Studio: Free 2D and 3D CAD in Rust

Open CAD Studio lets you draft precise 2D blueprints and model 3D shapes right in your browser. Built in Rust, it handles heavy files like DWG and DXF without choking, thanks to GPU-accelerated rendering that makes the interface feel snappy even with complex designs. It even lets you pull in external reference drawings so multiple files stay in sync. The best part? It runs locally or online, keeping your data private while giving you professional tools for free. If you need reliable CAD that respects your privacy and doesn't cost a dime, this is the real deal.

🆔 @hackernewsgithubprojects

📦 jordanrendric/claude-video-vision

Claude Code Video Vision

Watch Claude actually see and hear videos by passing a YouTube link or local file into Claude Code and getting back clear frame images and spoken words. This plugin uses ffmpeg to pull key pictures and sends the sound to your preferred audio tool, whether that is the Gemini API, OpenAI, or a fully local whisper setup on your own machine. It is genuinely clever because Claude adjusts the video quality and frame rate based on what you ask, so you get detailed shots for specific moments and lighter previews for long summaries.

🆔 @hackernewsgithubprojects

📦 universal-commerce-protocol/ucp

Universal Commerce Protocol Explained

UCP is the open standard that lets AI agents and apps talk to stores without messy custom code. Instead of building one-off integrations for every shop, businesses publish a simple profile declaring what they can do, like checkout or loyalty rewards. Your favorite app or bot reads that profile, discovers the capabilities, and handles the rest using secure, standard methods. It means your smart assistant can find products, manage your cart, and pay for you across any site that supports the protocol. No more manual data entry or risky workarounds.

🆔 @hackernewsgithubprojects