📦 dreamzero0/dreamzero

DreamZero: The Robot That Predicts the Future

DreamZero makes robots act like they can see the future, letting them perform complex tasks without ever seeing them before. It’s a world action model that simultaneously predicts what the video will look like and what moves the robot should make, essentially dreaming out the next step in real time. This is huge because it solves the massive data problem in robotics; instead of needing thousands of hours of practice for every new task, this system generalizes instantly to unseen challenges. It even topped major leaderboards by learning entirely from standard datasets, proving that predicting the visual world is the key to smart, flexible robot behavior.

🆔 @hackernewsgithubprojects

📦 inevolin/k8s-cpu-limits-analyzed

K8s CPU Limits: The Hidden Performance Killer

This analysis proves that setting CPU limits in Kubernetes is silently destroying your application performance. While most developers treat limits as safe headroom, this repository demonstrates that they actually cause severe throttling, making apps up to four times slower without raising any red flags on standard dashboards. The project provides a clear, evidence-based guide explaining why removing these limits while keeping CPU requests is the only way to fix unexpected slowness and hidden memory issues. The core takeaway is simple: stop setting CPU limits to avoid artificial bottlenecks, and instead rely on requests to guarantee your share of the processor.

📰 https://news.ycombinator.com/item?id=49296939

🆔 @hackernewsgithubprojects

📦 vvedantb/eva

EVA: Cloud AI Coding Agents That Work While You Sleep

EVA is the cloud agent orchestrator that lets AI coding assistants work on your code while you focus on your day job. It spins up safe, isolated cloud environments where AI agents can run long tasks, browse live previews, and write code without touching your local machine. You simply point it at a GitHub repo, drop in a task, and watch it go. When it’s done, you get a clean pull request with diffs to review—no local setup, no babysitting, just shipped work.

📰 https://news.ycombinator.com/item?id=48875320

🆔 @hackernewsgithubprojects

📦 lzyang2000/perceptive_cbf_rl

PAC-MAN: Humanoid Dodgeball Safety

A humanoid robot just dodged a thrown ball nineteen times out of twenty without falling, using only a simple depth camera on its head. This is PAC-MAN, a research project from Caltech that teaches a Unitree G1 robot to avoid physical harm. Instead of just learning to move, the robot is trained with strict safety rules that act like invisible barriers. It watches a small, sparse image of the ball approaching and instantly decides whether to duck, step left, or step right. The coolest part is that it works on the real robot right away, no extra tuning needed.

🆔 @hackernewsgithubprojects

📦 benja/ask

Ask: The Terminal AI That Keeps Its Hands Off

Ask is the terminal command that hands you the answer without taking control of your files. Most coding tools edit your code behind the scenes, but Ask runs in read-only mode, forcing you to type the commands yourself. You ask a question, get a quick reply, and your shell stays right where you left it. It supports major AI agents like Codex and Claude, saving every session so you can pick up right where you left off. This is the perfect way to learn from an AI without worrying about it accidentally breaking your project. Stop letting bots code for you and start understanding the tools in your own terminal.

📰 https://news.ycombinator.com/item?id=49412440

🆔 @hackernewsgithubprojects

📦 justrach/codegraff

Codegraff: The Operating System for AI Agents

Codegraff runs AI agents like a full operating system, not just a chatbot. Built in Zig for speed, it handles the heavy lifting of memory management, tool execution, and sub-agent orchestration so your AI can actually do work, not just talk about it. The standout feature is its evolution loop, which allows the system to learn from past performance and improve its own coding strategies over time. This turns a static model into a persistent, self-improving worker that can manage complex tasks, debug errors, and verify results. It is a serious look at how AI infrastructure needs to evolve to support real autonomy.

🆔 @hackernewsgithubprojects

📦 opentokenz/mcpx

MCX: The Bridge That Lets AI Edit Your Local Code

MCX is the local gateway that finally lets AI assistants safely touch your actual code. Instead of just chatting, this tool gives models like ChatGPT and Claude direct, structured access to your project files, terminals, and build tasks right from your machine. It solves the messy problem of bridging cloud-based AI with your private, local environment by providing a single, secure interface. You get full visibility into code changes and can approve or deny specific actions before they happen. It turns your local setup into a smart, interactive workspace. If you want your AI to genuinely help you code without guessing, this is how you make it work.

🆔 @hackernewsgithubprojects

📦 ori-mrg/prioreye

PriorEye: Teaching Cars to See Around Corners

PriorEye gives self-driving cars a photographic memory of the road ahead. It feeds the system past street views from the same location, captured on different days, so the car can anticipate obstacles before they appear in the live camera feed. In one test, the car slowed down for a crosswalk it couldn't see yet, simply because it had seen it before. This adds a layer of foresight that helps the vehicle drive safer and more calmly, even when the current view is blocked by shadows or weather. It turns driving software from a reactive system into something more like an experienced human driver who knows the neighborhood.

🆔 @hackernewsgithubprojects

📦 piratuks/invoice-builder

Invoice Builder: Your Offline Invoice Maker

Invoice Builder runs entirely on your computer, storing every client, item, and draft inside a local database file that never leaves your machine. This Electron-based desktop app solves the privacy and speed problems of online tools by giving freelancers full control over their financial data. You can create detailed invoices and quotes, then export them as polished PDFs or structured XML files to meet specific digital requirements. Because everything happens locally, there are no servers to manage and no monthly fees to worry about. It is a private, reliable way to handle billing without ever uploading a single byte to the cloud.

🆔 @hackernewsgithubprojects

📦 duty1g/x64dbg-mcp-server

Your AI Assistant Just Learned to Debug Code

The x64dbg-mcp-server is the bridge that lets your AI assistant take the wheel of professional reverse engineering. It turns your desktop debugger into a smart, controllable endpoint where an AI can step through code, read memory, and set breakpoints without you touching a single key. Built from scratch in Zig, it runs as a single file with zero external dependencies, so it stays fast and clean. The coolest part is how it works: the AI doesn't just watch the code; it actively drives the debugging session to figure out how a program behaves in real time.

🆔 @hackernewsgithubprojects

📦 bbaudio-2025/comfyui-mmh3-ultimateupscale

MMH3 Ultimate Upscale Fixes GPU Memory Issues

MMH3 Ultimate Upscale is the ComfyUI node that lets you enhance long, high-resolution MiniMax H3 videos without blowing up your graphics card memory. This tool solves a major problem for AI video creators: standard upscaling tools simply cannot handle the massive size of long clips or the unique way this specific video model stores audio and picture together. By breaking your video into small time slices and spatial tiles, this node processes them one piece at a time. This keeps your memory usage low enough to run on smaller hardware.

🆔 @hackernewsgithubprojects

📦 nomadamas/cozyclay

CozyClay: Directing Video with AI

CozyClay lets an AI assistant move your camera and pose your characters just by typing plain text into a chat box. This open source studio runs entirely in your browser, giving you a full 3D stage to block scenes and plan shots without installing heavy software. The real surprise is the connection it makes between text and motion. You can ask for a low wide profile shot, and the virtual camera instantly flies into position. You can even describe a character sprinting and tripping, and the tool generates the physical animation for you.

🆔 @hackernewsgithubprojects

📦 nvidia/skillevaluator

SkillEvaluator: Testing AI Skills

SkillEvaluator by NVIDIA acts as a quality control station for the instruction files that give AI agents their abilities. The most surprising part is that it doesn't just check if those instructions are written correctly, but actually runs the agent in a sandbox to see if the new skill genuinely improves its performance. Think of it like a software update that only ships after proving it works, rather than just hoping it does. It catches security risks, finds redundant instructions, and measures real behavior changes before you deploy them.

🆔 @hackernewsgithubprojects

📦 b-nnett/grok-bot-0.18-reconstructed

Grok Bot 0.18 Reconstructed: The AI Switchboard

Take a popular AI desktop app and swap its fixed backend for a flexible switchboard that connects to your existing Cursor, Claude, or OpenRouter sessions. Grok Bot 0.18 Reconstructed is a hacker’s reverse-engineered take on the official macOS application, turning a black box into a transparent, modifiable tool. The project’s standout feature is a local inference router that lets you redirect your AI chats to any compatible provider without losing the original app’s polished interface or plugin support. It also allows you to run the code execution sandbox entirely on your own machine using Docker, cutting out the cloud.

🆔 @hackernewsgithubprojects

📦 thebuggeddev/football-stadium-kimi

Football Stadium Kimi: The 3D Seat Viewer

Fifty thousand seats, zero downloaded 3D models. The project called Football Stadium Kimi builds an entire stadium bowl purely from code. It is a web tool that lets you pick any seat in a three-tier arena and fly into a first-person view to see the exact sightline before you buy a ticket. Below you, a live match simulation plays out while thousands of animated fans cheer in the stands. This solves the problem of guessing what a view looks like by giving you a realistic, fully rendered preview of the pitch from your specific chair.

🆔 @hackernewsgithubprojects

📦 tenequm/pond

Pond: The Searchable Archive for All Your AI Agent Sessions

Pond turns your scattered AI agent history into a single, searchable archive that your tools can actually query. Instead of losing work when you switch from one coding assistant to another, this tool captures every session from platforms like Claude Code and Codex, storing them losslessly in a local folder or your own cloud bucket. It then builds an index that lets you ask specific questions, like how you solved a tricky bug months ago, and get a precise answer without reading through massive logs. This solves the problem of digital amnesia, ensuring that the context of your past decisions remains accessible and usable by any future agent.

📰 https://news.ycombinator.com/item?id=49376500

🆔 @hackernewsgithubprojects

📦 adolanium/hermes-resetwatch

Resetwatch: Your AI Plan Dashboard

Resetwatch turns your scattered AI subscription limits into a single, live dashboard inside Hermes Desktop. It pulls real-time usage data from providers like Claude, Codex, and Cursor using existing local logins, so you instantly see exactly how much quota is left and precisely when it resets. No manual refreshing, no guessing, and no messy web scraping involved. Just clear, honest numbers that update automatically every few minutes while you work. It even handles older vendors by letting you set simple manual timers if needed. This is the cleanest way to stop worrying about hitting your monthly cap, giving you total control over your AI budget in one place.

🆔 @hackernewsgithubprojects

📦 cclank/lanshu-create-ai-presenter-video

How Lanshu Creates AI Presenter Videos

The most surprising part of the Lanshu Create AI Presenter Video project is that it treats the spoken narration as the master clock for the entire video, ensuring every visual element aligns perfectly with the audio. This repository acts as a structured guide for creating realistic, publish-ready videos where a person appears to speak to the camera. It solves the problem of inconsistent AI generation by enforcing strict checks on identity, lip sync, and audio timing before you even start rendering. By locking the script and voice first, it prevents the common issue of AI faces drifting or mouth movements feeling off.

🆔 @hackernewsgithubprojects

📦 deep-jlu/awesome-graph-engineering

Graph Engineering: The Blueprint for AI Agents

Instead of treating AI agents as isolated chatbots, Awesome Graph Engineering maps out a structured path to system-level intelligence using graph structures. This curated repository, built by researchers at JLU, organizes papers, benchmarks, and tools into a clear hierarchy: from basic model training, to individual agent skills, up to complex system coordination. It solves the problem of scattered research by showing how explicit, dynamic graphs can organize tasks, manage memory, and let multiple agents coordinate effectively. Whether you are building software automation, scientific discovery systems, or healthcare assistants, this single resource is your map.

🆔 @hackernewsgithubprojects

📦 cyberful/cyberful

Cyberful: The Open-Source AI Red Team

Cyberful acts as an autonomous security lab that orchestrates over three hundred tools to hunt down vulnerabilities before real attackers do. It is not just a chatbot; it is a structured system where independent agents test exploit paths while a strict control layer ensures every finding is verified and evidence is preserved. This setup turns complex penetration testing into a repeatable, open-source workflow that anyone can run. It is a clever way to bring serious, multi-agent security research to your own infrastructure without hiring a full red team. Keep this in mind if you want to audit your own systems with serious, verifiable depth.

🆔 @hackernewsgithubprojects