📦 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

📦 pytraveler/minimax-h3-prompt-rewriter-comfyui

MiniMax H3 Prompt Rewriter for ComfyUI

MiniMax H3 Prompt Rewriter for ComfyUI is the local workflow that turns a simple sentence into a professional video script. It takes a short prompt in any language and expands it into a structured English description with precise camera shots and synchronized audio details. This solves the problem of writing complex prompts manually, ensuring your AI video generator gets exactly the timing and sound cues it needs. The standout feature is its ability to run entirely on your own hardware, offering a lightweight version that works on modest graphics cards. You get production-ready descriptions without sending your creative ideas to external servers.

🆔 @hackernewsgithubprojects

📦 aiimaginglab/pcflow

PCFlow: Fix Blurry Photos in Just Three Steps

Clean up blurry, noisy, or damaged photos in just three steps. PCFlow is a new method that makes image restoration fast and visually stunning. It solves the annoying tradeoff where fixing pixel errors usually makes images look smooth and artificial. Instead, it uses a clever flow matching technique to jump straight to a realistic result. The coolest part is how it uses a conflict-free gradient strategy. This prevents the model from getting stuck when trying to balance sharpness and accuracy. It is lightweight and uses a simple convolutional backbone to achieve high-quality results without heavy computational costs. This is the smart way to restore images with speed and style.

🆔 @hackernewsgithubprojects

📦 llmllmllm/bpw

BPW: Fixing How We Test AI Systems

BPW is the diagnostic tool that ensures your AI system tests actually catch the problems hiding in plain sight. Traditional test compression looks for typical requests, but BPW hunts for rare, weird cases that expose deep system flaws. By preserving these specific pressure points, it creates a smaller replay suite that is statistically unique but diagnostically powerful. This framework helps engineers verify that their infrastructure can handle real world stress without wasting resources on redundant data. It is a vital step toward reliable, evidence based evaluation for large language model serving systems.

🆔 @hackernewsgithubprojects

📦 stokou/facet-terminal

FACET: How a Small AI Model Beats Big Ones on Terminal Tasks

FACET Terminal turns seven thousand raw code snippets into six thousand verified, executable computer tasks. The core problem it solves is that most AI-generated instructions are just text, often missing the actual environment needed to run them. This project builds the real computer setup first, then writes the task, solution, and checker based on that single, shared state. This ensures the challenge is actually solvable. The result is a small, fine-tuned model that scores higher on terminal benchmarks than much larger competitors. If you build AI agents, this is the framework to make them actually work.

🆔 @hackernewsgithubprojects

📦 nekodificador/comfyui-nkd-basic-tools

The ComfyUI Node Pack That Lets You Drag Handles On Your Images

NKD Basic Tools is the ComfyUI node pack that finally lets you drag handles directly on your images to pose facial expressions and grade color without leaving the canvas. This repository solves the busywork of complex workflows by bundling everyday utilities into single nodes, such as cropping a face for a model and stitching it back in seamlessly, or painting masks with a pen tool that saves editable control points. The most surprising feature is the live preview system, which allows you to adjust skin tones, blur fields, and film grain right inside the node without running the entire graph.

🆔 @hackernewsgithubprojects

📦 aws/agentcore-cli

AgentCore CLI: Your Agent in the Terminal

Spin up a full artificial intelligence agent right from your terminal. AgentCore CLI handles the heavy lifting of deploying, testing, and managing AI agents without forcing you to write infrastructure code by hand. It connects your agent to cloud resources, lets you test it locally before it goes live, and even helps you evaluate how well it performs. The real magic is that it turns complex cloud setup into simple commands, so you can focus on building your agent logic instead of wrestling with server configurations. If you want to move faster with AI development, this is your new command line companion.

🆔 @hackernewsgithubprojects

📦 miaai-lab/qwen3.8-27b-nvfp4-rtx-5090

Qwen 3.8 27B on a Single RTX 5090

A twenty-seven billion parameter language model now runs on a single consumer graphics card that still drives your desktop display. Mia AI Lab’s project, Qwen 3.8 27B on a Single RTX 5090, turns one script into a fully functional, OpenAI-compatible API server. The surprising capability here is that it achieves a full 256,000-token context window on a 32GB GPU, thanks to a heavily optimized 4-bit KV cache and a specific patch that fixes garbled output from the underlying inference engine. You get roughly 160 tokens per second for single-stream generation, with the system intelligently managing memory so it doesn’t eat your graphics card’s RAM needed for your actual desktop.

🆔 @hackernewsgithubprojects

📦 aarr-bench/aarri-bench

AARRI-Bench: The Research Intern Test

Stop asking if AI can code. AARRI-Bench asks if it can think like a scientist. This project drops AI agents into the shoes of a research intern, testing them on the messy, human parts of research that code alone can't solve. It’s not about writing algorithms; it’s about spotting a flawed experiment, reading between the lines of a lab partner’s email, and knowing when to quit a dead-end project. The goal is to expose the gap between a smart assistant and a real researcher. If you’ve ever wondered what an AI is actually missing when it tries to do science, this is the clearest way to see it.

🆔 @hackernewsgithubprojects