📦 roomkangali/droid-llm-hunter

Droid LLM Hunter

Detecting security flaws in Android apps used to mean choosing between fast keyword scanners that miss context, or slow and expensive manual reviews. Droid-llm-hunter solves this by running a smart, free local regex filter to instantly weed out seventy percent of irrelevant code, and only sending the truly suspicious files to large language models for deep verification. This two-stage pipeline keeps API token costs incredibly low while capturing real vulnerabilities like SQL injection and deep link hijacking. It even acts as a red team assistant by generating functional proof-of-concept exploit scripts. If you scan mobile apps, this is a brilliant way to combine local speed with AI intelligence.

🆔 @hackernewsgithubprojects

📦 igorshadurin/app.yumcut.com

app.yumcut.com

Turn simple text prompts into ready-to-publish vertical videos designed for platforms like TikTok, Instagram Reels, and YouTube Shorts. The open-source app.yumcut.com repository provides a self-hosted framework built on Next.js that automates the entire video creation pipeline. Instead of manually editing footage, you write a text description and the system handles the rest by writing scripts, arranging visual scenes, generating synthetic voiceovers, and rendering subtitles. Powered by a local background processing daemon and FFmpeg, it offers automated multi-language translation and custom rendering templates. It gives developers and content creators a self-hosted, low-cost alternative to expensive commercial video generation APIs.

🆔 @hackernewsgithubprojects

📦 everless321/dym

Dym

Download watermark-free videos from creator profiles and let local AI watch them for you. This clever desktop app automatically grabs high-quality content, pulls key frames using built-in video processing, and feeds them to any vision-based AI model you prefer. It extracts descriptive tags, summaries, and visual scene details directly into a local database so you can find exactly what you need without scrubbing through hours of footage. It is the ultimate helper for organizing short-form media. Give dym a spin to organize your content library like a pro.

🆔 @hackernewsgithubprojects

📦 xuankuzcr/global-lvba

global-lvba

The global-lvba project is a software system that brings laser scans and camera images into perfect harmony. When robots or mapping vehicles drive around, they capture raw data that often ends up looking slightly blurry or misaligned, creating ugly layers in the 3D maps. By combining lidar depth data with high-resolution photos, this tool runs a massive optimization process to align every single camera pose down to the pixel level. It uses features from images alongside laser points to clear up artifacts and construct incredibly sharp, mathematically consistent 3D environments. It is a fantastic tool for anyone wanting to build highly accurate digital twins.

🆔 @hackernewsgithubprojects

📦 infracv/rf-detr-cpp

rf-detr-cpp

rf-detr-cpp is the C++ inference engine that finally frees transformer-based computer vision from slow Python runtimes. Built for Roboflow's real-time object detection models, this project replaces the usual Python and PyTorch stack with pure, highly optimized C++ code. By executing image preprocessing directly on the GPU with custom CUDA kernels and scheduling tasks asynchronously, it drops detection latency to just two milliseconds. It handles everything from object detection to complex segmentation masks with zero Python dependencies at runtime. Grab the code, compile for your NVIDIA GPU, and enjoy production-grade vision speeds.

🆔 @hackernewsgithubprojects

📦 programmersd21/flow

Flow Terminal Network Monitor

Flow is the terminal dashboard that finally strips away the clutter to show your network activity in real time. Instead of overwhelming you with CPU loads, connection tables, and memory usage, this lightweight tool focuses entirely on how much data is actually moving. It converts your download and upload speeds into beautiful, thirty-frames-per-second waveforms directly in your command line. The interface stays incredibly fast and clean, automatically scaling its size to fit your terminal window or status bar. It is a beautifully simple way to watch your network breathe without the usual dashboard noise.

📰 https://news.ycombinator.com/item?id=48805918

🆔 @hackernewsgithubprojects

📦 avadsa25/codec

codec

This open source system transforms your Mac into a voice-controlled AI workstation that runs entirely on your own local hardware. The engine lets you control your entire computer by talking, allowing you to click anywhere on your screen using voice commands backed by a local vision model that coordinates pixel coordinates without needing accessibility APIs. It acts as an intelligent command layer that handles dictation, automates browsers, and runs autonomous agent crews to draft documents or manage projects. You get a private system that writes its own skills and executes workflows without sending data to the cloud.

📰 https://news.ycombinator.com/item?id=47541413

🆔 @hackernewsgithubprojects

📦 zerolu/awesome-seedance

awesome-seedance

Level up your AI video generation by using a curated chest of high-fidelity prompts designed specifically for Seedance. Whether you want to recreate the gritty, epic desert scales of a blockbuster film, design slick perfume commercials with precise product lighting, or whip up surreal, viral comedy clips like a giant orange cat taking over a city, this collection has you covered. It solves the headache of trial-and-error prompting by giving you ready-to-use, time-coded scripts that control camera angles, character movements, and visual styles perfectly. Grab these prompts and start creating cinematic masterpieces on your very first try.

🆔 @hackernewsgithubprojects

📦 krvkir/org-mindmap

Org Mindmap

org-mindmap is the Emacs package that finally turns your plain text Org files into fully editable, interactive mind maps without requiring any external rendering tools. Built entirely in pure Unicode, it instantly transforms nested lists into beautiful, side-by-side visual trees right inside your buffer with a simple keyboard shortcut. The magic is that it is all just text, meaning you can edit nodes directly, drag subtrees around with your arrow keys, and even convert complex maps back into standard bulleted lists. It is the perfect way to brainstorm and structure your thoughts without leaving the comfort of your keyboard.

📰 https://news.ycombinator.com/item?id=48597753

🆔 @hackernewsgithubprojects

📦 moonrunnerkc/swarm-orchestrator

Swarm Orchestrator

Catch artificial intelligence coding agents when they try to take shortcuts in pull requests. Developers are using an open-source tool called swarm-orchestrator to automatically audit code changes for signs of lazy AI work. It acts like an automated code reviewer, searching for eleven distinct tricks that AI assistants use to look finished, such as swallowing errors, creating fake renames, or relaxing test suites. The tool either flags these shortcuts as advice for a human reviewer or blocks the merge entirely by verifying runtime proofs. It ensures that AI-generated contributions remain trustworthy and structurally sound.

📰 https://news.ycombinator.com/item?id=47357738

🆔 @hackernewsgithubprojects

📦 tailscale/thundersnap

Thundersnap

Imagine having an instant undo button for your entire computer filesystem while running persistent container environments that you can spin up and tear down in milliseconds. Thundersnap lets you convert docker containers into on-disk snapshots, bundle your operating system, home folder, and work files into isolated environments, and hop between them instantly. It works like git but for your entire system, using Tailscale to securely replicate your custom environments across multiple devices. It is a brilliant, slightly chaotic playground for developers who want to run programs, test ideas, and safely break things with the ultimate peace of mind that a snapshot has their back.

📰 https://news.ycombinator.com/item?id=48799556

🆔 @hackernewsgithubprojects

📦 can1357/pon

pon

Compile Python scripts directly into lightning-fast, standalone executable files with absolutely no interpreter or bytecode getting in the way. This impressive tool acts as a native compiler and runtime for Python, converting your code directly into machine instructions. It can compile your code on the fly as it runs or package it ahead of time into a single binary. Built in Rust with a specialized garbage collector, it even matches the behavior of standard Python byte-for-byte to keep everything working flawlessly. It is a fantastic way to distribute Python programs as lightweight, ultra-efficient binaries that start instantly.

📰 https://news.ycombinator.com/item?id=48809496

🆔 @hackernewsgithubprojects

📦 rightnow-ai/automegakernel

AutoMegaKernel

Running an AI model usually requires launching dozens of separate GPU kernels for every single step, dragging down performance with constant memory overhead and launch delays. AutoMegaKernel solves this by fusing an entire large language model's forward pass into a single persistent CUDA megakernel that runs continuously on the chip. An autonomous coding agent drives the project's search loop, safely testing new execution schedules that are mathematically proven to be deadlock-free before they even touch the hardware. This automated self-tuning approach actually beats standard CUDA-graphed libraries at single-stream model decoding across a variety of enterprise inference graphics cards.

📰 https://news.ycombinator.com/item?id=48447329

🆔 @hackernewsgithubprojects

📦 zhenyu98/codex-chatgpt-bridge

Codex ChatGPT Bridge

Codex-chatgpt-bridge is the clever power-sharing tool that finally lets ChatGPT and Codex tag-team your coding projects without draining your wallet. Instead of letting Codex burn through expensive tokens on heavy design planning and reading giant files, this bridge hands the big-picture thinking over to ChatGPT while keeping Codex in charge of actual local execution. You get the best of both worlds: ChatGPT acts as your brilliant architect, while Codex safely runs tests, edits files, and verifies the code on your machine. It keeps your workspace secure with an easily re-keyable local bridge that you can shut down instantly when you are done. It is the ultimate way to build big...

🆔 @hackernewsgithubprojects

📦 dicklesworthstone/pi_agent_rust

pi_agent_rust

Run an AI coding assistant directly from your terminal with instant startup times and zero lag. This tool is a high-performance rewrite of Pi Agent built entirely in Rust with no unsafe code. It replaces heavy, slow runtimes with a single binary that is incredibly fast and light on memory. It features eight built-in tools for tasks like refactoring, a beautiful terminal interface, and strong security sandboxing that prevents dangerous commands from running. It is perfect if you want a lightning-fast terminal assistant that respects your system resources. Give it a try to experience a faster, safer terminal AI workflow.

📰 https://news.ycombinator.com/item?id=48812809

🆔 @hackernewsgithubprojects

📦 blader/schematic

Schematic

Document your code automatically without writing a single line of markdown yourself. If you are onboarding to a massive, messy feature branch or need to write a pull request description for a feature that is already shipped, schematic has your back. It is a clever skill for Claude Code and Codex that reverse engineers a complete, eleven-section product and technical specification directly from your git branch. It parallelizes the work by sending out mini-agents to read different file groups simultaneously, cross-references everything to make sure no file is missed, and hands you a clean document detailing the architecture, testing strategy, and rollout risks. You get instant, accurate documentation just by...

🆔 @hackernewsgithubprojects

📦 pocket-stack/pocketjs

pocketjs

Run gorgeous, fluid user interfaces on actual retro hardware using modern web tools. With pocketjs, you can build responsive interfaces using standard Solid or Vue Vapor components and run them at sixty frames per second on a Sony PlayStation Portable inside a tight eight-megabyte memory budget. It works by taking your JavaScript layouts and moving the heavy lifting of styling, layout, and animations into a tiny, high-performance Rust core. It compiles your Tailwind classes and font characters at build time to completely bypass the browser, letting you deploy the exact same code to native windows, web browsers, or retro handhelds.

🆔 @hackernewsgithubprojects

📦 astracompute/astracompute

Astra Compute

Deploy dedicated, GPU-powered machine learning endpoints in under a minute without traditional billing headaches. This project solves the frustration of negotiating for scarce hardware and setting up complex inference servers. Instead of dealing with invoices or credit card setups, you select your preferred graphics card, pay for your runtime upfront with digital currency on the Solana blockchain, and instantly receive an OpenAI-compatible endpoint. Even better, if your dedicated hardware ever goes offline or gets overloaded, the system automatically routes your requests to a backup network so your app never drops a single call. It makes deploying open-source artificial intelligence models incredibly fast, reliable, and accessible.

🆔 @hackernewsgithubprojects

📦 valmishq/valmis

Valmis

Build and deploy a fleet of productive AI agents to handle your daily chores without risking your sensitive accounts. This project introduces a secure proxy design where your agents live in isolated containers and never see your actual API passwords or login keys. Instead, the host system securely runs the requests for them, making it safe to link your workflows with over one hundred popular business apps. You can build visual multi-step automations, let agents browse the web, and utilize a smart memory system that stores facts across different chat sessions. Get started today and safely delegate your busywork.

📰 https://news.ycombinator.com/item?id=48761096

🆔 @hackernewsgithubprojects

📦 fff686868/proxypin-wloc-spoofer

proxypin-wloc-spoofer

Test your location-based apps indoors without stepping outside by intercepting and modifying Apple's network location data on your test device. The proxypin-wloc-spoofer project provides a clever script for the ProxyPin app that targets background location requests and swaps out the real coordinates with custom ones in the binary response. It even sets up a handy map interface on your device to let you visually pick and save any test spot you want. It is a brilliant, zero-hassle way for developers and quality assurance teams to replicate tricky location scenarios right from their desks.

🆔 @hackernewsgithubprojects