This media is not supported in your browser
VIEW IN TELEGRAM
📦 adventdevinc/kudu
kudu
Kudu is the open-source system maintenance tool that finally brings comprehensive device cleaning and security scanning to Windows, Mac, and Linux under a single, unified interface. Instead of running separate programs for system clutter, duplicate files, startup management, and malware threat detection, this app packs everything into one lightweight dashboard. It even includes specialized features like game mode optimization, file shredding, and vulnerability tracking to keep your computer running smoothly and securely. It is the perfect, straightforward utility for anyone looking to reclaim disk space and guard their privacy without dealing with bloated commercial software. Give your operating system a fresh start today.
🆔 @hackernewsgithubprojects
kudu
Kudu is the open-source system maintenance tool that finally brings comprehensive device cleaning and security scanning to Windows, Mac, and Linux under a single, unified interface. Instead of running separate programs for system clutter, duplicate files, startup management, and malware threat detection, this app packs everything into one lightweight dashboard. It even includes specialized features like game mode optimization, file shredding, and vulnerability tracking to keep your computer running smoothly and securely. It is the perfect, straightforward utility for anyone looking to reclaim disk space and guard their privacy without dealing with bloated commercial software. Give your operating system a fresh start today.
🆔 @hackernewsgithubprojects
This media is not supported in your browser
VIEW IN TELEGRAM
📦 pleaseprompto/google-ai-mode-skill
google-ai-mode-skill
The google-ai-mode-skill is the Claude Code add-on that finally stops you from burning thousands of tokens on basic web searches. Instead of making Claude manually click, read, and analyze ten different website links, this clever tool launches a silent local browser to let Google's AI Mode do the heavy lifting for you. It pulls back a single, pre-synthesized answer complete with inline citations, keeping your context window clean and your API costs incredibly low. It is entirely self-contained, runs locally without needing any API keys, and even saves your browser profile to bypass annoying captchas. Grab this skill to give your terminal agent superpowered research skills for free.
🆔 @hackernewsgithubprojects
google-ai-mode-skill
The google-ai-mode-skill is the Claude Code add-on that finally stops you from burning thousands of tokens on basic web searches. Instead of making Claude manually click, read, and analyze ten different website links, this clever tool launches a silent local browser to let Google's AI Mode do the heavy lifting for you. It pulls back a single, pre-synthesized answer complete with inline citations, keeping your context window clean and your API costs incredibly low. It is entirely self-contained, runs locally without needing any API keys, and even saves your browser profile to bypass annoying captchas. Grab this skill to give your terminal agent superpowered research skills for free.
🆔 @hackernewsgithubprojects
This media is not supported in your browser
VIEW IN TELEGRAM
📦 dominostars/playtranslate
Playtranslate
Translate foreign language games directly on your Android screen in real time while you play. This clever app acts as a smart, live overlay that reads foreign text right off your display, translating dialouge and menu options instantly. It supports offline engines like Yomitan and PaddleOCR, meaning you do not even need an active internet connection to understand what is happening. Best of all, it integrates directly with Anki, allowing you to instantly save new words to study cards with a single tap. Grab this app to make imported games your personal language classroom.
🆔 @hackernewsgithubprojects
Playtranslate
Translate foreign language games directly on your Android screen in real time while you play. This clever app acts as a smart, live overlay that reads foreign text right off your display, translating dialouge and menu options instantly. It supports offline engines like Yomitan and PaddleOCR, meaning you do not even need an active internet connection to understand what is happening. Best of all, it integrates directly with Anki, allowing you to instantly save new words to study cards with a single tap. Grab this app to make imported games your personal language classroom.
🆔 @hackernewsgithubprojects
This media is not supported in your browser
VIEW IN TELEGRAM
📦 optim-agent/optim-agent
Optim Agent
The parameter-tuning assistant that actually understands what your code is trying to achieve. Instead of treating your variables like anonymous math coordinates, optim-agent lets coding agents like Claude or Codex read your code, understand the real-world context of your parameters, and propose smart configurations. It bridges the gap between what a parameter means and how it performs, optimizing everything from machine learning models to decision rules without wasting expensive evaluations. If you want a smarter way to tune your systems, check out this repository to let AI do the heavy lifting for you.
🆔 @hackernewsgithubprojects
Optim Agent
The parameter-tuning assistant that actually understands what your code is trying to achieve. Instead of treating your variables like anonymous math coordinates, optim-agent lets coding agents like Claude or Codex read your code, understand the real-world context of your parameters, and propose smart configurations. It bridges the gap between what a parameter means and how it performs, optimizing everything from machine learning models to decision rules without wasting expensive evaluations. If you want a smarter way to tune your systems, check out this repository to let AI do the heavy lifting for you.
🆔 @hackernewsgithubprojects
This media is not supported in your browser
VIEW IN TELEGRAM
📦 px0-ai/px0
px0
Update and tweak your AI prompts in production instantly without redeploying your application code. This project acts as a central control hub for your AI prompts, agent skills, and tool schemas. Instead of hardcoding prompts inside your software, you register them in a central place using versioned templates that connect to major providers like OpenAI and Anthropic. When a prompt needs a quick adjustment, you update it in the registry, and your live application gets the update immediately with visual history tracking and full rollback safety. It completely decouples your AI logic from your software deployment cycle, saving you from constant rebuilds.
🆔 @hackernewsgithubprojects
px0
Update and tweak your AI prompts in production instantly without redeploying your application code. This project acts as a central control hub for your AI prompts, agent skills, and tool schemas. Instead of hardcoding prompts inside your software, you register them in a central place using versioned templates that connect to major providers like OpenAI and Anthropic. When a prompt needs a quick adjustment, you update it in the registry, and your live application gets the update immediately with visual history tracking and full rollback safety. It completely decouples your AI logic from your software deployment cycle, saving you from constant rebuilds.
🆔 @hackernewsgithubprojects
This media is not supported in your browser
VIEW IN TELEGRAM
📦 inclusionai/avernet
Avernet
Organize teams of digital agents that actually work together instead of running in isolated silos. This platform provides the shared infrastructure needed to connect, coordinate, and run different AI agents in a unified network. It solves a massive problem in tech where individual bots cannot easily find each other or align on goals, which often forces humans to manually pass tasks back and forth. Already managing thousands of active bots inside a major enterprise, it provides the essential identity, memory, and coordination tools to build a truly cooperative digital ecosystem. It is a fascinating glimpse into how future organizations will run.
🆔 @hackernewsgithubprojects
Avernet
Organize teams of digital agents that actually work together instead of running in isolated silos. This platform provides the shared infrastructure needed to connect, coordinate, and run different AI agents in a unified network. It solves a massive problem in tech where individual bots cannot easily find each other or align on goals, which often forces humans to manually pass tasks back and forth. Already managing thousands of active bots inside a major enterprise, it provides the essential identity, memory, and coordination tools to build a truly cooperative digital ecosystem. It is a fascinating glimpse into how future organizations will run.
🆔 @hackernewsgithubprojects
This media is not supported in your browser
VIEW IN TELEGRAM
📦 aaddrick/claude-pipeline
Claude Pipeline
You can now drop a complete multi-agent development pipeline directly into any coding project. A project called claude-pipeline acts as a portable folder template that instantly upgrades your local AI assistant into a team of ten specialized developers, reviewers, and automated quality gates. It comes packed with process skills like test-driven development and systematic debugging, alongside automated workflows that handle issues, write implementation plans, and run safety checks completely locally. Instead of relying on a single general assistant, you get tailored agents that coordinate with each other to build, test, and refine your code, leaving you with a highly disciplined, automated development cycle.
🆔 @hackernewsgithubprojects
Claude Pipeline
You can now drop a complete multi-agent development pipeline directly into any coding project. A project called claude-pipeline acts as a portable folder template that instantly upgrades your local AI assistant into a team of ten specialized developers, reviewers, and automated quality gates. It comes packed with process skills like test-driven development and systematic debugging, alongside automated workflows that handle issues, write implementation plans, and run safety checks completely locally. Instead of relying on a single general assistant, you get tailored agents that coordinate with each other to build, test, and refine your code, leaving you with a highly disciplined, automated development cycle.
🆔 @hackernewsgithubprojects
This media is not supported in your browser
VIEW IN TELEGRAM
📦 batear-io/batear
Batear
Turn a tiny, inexpensive microcontroller and a basic microphone into an always-on acoustic drone detector. This clever project runs entirely at the edge with no cloud subscription or internet needed, analyzing audio signals locally to detect drone rotor harmonics the second they enter your airspace. It can alert you instantly through encrypted long-range radio signals or wired connections, and even plugs directly into your smart home dashboard to trigger automated alarms. It is an incredibly smart, budget-friendly way to protect local airspace using simple audio processing and everyday hardware.
🆔 @hackernewsgithubprojects
Batear
Turn a tiny, inexpensive microcontroller and a basic microphone into an always-on acoustic drone detector. This clever project runs entirely at the edge with no cloud subscription or internet needed, analyzing audio signals locally to detect drone rotor harmonics the second they enter your airspace. It can alert you instantly through encrypted long-range radio signals or wired connections, and even plugs directly into your smart home dashboard to trigger automated alarms. It is an incredibly smart, budget-friendly way to protect local airspace using simple audio processing and everyday hardware.
🆔 @hackernewsgithubprojects
This media is not supported in your browser
VIEW IN TELEGRAM
📦 gglab-ku/treethink
TreeThink
Large language models are notorious for hallucinating when they try to solve complex math, but treethink fixes this by forcing AI to actually check its work as it goes. Instead of just guessing the next line of a proof, it wraps the model inside a tree-search loop, exploring multiple parallel paths and verifying each step using real-world proof assistants like Lean and Coq. If a logical path hits a dead end, it backtracks and tries another branch. It turns mathematical reasoning into an interactive search, giving you a math-solving AI that is actually mathematically sound.
🆔 @hackernewsgithubprojects
TreeThink
Large language models are notorious for hallucinating when they try to solve complex math, but treethink fixes this by forcing AI to actually check its work as it goes. Instead of just guessing the next line of a proof, it wraps the model inside a tree-search loop, exploring multiple parallel paths and verifying each step using real-world proof assistants like Lean and Coq. If a logical path hits a dead end, it backtracks and tries another branch. It turns mathematical reasoning into an interactive search, giving you a math-solving AI that is actually mathematically sound.
🆔 @hackernewsgithubprojects
This media is not supported in your browser
VIEW IN TELEGRAM
📦 jtenniswood/espcontrol
EspControl
You can now transform a cheap thirty-dollar touchscreen into a fully customized smart home control panel without writing a single line of code or editing complex configuration files. With espcontrol, you just flash the firmware directly from your web browser, connect the screen to your wireless network, and add it to Home Assistant. From there, you get a beautiful, drag-and-drop web interface to arrange buttons for your lights, thermostats, and media players. It is the perfect way to mount dedicated, local control screens exactly where you need them around the house, keeping your smart home completely private and incredibly easy for guests to use.
🆔 @hackernewsgithubprojects
EspControl
You can now transform a cheap thirty-dollar touchscreen into a fully customized smart home control panel without writing a single line of code or editing complex configuration files. With espcontrol, you just flash the firmware directly from your web browser, connect the screen to your wireless network, and add it to Home Assistant. From there, you get a beautiful, drag-and-drop web interface to arrange buttons for your lights, thermostats, and media players. It is the perfect way to mount dedicated, local control screens exactly where you need them around the house, keeping your smart home completely private and incredibly easy for guests to use.
🆔 @hackernewsgithubprojects
This media is not supported in your browser
VIEW IN TELEGRAM
📦 ninagusev47/silent-crypto-miner
silent-crypto-miner
Build custom, self-contained cryptocurrency mining executables configured to automatically pause operations when system activity or resource usage spikes. This terminal-based builder allows creators to bundle mining configurations for multiple hardware-friendly algorithms directly into a single binary, complete with auto-failover pool support and thermal limits. Rather than managing complex command-line configurations manually, the interactive utility lets you pack target settings, custom icons, and registry start options directly into a lightweight package. It is an interesting utility for developers exploring hardware monitoring, background task scheduling, and customized binary creation. Try exploring the codebase to see how it packages external resources and handles automated process coordination across different operating systems.
🆔 @hackernewsgithubprojects
silent-crypto-miner
Build custom, self-contained cryptocurrency mining executables configured to automatically pause operations when system activity or resource usage spikes. This terminal-based builder allows creators to bundle mining configurations for multiple hardware-friendly algorithms directly into a single binary, complete with auto-failover pool support and thermal limits. Rather than managing complex command-line configurations manually, the interactive utility lets you pack target settings, custom icons, and registry start options directly into a lightweight package. It is an interesting utility for developers exploring hardware monitoring, background task scheduling, and customized binary creation. Try exploring the codebase to see how it packages external resources and handles automated process coordination across different operating systems.
🆔 @hackernewsgithubprojects
Media is too big
VIEW IN TELEGRAM
📦 alfadur7/llm-wiki-newsroom
LLM Wiki Newsroom
llm-wiki-newsroom is the self-evolving multi-agent newsroom that turns your raw documents into a fully cross-linked knowledge wiki. Instead of dumping files into a basic search engine, this tool uses a five-role virtual newsroom to analyze and organize your files. A reporter drafts pages, a columnist analyzes themes, and strict editors review the work so the writer never reviews their own writing. It runs entirely on your local machine with no API keys, automatically flagging conflicting claims between sources and creating an interactive knowledge graph. Your documents finally become a living, self-correcting encyclopedia.
🆔 @hackernewsgithubprojects
LLM Wiki Newsroom
llm-wiki-newsroom is the self-evolving multi-agent newsroom that turns your raw documents into a fully cross-linked knowledge wiki. Instead of dumping files into a basic search engine, this tool uses a five-role virtual newsroom to analyze and organize your files. A reporter drafts pages, a columnist analyzes themes, and strict editors review the work so the writer never reviews their own writing. It runs entirely on your local machine with no API keys, automatically flagging conflicting claims between sources and creating an interactive knowledge graph. Your documents finally become a living, self-correcting encyclopedia.
🆔 @hackernewsgithubprojects
This media is not supported in your browser
VIEW IN TELEGRAM
📦 engibacter/r2lpl
r2lpl
Teach self-driving cars to actively learn from their own mistakes instead of just mimicking perfect human drivers. This repository provides a clever framework called r2lpl that runs closed-loop driving simulations, catches the exact moments the AI messes up or gets into a tight spot, and retrieves better alternative driving maneuvers on the fly. It then uses a smart lifelong learning process to update the vehicle's driving policy over multiple rounds without erasing what it already knows. It dramatically boosts safety and handling in tough driving scenarios. Check out the code, run the simulations, and watch your driving models actually get smarter with every near-miss.
🆔 @hackernewsgithubprojects
r2lpl
Teach self-driving cars to actively learn from their own mistakes instead of just mimicking perfect human drivers. This repository provides a clever framework called r2lpl that runs closed-loop driving simulations, catches the exact moments the AI messes up or gets into a tight spot, and retrieves better alternative driving maneuvers on the fly. It then uses a smart lifelong learning process to update the vehicle's driving policy over multiple rounds without erasing what it already knows. It dramatically boosts safety and handling in tough driving scenarios. Check out the code, run the simulations, and watch your driving models actually get smarter with every near-miss.
🆔 @hackernewsgithubprojects
This media is not supported in your browser
VIEW IN TELEGRAM
📦 yu-369/vibecurb
VibeCurb
Force your favorite AI development tools to design gorgeous, premium websites instead of generating the same boring, average templates. By dropping this intelligent design engine directly into your coding environment, you replace standard AI guesswork with incredibly strict rules and quality gates. Before writing a single line of code, the system forces the AI agent to audit reference images, extract layout signals, and verify the build against premium design principles. It completely rejects generic gradients and safe layouts to deliver viewport-scale typography, cinematic depth, and precise grids that actually look human-designed. It is the ultimate tool for turning messy AI code into a masterpiece.
🆔 @hackernewsgithubprojects
VibeCurb
Force your favorite AI development tools to design gorgeous, premium websites instead of generating the same boring, average templates. By dropping this intelligent design engine directly into your coding environment, you replace standard AI guesswork with incredibly strict rules and quality gates. Before writing a single line of code, the system forces the AI agent to audit reference images, extract layout signals, and verify the build against premium design principles. It completely rejects generic gradients and safe layouts to deliver viewport-scale typography, cinematic depth, and precise grids that actually look human-designed. It is the ultimate tool for turning messy AI code into a masterpiece.
🆔 @hackernewsgithubprojects
This media is not supported in your browser
VIEW IN TELEGRAM
📦 soniqo/speech-android
speech-android
You can run a complete, private voice assistant entirely offline on your phone using just over one gigabyte of memory. The speech-android project makes this possible by packing a full audio processing suite into a local Android SDK. By combining lightweight speech-to-text, text-to-speech, voice activity detection, and noise cancellation, it processes everything on your device without sending a single byte of data to the cloud. It even hooks directly into Android's system-level speech services so other apps can use your local pipeline. It is a brilliant way to build ultra-private, fast voice applications.
🆔 @hackernewsgithubprojects
speech-android
You can run a complete, private voice assistant entirely offline on your phone using just over one gigabyte of memory. The speech-android project makes this possible by packing a full audio processing suite into a local Android SDK. By combining lightweight speech-to-text, text-to-speech, voice activity detection, and noise cancellation, it processes everything on your device without sending a single byte of data to the cloud. It even hooks directly into Android's system-level speech services so other apps can use your local pipeline. It is a brilliant way to build ultra-private, fast voice applications.
🆔 @hackernewsgithubprojects
This media is not supported in your browser
VIEW IN TELEGRAM
📦 greyhavenhq/greywall
Greywall
Lock down your filesystem, network, and system calls without the overhead of heavy containers. This tool lets you execute untrusted commands and AI coding agents inside a native, deny-by-default sandbox that restricts access to only your working directory, keeping sensitive folders like your SSH keys and environmental secrets completely secure. It acts as a lightweight, kernel-enforced barrier for Linux and macOS that blocks dangerous operations, routes network traffic through a transparent proxy with a live dashboard, and even lets you run a passive observation mode to map out exactly what a tool is trying to touch before you restrict it.
🆔 @hackernewsgithubprojects
Greywall
Lock down your filesystem, network, and system calls without the overhead of heavy containers. This tool lets you execute untrusted commands and AI coding agents inside a native, deny-by-default sandbox that restricts access to only your working directory, keeping sensitive folders like your SSH keys and environmental secrets completely secure. It acts as a lightweight, kernel-enforced barrier for Linux and macOS that blocks dangerous operations, routes network traffic through a transparent proxy with a live dashboard, and even lets you run a passive observation mode to map out exactly what a tool is trying to touch before you restrict it.
🆔 @hackernewsgithubprojects
This media is not supported in your browser
VIEW IN TELEGRAM
📦 hoainho/img2threejs
img2threejs
Most image-to-3D tools spit out messy, massive mesh files that are absolute nightmares to edit, but img2threejs does something completely different. You feed it a single reference image of an object or character, and it writes clean, highly structured TypeScript that builds a procedural, animation-ready Three.js model from scratch using code. It guides an AI agent through a locked, step-by-step sculpting pipeline, rendering the progress and self-correcting until the code matches the visual details. You get a lightweight, interactive 3D scene built from clean primitives and math, perfect for fast-loading web applications.
🆔 @hackernewsgithubprojects
img2threejs
Most image-to-3D tools spit out messy, massive mesh files that are absolute nightmares to edit, but img2threejs does something completely different. You feed it a single reference image of an object or character, and it writes clean, highly structured TypeScript that builds a procedural, animation-ready Three.js model from scratch using code. It guides an AI agent through a locked, step-by-step sculpting pipeline, rendering the progress and self-correcting until the code matches the visual details. You get a lightweight, interactive 3D scene built from clean primitives and math, perfect for fast-loading web applications.
🆔 @hackernewsgithubprojects
This media is not supported in your browser
VIEW IN TELEGRAM
📦 unable12/codebase-posters
Codebase Posters
Turn your git history into beautiful generative art that you can actually print and hang on your wall. Inside any repository, running a single command opens a local exhibition with nineteen distinct visual recipes that paint themselves live on your screen. The software translates your commit metadata into elegant canvases, depicting your midnight coding sessions as clusters of stars, or years of additions and deletions as gentle waves of color. Everything compiles completely on your machine with zero external dependencies, letting you customize colors and layouts before exporting a high-resolution, print-ready file to bring your development journey to life.
📰 https://news.ycombinator.com/item?id=48885500
🆔 @hackernewsgithubprojects
Codebase Posters
Turn your git history into beautiful generative art that you can actually print and hang on your wall. Inside any repository, running a single command opens a local exhibition with nineteen distinct visual recipes that paint themselves live on your screen. The software translates your commit metadata into elegant canvases, depicting your midnight coding sessions as clusters of stars, or years of additions and deletions as gentle waves of color. Everything compiles completely on your machine with zero external dependencies, letting you customize colors and layouts before exporting a high-resolution, print-ready file to bring your development journey to life.
📰 https://news.ycombinator.com/item?id=48885500
🆔 @hackernewsgithubprojects
This media is not supported in your browser
VIEW IN TELEGRAM
📦 itsplk/ps5-y2jb-autoloader
PS5 Y2JB Autoloader
The automated modding utility that finally takes the tedious manual work out of starting up an exploited PlayStation 5 console. Instead of manually pushing payloads to your device every single time you boot, this tool acts as a clever automated chain loader that runs directly through the console's built-in YouTube app. It automatically handles the initial kernel exploit phase and immediately fires up your custom payloads. If no manual setup is found, it automatically boots into a friendly web-based payload manager so you can configure everything straight from your web browser. It is the ultimate hands-off startup routine your PlayStation 5 deserves.
📰 https://news.ycombinator.com/item?id=48967115
🆔 @hackernewsgithubprojects
PS5 Y2JB Autoloader
The automated modding utility that finally takes the tedious manual work out of starting up an exploited PlayStation 5 console. Instead of manually pushing payloads to your device every single time you boot, this tool acts as a clever automated chain loader that runs directly through the console's built-in YouTube app. It automatically handles the initial kernel exploit phase and immediately fires up your custom payloads. If no manual setup is found, it automatically boots into a friendly web-based payload manager so you can configure everything straight from your web browser. It is the ultimate hands-off startup routine your PlayStation 5 deserves.
📰 https://news.ycombinator.com/item?id=48967115
🆔 @hackernewsgithubprojects
This media is not supported in your browser
VIEW IN TELEGRAM
📦 lopopolo/harness-engineering
Harness Engineering
Improve the output of your AI coding agents by shaping the environment around them instead of constantly switching models. The harness-engineering repository is a curated field guide and context bundle designed to feed your agents the exact business constraints, local rules, and repository knowledge they need to do their jobs. By treating the AI model as a stable, fixed worker, this project helps you feed agents just-in-time context, legible tools, and clear authority guidelines so they can operate real systems and verify their own work. It is a smart, practical approach to making AI agents more effective by giving them better local instructions.
📰 https://news.ycombinator.com/item?id=48963483
🆔 @hackernewsgithubprojects
Harness Engineering
Improve the output of your AI coding agents by shaping the environment around them instead of constantly switching models. The harness-engineering repository is a curated field guide and context bundle designed to feed your agents the exact business constraints, local rules, and repository knowledge they need to do their jobs. By treating the AI model as a stable, fixed worker, this project helps you feed agents just-in-time context, legible tools, and clear authority guidelines so they can operate real systems and verify their own work. It is a smart, practical approach to making AI agents more effective by giving them better local instructions.
📰 https://news.ycombinator.com/item?id=48963483
🆔 @hackernewsgithubprojects
This media is not supported in your browser
VIEW IN TELEGRAM
📦 prakhar1114/ai_mime
ai_mime
ai_mime is the macOS automation harness that finally turns your raw screen recordings into reliable, reusable scripts. Instead of fragile pixel-matching tools, you simply demonstrate a task once. The app analyzes your actions and screenshots, builds a coordinate-free workflow schema, and writes a deterministic Python script or browser automation to handle the work. If a layout changes or a step fails, a built-in assistant automatically analyzes the error, patches the code, and heals the script. It brings the perfect balance of reliable local code and intelligent self-healing, giving you robust desktop automations that actually last.
📰 https://news.ycombinator.com/item?id=48480492
🆔 @hackernewsgithubprojects
ai_mime
ai_mime is the macOS automation harness that finally turns your raw screen recordings into reliable, reusable scripts. Instead of fragile pixel-matching tools, you simply demonstrate a task once. The app analyzes your actions and screenshots, builds a coordinate-free workflow schema, and writes a deterministic Python script or browser automation to handle the work. If a layout changes or a step fails, a built-in assistant automatically analyzes the error, patches the code, and heals the script. It brings the perfect balance of reliable local code and intelligent self-healing, giving you robust desktop automations that actually last.
📰 https://news.ycombinator.com/item?id=48480492
🆔 @hackernewsgithubprojects