This media is not supported in your browser
VIEW IN TELEGRAM
📦 shepherd-agents/shepherd
shepherd
Run your AI agents inside a reversible, Git-like playground where you can safely preview every file change before it ever touches your real directory. That is exactly what this clever library makes possible. Instead of letting an AI agent loose on your actual codebase, it runs the task inside a secure sandbox and saves the work as a reviewable proposal. You get a durable execution trace that lets you inspect, run, select, or discard the proposed changes with simple commands. It makes AI development incredibly safe and stress-free because you remain the ultimate gatekeeper of your code.
🆔 @hackernewsgithubprojects
shepherd
Run your AI agents inside a reversible, Git-like playground where you can safely preview every file change before it ever touches your real directory. That is exactly what this clever library makes possible. Instead of letting an AI agent loose on your actual codebase, it runs the task inside a secure sandbox and saves the work as a reviewable proposal. You get a durable execution trace that lets you inspect, run, select, or discard the proposed changes with simple commands. It makes AI development incredibly safe and stress-free because you remain the ultimate gatekeeper of your code.
🆔 @hackernewsgithubprojects
This media is not supported in your browser
VIEW IN TELEGRAM
📦 ekwek1/soprano-factory
Soprano Factory
You can now train a custom text-to-speech model that generates voice audio at up to two thousand times real-time speed on a standard graphics card. A clever new training toolkit called soprano-factory packages this process into a tiny six-hundred-line script. It lets you feed in your own voice recordings to teach a lightweight, eighty-million parameter model how to speak like you, a friend, or any character you want. The resulting voice is crystal clear and runs on a normal laptop using almost no memory. If you want to build super fast, custom voice models on your own hardware, this is the perfect place to start.
🆔 @hackernewsgithubprojects
Soprano Factory
You can now train a custom text-to-speech model that generates voice audio at up to two thousand times real-time speed on a standard graphics card. A clever new training toolkit called soprano-factory packages this process into a tiny six-hundred-line script. It lets you feed in your own voice recordings to teach a lightweight, eighty-million parameter model how to speak like you, a friend, or any character you want. The resulting voice is crystal clear and runs on a normal laptop using almost no memory. If you want to build super fast, custom voice models on your own hardware, this is the perfect place to start.
🆔 @hackernewsgithubprojects
This media is not supported in your browser
VIEW IN TELEGRAM
📦 harrrshall/tinyrouter
TinyRouter
Tinyrouter is the tiny coordinator that finally makes multiple AI models work together as a single, smarter team. Instead of relying on one expensive LLM to do everything, this clever system uses a minuscule ten-thousand-parameter brain that looks at your question and decides which specialist model to call and what role it should play, whether that is a math genius, a factual writer, or a strict verifier. By training this tiny router through evolutionary trial-and-error rather than complex reinforcement learning, it consistently beats any single model on its own. It is the ultimate way to orchestrate open-source models on a budget.
🆔 @hackernewsgithubprojects
TinyRouter
Tinyrouter is the tiny coordinator that finally makes multiple AI models work together as a single, smarter team. Instead of relying on one expensive LLM to do everything, this clever system uses a minuscule ten-thousand-parameter brain that looks at your question and decides which specialist model to call and what role it should play, whether that is a math genius, a factual writer, or a strict verifier. By training this tiny router through evolutionary trial-and-error rather than complex reinforcement learning, it consistently beats any single model on its own. It is the ultimate way to orchestrate open-source models on a budget.
🆔 @hackernewsgithubprojects
This media is not supported in your browser
VIEW IN TELEGRAM
📦 handy-computer/transcribe.cpp
Transcribe.cpp
You can now run over sixty different speech-to-text models locally on your own hardware using a single lightweight library. This is transcribe.cpp, an open-source library built on the ggml runtime that lets you run transcription models on your CPU or GPU without heavy external dependencies. It supports sixteen major model families like Whisper, Canary, and Moonshine, offering both batch processing and real-time streaming. The project provides official bindings for Python, TypeScript, Rust, and Swift, making it incredibly easy to integrate local, high-performance transcription directly into almost any application. Check it out to build private, lightning-fast voice features today.
📰 https://news.ycombinator.com/item?id=48744571
🆔 @hackernewsgithubprojects
Transcribe.cpp
You can now run over sixty different speech-to-text models locally on your own hardware using a single lightweight library. This is transcribe.cpp, an open-source library built on the ggml runtime that lets you run transcription models on your CPU or GPU without heavy external dependencies. It supports sixteen major model families like Whisper, Canary, and Moonshine, offering both batch processing and real-time streaming. The project provides official bindings for Python, TypeScript, Rust, and Swift, making it incredibly easy to integrate local, high-performance transcription directly into almost any application. Check it out to build private, lightning-fast voice features today.
📰 https://news.ycombinator.com/item?id=48744571
🆔 @hackernewsgithubprojects
This media is not supported in your browser
VIEW IN TELEGRAM
📦 hkuds/openphone
OpenPhone
Control your smartphone autonomously using a local AI model that runs entirely on your device. OpenPhone is an open-source, three-billion-parameter vision-language model designed specifically to interact with mobile apps without relying on expensive, slow, or privacy-invasive cloud APIs. Instead of wasting time and money calling a large model for every single screen tap, this system builds a visual map of your favorite apps and replays routine actions instantly as local macros. The smart model only steps in when you ask for something complex or completely new, giving you blazing fast, secure, and cost-free automation right in your pocket.
🆔 @hackernewsgithubprojects
OpenPhone
Control your smartphone autonomously using a local AI model that runs entirely on your device. OpenPhone is an open-source, three-billion-parameter vision-language model designed specifically to interact with mobile apps without relying on expensive, slow, or privacy-invasive cloud APIs. Instead of wasting time and money calling a large model for every single screen tap, this system builds a visual map of your favorite apps and replays routine actions instantly as local macros. The smart model only steps in when you ask for something complex or completely new, giving you blazing fast, secure, and cost-free automation right in your pocket.
🆔 @hackernewsgithubprojects
This media is not supported in your browser
VIEW IN TELEGRAM
📦 zack0x01/payment-bypass-bug-lab
payment-bypass-bug-lab
The payment-bypass-bug-lab is the interactive playground that teaches you security testing by letting you legally hack your way past digital paywalls. Designed for curious minds, this project runs a local web application containing real-world flaws often found in actual online stores. You get to play the role of a security researcher, learning how to manipulate network requests to drop a purchase price to zero, dig out hidden direct links to premium files, or change your user profile status to paid. It is a brilliant, hands-on way to understand web vulnerabilities safely on your own computer.
🆔 @hackernewsgithubprojects
payment-bypass-bug-lab
The payment-bypass-bug-lab is the interactive playground that teaches you security testing by letting you legally hack your way past digital paywalls. Designed for curious minds, this project runs a local web application containing real-world flaws often found in actual online stores. You get to play the role of a security researcher, learning how to manipulate network requests to drop a purchase price to zero, dig out hidden direct links to premium files, or change your user profile status to paid. It is a brilliant, hands-on way to understand web vulnerabilities safely on your own computer.
🆔 @hackernewsgithubprojects
This media is not supported in your browser
VIEW IN TELEGRAM
📦 osmantic/ods
ods
Turn your personal computer into a fully private, self-hosted artificial intelligence powerhouse without spending a weekend wrestling with complex code or configuration files. This project automatically scans your machine, figures out exactly what graphics card you have, and instantly configures a complete local server stack with everything pre-wired and ready to roll. Instead of manually stitching together complicated tools, you get a clean chat screen, offline image generation, voice capabilities, and smart automated assistants talking to each other out of the box. It keeps your data completely offline and under your control. Run your own private virtual assistant directly on your home hardware today.
🆔 @hackernewsgithubprojects
ods
Turn your personal computer into a fully private, self-hosted artificial intelligence powerhouse without spending a weekend wrestling with complex code or configuration files. This project automatically scans your machine, figures out exactly what graphics card you have, and instantly configures a complete local server stack with everything pre-wired and ready to roll. Instead of manually stitching together complicated tools, you get a clean chat screen, offline image generation, voice capabilities, and smart automated assistants talking to each other out of the box. It keeps your data completely offline and under your control. Run your own private virtual assistant directly on your home hardware today.
🆔 @hackernewsgithubprojects
This media is not supported in your browser
VIEW IN TELEGRAM
📦 zhaozhaozhiyi/xiaochuangx
Xiaochuangx
Build and customize professional presentations, interactive video screenplays, and parametric three-dimensional designs entirely through specialized digital assistants. Xiaochuangx is an open-source workstation that connects diverse AI agents to specific creation workflows. Instead of relying on generic chat windows, it matches your tasks with dedicated, skill-based companions. You can orchestrate precise slide generation, script out video stages with voiceovers, or generate raw physical models using programmatic tools. It bridges high-level artificial intelligence with practical, production-ready outputs. It is a highly practical toolkit for any developer looking to build structured, agent-driven applications that go far beyond basic text chat.
🆔 @hackernewsgithubprojects
Xiaochuangx
Build and customize professional presentations, interactive video screenplays, and parametric three-dimensional designs entirely through specialized digital assistants. Xiaochuangx is an open-source workstation that connects diverse AI agents to specific creation workflows. Instead of relying on generic chat windows, it matches your tasks with dedicated, skill-based companions. You can orchestrate precise slide generation, script out video stages with voiceovers, or generate raw physical models using programmatic tools. It bridges high-level artificial intelligence with practical, production-ready outputs. It is a highly practical toolkit for any developer looking to build structured, agent-driven applications that go far beyond basic text chat.
🆔 @hackernewsgithubprojects
This media is not supported in your browser
VIEW IN TELEGRAM
📦 moli13337/arcaea-6.14.11c
arcaea-6.14.11c
You can host your own fully functional private server for the rhythm game Arcaea, complete with every single song and character unlocked right out of the box. This clever toolkit lets you run a local Flask-based server that handles everything from instant registration to multiplayer lobbies. It even includes a custom patching utility for the game client that bypasses security checks and redirects traffic to your new server, all without needing to root your Android device. It is a fantastic way to experiment with multiplayer features, customize your gameplay experience, and explore your favorite tracks on your own terms.
🆔 @hackernewsgithubprojects
arcaea-6.14.11c
You can host your own fully functional private server for the rhythm game Arcaea, complete with every single song and character unlocked right out of the box. This clever toolkit lets you run a local Flask-based server that handles everything from instant registration to multiplayer lobbies. It even includes a custom patching utility for the game client that bypasses security checks and redirects traffic to your new server, all without needing to root your Android device. It is a fantastic way to experiment with multiplayer features, customize your gameplay experience, and explore your favorite tracks on your own terms.
🆔 @hackernewsgithubprojects
This media is not supported in your browser
VIEW IN TELEGRAM
📦 zjunlp/skillx
SkillX
AI models usually have to relearn how to use their tools from scratch every single time, but SkillX changes that by automatically building a permanent, reusable skill library for agents based on their past mistakes and successes. Instead of saving messy, giant chat histories, this clever framework distills raw experience into a neat, three-tier library of planning, functional, and atomic skills. You can even take a skill library built by a giant model and plug it directly into a smaller, cheaper model to give it an instant ten-percent performance boost. It is like giving your code an automated playbook that actually gets smarter over time.
🆔 @hackernewsgithubprojects
SkillX
AI models usually have to relearn how to use their tools from scratch every single time, but SkillX changes that by automatically building a permanent, reusable skill library for agents based on their past mistakes and successes. Instead of saving messy, giant chat histories, this clever framework distills raw experience into a neat, three-tier library of planning, functional, and atomic skills. You can even take a skill library built by a giant model and plug it directly into a smaller, cheaper model to give it an instant ten-percent performance boost. It is like giving your code an automated playbook that actually gets smarter over time.
🆔 @hackernewsgithubprojects
This media is not supported in your browser
VIEW IN TELEGRAM
📦 realchendahuang/sub-store-cloudflare
sub-store-cloudflare
You can now merge all your internet proxy subscriptions, filter out dead nodes, and generate custom routing rules without managing a single server. This clever tool runs entirely on Cloudflare Workers and a D1 database, meaning you get a lightning-fast web dashboard that costs absolutely nothing to host. You simply feed it your various subscription links or raw node text, apply built-in filters to rename or deduplicate nodes, and it outputs one clean, perfectly structured link tailored to your favorite client. It is incredibly easy to set up with a single-click deploy button, giving you complete control over your network routing directly from the cloud.
🆔 @hackernewsgithubprojects
sub-store-cloudflare
You can now merge all your internet proxy subscriptions, filter out dead nodes, and generate custom routing rules without managing a single server. This clever tool runs entirely on Cloudflare Workers and a D1 database, meaning you get a lightning-fast web dashboard that costs absolutely nothing to host. You simply feed it your various subscription links or raw node text, apply built-in filters to rename or deduplicate nodes, and it outputs one clean, perfectly structured link tailored to your favorite client. It is incredibly easy to set up with a single-click deploy button, giving you complete control over your network routing directly from the cloud.
🆔 @hackernewsgithubprojects
This media is not supported in your browser
VIEW IN TELEGRAM
📦 rodrigogs/whats-reader
Whats Reader
Browse your exported WhatsApp chat history offline and secure your personal data right on your computer. With this app, you just drag and drop your exported chat zip file to read your old messages, search through conversations, and view active participant statistics. The most impressive part is that it transcribes your voice notes using a local artificial intelligence model that runs entirely inside your browser. No data ever leaves your machine, and you do not need any external servers or API keys. It is the perfect, private way to preserve and explore your favorite digital memories.
🆔 @hackernewsgithubprojects
Whats Reader
Browse your exported WhatsApp chat history offline and secure your personal data right on your computer. With this app, you just drag and drop your exported chat zip file to read your old messages, search through conversations, and view active participant statistics. The most impressive part is that it transcribes your voice notes using a local artificial intelligence model that runs entirely inside your browser. No data ever leaves your machine, and you do not need any external servers or API keys. It is the perfect, private way to preserve and explore your favorite digital memories.
🆔 @hackernewsgithubprojects
This media is not supported in your browser
VIEW IN TELEGRAM
📦 advai-x/advai-cli
advai-cli
You can now control your Chrome browser, manage local developer skills, and chat with AI models directly from your terminal using a single tool. The advai-cli project acts as a unified command-line bridge that links your local system to a web extension, letting you run Javascript, click buttons, and take screenshots on live web pages with simple terminal commands. It also lets you sync custom agent skills across different coding platforms and build local, searchable knowledge bases from markdown files. It is the ultimate terminal companion for developers who want to merge browser automation with local AI assistance. Grab it via pip or npm and start driving your browser from...
🆔 @hackernewsgithubprojects
advai-cli
You can now control your Chrome browser, manage local developer skills, and chat with AI models directly from your terminal using a single tool. The advai-cli project acts as a unified command-line bridge that links your local system to a web extension, letting you run Javascript, click buttons, and take screenshots on live web pages with simple terminal commands. It also lets you sync custom agent skills across different coding platforms and build local, searchable knowledge bases from markdown files. It is the ultimate terminal companion for developers who want to merge browser automation with local AI assistance. Grab it via pip or npm and start driving your browser from...
🆔 @hackernewsgithubprojects
This media is not supported in your browser
VIEW IN TELEGRAM
📦 cporter202/automate-for-growth
Automate for Growth
Automate for Growth is a complete open-source course that helps you build custom social media systems to generate and schedule weeks of posts in just minutes. Instead of spending hours writing captions or editing videos manually, this repository teaches you how to design reusable content frameworks, write smart prompts for text-to-video generators, and auto-publish across eight platforms simultaneously. It is the perfect handbook for creators or developers who want to scale their online presence using automated workflows and API integrations. Start building your own content machine today and let automation do the heavy lifting.
🆔 @hackernewsgithubprojects
Automate for Growth
Automate for Growth is a complete open-source course that helps you build custom social media systems to generate and schedule weeks of posts in just minutes. Instead of spending hours writing captions or editing videos manually, this repository teaches you how to design reusable content frameworks, write smart prompts for text-to-video generators, and auto-publish across eight platforms simultaneously. It is the perfect handbook for creators or developers who want to scale their online presence using automated workflows and API integrations. Start building your own content machine today and let automation do the heavy lifting.
🆔 @hackernewsgithubprojects
This media is not supported in your browser
VIEW IN TELEGRAM
📦 514-labs/dnsglobe
dnsglobe
You can now watch your DNS changes update in real time on a global world map right inside your command line. dnsglobe is a lightweight terminal tool written in Rust that queries thirty-four different public resolvers across the planet simultaneously. Instead of constantly refreshing ad-heavy website checkers, you just type in your domain and watch the terminal automatically re-poll every thirty seconds. It directly queries major networks like Google and Cloudflare alongside regional servers in places like Brazil and New Zealand, painting colored dots across a text-based map to show you exactly where your records have successfully updated and where they are still lagging behind.
📰 https://news.ycombinator.com/item?id=48798313
🆔 @hackernewsgithubprojects
dnsglobe
You can now watch your DNS changes update in real time on a global world map right inside your command line. dnsglobe is a lightweight terminal tool written in Rust that queries thirty-four different public resolvers across the planet simultaneously. Instead of constantly refreshing ad-heavy website checkers, you just type in your domain and watch the terminal automatically re-poll every thirty seconds. It directly queries major networks like Google and Cloudflare alongside regional servers in places like Brazil and New Zealand, painting colored dots across a text-based map to show you exactly where your records have successfully updated and where they are still lagging behind.
📰 https://news.ycombinator.com/item?id=48798313
🆔 @hackernewsgithubprojects
This media is not supported in your browser
VIEW IN TELEGRAM
📦 saganaki22/comfyui-voxcpm2
ComfyUI VoxCPM2
Design custom voices from scratch using simple text descriptions right inside ComfyUI. The comfyui-voxcpm2 extension integrates a massive two-billion parameter speech model, letting you generate high-fidelity forty-eight kilohertz audio in thirty different languages without needing any language tags. You can describe a voice using everyday terms like age, emotion, or pace, clone existing voices from short audio clips, and even train your own custom adapters directly in your workflow. It is an incredibly flexible tool for anyone looking to generate studio-quality, highly expressive speech for their creative projects.
🆔 @hackernewsgithubprojects
ComfyUI VoxCPM2
Design custom voices from scratch using simple text descriptions right inside ComfyUI. The comfyui-voxcpm2 extension integrates a massive two-billion parameter speech model, letting you generate high-fidelity forty-eight kilohertz audio in thirty different languages without needing any language tags. You can describe a voice using everyday terms like age, emotion, or pace, clone existing voices from short audio clips, and even train your own custom adapters directly in your workflow. It is an incredibly flexible tool for anyone looking to generate studio-quality, highly expressive speech for their creative projects.
🆔 @hackernewsgithubprojects
This media is not supported in your browser
VIEW IN TELEGRAM
📦 solatis/claude-config
Claude Config
Optimize your AI-assisted coding by structuring how the model thinks, plans, and remembers. The claude-config repository introduces a disciplined workflow for Claude Code to stop technical debt from building up. Instead of letting the AI write code immediately, this setup forces it to write out a clear plan first, dividing the work into manageable milestones. It also keeps the AI's focus sharp by only feeding it essential information just-in-time, using a clever system of minimal directory files and strict token budgets. It ensures your projects stay clean, organized, and easy to maintain over time.
🆔 @hackernewsgithubprojects
Claude Config
Optimize your AI-assisted coding by structuring how the model thinks, plans, and remembers. The claude-config repository introduces a disciplined workflow for Claude Code to stop technical debt from building up. Instead of letting the AI write code immediately, this setup forces it to write out a clear plan first, dividing the work into manageable milestones. It also keeps the AI's focus sharp by only feeding it essential information just-in-time, using a clever system of minimal directory files and strict token budgets. It ensures your projects stay clean, organized, and easy to maintain over time.
🆔 @hackernewsgithubprojects
This media is not supported in your browser
VIEW IN TELEGRAM
📦 linxiaotao/fuckclaude
Fuck Claude
Your browser's digital fingerprint might be secretly flagging you as a restricted user. A clever open-source tool called fuckclaude scans your local system to see if your browser matches the exact environment checks used by developer tools like Claude Code to block or flag users from China. Everything runs completely inside your browser with zero network requests or data uploads. It assigns weights to indicators like your system timezone, default locale, browser language, and even local Chinese system fonts to calculate an overall risk score. It is a brilliant way to audit your digital privacy and understand how modern AI tools fingerprint your machine.
🆔 @hackernewsgithubprojects
Fuck Claude
Your browser's digital fingerprint might be secretly flagging you as a restricted user. A clever open-source tool called fuckclaude scans your local system to see if your browser matches the exact environment checks used by developer tools like Claude Code to block or flag users from China. Everything runs completely inside your browser with zero network requests or data uploads. It assigns weights to indicators like your system timezone, default locale, browser language, and even local Chinese system fonts to calculate an overall risk score. It is a brilliant way to audit your digital privacy and understand how modern AI tools fingerprint your machine.
🆔 @hackernewsgithubprojects
This media is not supported in your browser
VIEW IN TELEGRAM
📦 mariusdjen/vpskit
Vpskit Server Setup
You can now completely secure and configure a fresh Linux server in minutes with just a single terminal command. Instead of relying on expensive third-party cloud control panels, vpskit is a clever local script that connects to your virtual private server over SSH to handle the heavy lifting. It automatically updates your system, creates a new non-root user, blocks brute-force login attempts, locks down SSH access, and configures a firewall. It even installs Docker and sets up Caddy as a reverse proxy with automated SSL. The coolest part is that all of your configurations and keys stay completely local and private on your machine.
🆔 @hackernewsgithubprojects
Vpskit Server Setup
You can now completely secure and configure a fresh Linux server in minutes with just a single terminal command. Instead of relying on expensive third-party cloud control panels, vpskit is a clever local script that connects to your virtual private server over SSH to handle the heavy lifting. It automatically updates your system, creates a new non-root user, blocks brute-force login attempts, locks down SSH access, and configures a firewall. It even installs Docker and sets up Caddy as a reverse proxy with automated SSL. The coolest part is that all of your configurations and keys stay completely local and private on your machine.
🆔 @hackernewsgithubprojects
This media is not supported in your browser
VIEW IN TELEGRAM
📦 cyber-note/full-bug-bounty-hunting-methodology-2026
Full Bug Bounty Hunting Methodology 2026
Full-bug-bounty-hunting-methodology-2026 is the security testing guide that treats asset discovery as a deep intelligence operation instead of a basic checklist. This extensive resource maps out a step-by-step offensive strategy for finding vulnerabilities in target organizations before ever launching an exploit. The absolute best part of this guide is its highly creative approach to bypass web firewalls by matching favicon fingerprint hashes across public databases to locate hidden origin servers. It is a brilliant blueprint for anyone wanting to learn how digital defense systems work in the real world. Check it out to level up your reconnaissance logic today.
🆔 @hackernewsgithubprojects
Full Bug Bounty Hunting Methodology 2026
Full-bug-bounty-hunting-methodology-2026 is the security testing guide that treats asset discovery as a deep intelligence operation instead of a basic checklist. This extensive resource maps out a step-by-step offensive strategy for finding vulnerabilities in target organizations before ever launching an exploit. The absolute best part of this guide is its highly creative approach to bypass web firewalls by matching favicon fingerprint hashes across public databases to locate hidden origin servers. It is a brilliant blueprint for anyone wanting to learn how digital defense systems work in the real world. Check it out to level up your reconnaissance logic today.
🆔 @hackernewsgithubprojects
This media is not supported in your browser
VIEW IN TELEGRAM
📦 synthetic-sciences/openscience
openscience
Run complex computational biology and chemistry pipelines using modular, pre-configured AI agents. This workbench acts as an open-source command center for scientific research, packaging domain-specific intelligence into specialized skills. Instead of fighting with brittle environments, you can orchestrate tasks across PyTorch, RDKit, scanpy, and even hardware integrations like liquid handlers. The single coolest aspect is how it translates abstract scientific protocols into executable code, letting you run molecular docking, sequence analysis, or clinical report generation through a unified interface. It bridges the gap between raw data and real discoveries, giving developers a brilliant shortcut to heavy-duty scientific computing.
📰 https://news.ycombinator.com/item?id=48786827
🆔 @hackernewsgithubprojects
openscience
Run complex computational biology and chemistry pipelines using modular, pre-configured AI agents. This workbench acts as an open-source command center for scientific research, packaging domain-specific intelligence into specialized skills. Instead of fighting with brittle environments, you can orchestrate tasks across PyTorch, RDKit, scanpy, and even hardware integrations like liquid handlers. The single coolest aspect is how it translates abstract scientific protocols into executable code, letting you run molecular docking, sequence analysis, or clinical report generation through a unified interface. It bridges the gap between raw data and real discoveries, giving developers a brilliant shortcut to heavy-duty scientific computing.
📰 https://news.ycombinator.com/item?id=48786827
🆔 @hackernewsgithubprojects