This media is not supported in your browser
VIEW IN TELEGRAM
π¦ bangtutorial/bang-motion
Bang Motion: AI Motion Graphics
Bang Motion stops your AI coding agent from creating boring slide shows. Instead, it builds full motion graphics that move like real videos with a moving camera and continuous scenes. It turns a simple request into a single HTML file that plays like a video, not a presentation. The project solves the problem of generic, static animations by forcing the agent to follow professional motion design rules. You get openers, promos, and explainers that actually look professional. It works with tools like Claude Code and Cursor. The takeaway is simple: you can now generate cinematic web animations without hiring a designer.
π @hackernewsgithubprojects
Bang Motion: AI Motion Graphics
Bang Motion stops your AI coding agent from creating boring slide shows. Instead, it builds full motion graphics that move like real videos with a moving camera and continuous scenes. It turns a simple request into a single HTML file that plays like a video, not a presentation. The project solves the problem of generic, static animations by forcing the agent to follow professional motion design rules. You get openers, promos, and explainers that actually look professional. It works with tools like Claude Code and Cursor. The takeaway is simple: you can now generate cinematic web animations without hiring a designer.
π @hackernewsgithubprojects
This media is not supported in your browser
VIEW IN TELEGRAM
π¦ strategic-automation/violin
Violin: The Pentest Profile That Keeps Your AI Honest
Violin gives you a structured way to run authorized penetration tests using an AI agent, but with strict guardrails so it doesn't just guess. The coolest part? It forces the AI to back up every finding with reproducible proof before it will even let you report it, meaning no more hallucinated vulnerabilities. It acts like a strict supervisor, checking its work against a set of playbooks for things like web app flaws or API issues. If youβre running security tests with AI, this is the difference between a helpful assistant and a reckless one. Itβs not about speed; itβs about trust.
π @hackernewsgithubprojects
Violin: The Pentest Profile That Keeps Your AI Honest
Violin gives you a structured way to run authorized penetration tests using an AI agent, but with strict guardrails so it doesn't just guess. The coolest part? It forces the AI to back up every finding with reproducible proof before it will even let you report it, meaning no more hallucinated vulnerabilities. It acts like a strict supervisor, checking its work against a set of playbooks for things like web app flaws or API issues. If youβre running security tests with AI, this is the difference between a helpful assistant and a reckless one. Itβs not about speed; itβs about trust.
π @hackernewsgithubprojects
This media is not supported in your browser
VIEW IN TELEGRAM
π¦ whaleyxbt/patchright-enhanced
How to Pass Cloudflare Like a Ghost
Open a Chrome session that passes Cloudflare and DataDome without breaking a sweat. Patchright Enhanced is a stealth browser toolkit built specifically for penetration testing and quality assurance. It wraps the Patchright engine to give you clean sessions that look indistinguishable from a real human user. The coolest part? It skips the messy JavaScript injection hacks most people use. Instead, it patches the browser engine directly so the automated flags simply don't exist. No more `navigator.webdriver` leaks. It just works. If you need to test your site's defenses, this is your go-to tool.
π @hackernewsgithubprojects
How to Pass Cloudflare Like a Ghost
Open a Chrome session that passes Cloudflare and DataDome without breaking a sweat. Patchright Enhanced is a stealth browser toolkit built specifically for penetration testing and quality assurance. It wraps the Patchright engine to give you clean sessions that look indistinguishable from a real human user. The coolest part? It skips the messy JavaScript injection hacks most people use. Instead, it patches the browser engine directly so the automated flags simply don't exist. No more `navigator.webdriver` leaks. It just works. If you need to test your site's defenses, this is your go-to tool.
π @hackernewsgithubprojects
This media is not supported in your browser
VIEW IN TELEGRAM
π¦ isas1/forever-ai-components
Forever AI Components: A UI Library for Bots
Your AI coding assistant usually builds user interfaces by guessing, but Forever AI Components gives it a massive cheat sheet. It contains over six hundred ready-made animated parts, like buttons, loaders, and cool visual backgrounds, each saved as a single, self-contained file with zero external dependencies. This is not just a code library for humans; it is specifically designed for bots. Every component comes with detailed instructions on when to use it and how to safely tweak the colors or spacing. This means your AI agent can search the catalog, pick the perfect piece, and drop it right into your project without breaking anything.
π @hackernewsgithubprojects
Forever AI Components: A UI Library for Bots
Your AI coding assistant usually builds user interfaces by guessing, but Forever AI Components gives it a massive cheat sheet. It contains over six hundred ready-made animated parts, like buttons, loaders, and cool visual backgrounds, each saved as a single, self-contained file with zero external dependencies. This is not just a code library for humans; it is specifically designed for bots. Every component comes with detailed instructions on when to use it and how to safely tweak the colors or spacing. This means your AI agent can search the catalog, pick the perfect piece, and drop it right into your project without breaking anything.
π @hackernewsgithubprojects
This media is not supported in your browser
VIEW IN TELEGRAM
π¦ career-ops-hq/career-ops
The AI Job Hunt
career ops is the local AI agent that turns your terminal into a rigorous job hunting engine. It stops you from wasting hours on bad leads by scanning portals, evaluating every listing, and giving each one a clear score so you know exactly which roles deserve your time. Instead of guessing if you are a good fit, it reads your resume against the job description and tells you the truth before you apply. This shifts the power back to you, ensuring you only chase the opportunities that actually match your career goals. It is the smart, private way to filter the noise and find your next big break.
π @hackernewsgithubprojects
The AI Job Hunt
career ops is the local AI agent that turns your terminal into a rigorous job hunting engine. It stops you from wasting hours on bad leads by scanning portals, evaluating every listing, and giving each one a clear score so you know exactly which roles deserve your time. Instead of guessing if you are a good fit, it reads your resume against the job description and tells you the truth before you apply. This shifts the power back to you, ensuring you only chase the opportunities that actually match your career goals. It is the smart, private way to filter the noise and find your next big break.
π @hackernewsgithubprojects
This media is not supported in your browser
VIEW IN TELEGRAM
π¦ manasvinyadav/lucid
Lucid: The Mac App That Knows When Your AI Is Actually Working
Lucid is the Mac menu bar app that finally stops your laptop from sleeping only when your AI coding agent is actually busy. Every other keep awake tool has to guess if work is happening, which means your Mac either never sleeps or wakes up mid build. Lucid listens directly to the coding agent's own events, so it knows the exact difference between the AI thinking and the AI waiting for you to type. It keeps the Mac awake with the lid closed during those long generations, then lets it sleep the second the agent goes idle. No more guessing, no more battery drain, and no more interrupted code builds.
π @hackernewsgithubprojects
Lucid: The Mac App That Knows When Your AI Is Actually Working
Lucid is the Mac menu bar app that finally stops your laptop from sleeping only when your AI coding agent is actually busy. Every other keep awake tool has to guess if work is happening, which means your Mac either never sleeps or wakes up mid build. Lucid listens directly to the coding agent's own events, so it knows the exact difference between the AI thinking and the AI waiting for you to type. It keeps the Mac awake with the lid closed during those long generations, then lets it sleep the second the agent goes idle. No more guessing, no more battery drain, and no more interrupted code builds.
π @hackernewsgithubprojects
This media is not supported in your browser
VIEW IN TELEGRAM
π¦ fast-editor/lynkr
Lynkr: Save Tokens with Smart Routing
Stop burning through your AI credits on basic coding tasks. Lynkr is a smart proxy that sits between your AI tools and the models, acting as a traffic cop for your code. It automatically sends simple questions to free, local models and routes only the hard, complex problems to your expensive cloud subscriptions. The coolest part is how it compresses the massive amounts of data your coding tools send, slashing token costs by over half without you changing a single line of code. It basically makes your AI subscription go further by ensuring you only pay for the heavy lifting.
π @hackernewsgithubprojects
Lynkr: Save Tokens with Smart Routing
Stop burning through your AI credits on basic coding tasks. Lynkr is a smart proxy that sits between your AI tools and the models, acting as a traffic cop for your code. It automatically sends simple questions to free, local models and routes only the hard, complex problems to your expensive cloud subscriptions. The coolest part is how it compresses the massive amounts of data your coding tools send, slashing token costs by over half without you changing a single line of code. It basically makes your AI subscription go further by ensuring you only pay for the heavy lifting.
π @hackernewsgithubprojects
This media is not supported in your browser
VIEW IN TELEGRAM
π¦ calix-l/danks
Danks: The AI That Masters Guandan
Danks is an artificial intelligence engine built specifically to beat humans at the four-player Chinese card game Guandan. The most interesting part is how it handles long-term strategy. In Guandan, playing a cheap card now can accidentally ruin your winning hand later, but Danks learns to see that trap coming. It uses a method called PPO, which is a type of reinforcement learning, to practice against itself thousands of times. This lets it understand which moves preserve its best card combinations for the end of the round. Itβs not just a random card picker; itβs a strategic partner that actually thinks ahead.
π @hackernewsgithubprojects
Danks: The AI That Masters Guandan
Danks is an artificial intelligence engine built specifically to beat humans at the four-player Chinese card game Guandan. The most interesting part is how it handles long-term strategy. In Guandan, playing a cheap card now can accidentally ruin your winning hand later, but Danks learns to see that trap coming. It uses a method called PPO, which is a type of reinforcement learning, to practice against itself thousands of times. This lets it understand which moves preserve its best card combinations for the end of the round. Itβs not just a random card picker; itβs a strategic partner that actually thinks ahead.
π @hackernewsgithubprojects
This media is not supported in your browser
VIEW IN TELEGRAM
π¦ agent-sh/agent-workspace-linux
The Agent's Secret Desk
Agent Workspace Linux is the hidden desktop that lets AI agents work without stealing your screen. Instead of hijacking your actual mouse and browser, it spins up a completely private, invisible Linux environment where the agent can open apps, type, and browse safely. You can even pop up a tiny floating window to watch what it is doing and pause it if it gets weird. It is perfect for letting an AI check out a website or run a program without messing up your real files or logged-in accounts.
π° https://news.ycombinator.com/item?id=48291255
π @hackernewsgithubprojects
The Agent's Secret Desk
Agent Workspace Linux is the hidden desktop that lets AI agents work without stealing your screen. Instead of hijacking your actual mouse and browser, it spins up a completely private, invisible Linux environment where the agent can open apps, type, and browse safely. You can even pop up a tiny floating window to watch what it is doing and pause it if it gets weird. It is perfect for letting an AI check out a website or run a program without messing up your real files or logged-in accounts.
π° https://news.ycombinator.com/item?id=48291255
π @hackernewsgithubprojects
This media is not supported in your browser
VIEW IN TELEGRAM
π¦ lfzk550/fanzha-ai-proxy
Fanzha AI Proxy: Chat With China's Anti-Scam AI
Plug your favorite chat tools directly into Chinaβs national anti-fraud AI. The Fanzha AI Proxy server bridges the gap between standard developer tools and a government security system that usually has no public access. It listens for standard chat requests, grabs a secure login session, and streams the AIβs fraud detection answers back in a format your code already understands. This lets you test how a real-world safety model handles tricky scam scenarios. It is a neat way to see how security logic works outside the usual chatbot world. Now you can explore real anti-fraud intelligence without needing complex integrations.
π @hackernewsgithubprojects
Fanzha AI Proxy: Chat With China's Anti-Scam AI
Plug your favorite chat tools directly into Chinaβs national anti-fraud AI. The Fanzha AI Proxy server bridges the gap between standard developer tools and a government security system that usually has no public access. It listens for standard chat requests, grabs a secure login session, and streams the AIβs fraud detection answers back in a format your code already understands. This lets you test how a real-world safety model handles tricky scam scenarios. It is a neat way to see how security logic works outside the usual chatbot world. Now you can explore real anti-fraud intelligence without needing complex integrations.
π @hackernewsgithubprojects
This media is not supported in your browser
VIEW IN TELEGRAM
π¦ theoleecj/openjev
OpenJev: Run AI Decisions in Your Browser
Run complex AI decisions on your own hardware, right now. OpenJev is an open-source tool that reads answers directly from a small language model instead of waiting for it to write out a sentence. This skips the slow typing process, making your AI logic roughly five times faster. Itβs perfect for testing real-time choices on a single home computer. No cloud servers, no waitlists, just a clean, auditable result on your own screen.
π @hackernewsgithubprojects
OpenJev: Run AI Decisions in Your Browser
Run complex AI decisions on your own hardware, right now. OpenJev is an open-source tool that reads answers directly from a small language model instead of waiting for it to write out a sentence. This skips the slow typing process, making your AI logic roughly five times faster. Itβs perfect for testing real-time choices on a single home computer. No cloud servers, no waitlists, just a clean, auditable result on your own screen.
π @hackernewsgithubprojects
This media is not supported in your browser
VIEW IN TELEGRAM
π¦ sarahroselives/dedective
Dedective: Hear Both Sides of Cordless Calls
Dedective is the cordless phone decoder that plays both sides of the call at once. This Linux tool connects to a cheap radio hardware card to listen for old style cordless phones. Instead of just finding a signal, it actually turns the static back into human speech. The coolest part is that it mixes the voice from the base station and the handset into one stream, so you hear the entire conversation happening live. It even follows the call if it jumps to a new frequency. It is a neat way to see how this old technology works right on your computer.
π° https://news.ycombinator.com/item?id=47475469
π @hackernewsgithubprojects
Dedective: Hear Both Sides of Cordless Calls
Dedective is the cordless phone decoder that plays both sides of the call at once. This Linux tool connects to a cheap radio hardware card to listen for old style cordless phones. Instead of just finding a signal, it actually turns the static back into human speech. The coolest part is that it mixes the voice from the base station and the handset into one stream, so you hear the entire conversation happening live. It even follows the call if it jumps to a new frequency. It is a neat way to see how this old technology works right on your computer.
π° https://news.ycombinator.com/item?id=47475469
π @hackernewsgithubprojects
This media is not supported in your browser
VIEW IN TELEGRAM
π¦ oihalitz/xdp-dns-evadeproxy
Evade Proxy: Bypassing ISP Blocks
Evade Proxy quietly swaps out blocked website addresses in your DNS responses. Your internet provider sometimes blocks entire groups of servers by mistake, taking down hundreds of unrelated sites with them. This project, built for the XDP DNS service, watches for those bad addresses and instantly replaces them with a working neighbor from the same network range. It does this right in the middle of the DNS answer, so your device gets a good address without you ever knowing anything was wrong. The result is simple: websites that disappeared due to a clumsy block just keep working.
π° https://news.ycombinator.com/item?id=49685280
π @hackernewsgithubprojects
Evade Proxy: Bypassing ISP Blocks
Evade Proxy quietly swaps out blocked website addresses in your DNS responses. Your internet provider sometimes blocks entire groups of servers by mistake, taking down hundreds of unrelated sites with them. This project, built for the XDP DNS service, watches for those bad addresses and instantly replaces them with a working neighbor from the same network range. It does this right in the middle of the DNS answer, so your device gets a good address without you ever knowing anything was wrong. The result is simple: websites that disappeared due to a clumsy block just keep working.
π° https://news.ycombinator.com/item?id=49685280
π @hackernewsgithubprojects
This media is not supported in your browser
VIEW IN TELEGRAM
π¦ azadnaeemi/gt2n
GT2N: The 2nm Chip Blueprint
GT2N lets you design actual chips on the bleeding-edge two-nanometer node without paying a single cent to a foundry. It is an open-source process design kit that gives you the exact blueprints, device models, and standard cells needed to build circuits. The coolest part is that it lets you test different transistor widths and voltages to see how they change your chipβs power and speed. If you are a student or hobbyist wanting to peek behind the curtain of modern chip fabrication, this is your front-row seat to the future. Grab the repo and start building.
π @hackernewsgithubprojects
GT2N: The 2nm Chip Blueprint
GT2N lets you design actual chips on the bleeding-edge two-nanometer node without paying a single cent to a foundry. It is an open-source process design kit that gives you the exact blueprints, device models, and standard cells needed to build circuits. The coolest part is that it lets you test different transistor widths and voltages to see how they change your chipβs power and speed. If you are a student or hobbyist wanting to peek behind the curtain of modern chip fabrication, this is your front-row seat to the future. Grab the repo and start building.
π @hackernewsgithubprojects
This media is not supported in your browser
VIEW IN TELEGRAM
π¦ nota-america/forgecat-agent-profiles
ForgeCat Agent Profiles
Grab production-ready setups for your favorite coding bots in seconds. ForgeCat Agent Profiles takes messy, scattered AI agent configurations and turns them into clean, installable packages you can grab with one simple command. It solves the headache of copying files between tools by giving you a single catalog that works across Claude Code, Cursor, and Codex. You get real, tested workflows from trusted sources, complete with proper licensing so you always know exactly what you are running. No more guessing if a setup actually works. Just search, install, and get your AI agents working exactly how you want, instantly.
π @hackernewsgithubprojects
ForgeCat Agent Profiles
Grab production-ready setups for your favorite coding bots in seconds. ForgeCat Agent Profiles takes messy, scattered AI agent configurations and turns them into clean, installable packages you can grab with one simple command. It solves the headache of copying files between tools by giving you a single catalog that works across Claude Code, Cursor, and Codex. You get real, tested workflows from trusted sources, complete with proper licensing so you always know exactly what you are running. No more guessing if a setup actually works. Just search, install, and get your AI agents working exactly how you want, instantly.
π @hackernewsgithubprojects
This media is not supported in your browser
VIEW IN TELEGRAM
π¦ anthropics/claude-tag-plugins
Claude Tag Plugins: The Ultimate AI Connector
Claude Tag Plugins is the open-source toolkit that lets Anthropicβs AI agents talk directly to the software your team already uses. Instead of writing complex code to connect Claude to every single tool, you simply install the specific plugins you need. The real surprise here is how modular it is. You can give Claude the ability to read your Jira tickets, query your Snowflake database, or even manage your on-call rotations without touching any manual setup. It works like a plug-and-play system, where each service acts as its own distinct package. This means your AI assistant only knows what it needs to know for your specific workflow.
π @hackernewsgithubprojects
Claude Tag Plugins: The Ultimate AI Connector
Claude Tag Plugins is the open-source toolkit that lets Anthropicβs AI agents talk directly to the software your team already uses. Instead of writing complex code to connect Claude to every single tool, you simply install the specific plugins you need. The real surprise here is how modular it is. You can give Claude the ability to read your Jira tickets, query your Snowflake database, or even manage your on-call rotations without touching any manual setup. It works like a plug-and-play system, where each service acts as its own distinct package. This means your AI assistant only knows what it needs to know for your specific workflow.
π @hackernewsgithubprojects
This media is not supported in your browser
VIEW IN TELEGRAM
π¦ 0xsero/glm-5.3-flash-dgx-spark
Run GLM 5.3 Flash on a Single Spark
Run a three hundred and twenty billion parameter AI model on a single desktop computer, powered by just one GPU, using a simple container command. The GLM 5.3 Flash DGX Spark repository achieves this by compressing the massive model into a compact format that fits entirely in one hundred and twenty eight gigabytes of memory. This eliminates the need for expensive multi-server clusters, allowing you to serve high-quality, long-context AI responses locally. The project includes verified benchmarks proving the compressed model retains nearly all the original reasoning and vision capabilities. If you want to run frontier-level AI hardware on a single Spark device, this is the exact recipe to use.
π @hackernewsgithubprojects
Run GLM 5.3 Flash on a Single Spark
Run a three hundred and twenty billion parameter AI model on a single desktop computer, powered by just one GPU, using a simple container command. The GLM 5.3 Flash DGX Spark repository achieves this by compressing the massive model into a compact format that fits entirely in one hundred and twenty eight gigabytes of memory. This eliminates the need for expensive multi-server clusters, allowing you to serve high-quality, long-context AI responses locally. The project includes verified benchmarks proving the compressed model retains nearly all the original reasoning and vision capabilities. If you want to run frontier-level AI hardware on a single Spark device, this is the exact recipe to use.
π @hackernewsgithubprojects
This media is not supported in your browser
VIEW IN TELEGRAM
π¦ ruc-datalab/evoontology
EvoOntology: The Self-Evolving Data Brain
Teaches your AI agent to understand complex databases by building a living map of your data instead of forcing it to guess every time. EvoOntology solves the problem where smart code tools stumble over messy tables because they lack context. It builds a clear guide that explains exactly what every column means, then updates that guide automatically as your agent learns. The surprising part is that the knowledge layer improves itself by watching how the agent works, making it smarter with every task. If you want your tools to stop making errors and start truly understanding your business data, this is the layer that makes it happen.
π @hackernewsgithubprojects
EvoOntology: The Self-Evolving Data Brain
Teaches your AI agent to understand complex databases by building a living map of your data instead of forcing it to guess every time. EvoOntology solves the problem where smart code tools stumble over messy tables because they lack context. It builds a clear guide that explains exactly what every column means, then updates that guide automatically as your agent learns. The surprising part is that the knowledge layer improves itself by watching how the agent works, making it smarter with every task. If you want your tools to stop making errors and start truly understanding your business data, this is the layer that makes it happen.
π @hackernewsgithubprojects
This media is not supported in your browser
VIEW IN TELEGRAM
π¦ derpyu520/qq-bridge
qq-bridge: The AI That Joins Your Group Chat
qq-bridge is the messaging bridge that turns a standard AI assistant into a believable friend inside your group chat. It connects your favorite instant messenger directly to a local AI agent, allowing the computer to read, think, and reply to messages just like a real person would. The most surprising part is how it learns to fit in; the system actively studies the specific slang and internet expressions used by your friends, only adopting them after you confirm they fit the group's vibe. This creates a natural, low-key presence where the AI can observe the room, decide when to speak, and even stay quiet to let things breathe.
π @hackernewsgithubprojects
qq-bridge: The AI That Joins Your Group Chat
qq-bridge is the messaging bridge that turns a standard AI assistant into a believable friend inside your group chat. It connects your favorite instant messenger directly to a local AI agent, allowing the computer to read, think, and reply to messages just like a real person would. The most surprising part is how it learns to fit in; the system actively studies the specific slang and internet expressions used by your friends, only adopting them after you confirm they fit the group's vibe. This creates a natural, low-key presence where the AI can observe the room, decide when to speak, and even stay quiet to let things breathe.
π @hackernewsgithubprojects
This media is not supported in your browser
VIEW IN TELEGRAM
π¦ alesha-pro/tools
Tools: Make AI Video With Sound On Your Own PC
Tools is the open source collection that finally makes home video generation with sound actually practical. Built by someone running four high end graphics cards, it packages everything needed to run the MiniMax H3 model locally. The standout feature is synchronized audio. Instead of generating silent clips and bolting sound on later, this model creates the visuals and the matching voice and music in one single pass. It also includes smart workflows that split the heavy lifting across multiple graphics cards to cut render times from nineteen minutes down to under seven.
π @hackernewsgithubprojects
Tools: Make AI Video With Sound On Your Own PC
Tools is the open source collection that finally makes home video generation with sound actually practical. Built by someone running four high end graphics cards, it packages everything needed to run the MiniMax H3 model locally. The standout feature is synchronized audio. Instead of generating silent clips and bolting sound on later, this model creates the visuals and the matching voice and music in one single pass. It also includes smart workflows that split the heavy lifting across multiple graphics cards to cut render times from nineteen minutes down to under seven.
π @hackernewsgithubprojects