📦 sudharsanselvaraj/token-print

Token Print: See Your AI Model Think

Watch your language model think in real time. Token Print renders the actual math happening inside an AI as a live, three dimensional scene, letting you see attention heads and data streams move as the model generates words. This isn't a static diagram or a fake demo; it pulls live numbers from a real model to show you exactly what is happening. It solves the problem of AI being a black box by making the invisible process visible and tangible. If you want to truly understand how these models work, this tool turns abstract code into a concrete visual experience you can actually see.

🆔 @hackernewsgithubprojects

📦 jamespolyakov9829/captcha-api

captcha-api

Solve tough browser verification hurdles automatically using a lightweight Python client that runs with zero external dependencies. This project handles both Cloudflare Turnstile widgets and verification challenges inside a single interface. It stands out by matching your request with a precise browser identity block, including custom header sequences and fingerprint emulation, so your target website actually accepts the solved token instead of throwing it away. You can estimate your exact API costs beforehand, track spending in real-time, and run multi-threaded batch operations without writing complex concurrency logic. It is a clean, standard-library-only tool built to keep automated tasks running smoothly.

🆔 @hackernewsgithubprojects

📦 michael-jiahao-zhang/game-the-llm-reviewer

Game the LLM Reviewer

Peer reviewers powered by artificial intelligence often score the exact same scientific paragraph differently depending on how it is phrased. The tool called Game the LLM Reviewer solves this by making tiny, meaning-preserving edits to a finished paper. It rearranges sentences to highlight key contributions and frames data as clear gains, all without changing the actual science. This defensive rewrite helps ensure your research is judged on its merit, not its wording. It is a final polish for any author wanting to protect their work from algorithmic bias. Use this simple skill to make your paper impossible to misread before you submit it.

🆔 @hackernewsgithubprojects

📦 hirotomasato/yowes

Yowes

This lightweight tool can instantly generate high-resolution, realistic teacher verification documents like ID cards, employment letters, and teaching licenses for thirteen different countries. Known as yowes, it functions as a headless server using the Model Context Protocol, allowing AI assistants to directly create these files during a conversation. Instead of relying on generic placeholders, yowes features real school databases with local street addresses, consistent profile photos, and built-in fonts so that everything looks completely authentic right out of the box. It is an incredibly clever way to integrate automated, localized document generation straight into your favorite AI developer tools.

🆔 @hackernewsgithubprojects

📦 livecontext-ai/livecontext-ce

LiveContext: The Self-Hosted AI Automation Platform

LiveContext lets you describe a job in plain chat and instantly generates a working, self-hosted automation complete with a visual workflow, scoped AI agents, and a custom app interface. This open-source platform acts as a self-contained alternative to tools like Zapier or N8N, but with a major twist: it builds the entire system for you. Instead of stitching together separate chatbots and automation tools, you get a single canvas where the chat builds the logic, the agents execute the tasks, and the app displays the results. It is designed to be transparent, so you can see exactly what the AI is doing and how much it costs.

🆔 @hackernewsgithubprojects

📦 scenario-labs/skills

Skills: The Creative Toolset for AI Agents

One prompt can now spin up a fully consistent character, generate matching 3D meshes, and cut a finished music video, all without leaving your terminal. This repository, simply called Skills, turns coding assistants into professional creative studios. It teaches agents like Claude or Copilot to speak directly to a specialized media server, handling everything from pixel art and audio to complex video edits. The magic lies in consistency, where the same character looks identical across a hundred different scenes. If you build games or videos, this toolkit turns your code editor into a production line. It is the bridge between writing code and shipping actual creative work.

🆔 @hackernewsgithubprojects

📦 secwind7/polytech-tree

Polytech Tree: A 3D Map of Human Innovation

Fly through a three dimensional tower that stacks the entire history of human technology, from the first stone tools all the way to modern electronics. This project visualizes how every major invention is physically supported by the ideas that came before it, turning abstract history into a tangible structure you can explore with your mouse. It solves the problem of seeing how complex innovations actually connect by mapping the prerequisites as glowing lines that link the layers of time together. You can hover over any shape to read a brief summary, or start a guided camera tour that spirals up the tower to show the flow of progress.

🆔 @hackernewsgithubprojects

📦 goncafer47/stablecoin-payment-gateway

Stablecoin Payment Gateway: Take Zero Fees

You can now charge for your API calls using the old HTTP four hundred and two status code, effectively turning any web endpoint into a paid service with stablecoins. This self-hosted gateway lets you accept dollars in digital form across eight different networks while keeping your private keys entirely safe. It watches the blockchain to confirm payments and sends secure alerts to your server, all without a single cent in platform fees or identity checks. If you want to accept crypto payments without handing your money to a third party, this Python tool is the way to do it.

🆔 @hackernewsgithubprojects

📦 trustfuture/simon-skills

Simon Skills: Make Videos Without Showing Your Face

Turn one topic into a finished video. Simon Skills gives an AI agent the tools to research facts, write scripts, add voiceover, and design thumbnails. It creates long investigation pieces or short whiteboard explainers. The AI handles the heavy lifting so you get a ready-to-post file. This is perfect for creators who want results without filming themselves. The repo uses real workflows to avoid common mistakes. You get a clear, professional result fast. Try it and see how easy content creation becomes.

🆔 @hackernewsgithubprojects

📦 amitshekhariitbhu/ai-system-design

AI System Design

There is one place that actually explains how to build large language model systems without the headache. This guide, called AI System Design, walks you through the messy reality of serving models, managing memory, and wiring up agents. It cuts through the noise by breaking down complex hardware and data retrieval into plain, digestible steps. You will learn exactly how to handle latency, cache smartly, and scale your infrastructure. It is the missing manual for anyone building real AI products. No more guessing why your server slows down. Just clear, practical answers. Bookmark this repo now. It is the only refresher you will ever need to master the stack.

🆔 @hackernewsgithubprojects

📦 luketheneuromancer/system-design-notes-zh

Mastering System Design Interviews in Chinese

Prepare for system design interviews with a comprehensive Chinese translation of the System Design Notes repository. This resource translates the popular system-design-notes book by liquidslr into Chinese, helping developers prepare for interviews at top tech companies. The repository covers essential topics like scaling, load balancing, database sharding, caching, and designing complex systems like YouTube, Google Drive, and payment systems. It includes diagrams, explanations, and real-world examples to make learning accessible. Perfect for engineers who prefer studying in Chinese or want a clear, structured guide to high-level system architecture. Start building scalable systems with this detailed and practical study guide.

🆔 @hackernewsgithubprojects

📦 win4r/museai-skills

Inside the Muse AI Brain

Peek inside the actual brain of a personal AI agent. This repository preserves the exact instructions that teach the system how to think. You get to see the specific rules for handling email, booking flights, or even forgetting things on purpose. It is not just code; it is a map of logic. It shows you exactly when to ask for permission and how to verify that a job is truly done. This is a rare look at the hidden machinery behind the chat. It turns a black box into a clear blueprint. If you build agents, this is your cheat sheet. It reveals the secret architecture of trust.

🆔 @hackernewsgithubprojects

📦 apify/mcpc

mcpc: The Universal MCP CLI

Turn any Model Context Protocol server into a simple command line tool with mcpc. It handles the messy parts like login, connection management, and output formatting so you just get the data you need. Think of it as a universal translator that lets your terminal talk directly to AI servers, whether they run locally or over the web. This is especially cool because it makes complex AI capabilities accessible without writing custom glue code for every single app. It just works, keeping your sessions alive and your data clean. If you build with AI tools, this saves you a ton of headache.

🆔 @hackernewsgithubprojects

📦 ghaida/intent

Design with Intent: Your New AI Design Team

Design with Intent is the AI agent collection that finally makes sure your products have a reason for existing. Instead of just asking a chatbot to draw a button, this tool hands you six distinct AI personas, like Ember for research and Wren for design, who actually think through the why behind every decision. It comes with a massive list of sneaky tricks that apps use to trick you, so these agents actively protect you from building bad, manipulative software. You just paste their instructions into your favorite AI tool, and they handle everything from the initial strategy to the final handoff to your developers.

🆔 @hackernewsgithubprojects

📦 kaolti/phantomat

phantomat

Break away from rigid virtual workspaces by turning your desktop into a massive, zoomable infinite canvas. This clever system places all of your running applications on a single endless plane that you can pan, zoom, and organize freely. Multiple monitors function as a unified physical desk, allowing you to drag windows seamlessly across the seams of your screens in one continuous movement. Best of all, hitting a quick shortcut pulls the camera back through a beautiful curved lens, letting you type a few letters to instantly search, filter, and glide straight to the exact window you need on your map.

🆔 @hackernewsgithubprojects

📦 supermemoryai/company-brain

The Slack Bot That Remembers Everything

Company Brain is the Slack teammate that actually remembers everything your team says and then goes to do the work. It solves the problem of scattered knowledge by listening to your channels and building a private, permission-aware memory of every decision and discussion. The most surprising part is that it does not just chat; it takes action by opening issues, checking pull requests, and even running code to fix problems while you sleep. Since it was recently open-sourced, you can deploy this powerful, self-hosted agent in minutes using Cloudflare.

🆔 @hackernewsgithubprojects

📦 qybaihe/mu

mu: The Coding Agent That Thinks Before It Acts

mu is the coding agent that finally stops wasting your attention on routine choices. Instead of letting a massive model burn energy deciding if every single command is safe or if old data still matters, mu uses a tiny, lightning-fast judge to handle those thirty-five small calls automatically. This keeps your big model focused entirely on writing the actual code, making the whole process faster and cheaper. It is a fresh way to build AI helpers that actually respect your time and money. If you want an assistant that thinks carefully before it acts without the usual slowdown, mu is the tool to watch.

🆔 @hackernewsgithubprojects

📦 ollaya-dev/ollaya

Run decision models locally with Ollaya

Ollaya runs open decision models right on your computer, exactly the way Ollama handles large language models. Instead of generating text, these models read a message or ticket and instantly return calibrated probabilities for specific questions, like urgency or churn risk. You get millisecond results without sending data to the cloud. The coolest part is that it speaks the same API as TypeSafe, so your existing clients work by just changing one environment variable. It pulls small graphs from authors and runs them locally on your CPU or GPU. It is fast, private, and built in Rust.

🆔 @hackernewsgithubprojects

📦 ysh1112/codex-model-watch

Codex Model Watch: Catch Silent Model Swaps

Stop guessing if your premium AI model is actually working. Codex Model Watch is a local tool that proves exactly what model served your request, catching silent downgrades where you ask for the big brain and get the cheap one instead. It reads your local logs to track quota and errors, but its killer feature is an active probe that pings the server to verify if you are really getting the model you paid for. This solves the mystery of why your output quality suddenly drops, giving you hard data on whether you were swapped to a smaller model. It runs entirely on your computer with zero cloud dependencies.

🆔 @hackernewsgithubprojects

📦 kytyps5/kytyps5

Play PS5 Games on Your PC With KytyPS5

Run PlayStation 5 games directly on your computer with KytyPS5, an open-source emulator that lets you boot and play titles like Astro Bot and Demon's Souls without owning the hardware. Written in C++, this project translates the console's graphics and system instructions so your PC or laptop can handle the processing, currently supporting Windows and Linux while experimenting with macOS support. The most surprising part is that it already boots a variety of major 3D titles, including games built with Unreal and Unity, proving that running next-gen console software on standard desktop hardware is closer to reality than ever before.

🆔 @hackernewsgithubprojects

📦 wdobry/laya-playground

Laya Plays Games With Real Math

Laya is the open-source decision model that actually plays video games on your laptop. It skips the usual language generation entirely, swapping in a tiny, fast brain that reads a simple sentence describing the game state and instantly returns a probability score. Watch it fly through Flappy Bird or stack blocks in Tetris at thirty decisions per second, all running offline without a single cloud API call. This repository gives you the code, a benchmark, and a guide to use this local, private math engine for your own real-time apps, proving that speed and accuracy don't always require a massive, expensive chatbot.

🆔 @hackernewsgithubprojects