Github Top Repositories

💡 anthropics/claude-plugins-official just hit the trending charts — here's why it matters. 🔗 https://github.com/anthropics/claude-plugins-official 📝 Official, Anthropic-managed directory of high quality Claude Code Plugins. ────────────────────────────── The anthropics/claude-plugins-official GitHub repository is a curated directory of high-quality plugins for Claude Code. It contains both internal plugins developed by Anthropic and third-party plugins from partners and the community. To use these plugins, you can install them directly from the marketplace via /plugin install {plugin-name}@claude-plugins-official or browse for them in /plugin > Discover. From a technical standpoint, each plugin follows a standard structure, including a plugin.json file with metadata and optional configurations for MCP servers, slash commands, agents, and skills. This repository is ideal for Claude Code users, developers, and partners looking to extend the platform's functionality. One-liner takeaway: Unlock Claude Code's full potential with the anthropics/claude-plugins-official repository, your one-stop shop for high-quality, community-driven plugins. ────────────────────────────── 🧠 Channel: https://t.me/GithubRe

🎯 Lum1104/Understand-Anything landed on trending. Worth a proper look. 🔗 https://github.com/Lum1104/Understand-Anything 📝 Graphs that teach > graphs that impress. Turn any code into an interactive knowledge graph you can explore, search, and ask questions about. Works with Claude Code, Codex, Cursor, Copilot, Gemini CLI, and more. ────────────────────────────── Understand Anything is a revolutionary tool that turns any codebase, knowledge base, or docs into an interactive knowledge graph. This graph can be explored, searched, and questioned, making it easier to understand complex systems. The tool is compatible with various platforms, including Claude Code, Codex, Cursor, Copilot, and Gemini CLI. The key features of Understand Anything include: - Interactive knowledge graph: Every file, function, and class is a node that can be clicked, searched, and explored. - Guided tours: Auto-generated walkthroughs of the architecture, ordered by dependency. - Fuzzy and semantic search: Find anything by name or by meaning. - Diff impact analysis: See which parts of the system your changes affect before you commit. To get started, simply install the plugin using /plugin marketplace add Lum1104/Understand-Anything and /plugin install understand-anything. Then, analyze your codebase with /understand and explore the interactive dashboard with /understand-dashboard. The tool is designed for anyone who wants to understand complex codebases, including developers, PMs, and power users. With its persona-adaptive UI, the dashboard adjusts its detail level based on who you are. In short, Understand Anything is a game-changer for anyone who wants to unlock the secrets of complex codebases and knowledge bases. Stop reading code blind, start seeing the big picture — and discover the power of interactive knowledge graphs with Understand Anything. You can now see the forest for the trees. ────────────────────────────── 🧠 Channel: https://t.me/GithubRe

AI is moving fast. Accountability is not. That is why we built the open source core of Forkit Dev. Forkit Dev introduces Model Passports and Agent Passports so AI systems can be tracked, verified, and understood across their lifecycle. Open source repo: https://github.com/arpitasarker01/Forkit_Dev If you care about trustworthy AI, open source infrastructure, model lineage, or compliance ready deployment, check it out and share your thoughts.

🚀 Meet karpathy/nn-zero-to-hero: a gem from today's GitHub trending list. 🔗 https://github.com/karpathy/nn-zero-to-hero 📝 Neural Networks: Zero to Hero ────────────────────────────── The Neural Networks: Zero to Hero course is a comprehensive series of YouTube videos and Jupyter notebooks that take you on a journey from the basics of neural networks to building complex models like GPT. The course is designed for those with a basic knowledge of Python and a vague recollection of calculus from high school. Key features of the course include building micrograd, a minimal neural network framework, and makemore, a character-level language model. You'll learn about backpropagation, training neural networks, and the overall framework of language modeling. To get started, you can access the YouTube video lectures and Jupyter notebook files in the lectures/ directory. The course is suitable for anyone interested in learning about neural networks, from beginners to experienced practitioners. Some technical highlights of the course include implementing a multilayer perceptron (MLP) character-level language model, introducing torch.Tensor and its subtleties, and building a Generatively Pretrained Transformer (GPT) from scratch. The course is ideal for students, researchers, and practitioners who want to gain a deep understanding of neural networks and their applications. In summary, this course is a hands-on guide to learning neural networks, and by the end of it, you'll be well on your way to becoming a neural network expert - so, join the journey and become a neural network hero! ────────────────────────────── 🧠 Channel: https://t.me/GithubRe

🔥 yt-dlp/yt-dlp is trending — and it deserves your attention. 🔗 https://github.com/yt-dlp/yt-dlp 📝 A feature-rich command-line audio/video downloader ────────────────────────────── yt-dlp is a feature-rich command-line audio/video downloader that supports thousands of sites. It's a fork of youtube-dl, with a wide range of options for customizing downloads, including video selection, format selection, and post-processing. The tool can be installed using pip or by downloading pre-compiled binaries for various platforms. The configuration file allows for further customization, and the tool also supports plugins and embedding in other applications. The project is actively maintained, with regular updates and a strong focus on community involvement. Whether you're a casual user or a power user, yt-dlp has the features and flexibility you need to download your favorite videos and audio files. So why settle for limited video downloaders when you can have it all with yt-dlp? Download it now and experience the power of unlimited video downloading! ────────────────────────────── 🧠 Channel: https://t.me/GithubRe

Everyone thinks markets are “experts vs newbies”… but the truth is crowds can beat analysts when the question is binary. 🧠⚡️ Trade the crowd’s opinion Pick a trending topic, take YES/NO, and watch the odds move in real time - settled on-chain. 📊🔗 Enter via launch the Mini App and get the answer before it becomes news. 🟢🔥 ➡️ Start your first YES/NO position #ad 📢 InsideAd

📌 Spotted on GitHub Trending: can1357/oh-my-pi — let's break it down. 🔗 https://github.com/can1357/oh-my-pi 📝 ⌥ AI Coding agent for the terminal — hash-anchored edits, optimized tool harness, LSP, Python, browser, subagents, and more ────────────────────────────── The oh-my-pi repository on GitHub is a cutting-edge coding agent that ships with a robust set of features, including 40+ providers, 32 built-in tools, and 13 LSP operations. This project is a fork of Pi by @mariozechner, and it has been continuously tuned by real-world use. To get started, users can install oh-my-pi using curl -fsSL https://omp.sh/install | sh on macOS and Linux, or bun install -g @oh-my-pi/pi-coding-agent with Bun. The agent is designed to work seamlessly with various tools and technologies, including git, GitHub, and JSON. It also supports features like time-traveling stream rules, first-class subagents, and code review with priorities and a verdict. With oh-my-pi, users can enjoy a wide range of benefits, from perfect edits and fewer tokens to unapologetically native performance on Windows. The project is written in Rust and TypeScript, and it uses the Bun runtime. In short, oh-my-pi is an incredibly powerful coding agent that can revolutionize the way you work with code - install it and experience the future of coding today. ────────────────────────────── 🧠 Channel: https://t.me/GithubRe

🚀 Meet Fincept-Corporation/FinceptTerminal: a gem from today's GitHub trending list. 🔗 https://github.com/Fincept-Corporation/FinceptTerminal 📝 FinceptTerminal is a modern finance application offering advanced market analytics, investment research, and economic data tools, designed for interactive exploration and data-driven decision-making in a user-friendly environment. ────────────────────────────── Fincept Terminal is a state-of-the-art financial intelligence platform that offers institutional-grade financial analytics, AI automation, and unlimited data connectivity. It's built using C++20 and Qt6 for a native desktop application experience. The platform includes features like multi-asset analytics, AI agents, 100+ data connectors, real-time trading, and a quant lab for machine learning models. Key highlights include a node editor for automation pipelines, a maritime tracking system, and geopolitical analysis tools. Fincept Terminal supports various platforms, including Windows, Linux, and macOS, with options for quick start, Docker, and manual builds from source. Audience: This platform is designed for financial professionals, researchers, and developers looking for a robust tool to analyze and automate financial data. To get started, users can download the installer or build from source using the provided scripts and prerequisites. In short, Fincept Terminal is a powerful platform that combines financial analytics, AI, and data connectivity to help users make informed decisions. With its extensive features and customization options, it's an ideal solution for those seeking a comprehensive financial intelligence tool. The punchy one-liner takeaway: Revolutionize your financial analysis with Fincept Terminal, the ultimate platform for professionals who demand precision, power, and limitless data connectivity. ────────────────────────────── 🧠 Channel: https://t.me/GithubRe

📌 Spotted on GitHub Trending: trimstray/the-book-of-secret-knowledge — let's break it down. 🔗 https://github.com/trimstray/the-book-of-secret-knowledge 📝 A collection of inspiring lists, manuals, cheatsheets, blogs, hacks, one-liners, cli/web tools and more. ────────────────────────────── The Book of Secret Knowledge is a curated collection of inspiring lists, manuals, cheatsheets, blogs, hacks, one-liners, cli/web tools, and more. It's designed for System and Network administrators, DevOps, Pentesters, and Security Researchers, but anyone can find useful information here. The repository is constantly updated with new tools, tutorials, and other resources. You can contribute to the project by submitting pull requests, and financial contributions are also welcome. The repository includes a wide range of topics, such as CLI Tools, GUI Tools, Web Tools, Systems/Services, Networks, and more. With its vast collection of resources, the Book of Secret Knowledge is a valuable resource for anyone looking to improve their skills. Unlock the secrets of the command line and become a master of your craft! ────────────────────────────── 🧠 Channel: https://t.me/GithubRe

💡 byJoey/cfnew just hit the trending charts — here's why it matters. 🔗 https://github.com/byJoey/cfnew 📝 No description. ────────────────────────────── CFnew is a Cloudflare Worker-based project that provides a versatile and customizable solution for managing and optimizing network connections. The key features of CFnew include support for multiple protocols (VLESS, Trojan, and xhttp), custom paths, delay testing, subscription conversion, and graphical management. Usage is straightforward: after deploying the worker, users can access a graphical interface to configure settings, including customizing protocols, paths, and subscription sources. The interface also includes tools for delay testing and optimization. Technical highlights of CFnew include its use of Cloudflare KV for storing configurations, which allows for real-time updates without requiring redeployment. The project also leverages various optimization techniques to reduce latency and improve overall performance. CFnew is designed for a wide range of users, from individuals seeking to optimize their internet connections to organizations looking for a customizable solution for managing network traffic. With its easy-to-use interface and robust feature set, CFnew is an attractive option for anyone looking to enhance their online experience. The project's open-source nature and active community contribute to its growth and development, ensuring that CFnew remains a dynamic and innovative solution in the field of network optimization. In summary, CFnew is a powerful tool for optimizing network connections, offering a unique combination of customization, ease of use, and performance. Whether you're a tech-savvy individual or an organization seeking to improve your online presence, CFnew is definitely worth exploring. With CFnew, you can take control of your internet and experience a faster, more secure, and more reliable connection - optimize your way to a better online experience. ────────────────────────────── 🧠 Channel: https://t.me/GithubRe

🎯 odoo/odoo landed on trending. Worth a proper look. 🔗 https://github.com/odoo/odoo 📝 Odoo. Open Source Apps To Grow Your Business. ────────────────────────────── Odeo is a suite of web-based open source business apps, including CRM, eCommerce, Warehouse Management, and more. These apps can be used standalone or integrated for a full-featured ERP system. To get started, follow the setup instructions or explore Odoo eLearning and developer tutorials. For security issues, check the Responsible Disclosure page. Odeo is perfect for businesses and developers looking for a customizable and scalable solution. With its wide range of apps and seamless integration, Odeo is the ultimate tool for streamlining business operations - one app to rule them all. ────────────────────────────── 🧠 Channel: https://t.me/GithubRe

🔥 Lum1104/Understand-Anything is trending — and it deserves your attention. 🔗 https://github.com/Lum1104/Understand-Anything 📝 Graphs that teach > graphs that impress. Turn any code into an interactive knowledge graph you can explore, search, and ask questions about. Works with Claude Code, Codex, Cursor, Copilot, Gemini CLI, and more. ────────────────────────────── Understand Anything is a powerful tool that turns any codebase, knowledge base, or docs into an interactive knowledge graph. It works with various platforms like Claude Code, Codex, and Copilot, allowing you to explore, search, and ask questions about your code. The key features include: - An interactive dashboard to visualize your codebase as a graph - Guided tours to learn the architecture in the right order - Fuzzy and semantic search to find anything by name or meaning - Diff impact analysis to see which parts of the system your changes affect - Persona-adaptive UI to adjust the detail level based on your role To get started, simply install the plugin and run the `/understand` command to analyze your codebase. You can then explore the dashboard, ask questions, and learn from the graph. Technical highlights include a multi-agent pipeline that analyzes your project, automatic grouping by architectural layer, and support for multiple languages. The target audience is anyone who wants to understand complex codebases, including developers, team leads, and technical writers. In summary, Understand Anything is a game-changer for anyone struggling to comprehend large codebases - it's like having a personal guide to show you how every piece fits together. ────────────────────────────── 🧠 Channel: https://t.me/GithubRe

🔍 Deep-diving into dotnet/skills — fresh off the trending list. 🔗 https://github.com/dotnet/skills 📝 Repository for skills to assist AI coding agents with .NET and C# ────────────────────────────── The dotnet/skills repository is a collection of core skills and custom agents for coding agents, curated by the .NET team. It includes a range of plugins, such as dotnet, dotnet-data, and dotnet-ai, which provide skills for handling common .NET coding tasks, data access, and AI-related tasks. To get started, you can install the plugins using the Copilot CLI or Claude Code by adding the marketplace and installing the desired plugin. You can also use VS Code or Cursor to install and manage plugins. The repository follows the agentskills.io open standard, making it compatible with OpenAI Codex. You can install individual skills using the skill-installer CLI. The target audience for this repository includes .NET developers, data scientists, and AI enthusiasts who want to leverage the power of coding agents to improve their productivity and efficiency. Overall, the dotnet/skills repository is a valuable resource for anyone looking to tap into the potential of coding agents and take their .NET development skills to the next level. With dotnet/skills, you can supercharge your coding workflow and unlock new possibilities for automation and innovation - automate your code, elevate your craft. ────────────────────────────── 🧠 Channel: https://t.me/GithubRe

🔍 Deep-diving into ChromeDevTools/chrome-devtools-mcp — fresh off the trending list. 🔗 https://github.com/ChromeDevTools/chrome-devtools-mcp 📝 Chrome DevTools for coding agents ────────────────────────────── The Chrome DevTools MCP repository provides a Model-Context-Protocol (MCP) server that allows coding agents to control and inspect a live Chrome browser. This enables reliable automation, in-depth debugging, and performance analysis. Key features include: - Performance insights: recording traces and extracting actionable performance insights - Advanced browser debugging: analyzing network requests, taking screenshots, and checking browser console messages - Reliable automation: automating actions in Chrome using puppeteer To get started, add the MCP server config to your client, then install the server using npx chrome-devtools-mcp@latest. This tool is designed for developers and coding agents, such as Antigravity, Claude, and Copilot. One-liner takeaway: Supercharge your coding agents with the Chrome DevTools MCP for unparalleled browser automation and debugging capabilities! ────────────────────────────── 🧠 Channel: https://t.me/GithubRe

🔍 Deep-diving into rohitg00/ai-engineering-from-scratch — fresh off the trending list. 🔗 https://github.com/rohitg00/ai-engineering-from-scratch 📝 Learn it. Build it. Ship it for others. ────────────────────────────── The AI Engineering from Scratch curriculum is a comprehensive, free, and open-source resource designed to bridge the gap between AI education and industry preparedness. It consists of 20 phases and 435 lessons, covering a wide range of topics from math foundations to autonomous systems. Each lesson follows a structured approach, starting with a problem statement, followed by math explanations, and culminating in code implementation in languages such as Python, TypeScript, Rust, or Julia. The curriculum is designed for individuals who want to understand how AI actually works, not just call APIs. With a focus on hands-on learning, every lesson ships with a reusable artifact, such as a prompt, skill, agent, or MCP server, that can be installed or pasted into daily workflows. Whether you're a beginner or an experienced practitioner, this curriculum provides a structured path to mastering AI engineering. Build it from scratch, and you'll truly understand it. ────────────────────────────── 🧠 Channel: https://t.me/GithubRe

🎯 ruvnet/RuView landed on trending. Worth a proper look. 🔗 https://github.com/ruvnet/RuView 📝 π RuView turns commodity WiFi signals into real-time spatial intelligence, vital sign monitoring, and presence detection — all without a single pixel of video. ────────────────────────────── RuView is a WiFi sensing platform that turns radio signals into spatial intelligence, detecting people, measuring breathing and heart rate, tracking movement, and monitoring rooms without cameras or wearables. The system uses Channel State Information (CSI) from low-cost ESP32 sensors and runs entirely on edge hardware. Key features include presence and occupancy detection, vital signs measurement, activity recognition, environment mapping, and sleep quality monitoring. The system learns each environment locally using spiking neural networks and adapts in under 30 seconds. To get started, you can use the Docker image with simulated data, live sensing with ESP32-S3 hardware, or the full system with Cognitum Seed. The pretrained model is available on Hugging Face. RuView is suitable for researchers, developers, and users interested in WiFi-based sensing applications. The platform is extensively documented and has a large community of contributors. In short, RuView turns WiFi into a powerful sensing tool, providing insights into people's presence, activities, and well-being without invading their privacy — the future of sensing is here, and it's WiFi-based. ────────────────────────────── 🧠 Channel: https://t.me/GithubRe