⚡ xbtlin/ai-berkshire is making waves. Here's the full picture.

🔗 https://github.com/xbtlin/ai-berkshire
📝 AI 时代的伯克希尔：基于 Claude Code 的价值投资研究框架。巴菲特·芒格·段永平·李录四大师方法论 + 多Agent并行研究。| AI-era Berkshire: a value investing research framework built on Claude Code. 4 masters' methodologies + multi-agent adversarial analysis.
──────────────────────────────

Introduction to AI Berkshire: AI Berkshire is an investment research framework that leverages Claude Code to systematize and structure the methodologies of four value investing masters: Warren Buffett, Charlie Munger, Simon Shou, and Li Lu. This framework provides professional-level investment research, aiming to redefine the depth and efficiency of investment research using AI.

Key Features:
- Comprehensive investment research framework
- Based on the methodologies of four value investing masters
- Utilizes Claude Code for professional-level research
- Provides a structured approach to investment research
- Offers various skills for different aspects of investment research, including deep company research, earnings review, and portfolio management

Technical Highlights:
- Utilizes Claude Code for investment research
- Employs a structured approach to research, including data collection, analysis, and decision-making
- Incorporates multiple skills for different aspects of investment research
- Provides a comprehensive framework for investment research, covering various aspects, including company research, earnings analysis, and portfolio management

Audience: AI Berkshire is designed for investors, researchers, and financial professionals seeking to leverage AI in their investment research. The framework is suitable for those looking for a comprehensive and structured approach to investment research, utilizing the methodologies of renowned value investing masters.

Usage:
- Install Claude Code and the AI Berkshire skills
- Use the various skills, such as `/investment-research`, `/earnings-review`, and `/portfolio-management`, to conduct investment research
- Leverage the framework to gain insights into companies, industries, and portfolios, and make informed investment decisions

Takeaway: AI Berkshire offers a unique investment research framework that combines the methodologies of four value investing masters with the power of AI, providing a comprehensive and structured approach to investment research.

──────────────────────────────
🧠 Channel: https://xn--r1a.website/GithubRe

🌟 mauriceboe/TREK caught my eye on GitHub Trending today.

🔗 https://github.com/mauriceboe/TREK
📝 A self-hosted travel/trip planner with real-time collaboration, interactive maps, PWA support, SSO, budgets, packing lists, and more.
──────────────────────────────

TREK is a self-hosted, real-time collaborative travel planner with maps, budgets, packing lists, a journal, and AI built in. It offers key features like trip planning, travel management, collaboration, and mobile support. docker run can be used to get started in 30 seconds. The tech stack includes Node.js, NestJS, SQLite, React, Vite, TypeScript, Tailwind, Leaflet, and Docker. The target audience includes travelers and adventure seekers who want to plan and manage their trips collaboratively. TREK is available as a Docker image and can be installed as a PWA. With its real-time sync and multi-user support, TREK is the perfect tool for planning your next trip - Plan your next adventure with TREK today!

──────────────────────────────
🧠 Channel: https://xn--r1a.website/GithubRe

🌟 apple/container caught my eye on GitHub Trending today.

🔗 https://github.com/apple/container
📝 A tool for creating and running Linux containers using lightweight virtual machines on a Mac. It is written in Swift, and optimized for Apple silicon.
──────────────────────────────

The apple/container GitHub repository offers a powerful tool for creating and running Linux containers on Macs with Apple silicon. Written in Swift, it's optimized for performance and compatibility with OCI-compatible container images. You can easily pull and run images from standard container registries, and push your custom images for use in other OCI-compatible applications.

To get started, simply download and install the latest signed installer package, then start the system service with a container system start command. The tool is supported on macOS 26 and later, and you can upgrade or downgrade versions using the provided scripts.

Some key features include:
- Consuming and producing OCI-compatible container images
- Support for Apple silicon
- Low-level container, image, and process management using the Containerization Swift package

The repository provides extensive documentation, including a guided tour, technical overview, and full command reference, making it easy to learn and use the tool. Whether you're a developer or just getting started with containerization, apple/container is a great resource.

The project is under active development, with contributions welcome and encouraged. So why wait? Dive in and explore the world of containerization with apple/container - it's the perfect tool to containerize your workflow!

──────────────────────────────
🧠 Channel: https://xn--r1a.website/GithubRe

💡 JCodesMore/ai-website-cloner-template just hit the trending charts — here's why it matters.

🔗 https://github.com/JCodesMore/ai-website-cloner-template
📝 Clone any website with one command using AI coding agents
──────────────────────────────

AI Website Cloner Template is a reusable template for reverse-engineering any website into a clean, modern Next.js codebase using AI coding agents. The template allows you to point it at a URL, run the /clone-website command, and your AI agent will inspect the site, extract design tokens and assets, write component specs, and dispatch parallel builders to reconstruct every section.

The template is designed to work with a variety of AI coding agents, including Claude Code, Codex CLI, and GitHub Copilot. It features a multi-phase pipeline that includes reconnaissance, foundation, component specs, parallel build, and assembly & QA.

To get started, you can create your own repository from the template, install dependencies, start your AI agent, and run the /clone-website skill. The template also includes a AGENTS.md file that provides instructions for using different AI coding agents.

The template is built using Next.js 16, shadcn/ui, and Tailwind CSS v4, and includes a range of features such as design token extraction, asset downloading, and component spec writing.

Key Takeaway: With the AI Website Cloner Template, you can easily reverse-engineer any website into a modern Next.js codebase using AI coding agents, making it a powerful tool for platform migration, lost source code recovery, and learning.

──────────────────────────────
🧠 Channel: https://xn--r1a.website/GithubRe

💡 garrytan/gstack just hit the trending charts — here's why it matters.

🔗 https://github.com/garrytan/gstack
📝 Use Garry Tan's exact Claude Code setup: 23 opinionated tools that serve as CEO, Designer, Eng Manager, Release Manager, Doc Engineer, and QA
──────────────────────────────

Garry Tan's gstack is a revolutionary open-source tool that turns AI into a virtual engineering team. As the President & CEO of Y Combinator, Garry has worked with thousands of startups and has now created a tool that enables founders and CEOs to ship products faster than traditional teams. With gstack, you can go from idea to production in minutes, not days or weeks.

The tool offers a range of features, including /office-hours for reframing your product, /plan-ceo-review for rethinking the problem, and /review for catching bugs. It also includes /qa for testing and /ship for deploying your product.

Garry has seen incredible results with gstack, shipping 3 production services and 40+ features in just 60 days, all while running Y Combinator full-time. The tool is designed for founders and CEOs, first-time Claude Code users, and tech leads and staff engineers.

To get started, simply install gstack and run /office-hours to describe your project. From there, you can use various skills to plan, build, review, and ship your product.

One-liner takeaway: With gstack, you can build and ship products faster than ever before, and it's completely free and open-source.

──────────────────────────────
🧠 Channel: https://xn--r1a.website/GithubRe

🎯 aws/agent-toolkit-for-aws landed on trending. Worth a proper look.

🔗 https://github.com/aws/agent-toolkit-for-aws
📝 Official, AWS-supported MCP servers, skills, and plugins to help AI agents build on AWS
──────────────────────────────

The Agent Toolkit for AWS is an open-source project that enables AI coding agents to build, deploy, and manage applications on AWS. It provides a set of tools, knowledge, and guardrails for agents to work with AWS services, including Claude Code, Codex, Cursor, and Kiro.

The toolkit includes plugins that bundle AWS MCP Server configuration and agent skills, such as aws-core, aws-agents, and aws-data-analytics. These plugins cover various aspects of AWS, including service selection, CDK/CloudFormation, serverless, containers, storage, observability, billing, SDK usage, and deployment.

To get started, users can install the plugins using their preferred coding agent, such as Claude Code or Codex. For example, in Claude Code, users can install the aws-core plugin using the command /plugin install aws-core@claude-plugins-official.

The toolkit also includes skills that are curated packages of instructions and reference materials for completing specific AWS tasks. Users can load skills on demand, and agents can discover and retrieve relevant skills as needed.

The AWS MCP Server is a key component of the toolkit, providing a managed server that gives agents access to AWS through the Model Context Protocol. It offers features such as full AWS API coverage, sandboxed script execution, real-time documentation access, and enterprise controls.

The Agent Toolkit for AWS is suitable for developers, DevOps teams, and organizations that want to leverage AI coding agents to streamline their workflows and improve productivity on AWS.

In summary, the Agent Toolkit for AWS is a powerful tool that empowers AI coding agents to work seamlessly with AWS services, and its adoption can revolutionize the way you develop, deploy, and manage applications on AWS.

──────────────────────────────
🧠 Channel: https://xn--r1a.website/GithubRe

💡 mukul975/Anthropic-Cybersecurity-Skills just hit the trending charts — here's why it matters.

🔗 https://github.com/mukul975/Anthropic-Cybersecurity-Skills
📝 817 structured cybersecurity skills for AI agents · Mapped to 6 frameworks: MITRE ATT&CK, NIST CSF 2.0, MITRE ATLAS, D3FEND, NIST AI RMF & MITRE F3 (Fight Fraud) · agentskills.io standard · Works with Claude Code, GitHub Copilot, Codex CLI, Cursor, Gemini CLI & 20+ platforms · 29 security domains · Apache 2.0
──────────────────────────────

Unlock Expert-Level Cybersecurity Skills for Your AI Agent

The Anthropic Cybersecurity Skills repository on GitHub provides a comprehensive library of 817 production-grade cybersecurity skills, spanning 29 security domains. These skills are designed to help AI agents develop the expertise of a senior security analyst, enabling them to tackle complex cybersecurity challenges with ease.

The repository includes six industry frameworks, such as MITRE ATT&CK, NIST CSF 2.0, and MITRE D3FEND, ensuring unified cross-framework coverage. Each skill is carefully crafted to provide step-by-step execution and verification, giving AI agents the structured decision-making workflow they need to succeed.

To get started, simply clone the repository and point your AI agent at it. The skills are compatible with various AI platforms, including Claude Code, GitHub Copilot, and OpenAI Codex CLI.

Key highlights:
- 817 production-grade cybersecurity skills
- 29 security domains, including cloud security, threat hunting, and digital forensics
- Six industry frameworks for unified cross-framework coverage
- Compatible with 26+ AI platforms
- agentskills.io open standard for seamless integration

Whether you're a security professional, developer, or enterprise team, this repository is an invaluable resource for giving your AI agent the cybersecurity skills it needs to excel. Take the GARS-2026 survey to contribute to the global agentic AI readiness study and get 50 Casky Tokens for early access to casky.ai.

Give your AI agent the gift of expert-level cybersecurity skills today!

──────────────────────────────
🧠 Channel: https://xn--r1a.website/GithubRe

🚀 Meet alibaba/page-agent: a gem from today's GitHub trending list.

🔗 https://github.com/alibaba/page-agent
📝 JavaScript in-page GUI agent. Control web interfaces with natural language.
──────────────────────────────

The alibaba/page-agent GitHub repository is home to the innovative Page Agent, a GUI agent that can control web interfaces with natural language. This project allows for easy integration with just a few lines of in-page JavaScript, eliminating the need for browser extensions, Python, or headless browsers. Key features include text-based DOM manipulation, the ability to bring your own LLMs, and an optional Chrome extension for multi-page tasks.

The Page Agent is versatile and can be used in various use cases, such as creating a SaaS AI copilot, implementing smart form filling, enhancing accessibility, and more. To get started, users can try the one-line integration with a free demo LLM or install the package via npm install page-agent.

From a technical standpoint, the project is built using TypeScript and has a relatively small bundle size. The repository is actively maintained and welcomes contributions from the community. The project is licensed under the MIT License and acknowledges the work of the browser-use project.

The Page Agent is designed for client-side web enhancement and can be used by developers, businesses, and individuals looking to automate web interactions or create custom AI-powered interfaces. With its ease of use and flexibility, the Page Agent has the potential to revolutionize the way we interact with web applications. Star this repo if you find PageAgent helpful - it's a game-changer for web automation and AI-powered interfaces!

──────────────────────────────
🧠 Channel: https://xn--r1a.website/GithubRe

🌟 IceWhaleTech/CasaOS caught my eye on GitHub Trending today.

🔗 https://github.com/IceWhaleTech/CasaOS
📝 CasaOS - A simple, easy-to-use, elegant open-source Personal Cloud system.
──────────────────────────────

CasaOS is an open-source personal cloud system designed for home scenarios, providing a low-cost data collaboration solution and a personalized copilot. The key features of CasaOS include a friendly UI, multiple hardware and base system support, selected apps in the app store, and elegant drive and file management.

To get started with CasaOS, you can install it on a compatible system such as Debian, Ubuntu, or Raspberry Pi OS, using a one-liner installation command:

wget -qO- https://get.casaos.io | sudo bash

or

curl -fsSL https://get.casaos.io | sudo bash

.

CasaOS is a community-driven project, and contributions are welcome. Whether you're a developer, designer, or simply a user, you can help shape the future of CasaOS.

The target audience for CasaOS includes individuals and small organizations looking for a cost-effective and efficient computing solution.

In summary, CasaOS is a game-changer for personal cloud computing - take control of your digital life with CasaOS, your personal cloud.

──────────────────────────────
🧠 Channel: https://xn--r1a.website/GithubRe

🚀 Meet opendatalab/MinerU: a gem from today's GitHub trending list.

🔗 https://github.com/opendatalab/MinerU
📝 Transforms complex documents like PDFs and Office docs into LLM-ready markdown/JSON for your Agentic workflows.
──────────────────────────────

MinerU is an open-source, high-accuracy document parsing engine designed for LLM, RAG, and Agent workflows. It supports the conversion of various file formats, including PDF, DOCX, PPTX, XLSX, images, and web pages, into structured Markdown or JSON. Key features include native support for DOCX, PPTX, and XLSX parsing, formulas to LaTeX conversion, and tables to HTML reconstruction. The engine also supports scanned documents, handwriting, multi-column layouts, and cross-page table merging.

Technical highlights of MinerU include its VLM + OCR dual engine, which enables 109-language OCR recognition, and its support for domestic AI chips such as Ascend, Cambricon, and Enflame. The engine can be integrated with various frameworks, including LangChain, Dify, and FastGPT, and can be deployed privately and fully offline.

Audience for MinerU includes developers, researchers, and users who need to parse and convert documents into structured formats for various applications, such as AI coding tools, RAG frameworks, and no-code platforms. With its high-accuracy parsing capabilities, flexible integration options, and support for multiple AI chips, MinerU is a powerful tool for anyone looking to streamline their document processing workflows.

MinerU is available in multiple formats, including a web version, desktop client, and API access, making it easy to get started with the platform. Overall, MinerU is a versatile and powerful document parsing engine that can help users unlock the full potential of their documents and streamline their workflows. Get started with MinerU today and discover a new world of document parsing possibilities!

──────────────────────────────
🧠 Channel: https://xn--r1a.website/GithubRe

🎯 Free-TV/IPTV landed on trending. Worth a proper look.

🔗 https://github.com/Free-TV/IPTV
📝 M3U Playlist for free TV channels
──────────────────────────────

The Free-TV/IPTV GitHub repository provides a curated list of free TV channels from around the world, available for streaming via IPTV players. The playlist is carefully maintained to ensure quality over quantity, with a focus on HD channels, no duplicate or regional feeds, and only officially free channels.

To use the playlist, simply point your IPTV player to the provided M3U8 file. The repository also includes a list of feed sources and guidelines for contributing to the playlist.

The main goals of this project are to provide a high-quality, free TV channel playlist, with a focus on mainstream channels that are available to everyone. The playlist is generated using a Python script and is updated regularly.

The target audience for this repository includes anyone looking for free TV channels, including those who want to cut the cord and streaming enthusiasts.

Technical highlights of the project include the use of M3U8 playlists, geoIP blocking, and live YouTube channels.

Overall, the Free-TV/IPTV repository is a valuable resource for anyone looking for free TV channels, and its focus on quality and mainstream content makes it a great option for streaming enthusiasts.
Cut the cord and get free TV with Free-TV/IPTV!

──────────────────────────────
🧠 Channel: https://xn--r1a.website/GithubRe