Github Top Repositories

🔥 aws/agent-toolkit-for-aws is trending — and it deserves your attention. 🔗 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 a powerful tool that enables AI coding agents to build, deploy, and manage applications on AWS. It provides a set of plugins and skills that work with popular coding agents like Claude Code, Codex, Cursor, and Kiro. The toolkit offers a range of features, including service selection, CDK/CloudFormation, serverless, containers, storage, observability, billing, and SDK usage. To get started, users can install plugins like aws-core, aws-agents, and aws-data-analytics using their coding agent's marketplace or by adding the toolkit's repository as a team marketplace. The toolkit also includes a set of rules files that provide recommended project-level configuration for using AWS effectively. The AWS MCP Server is a key component of the toolkit, providing full AWS API coverage, sandboxed script execution, real-time documentation access, and enterprise controls. The toolkit is designed for developers, DevOps teams, and anyone looking to leverage AI coding agents to streamline their workflows on AWS. With its robust features and user-friendly setup, the Agent Toolkit for AWS is a game-changer for anyone looking to unlock the full potential of AI-powered coding. One-liner takeaway: Supercharge your coding workflow with the Agent Toolkit for AWS and unlock the power of AI-driven development on the cloud. ────────────────────────────── 🧠 Channel: https://t.me/GithubRe

💡 calesthio/OpenMontage just hit the trending charts — here's why it matters. 🔗 https://github.com/calesthio/OpenMontage 📝 World's first open-source, agentic video production system. 12 pipelines, 52 tools, 500+ agent skills. Turn your AI coding assistant into a full video production studio. ────────────────────────────── Introducing OpenMontage, the first open-source, agentic video production system. This innovative platform allows you to create stunning videos by simply describing what you want in plain language. The agent handles everything from research and scripting to asset generation, editing, and final composition. Key Features: - Start from a reference video or a blank prompt - Automatic script generation and narration - AI-powered image and video generation - Free stock footage and music integration - Real-time subtitle generation and burn-in - Support for various AI coding assistants Technical Highlights: - Python 3.10+ and Node.js 18+ support - FFmpeg for post-production and encoding - Remotion and HyperFrames for composition Audience: OpenMontage is designed for anyone looking to create high-quality videos without extensive video production experience. It's perfect for content creators, marketers, educators, and developers who want to leverage AI-powered video production. With OpenMontage, you can create stunning videos at a fraction of the cost and time. Try it out and discover a new world of video production possibilities - your next video is just a prompt away. ────────────────────────────── 🧠 Channel: https://t.me/GithubRe

🔥 xbtlin/ai-berkshire is trending — and it deserves your attention. 🔗 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. ────────────────────────────── AI Berkshire 是一个基于 Claude Code 的投资研究框架，旨在将巴菲特、芒格、段永平、李录四位价值投资大师的方法论系统化、结构化，通过 AI Agent 实现专业级投资研究。这个框架不仅可以帮助您进行深度研究，还可以提供财报分析、行业筛选、持仓管理和思维工具等功能。 主要特点： * 使用 4个Agent并行 研究一家公司，模拟真实投研团队协作 * 四大师视角对抗，提供多角度的分析 * 结构化反偏见机制，确保分析的质量和决策的纪律 * 金融数据的精确性，提供可靠的数据支持 输出示例：

| 公司 | 通过? | 能力圈 | 好生意 | 护城河 | 管理层 | 安全边际 | 综合 |
|------|:-----:|:------:|:------:|:------:|:------:|:-------:|:----:|
| 腾讯 | 通过 | ★★★★★ | ★★★★★ | ★★★★★ | ★★★★★ | ★★★★☆ | 4.7 |
| 美团 | 通过 | ★★★★☆ | ★★★★☆ | ★★★★☆ | ★★★★★ | ★★★★★ | 4.3 |

适用人群： * 投资者 * 研究员 * 量化分析师 使用方法： * 安装 Claude Code 和 AI Berkshire 的 Skills * 使用 /investment-research、/investment-team 等命令调用相应的 Skills 总结： AI Berkshire 是一个功能强大的投资研究框架，可以帮助您进行深度研究、财报分析、行业筛选、持仓管理和思维工具等。其 4个Agent并行 的研究方式、四大师视角对抗 的分析方法、结构化反偏见机制 和 金融数据的精确性 都是其突出的特点。通过 AI Berkshire，您可以获得更好的投资决策支持。 ────────────────────────────── 🧠 Channel: https://t.me/GithubRe

⚡ mauriceboe/TREK is making waves. Here's the full picture. 🔗 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. ────────────────────────────── The TREK GitHub repository is a self-hosted, real-time collaborative travel planner that includes maps, budgets, packing lists, a journal, and AI built-in. Its key features are a drag-and-drop planner, interactive map, place search, and import capabilities, as well as travel management tools like reservations, costs, and packing lists. For usage, simply run the Docker command provided in the README to get started in 30 seconds. The technical highlights of TREK include its use of NestJS, React, and TypeScript, with real-time sync via WebSocket and authentication via JWT, OAuth, and OIDC. The ideal audience for TREK includes travelers who want to plan and manage their trips collaboratively, with features like multi-user trips, invite links, and role-based access. In short, TREK is the ultimate travel planning companion - plan your next trip with TREK and take your adventures to the next level! ────────────────────────────── 🧠 Channel: https://t.me/GithubRe

💡 alchaincyf/zhangxuefeng-skill just hit the trending charts — here's why it matters. 🔗 https://github.com/alchaincyf/zhangxuefeng-skill 📝 张雪峰.skill — 张雪峰的认知操作系统。高考志愿/考研/职业规划的实战思维框架。由女娲.skill生成。 ────────────────────────────── 张雪峰的认知操作系统 不是语录合集，而是一套可运行的思维框架。它基于5本著作、15+篇深度采访、30+条语录、11个关键决策记录和完整人生时间线的深度调研，提炼出5个核心心智模型、8条决策启发式和完整的表达DNA。这个skill可以帮助你分析专业选择、职业方向和人生规划等问题，提供明确的判断和建议。 核心心智模型 包括社会筛子论、选择>努力、就业倒推法、阶层现实主义和不可替代性检验等。这些模型可以帮助你理解社会的运作规律、做出合理的选择和规划人生。 使用方法 很简单，你可以通过 npx skills add alchaincyf/zhangxuefeng-skill 安装这个skill，然后告诉你的agent："用张雪峰的视角帮我分析这个专业选择" 或 "张雪峰会怎么看这个职业方向？"。 技术亮点 是这个skill基于开放的Agent Skills协议，可以在任何skills-compatible的AI agent runtime中运行。并且，它使用了女娲.skill这个工具来自动蒸馏心智模型和表达DNA。 适用人群 是所有想要提高自己认知能力和决策水平的人，特别是学生、职场人士和创业者。这个skill可以帮助你更好地理解社会和自己，做出更明智的选择。 总结，张雪峰的认知操作系统是一个非常实用的skill，可以帮助你提高认知能力和决策水平。它基于深度调研和开放的协议，可以在任何skills-compatible的AI agent runtime中运行。所以，用张雪峰的视角来分析你的问题吧！安装并试试看，你会发现它对你的帮助。你的未来，从今天开始。 ────────────────────────────── 🧠 Channel: https://t.me/GithubRe

🌟 opendatalab/MinerU caught my eye on GitHub Trending today. 🔗 https://github.com/opendatalab/MinerU 📝 Transforms complex documents like PDFs and Office docs into LLM-ready markdown/JSON for your Agentic workflows. ────────────────────────────── Introduction to MinerU: MinerU is a 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: - Native support for parsing DOCX, PPTX, and XLSX - Dual engine with VLM and OCR capabilities, supporting 109 languages - Integration with popular frameworks like LangChain, Dify, and FastGPT - Supports domestic AI chips and offers a range of deployment options, including private and fully offline modes Technical Highlights: - Accurate layout reconstruction and table detection - Automatic header and footer removal - Cross-page table merging and multi-column layout support - CLI, REST API, and Docker support for development and integration Audience: MinerU is designed for developers, researchers, and businesses looking to integrate high-accuracy document parsing capabilities into their workflows. Takeaway: With MinerU, unlock the full potential of your documents and streamline your workflow with its cutting-edge parsing capabilities and seamless integrations. ────────────────────────────── 🧠 Channel: https://t.me/GithubRe

⚡ ripienaar/free-for-dev is making waves. Here's the full picture. 🔗 https://github.com/ripienaar/free-for-dev 📝 A list of SaaS, PaaS and IaaS offerings that have free tiers of interest to devops and infradev ────────────────────────────── The free-for-dev GitHub repository is a curated list of software and services that offer free tiers, making it easier for developers to find and utilize these resources. This list is specifically tailored for infrastructure developers, including System Administrators and DevOps Practitioners. With contributions from over 1600 people, it's a comprehensive collection of as-a-Service offerings, including cloud providers, APIs, data and ML services, and more. Key features of this repository include its scope, which is limited to services that are useful for infrastructure developers, and its always-free limits, which ensure that the listed services are free for at least a year. The repository also considers the security perspective of each service, ensuring that services with restricted TLS are not included. To use this repository, simply browse through the various categories, which include Major Cloud Providers, Cloud management solutions, Analytics, Events, and Statistics, and more. Each category lists the available services, along with their free tier details. From a technical standpoint, the repository is well-organized, with a clear and concise Table of Contents that makes it easy to navigate. The repository also includes links to the Track Awesome List and other relevant resources. The target audience for this repository is infrastructure developers, including System Administrators and DevOps Practitioners. However, it can also be useful for anyone looking for free services to support their development work. In summary, the free-for-dev repository is a valuable resource for developers, providing a comprehensive list of free services and tools to support their work. The bottom line: Stop searching, start building with the free-for-dev repository. ────────────────────────────── 🧠 Channel: https://t.me/GithubRe

⚡ grafana/grafana is making waves. Here's the full picture. 🔗 https://github.com/grafana/grafana 📝 The open and composable observability and data visualization platform. Visualize metrics, logs, and traces from multiple sources like Prometheus, Loki, Elasticsearch, InfluxDB, Postgres and many more. ────────────────────────────── Grafana is an open-source platform for monitoring and observability, allowing you to query, visualize, alert on, and understand your metrics from various storage locations. With fast and flexible client-side graphs and panel plugins, you can create dynamic and reusable dashboards with template variables. Key features include Explore Metrics and Explore Logs for ad-hoc queries and dynamic drilldown, as well as Alerting for visually defining alert rules. Technical highlights include support for Mixed Data Sources, which allows mixing different data sources in the same graph. To get started, you can get Grafana and follow the installation guides. The platform is suitable for teams and individuals looking to foster a data-driven culture. With a strong focus on community involvement, Grafana encourages contributing to the project and provides resources such as a Contributing guide and Developer guide. Whether you're a developer, a data analyst, or simply a curious individual, Grafana has something to offer. So why not give it a try and experience the power of data visualization - Grafana: where data meets insight. ────────────────────────────── 🧠 Channel: https://t.me/GithubRe

💡 kunchenguid/no-mistakes just hit the trending charts — here's why it matters. 🔗 https://github.com/kunchenguid/no-mistakes 📝 git push no-mistakes ────────────────────────────── The no-mistakes tool is a game-changer for developers who want to ensure their code is clean and error-free before pushing it to the remote repository. Its purpose is to put a local git proxy in front of your real remote, allowing you to push to no-mistakes instead of origin. This triggers a disposable worktree, runs an AI-driven validation pipeline, and forwards the branch to the configured push target only after every check passes, automatically opening a clean PR. The key features of no-mistakes include its non-blocking nature, which means the pipeline runs in an isolated worktree without disrupting your work. It's also agent-agnostic, supporting various agents like claude, codex, and opencode. Additionally, it allows for agent-native interactions, enabling your coding agent to perform tasks and gate them. To use no-mistakes, simply run no-mistakes init to initialize the gate, then push your changes to no-mistakes instead of origin. The tool will take care of the rest, running the pipeline and opening a clean PR for you. From a technical standpoint, no-mistakes is built using Go and utilizes a Makefile for development tasks. The code is well-organized, and the documentation is thorough, making it easy to get started. The target audience for no-mistakes is developers who want to ensure their code is clean and error-free before pushing it to the remote repository. Whether you're working on a personal project or a large-scale enterprise application, no-mistakes is a valuable tool to have in your toolkit. In summary, no-mistakes is a powerful tool that helps you kill all the slop and raise clean PRs. With its non-blocking and agent-agnostic nature, it's a must-have for any developer who wants to ensure their code is error-free and clean. So, why not give it a try and experience the power of no-mistakes for yourself? Push smarter, not harder, with no-mistakes! ────────────────────────────── 🧠 Channel: https://t.me/GithubRe

There are hundreds of AI channels on YouTube. Here's why we made another one. Most AI content does one of two things: it stays so surface-level it teaches you nothing, or it goes so deep you need a PhD to follow along. We built Guidely for everyone in between. → We start with absolute beginners in mind → Then take you deeper, until the details actually click → Every guide is reviewed by experienced AI engineers → We don't make more content. We make better content. Whether you build, design, or market products, our goal is simple: leave you thinking "I've never seen it broken down this well." Two good places to start 👇 → AI vs ML vs Deep Learning vs GenAI ... But Done Right! The terms everyone uses. The distinctions are almost never explained clearly. We fix that: youtu.be/72yyLA2wRWc → How to Break into AI Engineering in 2026 A senior applied scientist shares what actually matters:  youtu.be/42vE7Ij4kdU If AI has ever felt overwhelming or noisy, this channel is for you. If the content resonates with you, please don’t forget to like and subscribe.

⚡ commaai/openpilot is making waves. Here's the full picture. 🔗 https://github.com/commaai/openpilot 📝 openpilot is an operating system for robotics. Currently, it upgrades the driver assistance system on 300+ supported cars. ────────────────────────────── openpilot is an operating system for robotics, currently used to upgrade the driver assistance system in over 300 supported cars. The key features of openpilot include its ability to run on various hardware, such as the comma four, and its extensive documentation. To use openpilot, you need a supported device, software, a supported car, and a car harness. The project is developed by comma and the community, with contributions welcomed through pull requests and issues on GitHub. The code is MIT licensed, and the project follows ISO26262 guidelines for safety. With its release-mici and nightly branches, openpilot offers a range of options for users, from stable releases to bleeding-edge development. Whether you're a developer or just a car enthusiast, openpilot is an exciting project to explore. Get ready to shift your driving experience into high gear with openpilot - the future of autonomous driving is here! ────────────────────────────── 🧠 Channel: https://t.me/GithubRe

⚡ google-labs-code/design.md is making waves. Here's the full picture. 🔗 https://github.com/google-labs-code/design.md 📝 A format specification for describing a visual identity to coding agents. DESIGN.md gives agents a persistent, structured understanding of a design system. ────────────────────────────── The DESIGN.md format is a specification for describing visual identities to coding agents, providing a structured understanding of design systems. It combines machine-readable design tokens (YAML front matter) with human-readable design rationale (markdown prose). The format includes colors, typography, rounded, and spacing tokens, as well as components that map to groups of sub-token properties. To get started, you can validate a DESIGN.md file using the lint command:

npx @google/design.md lint DESIGN.md

You can also compare two versions of a design system using the diff command:

npx @google/design.md diff DESIGN.md DESIGN-v2.md

The format is designed for use by agents, such as coding tools, to produce consistent UI designs. The DESIGN.md format is still in its alpha version, and the spec, token schema, and CLI are under active development. Expect changes as it matures. Design consistency made easy - with DESIGN.md, your coding agents will always be on the same page! ────────────────────────────── 🧠 Channel: https://t.me/GithubRe

🔍 Deep-diving into simplex-chat/simplex-chat — fresh off the trending list. 🔗 https://github.com/simplex-chat/simplex-chat 📝 SimpleX - the first messaging network operating without user identifiers of any kind - 100% private by design! iOS, Android and desktop apps 📱! ────────────────────────────── The SimpleX Chat is a revolutionary messaging platform that prioritizes user privacy, with no user identifiers of any kind. It protects your messages and metadata with double ratchet end-to-end encryption and an additional encryption layer. Available on Android and iOS, as well as a terminal app on Linux, MacOS, and Windows, SimpleX Chat allows users to make private connections by sharing a link or scanning a QR code. The platform has a strong focus on community, with user groups and a directory for users to connect and share information. To get started, simply install the app and connect with the team or other users. SimpleX Chat is 100% private by design, and its open-source nature allows for transparency and community involvement. Join the movement and experience the power of private messaging - your conversations, your privacy, your way. ────────────────────────────── 🧠 Channel: https://t.me/GithubRe

New to LBank? Unlock VIP2 and Trading Rewards VIP2 trial, transfer rewards, and trading bonuses for new users. Offer available until June 30. Sponsored By WaybienAds