Github Top Repositories

🔍 Deep-diving into addyosmani/agent-skills — fresh off the trending list. 🔗 https://github.com/addyosmani/agent-skills 📝 Production-grade engineering skills for AI coding agents. ────────────────────────────── The agent-skills repository provides a set of skills for AI coding agents, encoding workflows, quality gates, and best practices used by senior engineers. These skills are designed to be used across every phase of development. The repository includes 7 slash commands that map to the development lifecycle, such as /spec, /plan, /build, /test, /review, /code-simplify, and /ship. To get started, you can install the skills using various methods, including claude, cursor, gemini, windsurf, or opencode. The skills are also compatible with github copilot and other agents. The repository includes 22 skills in total, covering various aspects of software development, such as idea refinement, spec-driven development, planning, building, verifying, reviewing, and shipping. The skills are designed to be used by engineers and developers who want to improve the quality and efficiency of their software development process. Overall, the agent-skills repository provides a comprehensive set of skills for AI coding agents, helping to ensure that software development is done consistently and to a high standard. Key takeaway: agent-skills helps you build better software, faster, by providing a set of reusable, production-grade skills for AI coding agents. ────────────────────────────── 🧠 Channel: https://t.me/GithubRe

🌟 anthropics/financial-services caught my eye on GitHub Trending today. 🔗 https://github.com/anthropics/financial-services 📝 No description. ────────────────────────────── The anthropics/financial-services GitHub repository offers a collection of reference agents, skills, and data connectors tailored for financial services workflows, including investment banking, equity research, private equity, and wealth management. Key features include pre-built agents for tasks like pitch deck creation, market research, and earnings review, as well as vertical plugins that bundle skills and commands for specific financial services verticals. To use the repository, you can either install the agents and plugins as a Claude Cowork plugin or deploy them via the Claude Managed Agents API. Technical highlights include the use of agent.yaml files for managed agent deployment and the ability to customize the agents and skills to fit your firm's specific needs. The repository is designed for financial services professionals, including investment bankers, equity researchers, and wealth managers, who want to streamline their workflows and improve productivity. In summary, the anthropics/financial-services repository provides a powerful toolkit for financial services professionals to automate and enhance their workflows - automate your finance workflows with Claude. ────────────────────────────── 🧠 Channel: https://t.me/GithubRe

🚀 Meet bytedance/UI-TARS-desktop: a gem from today's GitHub trending list. 🔗 https://github.com/bytedance/UI-TARS-desktop 📝 The Open-Source Multimodal AI Agent Stack: Connecting Cutting-Edge AI Models and Agent Infra ────────────────────────────── Meet UI-TARS-desktop, a cutting-edge desktop application that brings the power of GUI Agent and Vision to your computer. It's part of the TARS stack, which includes Agent TARS, a general multimodal AI Agent. UI-TARS-desktop provides a native GUI Agent based on the UI-TARS model, allowing for local and remote computer control, as well as browser operation. With its one-click out-of-the-box CLI and hybrid browser agent, you can control browsers using GUI Agent, DOM, or a hybrid strategy. The application also features event stream and MCP integration, enabling seamless integration with real-world tools. To get started, simply run npx @agent-tars/cli@latest or visit the quick start guide. With UI-TARS-desktop, you can experience a new level of convenience and intelligence - Revolutionizing human-computer interaction, one click at a time. ────────────────────────────── 🧠 Channel: https://t.me/GithubRe

🎯 oracle-devrel/oracle-ai-developer-hub landed on trending. Worth a proper look. 🔗 https://github.com/oracle-devrel/oracle-ai-developer-hub 📝 Technical resources for AI developers to build applications, agents, and systems using Oracle AI Database and OCI services ────────────────────────────── The Oracle AI Developer Hub is a comprehensive repository that provides technical resources for building AI applications, agents, and systems using Oracle AI Database and OCI services. It's organized into several key areas, including Apps, Notebooks, Guides, and Agent Memory. The Apps section features reference implementations of AI-powered solutions, such as FitTracker, agentic_rag, and finance-ai-agent-demo. These apps demonstrate end-to-end implementations of AI applications, agents, and systems that leverage Oracle AI Database and OCI services. The Notebooks section offers Jupyter notebooks and interactive tutorials covering AI/ML model development, Oracle Database AI features, and OCI AI services integration patterns. Notebooks like agentic_rag_langchain_oracledb_demo and oracle_langchain_example provide hands-on experience with building AI agents and RAG applications. The Guides section provides comprehensive documentation, reference materials, and conference presentations on AI agent architecture, reasoning strategies, and memory systems. Guides like Building the Brain and Backbone of Enterprise AI Agents and Memory Engineering: The Discipline Behind Memory Augmented Agents offer in-depth insights into advanced reasoning and infrastructure strategies. The Agent Memory section focuses on the Oracle AI Agent Memory package, which provides a unified memory core for AI agents. Notebooks in this section demonstrate how to use Oracle AI Database as the memory core, serving conversation history, durable facts, and entity state from a single converged engine. This repository is ideal for AI developers, engineers, and researchers looking to build production-grade AI solutions. To get started, explore the Apps and Notebooks sections, and dive into the Guides and Agent Memory sections for more in-depth knowledge. The Oracle AI Developer Hub is your one-stop-shop for building innovative AI applications - start building today! ────────────────────────────── 🧠 Channel: https://t.me/GithubRe

🔥 decolua/9router is trending — and it deserves your attention. 🔗 https://github.com/decolua/9router 📝 Unlimited FREE AI coding. Connect Claude Code, Codex, Cursor, Cline, Copilot, Antigravity to FREE Claude/GPT/Gemini via 40+ providers. Auto-fallback, RTK -40% tokens, never hit limits. ────────────────────────────── 9Router is a FREE AI router and token saver that helps you never stop coding while saving 20-40% tokens with RTK and auto-fallback to free and cheap AI models. It connects all AI code tools to 40+ AI providers and 100+ models, making it a universal solution for coding needs. The key features of 9Router include RTK Token Saver, which auto-compresses tool result content to save tokens, and auto-fallback to free and cheap models when subscription quotas are exhausted. It also supports multi-account round-robin and quota tracking to maximize subscriptions. To use 9Router, simply install it globally with npm install -g 9router and run it with 9router. Then, connect a free provider like Kiro AI or OpenCode Free through the dashboard. You can also use it with your CLI tool by setting the endpoint to http://localhost:20128/v1 and copying the API key from the dashboard. 9Router is designed for developers and coders who want to save time and money on AI coding tools. With its easy setup and seamless integration with major AI coding tools, it's a must-have for anyone looking to optimize their coding workflow. In short, 9Router is a game-changer for AI coding - code more, pay less. ────────────────────────────── 🧠 Channel: https://t.me/GithubRe

🚀 Meet addyosmani/agent-skills: a gem from today's GitHub trending list. 🔗 https://github.com/addyosmani/agent-skills 📝 Production-grade engineering skills for AI coding agents. ────────────────────────────── Boost your coding game with the agent-skills repository, a collection of 21 production-grade engineering skills for AI coding agents. These skills cover the entire development lifecycle, from /spec to /ship, and include tasks like test-driven development, code review, and security hardening. With seven slash commands, you can easily activate the right skills for your project. The repository also includes pre-configured agent personas and reference checklists to help you get started. Whether you're using Claude Code, Cursor, or Gemini CLI, agent-skills has got you covered. Take your coding to the next level with this powerful tool - Code smarter, not harder. ────────────────────────────── 🧠 Channel: https://t.me/GithubRe

🌟 Lordog/dive-into-llms caught my eye on GitHub Trending today. 🔗 https://github.com/Lordog/dive-into-llms 📝 《动手学大模型Dive into LLMs》系列编程实践教程 ────────────────────────────── The Lordog/dive-into-llms GitHub repository is a hands-on programming tutorial series for getting started with large language models (LLMs). The project, also known as "动手学大模型", aims to provide a free and open-source resource for students and researchers to quickly learn and deploy LLMs. The tutorial series covers a range of topics, including 微调与部署 (model fine-tuning and deployment), 提示学习与思维链 (prompt learning and thought chain), 知识编辑 (knowledge editing), 数学推理 (mathematical reasoning), and more. The repository also includes a new series of tutorials, 大模型开发全流程 (the full process of large model development), developed in collaboration with Huawei's Ascend community. This series provides a comprehensive guide to developing and deploying LLMs, covering topics such as model development, optimization, and safety. The project welcomes contributions and issues discussions, and its contributors include researchers and students from Shanghai Jiao Tong University and the National University of Singapore. Whether you're a beginner or an experienced researcher, this repository has something to offer. So, dive into LLMs and start exploring the world of large language models - your next AI project is just a git clone away! ────────────────────────────── 🧠 Channel: https://t.me/GithubRe

🔥 playcanvas/supersplat is trending — and it deserves your attention. 🔗 https://github.com/playcanvas/supersplat 📝 3D Gaussian Splat Editor ────────────────────────────── The SuperSplat Editor is a free, open-source tool for creating and editing 3D Gaussian Splats. This web-based application allows users to inspect, optimize, and publish their splats without any downloads or installations. Key features include a live version available at https://superspl.at/editor, a user guide for learning, and a local development environment for contributors. To get started with local development, clone the repository and run npm install followed by npm run develop.

git clone https://github.com/playcanvas/supersplat.git
cd supersplat
npm install
npm run develop

The editor supports localization with multiple languages and is made possible by its open-source community. Whether you're a developer or a 3D artist, the SuperSplat Editor is a powerful tool for working with Gaussian Splats. Dive into the world of 3D splatting with the SuperSplat Editor - create, edit, and optimize with ease. ────────────────────────────── 🧠 Channel: https://t.me/GithubRe

🔍 Deep-diving into masterking32/MasterDnsVPN — fresh off the trending list. 🔗 https://github.com/masterking32/MasterDnsVPN 📝 Advanced DNS tunneling VPN for censorship bypass, optimized beyond DNSTT and SlipStream with low-overhead ARQ, resolver load balancing, high packet-loss stability and speed. ────────────────────────────── README not available for this repository. ────────────────────────────── 🧠 Channel: https://t.me/GithubRe

⚡ ChromeDevTools/chrome-devtools-mcp is making waves. Here's the full picture. 🔗 https://github.com/ChromeDevTools/chrome-devtools-mcp 📝 Chrome DevTools for coding agents ────────────────────────────── The Chrome DevTools for Agents (chrome-devtools-mcp) repository provides a Model-Context-Protocol (MCP) server that enables coding agents to control and inspect a live Chrome browser. Key features include performance insights, advanced browser debugging, and reliable automation. To use chrome-devtools-mcp, you'll need Node.js and Chrome installed. The repository provides a CLI for use without MCP. You can configure your MCP client to use the server by adding the provided config. The server supports various MCP clients, including Gemini, Claude, Copilot, and Cursor. It also provides a slim mode for basic browser tasks. Technical highlights include the use of puppeteer for automation and Chrome DevTools for performance insights. The server also sends usage statistics to Google by default, which can be disabled. The target audience for this repository includes developers and users of coding agents who want to leverage the power of Chrome DevTools for automation, debugging, and performance analysis. In short, chrome-devtools-mcp empowers your coding agent to supercharge your development workflow with the full power of Chrome DevTools - automate, debug, and optimize your way to better coding. ────────────────────────────── 🧠 Channel: https://t.me/GithubRe

🌟 rowboatlabs/rowboat caught my eye on GitHub Trending today. 🔗 https://github.com/rowboatlabs/rowboat 📝 Open-source AI coworker, with memory ────────────────────────────── Rowboat is an open-source AI coworker that helps you get work done by turning your work into a knowledge graph and acting on it. It connects to your email and meeting notes, builds a long-lived knowledge graph, and uses that context to assist you in various tasks. You can use Rowboat to generate decks, prep for meetings, track people or topics, and visualize your knowledge graph. The tool is local-first, meaning all your data is stored locally as plain Markdown, giving you full control over your information. Rowboat also supports integrations with various tools and services, including Gmail, Google Calendar, and Composio. Whether you're looking to boost your productivity or simply want a more organized workflow, Rowboat is definitely worth checking out. Here's a glimpse of what you can do with Rowboat in Python:

import rowboat

# Connect to your email and meeting notes
rowboat.connect_to_email()
rowboat.connect_to_meeting_notes()

# Generate a deck about your next quarter roadmap
rowboat.generate_deck("Next Quarter Roadmap")

Rowboat is perfect for anyone looking for a powerful AI coworker to help them stay organized and productive. Get started with Rowboat today and experience the power of a local-first AI coworker - your new best work buddy that keeps all your secrets, and helps you get work done! ────────────────────────────── 🧠 Channel: https://t.me/GithubRe

⚡ datawhalechina/easy-vibe is making waves. Here's the full picture. 🔗 https://github.com/datawhalechina/easy-vibe 📝 💻 vibe coding 2026 | Your first modern programming course for beginners to master step by step. ────────────────────────────── The datawhalechina/easy-vibe GitHub repository is a treasure trove for anyone looking to dive into the world of coding and AI development. Its primary purpose is to provide a beginner-friendly learning platform where users can turn their ideas into real products by conversing with AI. The key features include a step-by-step visual tutorial, immersive simulated coding, and visible AI principles. To get started, users can simply describe what they want, and the platform will guide them through the process. The repository offers various learning paths tailored to different needs, including a fast first win, turning an idea into a product prototype, building full-stack products, and advancing Claude Code and agent workflows. Technical highlights of the repository include interactive demos, cross-platform project tutorials, and a comprehensive knowledge base covering computer fundamentals, AI principles, and engineering practices. The platform is designed for a wide range of audiences, from complete beginners to mid-level and senior developers, as well as product managers and founders. In short, datawhalechina/easy-vibe is your one-stop-shop for learning AI-assisted coding, and with its interactive approach, you can turn your ideas into products in no time. So, what are you waiting for? Dive into the world of Easy-Vibe and start building your dream projects today - if you can talk, you can build apps! ────────────────────────────── 🧠 Channel: https://t.me/GithubRe

💡 datawhalechina/hello-agents just hit the trending charts — here's why it matters. 🔗 https://github.com/datawhalechina/hello-agents 📝 📚 《从零开始构建智能体》——从零开始的智能体原理与实践教程 ────────────────────────────── Hello-Agents is a comprehensive open-source project that aims to provide a systematic guide to building intelligent agents from scratch. The project is designed for AI developers, software engineers, and students who want to gain a deep understanding of intelligent agents and their applications. The project covers a wide range of topics, including the basics of intelligent agents, language models, and their applications. It provides a step-by-step guide on how to build intelligent agents, from the basics to advanced topics such as memory and retrieval, context engineering, and agent training. One of the key features of Hello-Agents is its emphasis on practical implementation. The project provides a fully executable codebase that allows users to implement and experiment with intelligent agents. The codebase is written in Python and is designed to be easy to understand and modify. The project also includes a range of real-world examples and case studies that demonstrate the application of intelligent agents in various domains. These examples include travel assistants, research agents, and social simulation agents. Overall, Hello-Agents is a valuable resource for anyone interested in building intelligent agents and gaining a deep understanding of the underlying technologies. With its comprehensive coverage of topics, practical implementation, and real-world examples, it is an ideal project for researchers, developers, and students alike. Start building your own intelligent agents today and join the Hello-Agents community to learn from and contribute to this exciting project! ────────────────────────────── 🧠 Channel: https://t.me/GithubRe

🌟 rohitg00/agentmemory caught my eye on GitHub Trending today. 🔗 https://github.com/rohitg00/agentmemory 📝 #1 Persistent memory for AI coding agents based on real-world benchmarks ────────────────────────────── The agentmemory GitHub repository provides a persistent memory solution for AI coding agents, allowing them to recall previous interactions and maintain context. The key features of agentmemory include auto-capture of interactions, retrieval accuracy of 95.2%, and support for multiple agents through MCP and REST API. To use npx @agentmemory/agentmemory, simply run the command, and the agent will start capturing interactions and maintaining context. This eliminates the need for re-explaining previous interactions, making it a valuable tool for developers. The technical highlights of agentmemory include its use of BM25, vector, and graph search algorithms, as well as its support for leases, signals, and SQLite storage. The repository also includes benchmarks and comparisons with other competitors, demonstrating the effectiveness of agentmemory. agentmemory is designed for developers who work with AI coding agents, particularly those who use Claude Code, Cursor, Gemini CLI, Codex CLI, and other MCP clients. With its easy-to-use interface and robust features, agentmemory is an essential tool for anyone looking to improve their productivity and efficiency when working with AI coding agents. In summary, agentmemory is a game-changer for AI coding agents, providing persistent memory and recall capabilities that make development faster and more efficient - with agentmemory, your coding agent remembers everything, so you don't have to. ────────────────────────────── 🧠 Channel: https://t.me/GithubRe