Github Top Repositories

🌟 addyosmani/agent-skills caught my eye on GitHub Trending today. 🔗 https://github.com/addyosmani/agent-skills 📝 Production-grade engineering skills for AI coding agents. ────────────────────────────── Agent Skills is a GitHub repository that provides production-grade engineering skills for AI coding agents. The skills encode workflows, quality gates, and best practices used by senior engineers during software development. They are packaged to ensure AI agents follow them consistently across every development phase. The repository includes 7 slash commands that map to the development lifecycle, activating the right skills automatically. These commands include /spec, /plan, /build, /test, /review, /code-simplify, and /ship. To get started, you can use the Quick Start guide, which provides instructions for installing the skills using various tools like Claude Code, Cursor, Gemini CLI, Windsurf, OpenCode, and GitHub Copilot. The repository includes 20 skills, each representing a structured workflow with steps, verification gates, and anti-rationalization tables. These skills cover various aspects of software development, such as defining what to build, planning, building, verifying, reviewing, and shipping. The skills are designed to work with any agent that accepts system prompts or instruction files, making them versatile and widely applicable. Key technical highlights include the use of plain Markdown for skill definitions, making them easy to understand and modify. The skills also include anti-rationalization tables to help agents overcome common excuses for skipping steps. The repository is suitable for developers, engineers, and AI researchers looking to improve the quality and consistency of their software development workflows. In summary, Agent Skills is a valuable resource for anyone looking to leverage AI agents in software development, providing a comprehensive set of skills to ensure high-quality and consistent results - automate your workflow with Agent Skills and take your development to the next level! ────────────────────────────── 🧠 Channel: https://t.me/GithubRe

⚡ anthropics/financial-services is making waves. Here's the full picture. 🔗 https://github.com/anthropics/financial-services 📝 No description. ────────────────────────────── The anthropics/financial-services GitHub repository offers a suite of reference agents, skills, and data connectors designed for financial services workflows, including investment banking, equity research, private equity, and wealth management. These agents can be installed as Claude Cowork plugins or deployed via the Claude Managed Agents API. The repository includes a range of named agents that automate specific workflows, such as pitch deck creation, market research, and earnings review, as well as vertical plugins that bundle skills and data connectors by financial services industry (FSI) vertical. The repository is divided into several sections, including plugins/ for agent and vertical plugins, managed-agent-cookbooks/ for Claude Managed Agent templates, and scripts/ for deployment and management scripts. To get started, users can install the agents and vertical plugins using Claude Code or by uploading a zip file to Claude Cowork. The repository also includes a range of technical highlights, such as integration with MCP servers for data connectivity and support for Claude Code and Claude Managed Agents. The repository is designed for financial services professionals and developers who want to automate and streamline their workflows using Claude agents and skills. Overall, the anthropics/financial-services repository provides a powerful toolkit for financial services teams to boost productivity and efficiency. With its flexible deployment options and customizable agents and skills, it's an ideal solution for teams looking to leverage the power of Claude to drive their workflows forward. Automate your financial workflows with Claude and focus on high-value tasks — the future of finance is here. ────────────────────────────── 🧠 Channel: https://t.me/GithubRe

🍀 Raika — #1 Gemble Bot Raika Game 5000+ slots, emoji games 96% RTP. Get 10% weekly bonus, free spins, instant payouts, VIP chat and 24/7 support. Join @raika and play with the best! ✅ Ad. 18+

🌟 Augani/openreel-video caught my eye on GitHub Trending today. 🔗 https://github.com/Augani/openreel-video 📝 OpenReel Video - Professional browser-based video editor. Open source CapCut alternative. 100% browser-based, no installation, no cloud uploads, no watermarks. ────────────────────────────── Introducing OpenReel Video, the open-source CapCut alternative for professional video editing in your browser. With no uploads or installs required, this 100% client-side editor offers a wide range of features, including a multi-track timeline, keyframe animations, color grading, audio effects, and GPU acceleration for smooth 4K editing and fast exports. Key highlights include: - 100% client-side editing for complete privacy - No installation needed, works in Chrome/Edge - Professional features like multi-track timeline and color grading - GPU acceleration for fast exports and smooth playback Technical highlights include the use of React, TypeScript, WebCodecs, and WebGPU for a high-performance editing experience. Audience: OpenReel Video is designed for anyone looking for a free, open-source video editing solution, from hobbyists to professionals. To get started, simply visit openreel.video to try it live, or check out the GitHub repository for more information. Takeaway: OpenReel Video is revolutionizing the world of video editing by making professional-grade tools accessible to everyone, for free, and with complete privacy. ────────────────────────────── 🧠 Channel: https://t.me/GithubRe

Did you know… The Binary Logic🔹 gives you access to amazing trading signals every day? I recently stumbled upon this channel, and let me tell you, it has been a game changer! 🚀📈 Every time I check in, I see real traders sharing their strategies, and it feels like we’re all in this journey together. Just like you, I’ve wasted money chasing losses, but now, I can secure my gains and even recover from past mistakes using their insights. I’m thrilled to see growing profits every week! - Investing is no longer a solo mission! - With signals up to 95% accuracy, you’ll feel confident trading. - Join a community of over 17,000 traders who are as passionate as you! Don’t miss out on this golden opportunity! 🔥👉 Start Your Journey Here #ad 📢 InsideAd

💡 aaif-goose/goose just hit the trending charts — here's why it matters. 🔗 https://github.com/aaif-goose/goose 📝 an open source, extensible AI agent that goes beyond code suggestions - install, execute, edit, and test with any LLM ────────────────────────────── The goose project is a native open source AI agent that runs on your machine, offering a desktop app, CLI, and API for various tasks such as code, workflows, research, writing, automation, and data analysis. It supports 15+ providers like Anthropic, OpenAI, and Google, and connects to 70+ extensions via the Model Context Protocol open standard. To get started, you can download the desktop app or install the CLI using a bash script. The project is part of the Agentic AI Foundation (AAIF) at the Linux Foundation and is built in Rust for performance and portability. The target audience includes developers, researchers, and anyone looking for a versatile AI agent. With its wide range of features and extensions, goose is an excellent choice for those seeking to streamline their workflows. In a nutshell, goose is the ultimate AI sidekick that helps you "migrate" your tasks to production - and that's no fowl play! ────────────────────────────── 🧠 Channel: https://t.me/GithubRe

🌟 PriorLabs/TabPFN caught my eye on GitHub Trending today. 🔗 https://github.com/PriorLabs/TabPFN 📝 ⚡ TabPFN: Foundation Model for Tabular Data ⚡ ────────────────────────────── The TabPFN repository on GitHub offers a powerful solution for tabular data classification and regression tasks. At its core, TabPFN is a PyTorch-based model that leverages a unique combination of techniques to achieve high performance. To get started with TabPFN, you can install it via pip using pip install tabpfn or try out the interactive Colab notebook for a hands-on experience. The model is relatively simple to use, with a basic example looking like this:

from tabpfn import TabPFNClassifier, TabPFNRegressor

clf = TabPFNClassifier()
clf.fit(X_train, y_train)  
predictions = clf.predict(X_test)

Key Features of TabPFN include support for both classification and regression tasks, the ability to handle large datasets, and a range of tools for interpretability and unsupervised learning. For those looking to extend the capabilities of TabPFN, the tabpfn-extensions repository provides a wealth of additional functionality. Whether you're a data scientist looking for a high-performance model or a developer seeking to integrate TabPFN into your application, this repository has something to offer. So why not dive in and explore the world of TabPFN today - your next machine learning breakthrough could be just a click away! ────────────────────────────── 🧠 Channel: https://t.me/GithubRe

💡 decolua/9router just hit the trending charts — here's why it matters. 🔗 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 game-changing, free AI router that saves you tokens and money by seamlessly connecting your favorite AI code tools to over 40 providers and 100+ models. With 9Router, you can auto-compress tool results, track quotas, and auto-fallback to cheaper or free models, ensuring you never stop coding. Key features include RTK Token Saver, multi-account support, and universal compatibility with tools like Claude Code, Codex, and OpenClaw. To get started, simply npm install -g 9router and connect a free provider like Kiro AI or OpenCode Free. 9Router is perfect for developers, coders, and anyone looking to maximize their AI potential without breaking the bank. With its easy setup and user-friendly dashboard, you can focus on what matters most - building amazing things. Technical highlights include support for 40+ API key providers, 100+ models, and OAuth providers like Claude Code and GitHub. Whether you're a seasoned pro or just starting out, 9Router is the perfect tool to supercharge your coding journey. In short, 9Router is a must-have for anyone looking to save time, save money, and unlock their full potential with AI. So why wait? Get started with 9Router today and experience the power of unlimited AI! Code smarter, not harder, with 9Router! ────────────────────────────── 🧠 Channel: https://t.me/GithubRe

🎯 docusealco/docuseal landed on trending. Worth a proper look. 🔗 https://github.com/docusealco/docuseal 📝 Open source DocuSign alternative. Create, fill, and sign digital documents ✍️ ────────────────────────────── DocuSeal is an open source platform that provides secure and efficient digital document signing and processing. With DocuSeal, you can create PDF forms to have them filled and signed online on any device with an easy-to-use, mobile-optimized web tool. Key features include a PDF form fields builder with 12 field types, multiple submitters per document, automated emails, and file storage on disk or cloud services like AWS S3. To get started, you can try the live demo or deploy DocuSeal in minutes using Docker or Docker Compose. DocuSeal is perfect for businesses looking to integrate seamless document signing into their web or mobile apps, especially in industries like banking, healthcare, and real estate. The platform is free and open source, with optional Pro Features available for companies that need more advanced functionality. In a nutshell, DocuSeal makes it easy to fill, sign, and process documents online - give it a try and streamline your document workflow today! ────────────────────────────── 🧠 Channel: https://t.me/GithubRe

⚡ vercel-labs/open-agents is making waves. Here's the full picture. 🔗 https://github.com/vercel-labs/open-agents 📝 An open source template for building cloud agents. ────────────────────────────── The Open Agents GitHub repository is an open-source reference application designed to build and run background coding agents on Vercel. It's a three-layer system consisting of a web app, an agent workflow, and a sandbox VM. The key feature is that the agent runs outside the sandbox, interacting with it through tools, allowing for a more flexible and scalable architecture. The repo includes a chat-driven coding agent, durable multi-step execution, and isolated Vercel sandboxes. To use it, you can fork the repository, import it into Vercel, and configure the environment variables. The code is organized into multiple packages, including the agent, sandbox, and shared utilities. With Open Agents, you can build and run custom coding agents on Vercel, enabling automated coding workflows. Automate your coding tasks with Open Agents - the future of coding is here. ────────────────────────────── 🧠 Channel: https://t.me/GithubRe

🔍 Deep-diving into VectifyAI/PageIndex — fresh off the trending list. 🔗 https://github.com/VectifyAI/PageIndex 📝 📑 PageIndex: Document Index for Vectorless, Reasoning-based RAG ────────────────────────────── PageIndex is a vectorless, reasoning-based RAG system that enables Large Language Models (LLMs) to perform context-aware retrieval over long documents. It builds a hierarchical tree index from documents and uses LLMs to reason over that index for agentic, context-aware retrieval. Key features include: no vector database, no chunking, better explainability and traceability, context-aware retrieval, and human-like retrieval. To use PageIndex, you can self-host it with this open-source repo, use the cloud service for production-grade results, or integrate it via MCP or API. The PageIndex Framework is available for a deeper dive, and cookbooks and tutorials provide additional usage guides and examples. Technical highlights include the ability to transform lengthy PDF documents into a semantic tree structure, similar to a "table of contents" but optimized for use with LLMs. PageIndex is suitable for financial reports, regulatory filings, academic textbooks, and more. The target audience includes developers, researchers, and professionals working with long documents that demand domain expertise and multi-step reasoning. Try PageIndex today and experience the power of reasoning-based retrieval: pip3 install --upgrade -r requirements.txt and python3 run_pageindex.py --pdf_path /path/to/your/document.pdf. Takeaway: PageIndex revolutionizes document retrieval with its vectorless, reasoning-based approach, making it an essential tool for anyone working with complex documents. ────────────────────────────── 🧠 Channel: https://t.me/GithubRe

📌 Spotted on GitHub Trending: addyosmani/agent-skills — let's break it down. 🔗 https://github.com/addyosmani/agent-skills 📝 Production-grade engineering skills for AI coding agents. ────────────────────────────── Production-grade engineering skills for AI coding agents are available in the addyosmani/agent-skills GitHub repository. These skills encode workflows, quality gates, and best practices that senior engineers use when building software, ensuring AI agents follow them consistently across every development phase. The repository includes 7 slash commands that map to the development lifecycle, such as /spec, /plan, /build, /test, /review, /code-simplify, and /ship. Each command activates the right skills automatically, and skills can also be activated based on what you're doing, such as designing an API or building UI. The repository provides a quick start guide for various platforms, including Claude Code, Cursor, Gemini CLI, Windsurf, OpenCode, GitHub Copilot, Kiro IDE & CLI, and Codex. With 20 skills available, developers can ensure their AI coding agents follow best practices and produce high-quality code. These skills cover various aspects of software development, including definition, planning, building, verification, review, and shipping. The repository also includes agent personas and reference checklists to support the skills. Overall, the addyosmani/agent-skills repository provides a valuable resource for developers to improve the quality and consistency of their code. Upgrade your coding game with production-grade engineering skills for AI agents! ────────────────────────────── 🧠 Channel: https://t.me/GithubRe

🚀 Meet LearningCircuit/local-deep-research: a gem from today's GitHub trending list. 🔗 https://github.com/LearningCircuit/local-deep-research 📝 ~95% on SimpleQA (e.g. Qwen3.6-27B on a 3090). Supports all local and cloud LLMs (llama.cpp, Ollama, Google, ...). 10+ search engines - arXiv, PubMed, your private documents. Everything Local & Encrypted. ────────────────────────────── Local Deep Research is an AI-powered research assistant that helps you perform deep, agentic research using multiple LLMs and search engines with proper citations. It's designed to run locally for privacy, allowing you to use any LLM and build your own searchable knowledge base. You own your data and can see exactly how it works. Key features include: - Automatic research across web, academic papers, and your own documents - Synthesis of research into a report with proper citations - 20+ research strategies for quick facts, deep analysis, or academic research - Encrypted library for storing and searching your documents - Support for multiple LLMs and search engines Usage is straightforward: simply pull and run the Docker image, or install using pip. You can also use Docker Compose for a more streamlined setup. From a technical standpoint, Local Deep Research uses SQLCipher for encrypted storage, and includes features like in-memory credentials and supply chain security. The project also prioritizes security transparency, with documented scanner suppressions and security alerts. This project is ideal for researchers, students, and anyone looking for a powerful, private research tool. With its focus on security, privacy, and customization, Local Deep Research is an excellent choice for those who want to take control of their research process. In short, Local Deep Research is a game-changer for anyone looking to level up their research skills - take control of your research, and unlock new insights with Local Deep Research. ────────────────────────────── 🧠 Channel: https://t.me/GithubRe

Unlock Your AI Career Join our Data Science Full Stack with AI Course – a real-time, project-based online training designed for hands-on mastery. Core Topics Covered •  Data Science using Python with Generative AI: Build end-to-end data pipelines, from data wrangling to deploying AI models with Python libraries like Pandas, Scikit-learn, and Hugging Face transformers. •  Prompt Engineering: Craft precise prompts to maximize output from models like GPT and Gemini for accurate, creative results. •  AI Agents & Agentic AI: Develop autonomous agents that reason, plan, and act using frameworks like Lang Chain for real-world automation. Why Choose This Course? This training emphasizes live sessions, industry projects, and practical skills for immediate job impact, similar to top programs offering 100+ hours of Python-to-AI progression. Ready to start? Call/WhatsApp: (+91)-7416877757 WhatsApp Link:- http://wa.me/+917416877757

🌟 InsForge/InsForge caught my eye on GitHub Trending today. 🔗 https://github.com/InsForge/InsForge 📝 InsForge is a Postgres-based backend with auth, storage, compute, hosting, and AI gateway. Built for coding agents. ────────────────────────────── InsForge is a backend development platform designed for AI-native developers, providing a semantic layer between AI coding agents and backend primitives like databases, authentication, and storage. The platform allows agents to understand, operate, and inspect backend systems, enabling efficient development and deployment of applications. Key features include a semantic layer for backend context engineering, support for multiple backend primitives, and a user-friendly interface for inspecting and configuring backend state. To get started with InsForge, you can either use the cloud-hosted version at insforge.dev or self-host it using Docker Compose. The platform provides a quickstart guide and comprehensive documentation to help you set up and use the platform. Technical highlights of InsForge include its support for PostgreSQL, S3-compatible file storage, and OpenAI-compatible API. The platform also provides a model gateway, edge functions, and site deployment capabilities. InsForge is designed for AI-native developers and provides a unique set of features that cater to their needs. Whether you're building a new application or migrating an existing one, InsForge provides a powerful backend platform to support your development needs. In summary, InsForge is a powerful backend platform that provides a semantic layer for AI coding agents to interact with backend primitives, making it an ideal choice for AI-native developers. So why wait? Star the repository and start building with InsForge today - revolutionize your backend development with the power of AI! ────────────────────────────── 🧠 Channel: https://t.me/GithubRe

📌 Spotted on GitHub Trending: z-lab/dflash — let's break it down. 🔗 https://github.com/z-lab/dflash 📝 DFlash: Block Diffusion for Flash Speculative Decoding ────────────────────────────── The DFlash repository on GitHub introduces a lightweight block diffusion model designed for speculative decoding, enabling efficient and high-quality parallel drafting. This model is supported by various backends, including Transformers, SGLang, vLLM, and MLX. To get started, users can install the required packages using pip install commands and then serve models using vllm serve or python -m sglang.launch_server commands. The repository also provides a quick start guide for each backend and a benchmarking script to evaluate the performance of DFlash. DFlash has been implemented with several models, including gemma-4-26B-A4B-it, Qwen3.5-27B, and LLaMA3.1-8B-Instruct, which can be found on the Hugging Face model hub. The key highlight of DFlash is its ability to accelerate language models, making it an exciting development in the field of natural language processing. In a nutshell, DFlash is a game-changer for language models, and its speculative decoding capabilities make it a must-try for anyone working with large language models. ────────────────────────────── 🧠 Channel: https://t.me/GithubRe