Github Top Repositories

🎯 calesthio/OpenMontage landed on trending. Worth a proper look. 🔗 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 tool allows you to describe what you want in plain language, and the agent handles research, scripting, asset generation, editing, and final composition. Key Features: - Turn your AI coding assistant into a full video production studio - Create image-based videos or real videos using free stock footage and open archives - Works with various AI coding assistants, including Claude Code, Cursor, Copilot, Windsurf, and Codex - pip install and npm install for easy setup - Supports multiple pipelines, including Remotion and HyperFrames Technical Highlights: - Use Python 3.10+ and Node.js 18+ for development - Leverage FFmpeg for encoding, subtitle burn-in, and audio mixing - Integrates with various APIs, including OpenAI, Google API, and Pexels API Audience: - Developers and creators looking for an open-source video production system - Those interested in AI-assisted video creation - Anyone wanting to produce high-quality videos without extensive manual editing Get started with OpenMontage today and experience the power of AI-assisted video creation! OpenMontage empowers creators to produce stunning videos with ease, and its open-source nature ensures a community-driven development process. With OpenMontage, the future of video production is here, and it's free. ────────────────────────────── 🧠 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

💡 mattpocock/skills just hit the trending charts — here's why it matters. 🔗 https://github.com/mattpocock/skills 📝 Skills for Real Engineers. Straight from my .claude directory. ────────────────────────────── The mattpocock/skills GitHub repository offers a collection of skills designed to improve your workflow and productivity when working with coding agents. These skills are small, easy to adapt, and composable, allowing you to mix and match them to suit your needs. The skills are based on decades of engineering experience and are designed to help you avoid common failure modes such as misalignment, verbosity, and poor code quality. To get started, you can use the npx skills@latest add mattpocock/skills command to install the skills, and then follow the quickstart guide to configure them for your project. The skills include features such as grilling sessions to help you align with the agent, shared language to reduce verbosity, and test-driven development to improve code quality. The repository is divided into several categories, including engineering, productivity, and misc, each containing a range of skills that can be used to improve your workflow. The skills are designed to be user-invoked or model-invoked, allowing you to choose when and how to use them. Overall, the mattpocock/skills repository offers a powerful set of tools to help you work more effectively with coding agents and improve the quality of your code. With these skills, you can take your coding to the next level and ship the best apps of your career. The key takeaway is: mastering these skills will make you a more efficient and effective developer. ────────────────────────────── 🧠 Channel: https://t.me/GithubRe

Unlock Your Profit Potential Recently, I stumbled upon a community that truly resonates with me - a place where we spread support and respect while earning profits! 💸✨ Sharing this connection has transformed my approach to trading, and it can do the same for you. In this channel, you’ll find no fluff. I’ve spent countless hours searching for the best resources, and I can confidently say that joining BINASOU4 is a game-changer. Dive into discussions about strategies and find valuable insights like what I found in this post that can amp up your trading skills. Don’t miss out on the chance to be part of this supportive family. Join us today! 👉 Connect and grow #ad 📢 InsideAd

🔥 asgeirtj/system_prompts_leaks is trending — and it deserves your attention. 🔗 https://github.com/asgeirtj/system_prompts_leaks 📝 Extracted system prompts from Anthropic - Claude Fable 5, Opus 4.8, Claude Code, Claude Design. OpenAI - ChatGPT 5.5 Thinking, GPT 5.5 Instant, Codex. Google - Gemini 3.5 Flash, 3.1 Pro, Antigravity. xAI - Grok, Cursor, Copilot, VS Code, Perplexity, and more. Updated regularly. ────────────────────────────── The asgeirtj/system_prompts_leaks GitHub repository is a community-driven effort to document system prompts for various AI chatbots, including Claude, ChatGPT, and Gemini. The purpose of this repo is to provide a centralized location for users to access and compare system prompts, which are the hidden rules and guidelines that govern AI behavior. Key features of this repository include a comprehensive collection of system prompts for different AI models, including older versions and variants. The repo also provides diff files to compare changes between different versions of system prompts. The repository is easy to use, with a simple and organized structure that allows users to navigate and find the system prompts they need. The repo is also technically sound, with a focus on providing accurate and up-to-date information. This repository is intended for a broad audience, including AI researchers, developers, and enthusiasts. Whether you're interested in understanding how AI chatbots work or simply want to explore the possibilities of AI, this repository is a valuable resource. In short, the asgeirtj/system_prompts_leaks repository is a powerful tool for anyone looking to unlock the secrets of AI chatbots - check it out and start exploring the hidden rules of AI today! ────────────────────────────── 🧠 Channel: https://t.me/GithubRe

🎯 byoungd/English-level-up-tips landed on trending. Worth a proper look. 🔗 https://github.com/byoungd/English-level-up-tips 📝 An advanced guide to learn English which might benefit you a lot 🎉 . 离谱的英语学习指南/英语学习教程/英语学习/学英语 ────────────────────────────── English-level-up-tips is a comprehensive guide to learning English, created by byoungd. The repo offers a detailed, step-by-step approach to improving English skills, covering key areas such as understanding, vocabulary, listening, reading, speaking, and writing. The guide also explores the role of AI in language learning, providing practical tips on how to utilize tools like Gemini and ChatGPT to enhance the learning experience. Whether you're a beginner or an advanced learner, this repo has something to offer. The author's passion for language learning and commitment to sharing knowledge make this guide an invaluable resource. The repo's

features

include a well-structured approach, engaging content, and a supportive community. The target audience for this repo includes anyone looking to improve their English skills, from students to professionals. One key takeaway: learning English should be a natural and enjoyable process, and with the right approach, anyone can achieve fluency. In short, English-level-up-tips is your one-stop-shop for all things English learning - so dive in and start your journey to linguistic mastery today! Remember, learning a language is a journey, not a destination - so enjoy the process and have fun! ────────────────────────────── 🧠 Channel: https://t.me/GithubRe

🎯 topoteretes/cognee landed on trending. Worth a proper look. 🔗 https://github.com/topoteretes/cognee 📝 Cognee is the open-source AI memory platform for agents. Give your AI agents persistent long-term memory across sessions with a self-hosted knowledge graph engine. ────────────────────────────── Cognee is an open-source AI memory platform that gives AI agents persistent long-term memory across sessions. It ingests data in any format, builds a self-hosted knowledge graph, and enables agents to recall, connect, and act with full context. Key features include vector embeddings, graph reasoning, and cognitive-science-grounded ontology generation. To get started, you can install Cognee using pip, then configure the LLM API key and run the pipeline using the provided example code. The platform also includes a CLI for easy interaction and a local UI for visualization. Technical highlights include support for multiple LLM providers, a flexible architecture, and a growing community of developers. Audience includes AI researchers, developers, and organizations looking to build more intelligent and persistent AI agents. Cognee is ideal for building company brains, creating knowledge infrastructure, and developing persistent and learning agents. With its easy-to-use interface and extensive documentation, Cognee is perfect for anyone looking to take their AI projects to the next level. Use Cognee to build intelligent AI agents that learn, remember, and improve over time — the future of AI depends on it. ────────────────────────────── 🧠 Channel: https://t.me/GithubRe

⚡ smicallef/spiderfoot is making waves. Here's the full picture. 🔗 https://github.com/smicallef/spiderfoot 📝 SpiderFoot automates OSINT for threat intelligence and mapping your attack surface. ────────────────────────────── SpiderFoot is an open-source intelligence (OSINT) automation tool that integrates with various data sources and uses multiple methods for data analysis. It has a web-based UI and can also be used via the command-line. Written in Python 3, SpiderFoot has over 200 modules and features like YAML-configurable correlation engine, CSV/JSON/GEXF export, and TOR integration for dark web searching. Key features include: - Highly configurable - Fully documented - Visualisations - API key export/import - SQLite back-end for custom querying You can use SpiderFoot for offensive or defensive purposes, targeting entities like IP addresses, domain names, and more. The tool can perform tasks such as host enumeration, email address extraction, and threat intelligence queries. To get started, you can install SpiderFoot using pip and run it using python3 ./sf.py -l 127.0.0.1:5001. SpiderFoot is perfect for security professionals, researchers, and anyone interested in OSINT. With its vast array of features and modules, SpiderFoot is a powerful tool for gathering and analyzing intelligence. One-liner takeaway: SpiderFoot is the ultimate OSINT tool for anyone looking to automate their intelligence gathering and analysis. ────────────────────────────── 🧠 Channel: https://t.me/GithubRe

💡 mikumifa/biliTickerBuy just hit the trending charts — here's why it matters. 🔗 https://github.com/mikumifa/biliTickerBuy 📝 b站会员购购票辅助工具 ────────────────────────────── biliTickerBuy is an open-source, free, and easy-to-use tool designed to assist with Bilibili membership purchases. Its primary purpose is to provide a simple and efficient way to buy Bilibili memberships. The main features of this tool include a user-friendly interface and streamlined purchase process. To use the tool, simply follow the installation guide and usage instructions. From a technical standpoint, the tool is built with a focus on non-intrusive design, ensuring that it does not interfere with the target server. This tool is ideal for individuals looking for a convenient and easy-to-use solution for Bilibili membership purchases. In short, biliTickerBuy is a must-have tool for anyone looking to simplify their Bilibili membership buying experience: automate your purchases with ease. ────────────────────────────── 🧠 Channel: https://t.me/GithubRe

🚀 Meet mukul975/Anthropic-Cybersecurity-Skills: a gem from today's GitHub trending list. 🔗 https://github.com/mukul975/Anthropic-Cybersecurity-Skills 📝 754 structured cybersecurity skills for AI agents · Mapped to 5 frameworks: MITRE ATT&CK, NIST CSF 2.0, MITRE ATLAS, D3FEND & NIST AI RMF · agentskills.io standard · Works with Claude Code, GitHub Copilot, Codex CLI, Cursor, Gemini CLI & 20+ platforms · 26 security domains · Apache 2.0 ────────────────────────────── Anthropic Cybersecurity Skills is an open-source library of 754 production-grade cybersecurity skills, covering 26 security domains and mapped to six industry frameworks, including MITRE ATT&CK, NIST CSF, and MITRE F3. This library enables AI agents to possess the security skills of a senior analyst, guiding them through expert-level security investigations in seconds. The library is designed to be AI-native, with YAML frontmatter for sub-second discovery and structured Markdown for step-by-step execution. It includes skills such as cloud security, threat hunting, and web application security, making it a comprehensive resource for cybersecurity professionals. To get started, users can clone the repository or use npx skills add mukul975/Anthropic-Cybersecurity-Skills. The library is compatible with various platforms, including Claude Code, GitHub Copilot, and OpenAI Codex CLI. The project aims to bridge the cybersecurity workforce gap by providing AI agents with structured domain knowledge. It is an independent, community-created project, not affiliated with Anthropic PBC. Key takeaway: Give your AI agent the security skills of a senior analyst with Anthropic Cybersecurity Skills, and revolutionize your security investigations. ────────────────────────────── 🧠 Channel: https://t.me/GithubRe

💡 DeusData/codebase-memory-mcp just hit the trending charts — here's why it matters. 🔗 https://github.com/DeusData/codebase-memory-mcp 📝 High-performance code intelligence MCP server. Indexes codebases into a persistent knowledge graph — average repo in milliseconds. 158 languages, sub-ms queries, 99% fewer tokens. Single static binary, zero dependencies. ────────────────────────────── Meet codebase-memory-mcp, the fastest and most efficient code intelligence engine for AI coding agents. This powerful tool indexes an average repository in milliseconds and answers structural queries in under 1ms. It supports 158 languages and ships as a single static binary for macOS, Linux, and Windows, making it easy to download, install, and use. The key features of codebase-memory-mcp include: * Extreme indexing speed: indexes the Linux kernel in 3 minutes * Plug and play: single static binary with no dependencies or API keys required * High-quality parsing: uses tree-sitter AST analysis and hybrid LSP semantic type resolution * Built-in graph visualization: 3D interactive UI for exploring the knowledge graph * 14 MCP tools: search, trace, architecture, impact analysis, and more To get started, simply run the install.sh script (or install.ps1 on Windows) and restart your coding agent. You can also manually install the binary and configure it to work with your preferred coding agent. With codebase-memory-mcp, you can enjoy features like semantic search, structural search, and cross-service linking, making it an essential tool for any developer. So why wait? Try codebase-memory-mcp today and experience the power of code intelligence like never before - it's like having a superpower for your code. ────────────────────────────── 🧠 Channel: https://t.me/GithubRe

🚀 Meet bytedance/deer-flow: a gem from today's GitHub trending list. 🔗 https://github.com/bytedance/deer-flow 📝 An open-source long-horizon SuperAgent harness that researches, codes, and creates. With the help of sandboxes, memories, tools, skill, subagents and message gateway, it handles different levels of tasks that could take minutes to hours. ────────────────────────────── DeerFlow is an open-source super agent harness that orchestrates sub-agents, memory, and sandboxes to do almost anything — powered by extensible skills. Its key features include skills and tools, sub-agents, sandbox and file system, context engineering, and long-term memory. To get started with DeerFlow, you can clone the repository, run the setup wizard, and choose your LLM provider, web search, and execution preferences. The project uses config.yaml for configuration and supports multiple deployment options, including Docker and local development. Some technical highlights of DeerFlow include its support for various LLM providers, such as OpenAI and Claude Code, and its integration with InfoQuest, a powerful search and crawling toolset. The project also provides a range of documentation and resources, including a official website with real demos and tutorials. DeerFlow is designed for developers and researchers who want to build and deploy complex AI systems. Its one-line agent setup feature allows you to easily integrate DeerFlow with other tools and platforms. In summary, DeerFlow is a powerful and flexible platform for building and deploying AI systems, and its extensible skills and super agent harness make it an ideal choice for developers and researchers who want to push the boundaries of what is possible with AI. The one-liner takeaway: DeerFlow empowers you to build and deploy AI systems that can do almost anything, with its super agent harness and extensible skills at your fingertips. ────────────────────────────── 🧠 Channel: https://t.me/GithubRe

🚀 Meet koala73/worldmonitor: a gem from today's GitHub trending list. 🔗 https://github.com/koala73/worldmonitor 📝 Real-time global intelligence dashboard. AI-powered news aggregation, geopolitical monitoring, and infrastructure tracking in a unified situational awareness interface ────────────────────────────── The World Monitor is a real-time global intelligence dashboard that leverages AI to aggregate news, track geopolitics, and monitor infrastructure. Its key features include 500+ curated news feeds, a dual map engine, and a Country Instability Index (CII). To use, simply git clone the repository, npm install, and npm run dev. The project boasts a tech stack that includes Vanilla TypeScript, Vite, and Tauri 2, with a deployment process that utilizes Vercel Edge Functions and Railway relay. The audience for this project includes researchers, educators, and professionals seeking to stay informed about global events. With its permissive AGPL-3.0-only license, the World Monitor is an excellent choice for those seeking a customizable and self-hosted solution. One-liner takeaway: Stay ahead of the curve with the World Monitor, your one-stop-shop for real-time global intelligence. ────────────────────────────── 🧠 Channel: https://t.me/GithubRe

⚡ ZhuLinsen/daily_stock_analysis is making waves. Here's the full picture. 🔗 https://github.com/ZhuLinsen/daily_stock_analysis 📝 LLM 驱动的多市场股票智能分析系统：多源行情、实时新闻、决策看板与自动推送，支持零成本定时运行。 LLM-powered multi-market stock analysis system with multi-source market data, real-time news, decision dashboard, automated notifications, and cost-free scheduled runs. ────────────────────────────── Daily Stock Analysis is an AI-powered stock analysis system that provides users with daily reports on their selected stocks. The system uses machine learning models to analyze market data, news, and social media sentiment to generate buy, sell, or hold recommendations. Key Features: The system supports multiple markets, including A-shares, Hong Kong stocks, US stocks, and more. It also provides a web-based interface for users to configure their stock portfolios, view analysis reports, and receive notifications. Usage: Users can configure the system to analyze their selected stocks and receive daily reports via various channels, including WeChat, Telegram, and email. Technical Highlights: The system uses a range of AI models, including Anspire and AIHubMix, to analyze market data and generate recommendations. It also supports multiple data sources, including TickFlow and AkShare. Audience: The system is designed for individual investors and financial professionals who want to stay on top of market trends and make informed investment decisions. One-liner Takeaway: Daily Stock Analysis is a powerful tool for investors who want to leverage AI-powered insights to make informed investment decisions and stay ahead of the market. ────────────────────────────── 🧠 Channel: https://t.me/GithubRe