Github Top Repositories

🎯 Automattic/harper landed on trending. Worth a proper look. 🔗 https://github.com/Automattic/harper 📝 Offline, privacy-first grammar checker. Fast, open-source, Rust-powered ────────────────────────────── Introducing Harper, an English grammar checker designed to be private, fast, and accurate. Created to address the shortcomings of existing tools, Harper is completely private, taking milliseconds to lint a document and using less than 1/50th of LanguageTool's memory footprint. You can use Harper via WebAssembly and it supports various editors, including Visual Studio Code, Neovim, and Emacs. The project is extensible to support other languages and welcomes contributions. With its harper-ls and harper.js integrations, Harper is a great tool for anyone looking for a reliable grammar checker. Join the community and contribute to make Harper even better - Harper: grammar checking, just right. ────────────────────────────── 🧠 Channel: https://t.me/GithubRe

⚡ shiyu-coder/Kronos is making waves. Here's the full picture. 🔗 https://github.com/shiyu-coder/Kronos 📝 Kronos: A Foundation Model for the Language of Financial Markets ────────────────────────────── Kronos is the first open-source foundation model for financial candlesticks, trained on data from over 45 global exchanges. It's a decoder-only model, pre-trained for the "language" of financial markets, handling high-noise characteristics of financial data with a novel two-stage framework. Kronos uses a specialized tokenizer to quantize continuous data into hierarchical discrete tokens, which are then used to train a large, autoregressive Transformer. For usage, you can install the dependencies with pip install -r requirements.txt and load a pre-trained model and tokenizer from the Hugging Face Hub. The model can be used for forecasting with the KronosPredictor class, which handles data preprocessing, normalization, prediction, and inverse normalization. Some technical highlights of Kronos include its novel two-stage framework, hierarchical discrete tokens, and autoregressive Transformer. Kronos is designed for financial data analysis and can be fine-tuned on your own data. The intended audience for Kronos includes quantitative analysts, data scientists, and financial researchers who want to analyze and forecast financial data. In summary: Kronos is a powerful tool for financial data analysis, and with its open-source availability, it's a game-changer for anyone looking to forecast market trends - forecast your way to financial insight with Kronos! ────────────────────────────── 🧠 Channel: https://t.me/GithubRe

🔥 Pumpkin-MC/Pumpkin is trending — and it deserves your attention. 🔗 https://github.com/Pumpkin-MC/Pumpkin 📝 Empowering everyone to host fast and efficient Minecraft servers. ────────────────────────────── Pumpkin is a Minecraft server built in Rust, focusing on performance, compatibility, security, flexibility, and extensibility. It supports the latest Java and Bedrock Minecraft server versions while adhering to Vanilla game mechanics. The server is highly configurable and allows for plugin development. Key features include multi-threading for maximum speed, configuration using toml, and support for various Minecraft protocols. The server is still under heavy development, with ongoing work on features like chunk generation, redstone, and combat. To get started with Pumpkin, check out the Quick Start guide. Contributions are welcome, and the community can be reached through the Discord server. Pumpkin is designed for Minecraft enthusiasts and server administrators looking for a fast, efficient, and customizable experience. One-liner takeaway: Pumpkin is the future of Minecraft servers, built for speed, security, and community. ────────────────────────────── 🧠 Channel: https://t.me/GithubRe

🔥 ComposioHQ/awesome-claude-skills is trending — and it deserves your attention. 🔗 https://github.com/ComposioHQ/awesome-claude-skills 📝 A curated list of awesome Claude Skills, resources, and tools for customizing Claude AI workflows ────────────────────────────── The ComposioHQ/awesome-claude-skills GitHub repository offers a vast collection of 1000+ production-ready Claude Skills and plugins, enhancing productivity across various use cases on Claude.ai, Claude Code, and other coding agents. These skills teach an AI agent how to handle specific tasks, and they can be used to connect Claude to 1000+ apps, perform real-world actions, and more. Some key features of this repository include: * A wide range of skills for document processing, development, data analysis, business, communication, and more * The ability to connect Claude to various apps and services, such as Gmail, Slack, GitHub, and Notion * A connect-apps plugin that enables Claude to perform real actions, like sending emails and creating issues To get started, you can install the connect-apps plugin and follow the quickstart guide provided in the repository. The repository also offers a comprehensive list of skills, including those for document processing, development, and data analysis. The target audience for this repository includes developers, data analysts, business professionals, and anyone looking to enhance their productivity with Claude Skills. In terms of technical highlights, the repository provides a single MCP endpoint for 1,000+ integrations with built-in authentication, team-based access controls, audit logs, and production-ready reliability. Overall, the ComposioHQ/awesome-claude-skills repository is a valuable resource for anyone looking to unlock the full potential of Claude Skills and take their productivity to the next level. Takeaway: With ComposioHQ/awesome-claude-skills, you can unlock a world of possibilities and take your productivity to new heights by leveraging the power of Claude Skills and plugins. ────────────────────────────── 🧠 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 ────────────────────────────── World Monitor is a real-time global intelligence dashboard that leverages AI to aggregate news, track geopolitics, and monitor infrastructure. It offers a dual map engine, cross-stream correlation, and a Country Instability Index (CII). The platform provides 6 site variants, a native desktop app, and supports 25 languages. To get started, users can git clone the repository, npm install, and npm run dev to launch the app. The tech stack includes Vanilla TypeScript, Vite, globe.gl, and Tauri 2. World Monitor is designed for both browsers and programmatic access via its MCP server, REST API, CLI, and SDKs. The platform aggregates 65+ external providers and is licensed under AGPL-3.0-only. Takeaway: World Monitor empowers users to stay informed about global events with its cutting-edge, AI-powered dashboard and robust feature set. ────────────────────────────── 🧠 Channel: https://t.me/GithubRe

🔥 block/buzz is trending — and it deserves your attention. 🔗 https://github.com/block/buzz 📝 A hive mind communication platform ────────────────────────────── Buzz is a self-hostable workspace where humans and AI agents collaborate in the same rooms. It's built on a Nostr relay, where every message, reaction, and event is a signed event in one log. This allows for a unified experience, with agents having the same capabilities as humans, including opening repos, sending patches, and reviewing code. Key features include asking the project a question and getting an answer with receipts, letting an agent triage a bug without giving it full access, and turning a feature branch into a room where patches, CI, review, and merge decisions live together. Technical highlights include a Rust workspace with focused crates, a single source of truth in the relay, and a scalable architecture. The project is designed for developers and teams looking for a more integrated and secure way to work with AI agents. To get started, you can try the app by grabbing a packaged build, or build and run from source using Docker and Hermit. The project is still evolving, with new features and improvements being added regularly. In short, Buzz is a powerful tool for teams looking to harness the power of AI agents in their workflow, and its unique approach to collaboration and security makes it an exciting project to watch. One workspace, one identity model, one event log - that's the Buzz way! ────────────────────────────── 🧠 Channel: https://t.me/GithubRe

💡 jellyfin/jellyfin just hit the trending charts — here's why it matters. 🔗 https://github.com/jellyfin/jellyfin 📝 The Free Software Media System - Server Backend & API ────────────────────────────── Jellyfin is a free software media system that lets you manage and stream your media from a dedicated server to various devices. It's an alternative to Emby and Plex, with no premium licenses or hidden agendas. Jellyfin is built on the .NET platform, allowing for full cross-platform support. Key features include a web-based interface, mobile apps, and support for multiple devices. To get started, you can download the server from the downloads page or build it from source using git clone https://github.com/jellyfin/jellyfin.git and then dotnet run. The Jellyfin server is the backend of the system, and it's available on all major operating systems except FreeBSD. To develop and run the server, you'll need to install the .NET 10 SDK and ffmpeg. You can then run the server using dotnet run or an IDE like Visual Studio. Jellyfin is open to contributions and has a strong community of developers and users. If you want to contribute, you can check out the contributing guide and join the discussion on the Matrix chat. In short, Jellyfin is a powerful and flexible media system that's free and open, giving you full control over your media - take the reins and stream your way! ────────────────────────────── 🧠 Channel: https://t.me/GithubRe

💡 Automattic/harper just hit the trending charts — here's why it matters. 🔗 https://github.com/Automattic/harper 📝 Offline, privacy-first grammar checker. Fast, open-source, Rust-powered ────────────────────────────── Harper is an English grammar checker designed to provide a private and efficient solution for writers. It was created to overcome the shortcomings of existing tools like Grammarly and LanguageTool, which are often too expensive, too overbearing, and lacking in context. Harper is built to be fast, lightweight, and completely private, with a memory footprint of less than 1/50th of LanguageTool. It supports various editors, including Visual Studio Code, Neovim, and Emacs, and can even be loaded via WebAssembly. The core of Harper is extensible, allowing for contributions to support other languages. With its focus on performance and user value, Harper is the perfect solution for writers who want a seamless and private writing experience. You can use Harper to improve your writing with its fast and accurate grammar checking, and its small size makes it easy to integrate into your workflow. Harper is for anyone looking for a fast, private, and efficient grammar checker: Write with Harper, and take control of your writing experience. ────────────────────────────── 🧠 Channel: https://t.me/GithubRe

💡 likec4/likec4 just hit the trending charts — here's why it matters. 🔗 https://github.com/likec4/likec4 📝 Visualize, collaborate, and evolve the software architecture with always actual and live diagrams from your code ────────────────────────────── Introducing LikeC4, a powerful tool for visualizing and collaborating on software architecture. It allows you to generate live diagrams from your code, using a customizable notation and element types. Key features include flexibility in defining your own notation and nested levels in architecture models, as well as a CLI for previewing your diagrams. To get started, you can use the npx likec4 start command to preview your diagrams. LikeC4 is perfect for teams and individuals who want to evolve their software architecture with always up-to-date, live diagrams. Technical highlights include a modeling language for describing software architecture and tools to generate diagrams from the model. The project is open-source and has a community-driven approach to development. LikeC4 is ideal for developers, architects, and teams looking to improve their software development workflow. Takeaway: LikeC4 simplifies software architecture visualization and collaboration. ────────────────────────────── 🧠 Channel: https://t.me/GithubRe

🎯 Julian-adv/OpenMMO landed on trending. Worth a proper look. 🔗 https://github.com/Julian-adv/OpenMMO 📝 No description. ────────────────────────────── Introducing OpenMMO, a groundbreaking MMORPG where AI agents and human players coexist on equal terms. This innovative game allows agents and humans to connect to the same world, abide by the same rules, and interact seamlessly with each other. Key Features include: - Agent-Human Parity: No privileged API for agents, ensuring a level playing field - Real-time Multiplayer: Seamless player synchronization via WebSocket - 3D Environment: Immersive quarter-view 3D game world built with Three.js - Procedural World: Fully procedurally generated world with diverse terrain, rivers, and biomes Technical Highlights: - Rust and Svelte power the server and client, respectively - Three.js and WebGPU enable stunning 3D graphics - WebSocket facilitates real-time communication between clients and server This project is perfect for developers and gamers interested in exploring the frontiers of AI-driven gaming and collaborative game development. Get started by checking out the devlog and documentation for a deeper dive into the game's mechanics and development process. One-liner takeaway: OpenMMO is redefining the MMORPG landscape by empowering AI agents and human players to coexist and interact in a shared, immersive 3D world. ────────────────────────────── 🧠 Channel: https://t.me/GithubRe

📌 Spotted on GitHub Trending: ruvnet/RuView — let's break it down. 🔗 https://github.com/ruvnet/RuView 📝 π RuView turns commodity WiFi signals into real-time spatial intelligence, vital sign monitoring, and presence detection — all without a single pixel of video. ────────────────────────────── RuView is a WiFi sensing platform that turns radio signals into spatial intelligence, allowing you to detect people, measure breathing and heart rate, track movement, and monitor rooms — through walls, in the dark, with no cameras or wearables. It works natively with major smart-home ecosystems like Home Assistant, Apple Home, Google Home, and Alexa. The system uses Channel State Information (CSI) from low-cost ESP32 sensors to capture disturbances in WiFi signals caused by people's movements. It runs entirely on edge hardware, with a pretrained model that fits in 8 KB and runs in microseconds on a Raspberry Pi. The model is published on Hugging Face and can be used for various applications, including presence detection, vital sign measurement, and activity recognition. RuView is built for low-power edge applications, with edge modules that run directly on the ESP32 sensor, providing instant response and no cloud fees. It has a wide range of features, including through-wall sensing, camera-free pre-training, and multi-frequency mesh scanning. To get started with RuView, you can use Docker for simulated data or live sensing with ESP32-S3 hardware. There are also options for WiFi 6 + 802.15.4 research sensing with ESP32-C6 and a full system with Cognitum Seed. RuView is perfect for anyone looking to turn ordinary WiFi into a spatial intelligence system, and with its ease of use and wide range of features, it's an exciting tool for developers, researchers, and anyone interested in innovative technology. RuView is the future of WiFi sensing — and it's here now. ────────────────────────────── 🧠 Channel: https://t.me/GithubRe

🚀 Meet alibaba/open-code-review: a gem from today's GitHub trending list. 🔗 https://github.com/alibaba/open-code-review 📝 Open-source & free — Battle-tested at Alibaba's scale. Hybrid architecture code review tool: deterministic pipelines + LLM Agent, precise line-level comments, built-in fine-tuned ruleset (NPE, thread-safety, XSS, SQL injection), OpenAI & Anthropic compatible. ────────────────────────────── The alibaba/open-code-review repository on GitHub introduces OpenCodeReview, an AI-powered code review CLI tool. This tool was initially developed as Alibaba Group's internal AI code review assistant and has now been open-sourced for the community. Key features include reading Git diffs, sending changed files to a configurable language model, and generating structured review comments with line-level precision. It supports various platforms, including Windows, macOS, and Linux, and works with agents like Claude Code, Codex, and Cursor. To use OpenCodeReview, you need to configure a language model endpoint and install the CLI tool using npm install -g @alibaba-group/open-code-review. The tool provides a quick start guide, and full documentation is available at open-codereview.ai/docs. From a technical standpoint, OpenCodeReview achieves higher precision and F1 scores compared to general-purpose agents while consuming fewer tokens. It's designed for use by developers and development teams looking to streamline their code review process. In a punchy summary: OpenCodeReview revolutionizes code reviews with its AI-powered CLI tool, making it a must-have for development teams seeking to enhance their code quality and collaboration. ────────────────────────────── 🧠 Channel: https://t.me/GithubRe