Github Top Repositories

🎯 semantica-agi/semantica landed on trending. Worth a proper look. 🔗 https://github.com/semantica-agi/semantica 📝 Graph-Native Infrastructure for Context and Accountable AI Systems ────────────────────────────── Semantica is an open-source, graph-native infrastructure for building context and accountable AI systems. It's designed to ingest enterprise data, extract relevant information, and construct a knowledge graph with full decision provenance. Key features include polyglot graph storage, RDF and LPG support, W3C standards, and interoperability. Technical highlights involve a deterministic reasoning engine, conflict detection, and ontology management. The platform is suitable for high-stakes, regulated domains such as finance, healthcare, and government. To get started, simply run pip install semantica and explore the ContextGraph class. The platform is ideal for AI/ML platform teams, data platform teams, compliance and audit teams, and regulated enterprises. In a nutshell, Semantica is the missing link between your AI agents and the context they need to make trustworthy decisions: use it to explain, to comply, and to trust your AI. ────────────────────────────── 🧠 Channel: https://t.me/GithubRe

⚡ deepseek-ai/awesome-deepseek-agent is making waves. Here's the full picture. 🔗 https://github.com/deepseek-ai/awesome-deepseek-agent 📝 No description. ────────────────────────────── The Awesome DeepSeek Agent repo is a treasure trove of guides for integrating DeepSeek models into popular AI agent and coding-assistant tools. With over 20 tools supported, including AstrBot, Cherry Studio, and GitHub Copilot, you can easily get started with DeepSeek-V4-Pro or DeepSeek-V4-Flash in your favorite tool. The guides cover installation, configuration, and first run, making it easy to start using these powerful models in just a few minutes. Whether you're a developer or an AI enthusiast, this repo is a must-visit. Here's a sneak peek at the code:

div align="center">

The repo also provides resources for getting an API key and accessing API documentation. So, what are you waiting for? Dive into the world of DeepSeek and unlock the full potential of AI-powered coding assistants - DeepSeek is the key to unlocking AI-powered coding mastery! ────────────────────────────── 🧠 Channel: https://t.me/GithubRe

🌟 cursor/plugins caught my eye on GitHub Trending today. 🔗 https://github.com/cursor/plugins 📝 Cursor plugin specification and official plugins ────────────────────────────── The Cursor plugins repository is a collection of official plugins for various developer tools, frameworks, and SaaS products. These plugins are designed to extend the functionality of the Cursor platform, providing a range of features such as incremental learning, team workflows, and security audits. Key features of the repository include a wide range of plugins, each with its own manifest and directory, making it easy to manage and install them. The plugins are categorized into different groups, including Developer Tools, Productivity, and Integrations, making it easy to find the one that suits your needs. To use these plugins, you can simply navigate to the repository, find the plugin you need, and follow the installation instructions. Each plugin has its own README.md file, which provides detailed information on how to install and use it. From a technical perspective, the repository is well-structured, with each plugin having its own directory and manifest file. The plugins are built using a variety of technologies, including JavaScript and TypeScript, and are designed to be highly customizable. The repository is suitable for a wide range of audiences, including developers, DevOps teams, and businesses looking to extend the functionality of their Cursor platform. In summary, the Cursor plugins repository is a valuable resource for anyone looking to extend the functionality of their Cursor platform. With its wide range of plugins, easy-to-use interface, and well-structured repository, it's a great place to start for anyone looking to get the most out of their Cursor experience. You can supercharge your development workflow with these plugins - get started now! ────────────────────────────── 🧠 Channel: https://t.me/GithubRe

🚀 Meet infiniflow/ragflow: a gem from today's GitHub trending list. 🔗 https://github.com/infiniflow/ragflow 📝 RAGFlow is a leading open-source Retrieval-Augmented Generation (RAG) engine that fuses cutting-edge RAG with Agent capabilities to create a superior context layer for LLMs ────────────────────────────── RAGFlow is a cutting-edge, open-source Retrieval-Augmented Generation (RAG) engine that offers a streamlined workflow for creating high-fidelity AI systems. With its converged context engine and pre-built agent templates, RAGFlow enables developers to transform complex data into production-ready AI systems with exceptional efficiency and precision. Key features include deep document understanding, template-based chunking, and grounded citations with reduced hallucinations. The system supports heterogeneous data sources and offers automated and effortless RAG workflow. To get started, users can try the cloud service or self-host the system using docker compose. The system architecture is designed for scalability and flexibility, with a configurable LLM and embedding models. The target audience for RAGFlow includes developers, data scientists, and businesses looking to create high-fidelity AI systems. With its intuitive APIs and streamlined workflow, RAGFlow is an ideal solution for those looking to leverage the power of RAG technology. In short, RAGFlow is a game-changer for AI development, and its ability to fuse cutting-edge RAG with agent capabilities makes it a must-try for anyone looking to create superior context layers for LLMs: Transform your data into intelligent AI systems with RAGFlow - the future of AI is here! ────────────────────────────── 🧠 Channel: https://t.me/GithubRe

🔍 Deep-diving into lightningpixel/modly — fresh off the trending list. 🔗 https://github.com/lightningpixel/modly 📝 Desktop app to generate 3D models from images using local AI — runs entirely on your GPU ────────────────────────────── Modly is a groundbreaking, open-source, AI-powered image-to-3D mesh generation tool that runs entirely on your GPU. This innovative desktop application is available for Windows, Linux, and Apple Silicon macOS. To get started with Modly, you can download the latest installer from the Releases page or clone the repository and run it directly. The application has a user-friendly interface that allows you to turn any photo into a 3D model. One of the key features of Modly is its extension system, which supports external model and process extensions. You can install extensions from GitHub repositories, and each extension includes a manifest.json file and the required runtime entry files. Modly also has a command-line interface (CLI) that allows agents and scripts to interact with the application without using the UI. The CLI provides a range of commands, including health, model, and workflow-run, which can be used to automate tasks and integrate Modly with other tools. The application is designed for developers, 3D artists, and anyone interested in AI-powered 3D modeling. With its MIT License, Modly is free to use and modify, making it an excellent choice for open-source enthusiasts. Overall, Modly is a powerful tool that can revolutionize the way you create 3D models. With its ease of use, flexibility, and customizability, Modly is an excellent choice for anyone looking to explore the world of AI-powered 3D modeling. Modly - Revolutionizing 3D modeling, one image at a time! ────────────────────────────── 🧠 Channel: https://t.me/GithubRe

🎯 github/spec-kit landed on trending. Worth a proper look. 🔗 https://github.com/github/spec-kit 📝 💫 Toolkit to help you get started with Spec-Driven Development ────────────────────────────── Spec Kit is an open-source toolkit that helps you build high-quality software with any AI coding agent. It flips the script on traditional development by making specifications executable, generating working implementations directly. Key features include: - specify init to initialize a project - /speckit.constitution to create project principles - /speckit.specify to define what you want to build - /speckit.plan to choose your tech stack - /speckit.tasks to generate actionable tasks - /speckit.implement to execute tasks and build your feature It's endlessly extensible with extensions and presets, and has a community-driven approach with contributed resources. The toolkit supports 30+ AI coding agents and has a Specify CLI for easy usage. Spec Kit is perfect for developers who want to define what to build before building it, and is suitable for whole organizations. One-liner takeaway: With Spec Kit, you can build high-quality software faster by making your specifications executable. ────────────────────────────── 🧠 Channel: https://t.me/GithubRe

Holy fucccccccck 🙀🤯😱🥱 Boom 💥 💥 💥 💥 $MEXICANUNC just printed me with massive profit My early entry on $MEXICANUNC turn my $600 to $323k in less 48 hours Not luck — timing, discipline, and the right network. Want early setups before they move? 👇 JOIN MY CHANNEL 👇 https://t.me/+40JBSSZtksdhNWM0 #ad 📢 InsideAd

🔥 holaboss-ai/holaOS is trending — and it deserves your attention. 🔗 https://github.com/holaboss-ai/holaOS 📝 Open-source All in One AI agent workspace. Run any agent — Claude Code, Codex — across your tools (100+ integrations + MCP), apps, browser, and files, with shared memory. Built-in models or BYOK. ────────────────────────────── Introducing holaOS, the ultimate workspace for you and your agent. This innovative platform allows you to run any agent, including Claude Code, Codex, or the built-in holaOS agent, in one local-first workspace. With holaOS, you can share the same memory, tools, and skills across different agents, ensuring consistent results and eliminating the need to rebuild your setup every time. Key Features: - Run any agent in one workspace - Shared memory and tools across agents - Local-first approach with editable files - Built-in frontier models with option to bring your own keys - HolaApps for interactive surfaces and agent-driven apps Technical Highlights: - Electron desktop app - TypeScript runtime - Modified Apache 2.0 license Audience: - Developers looking for a flexible and efficient workspace - Users who want to leverage the power of AI agents - Anyone interested in a local-first approach with editable files To get started, you can use the One-Line Install script or follow the manual installation steps. With holaOS, you can unlock the full potential of your agents and workflow. So, what are you waiting for? Upgrade your workflow with holaOS today and experience the future of productivity! ────────────────────────────── 🧠 Channel: https://t.me/GithubRe

🚀 Meet citrolabs/ego-lite: a gem from today's GitHub trending list. 🔗 https://github.com/citrolabs/ego-lite 📝 The fastest browser for AI agents to run browser automation, built for sharing your logged-in browser state with your AI agents, like Codex or Claude Code, without disturbing you. Zero cost, zero config. ────────────────────────────── Check out ego lite, the browser designed for humans and AI agents to work together seamlessly. Its key features include a dedicated Space for each agent, allowing for parallel work and multitasking, as well as a strong page Snapshot capability. To get started, you can download the macOS app or add the ego-browser skill with npx. Some technical highlights of ego lite are its code base approach, which enables faster runs with fewer tokens, and its ability to be driven by any agent through the ego-browser connection layer. The browser also offers experience accumulation, making your agent faster over time. Target audience includes developers and users who want to automate browser tasks with their AI agents. Whether you're using Claude Code, Codex, or a custom agent, ego lite provides a unified platform for you to work together efficiently. In a nutshell, ego lite is all about smarter browser automation - and the best part? It's free! So why wait? Dive into ego lite and discover a new way to work with your AI agents. With ego lite, you can automate your workflow and make your life easier - it's a game-changer! ────────────────────────────── 🧠 Channel: https://t.me/GithubRe

🔍 Deep-diving into smicallef/spiderfoot — fresh off the trending list. 🔗 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 numerous data sources and utilizes various methods for data analysis. It offers a web-based UI or CLI, over 200 modules, and supports Python 3.7+. Key features include a correlation engine, CSV/JSON/GEXF export, and TOR integration for dark web searching. Usage includes reconnaissance for red team exercises or penetration tests, and defensive scans to gather information about exposed Internet-facing assets. Technical highlights include a SQLite back-end for custom querying and a Dockerfile for Docker-based deployments. The tool is ideal for security professionals, researchers, and organizations seeking to automate OSINT tasks. With its highly configurable and fully documented architecture, SpiderFoot is a powerful tool for anyone looking to streamline their OSINT workflow. In short, SpiderFoot is a game-changer for OSINT - automate your reconnaissance with SpiderFoot and uncover the secrets you need. ────────────────────────────── 🧠 Channel: https://t.me/GithubRe

🎯 macro-inc/macro landed on trending. Worth a proper look. 🔗 https://github.com/macro-inc/macro 📝 Macro is a unified workspace for teams: email, chat, docs, tasks, agents, calls, and CRM — @-linked together with shared AI memory. ────────────────────────────── Macro is an all-in-one workspace designed for teams, unifying email, messages, docs, tasks, and CRM into a single, fast interface. The platform is built around blocks that are modular, extensible, and work together seamlessly. With features like multi-account unified inbox, channels and direct messages, linear-inspired tasks, real-time collaborative docs, and a built-in CRM, Macro aims to be the operating system for your team. The platform is designed to be highly customizable, with a focus on speed and reliability, built using SolidJS and Rust. Macro's key features include: - A bidirectional graph that stores cross-references between different blocks, allowing for seamless navigation and search. - A unified search tool that enables agents to search all file attachment PDFs directly. - A built-in window manager that lets you create multiple splits, allowing for easy multitasking. Macro is perfect for small companies or teams within larger companies looking for an integrated workspace. With its modular design and extensive documentation, Macro is an ideal solution for teams seeking to streamline their workflow. One-liner takeaway: Macro is the ultimate team operating system, where everything is linked and searchable, making it the perfect solution for teams looking to boost productivity and collaboration! ────────────────────────────── 🧠 Channel: https://t.me/GithubRe

💡 megadose/holehe just hit the trending charts — here's why it matters. 🔗 https://github.com/megadose/holehe 📝 holehe allows you to check if the mail is used on different sites like twitter, instagram and will retrieve information on sites with the forgotten password function. ────────────────────────────── The Holehe GitHub repository is a powerful Open-Source Intelligence (OSINT) tool that helps you find registered accounts from email addresses. It checks over 120 websites, including social media platforms like Twitter and Instagram, without alerting the target email. Key features include: - Retrieves information using the forgotten password function - Runs on Python 3 - Can be installed via pip3 install holehe, git clone, or docker build Usage examples are provided in the README, including a CLI Example:

holehe test@gmail.com

and a Python Example:

import trio
import httpx
from holehe.modules.social_media.snapchat import snapchat

async def main():
    email = "test@gmail.com"
    out = []
    client = httpx.AsyncClient()

    await snapchat(email, client, out)

    print(out)
    await client.aclose()

trio.run(main)

Technical highlights include: - Module output in a standard dictionary format - rateLimit, exists, emailrecovery, phoneNumber, and others data fields This tool is designed for OSINT professionals, security researchers, and developers who need to identify registered accounts for email addresses. One-liner takeaway: Holehe is a game-changer for OSINT, instantly revealing which online accounts are tied to an email address. ────────────────────────────── 🧠 Channel: https://t.me/GithubRe

📌 Spotted on GitHub Trending: cactus-compute/needle — let's break it down. 🔗 https://github.com/cactus-compute/needle 📝 14MB foundation model for tiny devices; phones, wearables, smart home, and robots. ────────────────────────────── Let's break down the Needle GitHub repository. Needle 2 is an open, 45M-parameter model designed for tool calling, device use, and structured extraction. It's built on the Simple Attention Network and is remarkably compact, with the entire model weighing in at just 14MB. Key features include being self-contained, with weights baked into the engine, a simple contract for tool calls, confidence-gated responses, tool retrieval, and bounded memory usage. To get started, you can pip install cactus-needle and describe your tools to integrate them into the model. The repository includes a playground for trying out the model in the browser and fine-tuning capabilities with LoRA. The model is suitable for developers and researchers looking for a lightweight,yet powerful tool for natural language processing tasks. One-liner takeaway: Needle 2 packs a punch as a compact, 45M-parameter model for tool calling and structured extraction, perfect for tiny devices and memory-constrained applications. ────────────────────────────── 🧠 Channel: https://t.me/GithubRe