Available now! Telegram Research 2025 — the year's key insights 
Github Top Repositories
Open in Telegram
Top GitHub repositories in one place 🚀 Explore the best projects in programming, AI, data science, and more.
Show more📈 Analytical overview of Telegram channel Github Top Repositories
Channel Github Top Repositories (@githubre) in the English language segment is an active participant. Currently, the community unites 13 235 subscribers, ranking 15 404 in the Education category and 32 648 in the India region.
📊 Audience metrics and dynamics
Since its creation on невідомо, the project has demonstrated rapid growth, gathering an audience of 13 235 subscribers.
According to the latest data from 07 June, 2026, the channel demonstrates stable activity. Although there has been a change in the number of participants by 344 over the last 30 days and by 12 over the last 24 hours, overall reach remains high.
- Verification status: Not verified
- Engagement rate (ER): The average audience engagement rate is 1.16%. Within the first 24 hours after publication, content typically collects 0.76% reactions from the total number of subscribers.
- Post reach: On average, each post receives 153 views. Within the first day, a publication typically gains 101 views.
- Reactions and interaction: The audience actively supports content: the average number of reactions per post is 1.
- Thematic interests: Content is focused on key topics such as repository, fork, programming, statistic, description.
📝 Description and content policy
The author describes the resource as a platform for expressing subjective opinions:
“Top GitHub repositories in one place 🚀
Explore the best projects in programming, AI, data science, and more.”
Thanks to the high frequency of updates (latest data received on 08 June, 2026), the channel maintains relevance and a high level of publication reach. Analytics show that the audience actively interacts with content, making it an important point of influence in the Education category.
13 235
Subscribers
+1224 hours
+997 days
+34430 days
Posts Archive
13 235
🚀 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
──────────────────────────────
The Anthropic Cybersecurity Skills repository provides a comprehensive library of 754 production-grade cybersecurity skills across 26 security domains. This open-source project aims to equip AI agents with the skills of a senior security analyst, enabling them to perform tasks such as threat hunting, incident response, and vulnerability management.
The repository includes
five framework mappings, including MITRE ATT&CK, NIST CSF 2.0, MITRE ATLAS, MITRE D3FEND, and NIST AI RMF, making it a unique and valuable resource for the cybersecurity community.
To get started, users can clone the repository or use the npx skills add mukul975/Anthropic-Cybersecurity-Skills command. The skills are designed to be used with various AI platforms, including Claude Code, GitHub Copilot, and OpenAI Codex CLI.
The project is not affiliated with Anthropic PBC and is an independent, community-created initiative. The repository is licensed under Apache-2.0 and is open to contributions.
Overall, the Anthropic Cybersecurity Skills repository has the potential to significantly enhance the capabilities of AI agents in the cybersecurity domain, and its open-source nature makes it an exciting development for the community.
Give your AI agent the security skills of a senior analyst — and watch it become a game-changer in cybersecurity.
──────────────────────────────
🧠 Channel: https://t.me/GithubRe
13 235
🚀 Meet affaan-m/ECC: a gem from today's GitHub trending list.
🔗 https://github.com/affaan-m/ECC
📝 The agent harness performance optimization system. Skills, instincts, memory, security, and research-first development for Claude Code, Codex, Opencode, Cursor and beyond.
──────────────────────────────
The ECC (Efficient Computing Companion) repository is a comprehensive system for agentic work, built on top of various AI agent harnesses like Claude Code, Codex, and OpenCode. With over 182K stars and 28K forks, it's a widely-recognized project that's been developed over 10 months of intensive daily use. ECC provides a range of features, including
skills, instincts, memory optimization, continuous learning, and security scanning. The system is production-ready and works across multiple harnesses, making it a versatile tool for developers.
The project is constantly evolving, with new features and updates being added regularly. The most recent version, v2.0.0-rc.1, includes a public surface refresh, operator workflows, and an ECC 2.0 alpha. The system has a large community of contributors and users, with over 170 contributors and 12 language ecosystems supported.
Whether you're a developer, researcher, or simply interested in AI, ECC is definitely worth checking out. With its comprehensive guides and extensive documentation, you'll be able to get started quickly and easily. So why wait? Dive into the world of ECC today and discover the power of efficient computing companions.
The ECC repository is a one-stop-shop for all your agentic work needs - it's the ultimate tool for anyone looking to streamline their workflow and boost productivity.
──────────────────────────────
🧠 Channel: https://t.me/GithubRe
13 235
💡 rohitg00/ai-engineering-from-scratch just hit the trending charts — here's why it matters.
🔗 https://github.com/rohitg00/ai-engineering-from-scratch
📝 Learn it. Build it. Ship it for others.
──────────────────────────────
The GitHub repository rohitg00/ai-engineering-from-scratch is a comprehensive, open-source curriculum designed to teach AI engineering from scratch. The purpose of this repository is to provide a structured approach to learning AI, covering 20 phases and 435 lessons that span ~320 hours of content.
Key features of this curriculum include its focus on building AI systems from raw math, using languages like
Python, TypeScript, Rust, and Julia. Each lesson follows a consistent structure, starting with the problem, deriving the math, writing the code, running the test, and keeping the resulting artifact.
The curriculum is designed for individuals who want to understand how AI actually works, not just call APIs. It's suitable for those who can write code in any language, with some familiarity with Python being helpful.
To get started, users can choose from three options: reading completed lessons on the website, cloning and running the repository, or finding their level using a placement quiz.
Every lesson ships with a reusable tool, such as prompts, skills, agents, or MCP servers, which can be installed or pasted into daily workflows.
The takeaway: Master AI engineering by building it from scratch, and become a part of a community that's shaping the future of artificial intelligence.
──────────────────────────────
🧠 Channel: https://t.me/GithubRe13 235
🎯 anthropics/knowledge-work-plugins landed on trending. Worth a proper look.
🔗 https://github.com/anthropics/knowledge-work-plugins
📝 Open source repository of plugins primarily intended for knowledge workers to use in Claude Cowork
──────────────────────────────
The anthropics/knowledge-work-plugins GitHub repository offers a collection of plugins designed to enhance Claude's capabilities, making it a specialist for various roles, teams, and companies. These plugins are compatible with Claude Cowork and Claude Code, allowing users to customize how work is done, which tools to use, and how to handle critical workflows.
The repository includes
11 open-sourced plugins, each catering to a specific job function, such as productivity, sales, customer-support, and more. These plugins bundle skills, connectors, slash commands, and sub-agents, providing a strong starting point for Claude to assist users in their respective roles.
To get started, users can install plugins directly from Claude Cowork or Claude Code using the following command:
claude plugin install sales@knowledge-work-pluginsplugin.json manifest, .mcp.json tool connections, commands directory, and skills directory. The plugins are file-based, using markdown and JSON, and require no coding, infrastructure, or build steps.
The true power of these plugins lies in their customizability. Users can modify the plugins to fit their company's specific tools, terminology, and processes, making Claude an integral part of their team. By contributing to the repository, users can also share their custom plugins and help others benefit from their expertise.
In summary, the anthropics/knowledge-work-plugins repository offers a powerful way to enhance Claude's capabilities, making it an indispensable tool for teams and companies - and with customization, Claude becomes a specialist that understands your world.
──────────────────────────────
🧠 Channel: https://t.me/GithubRe13 235
💡 Lum1104/Understand-Anything just hit the trending charts — here's why it matters.
🔗 https://github.com/Lum1104/Understand-Anything
📝 Graphs that teach > graphs that impress. Turn any code into an interactive knowledge graph you can explore, search, and ask questions about. Works with Claude Code, Codex, Cursor, Copilot, Gemini CLI, and more.
──────────────────────────────
Understand Anything is an innovative tool that turns any codebase, knowledge base, or documentation into an interactive knowledge graph. This graph can be explored, searched, and questioned, making it easier to understand complex systems. The tool works with various platforms, including Claude Code, Codex, Cursor, Copilot, and Gemini CLI.
Key features include:
-
Interactive knowledge graph: visualize your codebase as a graph, with every file, function, and class as a node that can be clicked, searched, and explored.
- Guided tours: auto-generated walkthroughs of the architecture, ordered by dependency.
- Fuzzy and semantic search: find anything by name or meaning.
- Diff impact analysis: see which parts of the system your changes affect before you commit.
Technical highlights:
- Multi-agent pipeline: analyzes your project and builds a knowledge graph.
- Tree-sitter + LLM hybrid: combines static analysis and LLMs for parsing and semantic analysis.
Audience: developers, teams, and organizations looking to improve their understanding of complex codebases and knowledge bases.
To get started, simply install the plugin and analyze your codebase. Then, explore the dashboard and start gaining insights into your system.
Understand Anything is a game-changer for anyone looking to simplify complex systems and improve their productivity. Try it out and start understanding anything!
──────────────────────────────
🧠 Channel: https://t.me/GithubRe
13 235
Turn Simple Tasks Into Rewards
Rozcash
Watch, play, complete tasks, and redeem rewards easily.
Ad. 18+
13 235
⚡ mukul975/Anthropic-Cybersecurity-Skills is making waves. Here's the full picture.
🔗 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
──────────────────────────────
The Anthropic Cybersecurity Skills repository on GitHub is a comprehensive library of 754 production-grade cybersecurity skills that can be integrated into AI agents to enhance their security capabilities. The skills are organized into 26 security domains and are mapped to five industry frameworks, including MITRE ATT&CK, NIST CSF 2.0, MITRE ATLAS, MITRE D3FEND, and NIST AI RMF.
To get started, users can clone the repository or use
npx skills add mukul975/Anthropic-Cybersecurity-Skills to immediately work with the skills. The repository is designed to be compatible with various AI platforms, including Claude Code, GitHub Copilot, and OpenAI Codex CLI.
The skills are structured to provide AI agents with the decision-making workflows that a senior security analyst would use, including when to use each technique, what prerequisites to check, and how to execute and verify results. Each skill is composed of a SKILL.md file, references directory, scripts directory, and assets directory.
The target audience for this repository includes security professionals, developers, and enterprise teams looking to enhance the security capabilities of their AI agents. By using this repository, users can give their AI agents the security skills of a senior analyst, enabling them to perform tasks such as threat hunting, incident response, and vulnerability management.
In summary, the Anthropic Cybersecurity Skills repository is a valuable resource for anyone looking to enhance the security capabilities of their AI agents, and with it, you can turn your AI into a cybersecurity powerhouse.
──────────────────────────────
🧠 Channel: https://t.me/GithubRe13 235
🌟 blakeblackshear/frigate caught my eye on GitHub Trending today.
🔗 https://github.com/blakeblackshear/frigate
📝 NVR with realtime local object detection for IP cameras
──────────────────────────────
The Frigate NVR is a complete and local NVR designed for Home Assistant with AI object detection. It uses
OpenCV and Tensorflow to perform real-time object detection locally for IP cameras.
Key features include tight integration with Home Assistant via a custom component, low overhead motion detection, and object detection with TensorFlow in separate processes for maximum FPS.
The system is designed to minimize resource use and maximize performance, making it suitable for users who want a powerful yet efficient NVR system.
To get started, users can view the documentation at https://docs.frigate.video and explore the supported object detectors.
This project is licensed under the MIT License, and donations can be made via Github Sponsors to support development.
Frigate NVR is perfect for those looking for a robust and feature-rich NVR system with AI object detection.
Takeaway: Frigate NVR brings AI-powered surveillance to your doorstep with real-time object detection and seamless integration with Home Assistant.
──────────────────────────────
🧠 Channel: https://t.me/GithubRe
13 235
I just leaked the YES/NO markets insiders are using 🤫🟢
Get in, pick a side, and let the crowd show its hand.
➡️ Unlock the markets
#ad 📢 InsideAd
13 235
🔍 Deep-diving into dotnet/skills — fresh off the trending list.
🔗 https://github.com/dotnet/skills
📝 Repository for skills to assist AI coding agents with .NET and C#
──────────────────────────────
The dotnet/skills repository is a treasure trove of curated core skills and custom agents for coding agents, focusing on .NET development. This project provides a wide range of plugins, including
dotnet, dotnet-data, dotnet-diag, and more, each catering to specific .NET-related tasks such as data access, performance investigations, and build skills.
To get started, you can install plugins using the Copilot CLI or Claude Code with commands like /plugin install <plugin>@dotnet-agent-skills, or use VS Code with the chat.plugins.enabled setting. You can also use the Codex CLI to install individual skills with skill-installer install https://github.com/dotnet/skills/tree/main/plugins/<plugin>/skills/<skill-name>.
This repository is perfect for .NET developers looking to streamline their workflow and leverage the power of AI-powered coding assistants. With its open-standard skills and compatible plugins, the dotnet/skills repository is an invaluable resource for anyone working with .NET technologies.
Takeaway: The dotnet/skills repository is your one-stop-shop for unlocking the full potential of .NET development with AI-powered coding assistants!
──────────────────────────────
🧠 Channel: https://t.me/GithubRe13 235
⚡ codecrafters-io/build-your-own-x is making waves. Here's the full picture.
🔗 https://github.com/codecrafters-io/build-your-own-x
📝 Master programming by recreating your favorite technologies from scratch.
──────────────────────────────
Imagine being able to create your own technology from scratch. The
codecrafters-io/build-your-own-x GitHub repository is a collection of guides and tutorials that allow you to do just that. With a wide range of topics, including 3D renderers, AI models, blockchains, and more, you can learn to build your own technologies and gain a deeper understanding of how they work.
The repository includes tutorials and code examples in various programming languages, such as C++, Java, Python, and JavaScript, making it accessible to developers of all levels. Whether you're interested in building a database, a bot, or a command-line tool, this repository has something for everyone.
The key features of this repository include its comprehensive guides, step-by-step tutorials, and community-driven approach. The technical highlights of the repository include its use of various programming languages and real-world examples.
The intended audience for this repository includes developers, students, and anyone interested in building their own technologies.
Build, learn, and have fun with the codecrafters-io/build-your-own-x repository - what you cannot create, you do not understand.
──────────────────────────────
🧠 Channel: https://t.me/GithubRe13 235
💡 666ghj/MiroFish just hit the trending charts — here's why it matters.
🔗 https://github.com/666ghj/MiroFish
📝 A Simple and Universal Swarm Intelligence Engine, Predicting Anything. 简洁通用的群体智能引擎，预测万物
──────────────────────────────
The MiroFish GitHub repository presents a next-generation AI prediction engine that utilizes multi-agent technology to create a high-fidelity parallel digital world. This world is populated by thousands of intelligent agents that interact and evolve, allowing for precise deductions of future trajectories. The engine can be used for various applications, including financial prediction and political news prediction.
Key features of MiroFish include its ability to extract seed information from the real world, construct a digital world, and simulate social evolution. Users can inject variables dynamically and receive a detailed prediction report. The engine is powered by
OASIS (Open Agent Social Interaction Simulations) and has received strategic support from Shanda Group.
To use MiroFish, users can deploy it from source code or via Docker. The repository provides a quick start guide that outlines the prerequisites, environment setup, and installation of dependencies. Users can also join the conversation and contribute to the project.
The target audience for MiroFish includes decision-makers, researchers, and individuals interested in multi-agent simulation and LLM applications. With its capabilities, MiroFish can be used as a rehearsal laboratory for testing policies and public relations, as well as a creative sandbox for exploring imaginative scenarios.
In summary, MiroFish is a powerful tool for predicting anything, and its applications are vast - rehearse the future in a digital sandbox, and win decisions after countless simulations.
──────────────────────────────
🧠 Channel: https://t.me/GithubRe
13 235
🎯 manaflow-ai/cmux landed on trending. Worth a proper look.
🔗 https://github.com/manaflow-ai/cmux
📝 Ghostty-based macOS terminal with vertical tabs and notifications for AI coding agents
──────────────────────────────
cmux is a Ghostty-based macOS terminal that streamlines your coding workflow with features like vertical tabs, notifications, and an in-app browser. Key features include notification rings, a notification panel, in-app browser, vertical and horizontal tabs, SSH support, and Claude Code Teams integration.
To get started with
cmux, you can download the DMG file from the GitHub releases page or install it using Homebrew with brew tap manaflow-ai/cmux and brew install --cask cmux.
Technical highlights of cmux include its native macOS app built with Swift and AppKit, GPU-accelerated rendering, and scriptable CLI and socket API. cmux is designed for developers who want a customizable and efficient coding workflow, and its target audience includes anyone looking for a powerful terminal replacement.
cmux is a primitive, not a solution - it provides a set of building blocks for you to create your own workflow. With its cmux.json configuration file, you can define custom commands and automate your workflow.
In short, cmux is a game-changer for coding workflows - it's not just a terminal, it's a launchpad for your coding productivity.
──────────────────────────────
🧠 Channel: https://t.me/GithubRe
