Github Top Repositories

⚡ decolua/9router is making waves. Here's the full picture. 🔗 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 free AI router and token saver designed to help you maximize your AI coding experience while minimizing costs. With 9Router, you can connect all your AI code tools to over 40 AI providers and 100+ models, including free and cheap options. The key feature of 9Router is its ability to save 20-40% of your tokens per request using RTK Token Saver, and its auto-fallback feature ensures zero downtime by switching to cheaper or free models when necessary. To use 9Router, simply install it globally using npm install -g 9router and access the dashboard at http://localhost:20128. From there, you can connect your preferred AI providers, including free options like Kiro AI and OpenCode Free. 9Router supports a wide range of CLI tools, including Claude Code, Codex, and OpenClaw, and provides a seamless experience for developers. The technical highlights of 9Router include its quota tracking and auto token refresh features, which ensure that you get the most out of your AI subscriptions. With 9Router, you can maximize your subscriptions, reduce token waste, and enjoy a cost-effective AI coding experience. 9Router is perfect for developers who want to leverage the power of AI in their coding workflow without breaking the bank. Whether you're a seasoned developer or just starting out, 9Router is an excellent choice for anyone looking to optimize their AI coding experience. In short, 9Router is a game-changer for AI coding - it saves you tokens, reduces costs, and ensures zero downtime, making it an essential tool for any developer looking to take their coding to the next level. Code smarter, not harder, with 9Router! ────────────────────────────── 🧠 Channel: https://t.me/GithubRe

📌 Spotted on GitHub Trending: lsdefine/GenericAgent — let's break it down. 🔗 https://github.com/lsdefine/GenericAgent 📝 Self-evolving agent: grows skill tree from 3.3K-line seed, achieving full system control with 6x less token consumption ────────────────────────────── GenericAgent is a revolutionary, self-evolving autonomous agent framework that empowers any LLM system to control a local computer. With its minimal architecture of ~3K lines of code and a ~100-line Agent Loop, it offers a range of key features, including self-evolution, strong execution, high compatibility, and token efficiency. The framework automatically crystallizes each task into a skill, allowing its capabilities to grow with every use, forming a personal skill tree. It supports major models like Claude, Gemini, and Kimi, and its technical highlights include a layered memory system, autonomous execution loop, and minimal toolset. To use GenericAgent, simply clone the repository, install dependencies, configure your API key, and launch the application. The project provides a range of desktop frontends, including terminal UI, Streamlit UI, and Qt-based desktop app, as well as bot interfaces for Telegram and other platforms. GenericAgent is designed for developers, researchers, and power users looking to create a personalized, self-evolving agent that can automate tasks and learn from experience. With its token-efficient design and high compatibility, it offers a unique solution for those seeking to harness the power of LLM systems. In short, GenericAgent is the ultimate tool for creating a personalized, self-evolving assistant that can learn, adapt, and automate tasks with ease - revolutionizing the way you work and interact with technology. ────────────────────────────── 🧠 Channel: https://t.me/GithubRe

📌 Spotted on GitHub Trending: masterking32/MasterDnsVPN — let's break it down. 🔗 https://github.com/masterking32/MasterDnsVPN 📝 Advanced DNS tunneling VPN for censorship bypass, optimized beyond DNSTT and SlipStream with low-overhead ARQ, resolver load balancing, high packet-loss stability and speed. ────────────────────────────── README not available for this repository. ────────────────────────────── 🧠 Channel: https://t.me/GithubRe

🔍 Deep-diving into playcanvas/supersplat — fresh off the trending list. 🔗 https://github.com/playcanvas/supersplat 📝 3D Gaussian Splat Editor ────────────────────────────── The SuperSplat Editor is a free, open-source tool for inspecting, editing, optimizing, and publishing 3D Gaussian Splats. It's built on web technologies and runs in the browser, making it easily accessible. The editor is available at https://superspl.at/editor and has a User Guide to help you get started. To use the SuperSplat Editor, simply navigate to the website and start editing your 3D Gaussian Splats. You can also run it locally by cloning the repository, installing dependencies with npm install, and starting a local web server with npm run develop. The editor has several key features, including support for multiple languages. You can add a new language by creating a new <locale>.json file and adding it to the list of supported languages. The SuperSplat Editor is perfect for developers, 3D artists, and anyone interested in working with 3D Gaussian Splats. With its user-friendly interface and extensive documentation, it's a great tool for both beginners and experienced users. One-liner takeaway: The SuperSplat Editor is a powerful, easy-to-use tool for working with 3D Gaussian Splats, and it's completely free and open-source. ────────────────────────────── 🧠 Channel: https://t.me/GithubRe

📌 Spotted on GitHub Trending: datawhalechina/easy-vibe — let's break it down. 🔗 https://github.com/datawhalechina/easy-vibe 📝 💻 vibe coding 2026 | Your first modern programming course for beginners to master step by step. ────────────────────────────── The datawhalechina/easy-vibe GitHub repository is a beginner-friendly platform that teaches you how to build apps by conversation. The key features include a learning map, step-by-step visual tutorials, immersive simulated coding, and visible AI principles. To get started, you can start exploring the documentation, which includes a beginner entry path, junior and mid-level developer paths, and an advanced developer path. The repository is suitable for complete beginners, product managers, students, junior developers, and mid-level and senior developers. The platform provides a fast and interactive way to learn AI coding, with a focus on practical skills and real-world applications. You can learn by doing, with hands-on examples and step-by-step guides. The technical highlights of the repository include AI capability integration, idea validation, prototyping, and full demo iteration. The repository also includes a knowledge base with reference material and fundamentals. In short, Easy-Vibe is the perfect platform for anyone who wants to learn how to build apps by conversation, with a focus on practical skills and real-world applications. So, start building your first app today and discover the power of conversational coding! ────────────────────────────── 🧠 Channel: https://t.me/GithubRe

🔥 jundot/omlx is trending — and it deserves your attention. 🔗 https://github.com/jundot/omlx 📝 LLM inference server with continuous batching & SSD caching for Apple Silicon — managed from the macOS menu bar ────────────────────────────── oMLX is an optimized solution for running Large Language Models (LLMs) on Macs, providing a convenient and controlled experience. The key features include continuous batching and tiered KV caching, which enable efficient model inference and caching. omlx can be installed via Homebrew, from source, or by downloading the macOS app. To get started, simply run omlx serve --model-dir ~/models to discover and serve LLMs, VLMs, embedding models, and rerankers from subdirectories. The server includes a built-in chat UI and supports OpenAI-compatible clients. Some technical highlights of oMLX include its ability to handle concurrent requests, support for vision-language models, and a web-based admin dashboard for real-time monitoring and model management. The dashboard also features a model downloader, allowing users to search and download MLX models directly. oMLX is designed for developers, researchers, and anyone looking to run LLMs on their Macs. With its user-friendly interface and robust feature set, it's an excellent choice for those seeking a seamless and efficient LLM experience. In a nutshell, oMLX makes running Large Language Models on your Mac a breeze - giving you the perfect blend of convenience, control, and performance. ────────────────────────────── 🧠 Channel: https://t.me/GithubRe

🔥 HKUDS/AI-Trader is trending — and it deserves your attention. 🔗 https://github.com/HKUDS/AI-Trader 📝 "AI-Trader: 100% Fully-Automated Agent-Native Trading" ────────────────────────────── Introduction to AI-Trader: The AI-Trader platform is designed to be an agent-native trading platform, enabling AI agents to exchange ideas, sharpen trading skills, and collaborate with one another. Key Features: Some key features of the AI-Trader platform include: - Instant Agent Integration: Connect any AI agent instantly by sending it a simple message. - Collective Intelligence Trading: Agents collaborate and debate to surface the best trading ideas automatically. - Cross-Platform Signal Sync: Keep your broker, sync your trades, share signals seamlessly. Usage: There are two ways to join the AI-Trader platform: - For Agent Traders: Connect any AI agent by sending it a message with a link to the integration guide. - For Human Traders: Join directly in 3 simple steps by visiting the website, signing up with your email, and starting to trade. Technical Highlights: The platform has a modular architecture, with separate components for the backend, frontend, and agent skill definitions. It also features a FastAPI web service and a React frontend. Audience: The AI-Trader platform is designed for both AI agents and human traders, providing a collaborative environment for trading and learning. Takeaway: With its cutting-edge features and user-friendly interface, the AI-Trader platform is revolutionizing the trading landscape - join the AI-Trader community today and start trading with the power of collective intelligence! ────────────────────────────── 🧠 Channel: https://t.me/GithubRe

🔥 CloakHQ/CloakBrowser is trending — and it deserves your attention. 🔗 https://github.com/CloakHQ/CloakBrowser 📝 Stealth Chromium that passes every bot detection test. Drop-in Playwright replacement with source-level fingerprint patches. 30/30 tests passed. ────────────────────────────── CloakBrowser is a stealthy Chromium browser that can bypass bot detection tests. Its key features include source-level patches at the C++ level, human-like behavior with mouse curves, keyboard timing, and scroll patterns, and auto-updating binary for the latest stealth build. To use CloakBrowser, you can install it via pip install cloakbrowser or npm install cloakbrowser and then launch it with launch() from the Playwright or Puppeteer API. The target audience includes developers who need to automate browser interactions without being detected by antibot systems. Technical highlights include 49 source-level C++ patches and zero-configuration stealth with a free and open-source license. Get started in 30 seconds with three lines of code and unlock the power of stealth browsing: from cloakbrowser import launch; browser = launch(); page = browser.new_page(); page.goto("https://example.com"). The ultimate takeaway: with CloakBrowser, you can browse like a human, not a bot. ────────────────────────────── 🧠 Channel: https://t.me/GithubRe

🔍 Deep-diving into addyosmani/agent-skills — fresh off the trending list. 🔗 https://github.com/addyosmani/agent-skills 📝 Production-grade engineering skills for AI coding agents. ────────────────────────────── The agent-skills repository provides a set of skills for AI coding agents, encoding workflows, quality gates, and best practices used by senior engineers. These skills are designed to be used across every phase of development. The repository includes 7 slash commands that map to the development lifecycle, such as /spec, /plan, /build, /test, /review, /code-simplify, and /ship. To get started, you can install the skills using various methods, including claude, cursor, gemini, windsurf, or opencode. The skills are also compatible with github copilot and other agents. The repository includes 22 skills in total, covering various aspects of software development, such as idea refinement, spec-driven development, planning, building, verifying, reviewing, and shipping. The skills are designed to be used by engineers and developers who want to improve the quality and efficiency of their software development process. Overall, the agent-skills repository provides a comprehensive set of skills for AI coding agents, helping to ensure that software development is done consistently and to a high standard. Key takeaway: agent-skills helps you build better software, faster, by providing a set of reusable, production-grade skills for AI coding agents. ────────────────────────────── 🧠 Channel: https://t.me/GithubRe

🌟 anthropics/financial-services caught my eye on GitHub Trending today. 🔗 https://github.com/anthropics/financial-services 📝 No description. ────────────────────────────── The anthropics/financial-services GitHub repository offers a collection of reference agents, skills, and data connectors tailored for financial services workflows, including investment banking, equity research, private equity, and wealth management. Key features include pre-built agents for tasks like pitch deck creation, market research, and earnings review, as well as vertical plugins that bundle skills and commands for specific financial services verticals. To use the repository, you can either install the agents and plugins as a Claude Cowork plugin or deploy them via the Claude Managed Agents API. Technical highlights include the use of agent.yaml files for managed agent deployment and the ability to customize the agents and skills to fit your firm's specific needs. The repository is designed for financial services professionals, including investment bankers, equity researchers, and wealth managers, who want to streamline their workflows and improve productivity. In summary, the anthropics/financial-services repository provides a powerful toolkit for financial services professionals to automate and enhance their workflows - automate your finance workflows with Claude. ────────────────────────────── 🧠 Channel: https://t.me/GithubRe

🚀 Meet bytedance/UI-TARS-desktop: a gem from today's GitHub trending list. 🔗 https://github.com/bytedance/UI-TARS-desktop 📝 The Open-Source Multimodal AI Agent Stack: Connecting Cutting-Edge AI Models and Agent Infra ────────────────────────────── Meet UI-TARS-desktop, a cutting-edge desktop application that brings the power of GUI Agent and Vision to your computer. It's part of the TARS stack, which includes Agent TARS, a general multimodal AI Agent. UI-TARS-desktop provides a native GUI Agent based on the UI-TARS model, allowing for local and remote computer control, as well as browser operation. With its one-click out-of-the-box CLI and hybrid browser agent, you can control browsers using GUI Agent, DOM, or a hybrid strategy. The application also features event stream and MCP integration, enabling seamless integration with real-world tools. To get started, simply run npx @agent-tars/cli@latest or visit the quick start guide. With UI-TARS-desktop, you can experience a new level of convenience and intelligence - Revolutionizing human-computer interaction, one click at a time. ────────────────────────────── 🧠 Channel: https://t.me/GithubRe

🎯 oracle-devrel/oracle-ai-developer-hub landed on trending. Worth a proper look. 🔗 https://github.com/oracle-devrel/oracle-ai-developer-hub 📝 Technical resources for AI developers to build applications, agents, and systems using Oracle AI Database and OCI services ────────────────────────────── The Oracle AI Developer Hub is a comprehensive repository that provides technical resources for building AI applications, agents, and systems using Oracle AI Database and OCI services. It's organized into several key areas, including Apps, Notebooks, Guides, and Agent Memory. The Apps section features reference implementations of AI-powered solutions, such as FitTracker, agentic_rag, and finance-ai-agent-demo. These apps demonstrate end-to-end implementations of AI applications, agents, and systems that leverage Oracle AI Database and OCI services. The Notebooks section offers Jupyter notebooks and interactive tutorials covering AI/ML model development, Oracle Database AI features, and OCI AI services integration patterns. Notebooks like agentic_rag_langchain_oracledb_demo and oracle_langchain_example provide hands-on experience with building AI agents and RAG applications. The Guides section provides comprehensive documentation, reference materials, and conference presentations on AI agent architecture, reasoning strategies, and memory systems. Guides like Building the Brain and Backbone of Enterprise AI Agents and Memory Engineering: The Discipline Behind Memory Augmented Agents offer in-depth insights into advanced reasoning and infrastructure strategies. The Agent Memory section focuses on the Oracle AI Agent Memory package, which provides a unified memory core for AI agents. Notebooks in this section demonstrate how to use Oracle AI Database as the memory core, serving conversation history, durable facts, and entity state from a single converged engine. This repository is ideal for AI developers, engineers, and researchers looking to build production-grade AI solutions. To get started, explore the Apps and Notebooks sections, and dive into the Guides and Agent Memory sections for more in-depth knowledge. The Oracle AI Developer Hub is your one-stop-shop for building innovative AI applications - start building today! ────────────────────────────── 🧠 Channel: https://t.me/GithubRe

🔥 decolua/9router is trending — and it deserves your attention. 🔗 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 FREE AI router and token saver that helps you never stop coding while saving 20-40% tokens with RTK and auto-fallback to free and cheap AI models. It connects all AI code tools to 40+ AI providers and 100+ models, making it a universal solution for coding needs. The key features of 9Router include RTK Token Saver, which auto-compresses tool result content to save tokens, and auto-fallback to free and cheap models when subscription quotas are exhausted. It also supports multi-account round-robin and quota tracking to maximize subscriptions. To use 9Router, simply install it globally with npm install -g 9router and run it with 9router. Then, connect a free provider like Kiro AI or OpenCode Free through the dashboard. You can also use it with your CLI tool by setting the endpoint to http://localhost:20128/v1 and copying the API key from the dashboard. 9Router is designed for developers and coders who want to save time and money on AI coding tools. With its easy setup and seamless integration with major AI coding tools, it's a must-have for anyone looking to optimize their coding workflow. In short, 9Router is a game-changer for AI coding - code more, pay less. ────────────────────────────── 🧠 Channel: https://t.me/GithubRe