Github Top Repositories

🌟 tirth8205/code-review-graph caught my eye on GitHub Trending today. 🔗 https://github.com/tirth8205/code-review-graph 📝 Local-first code intelligence graph for MCP and CLI. Builds a persistent map of your codebase so AI coding tools read only what matters, with benchmarked context reductions on reviews and large-repo workflows. ────────────────────────────── The code-review-graph tool is designed to optimize your code review process by building a structural map of your codebase and tracking changes incrementally. This allows your AI assistant to focus on the most relevant parts of your code, reducing the number of tokens it needs to read and making the review process more efficient. The key features of code-review-graph include its ability to parse your codebase into an abstract syntax tree (AST) using Tree-sitter, store the AST as a graph of nodes and edges, and query the graph to determine the minimal set of files that need to be reviewed. To use code-review-graph, you can install it via pip install code-review-graph and then run code-review-graph install to set up the tool for your project. The tool supports a wide range of programming languages, including Python, JavaScript, and Java, and allows you to add support for custom languages by creating a languages.toml file. code-review-graph is designed for developers who want to optimize their code review process and reduce the time and resources required for code reviews. With its advanced features and support for custom languages, it's an ideal tool for any development team looking to streamline their workflow. In short, code-review-graph helps you review smarter, not harder, by giving your AI assistant the context it needs to focus on the most important parts of your code. ────────────────────────────── 🧠 Channel: https://t.me/GithubRe

🔥 Significant-Gravitas/AutoGPT is trending — and it deserves your attention. 🔗 https://github.com/Significant-Gravitas/AutoGPT 📝 AutoGPT is the vision of accessible AI for everyone, to use and to build on. Our mission is to provide the tools, so that you can focus on what matters. ────────────────────────────── The AutoGPT GitHub repository is an open-source platform that enables users to build, deploy, and run AI agents that can automate various tasks and workflows. With AutoGPT, users can describe an outcome in plain English or use a visual builder to shape every step of the process, and then run the agent on demand, on a schedule, or from a trigger. The platform offers four main surfaces: AutoPilot, Agents, Marketplace, and Build, which provide a range of features and functionalities for creating and managing AI agents. The AutoGPT platform is available in both hosted and self-hosted options, with the hosted version providing a managed infrastructure and model access, while the self-hosted version requires users to provide their own infrastructure and model API keys. The platform supports a wide range of integrations with popular apps and services, including Gmail, Google Calendar, GitHub, and Slack. AutoGPT is designed for a wide range of users, from individuals to businesses, and offers a range of features and functionalities that can help automate various tasks and workflows. Whether you're looking to automate executive operations, sales, marketing, engineering, customer support, or research tasks, AutoGPT provides a powerful and flexible platform for creating and managing AI agents. One-liner takeaway: AutoGPT is a game-changing platform that empowers users to automate tasks and workflows with ease, giving them back 10 hours every week to focus on what matters most. ────────────────────────────── 🧠 Channel: https://t.me/GithubRe

📌 Spotted on GitHub Trending: TapXWorld/ChinaTextbook — let's break it down. 🔗 https://github.com/TapXWorld/ChinaTextbook 📝 所有小初高、大学PDF教材。 ────────────────────────────── ChinaTextbook is an open-source repository providing free access to Chinese textbooks, aiming to promote compulsory education and bridge the educational gap between regions. The repository contains a wide range of mathematics textbooks for primary, junior high, and senior high school, as well as university-level mathematics materials, including linear algebra, discrete mathematics, and probability theory. To use the repository, simply browse through the directories and download the desired textbooks. Note that some files may be split into multiple parts due to GitHub's file size limits. To merge these split files, you can use the provided mergePDFs-windows-amd64.exe program. The target audience for this repository includes students, teachers, and anyone interested in Chinese education. The takeaway: empowering education, one free textbook at a time. ────────────────────────────── 🧠 Channel: https://t.me/GithubRe

🔥 google/guava is trending — and it deserves your attention. 🔗 https://github.com/google/guava 📝 Google core libraries for Java ────────────────────────────── The google/guava repository is a collection of core Java libraries developed by Google. These libraries provide new collection types, such as multimap and multiset, immutable collections, a graph library, and utilities for concurrency, I/O, hashing, primitives, strings, and more. To use Guava, you can add it to your build using Maven or Gradle, with two different "flavors" available: one for use on a Java 8+ JRE and one for use on Android. Some key features of Guava include Serializable support, Java 8+ compatibility, and a wide range of Java libraries. Guava is suitable for Java developers of all levels, from beginners to experienced professionals, who want to simplify their coding process. Overall, the google/guava repository is a valuable resource for any Java developer looking to streamline their workflow. Guava simplifies Java development with its robust set of libraries - use it to upgrade your coding game! ────────────────────────────── 🧠 Channel: https://t.me/GithubRe

⚡ huangruiteng/loopx is making waves. Here's the full picture. 🔗 https://github.com/huangruiteng/loopx 📝 Lightweight loop engineering state kernel for long-running AI agent teams. Agent-loop agnostic across Codex, Claude Code, and other coding agents, with durable goals, quota-aware auto-wake, executable todos, evidence logs, and verifiable handoffs. ────────────────────────────── LoopX is a local control plane for long-running AI agent work, keeping objectives, gates, todos, evidence, and quota stable across turns. It's designed for loop engineering, allowing humans to manage and improve AI workflows. Key features include: * A compact state kernel for tracking goals, todos, and evidence * Agent-agnostic design, supporting various AI agents like Codex, Claude Code, and Cursor * Human judgment integration, ensuring humans are involved in critical decision-making To use LoopX, simply install it via curl and bash, then connect it to your project. You can start from your agent, such as Codex App or Claude Code, and use the loopx command to manage your workflow. LoopX is useful for multi-day engineering, research, and experiment objectives, as well as issue and PR loops that require preserving scope, evidence, and review state. It's not an autonomous production controller, but rather a tool to help humans manage and improve AI-driven workflows. The takeaway: Keep the loop moving, keep the judgment human. ────────────────────────────── 🧠 Channel: https://t.me/GithubRe

⚡ goauthentik/authentik is making waves. Here's the full picture. 🔗 https://github.com/goauthentik/authentik 📝 The authentication glue you need. ────────────────────────────── Authentik is an open-source Identity Provider (IdP) for modern Single Sign-On (SSO). It supports various protocols like SAML, OAuth2/OIDC, LDAP, and RADIUS, making it suitable for self-hosting in small labs to large production clusters. You can install authentik using Docker Compose, Kubernetes (Helm Chart), AWS CloudFormation, or DigitalOcean Marketplace. The project has a strong focus on development and contributions, with extensive developer documentation and a contribution process in place. Security is also a top priority, with guidelines outlined in the SECURITY.md file. Authentik is licensed under MIT License, CC BY-SA 4.0, and an Enterprise License for commercial use. Takeaway: Authentik is your one-stop-shop for a robust, open-source identity management system that's free, flexible, and feature-rich. ────────────────────────────── 🧠 Channel: https://t.me/GithubRe

🌟 mattpocock/skills caught my eye on GitHub Trending today. 🔗 https://github.com/mattpocock/skills 📝 Skills for Real Engineers. Straight from my .agents directory. ────────────────────────────── The mattpocock/skills GitHub repository offers a collection of skills designed to enhance your experience with coding agents like Claude Code and Codex. The purpose of these skills is to help you work more efficiently and effectively with AI-powered tools, addressing common issues such as misalignment, verbosity, and code quality. Key features include grilling sessions to ensure you and the agent are aligned, a shared language to reduce verbosity, and feedback loops to improve code quality. The skills are small, easy to adapt, and composable, allowing you to customize them to fit your needs. To get started, you can install the skills using the claude plugins install mattpocock-skills command or by running npx skills@latest add mattpocock/skills. Once installed, you can use skills like /grill-me and /grill-with-docs to improve your workflow. These skills are designed for real engineers who want to take control of their coding process and work more effectively with AI-powered tools. With these skills, you can ship better apps and improve your overall coding experience. In short, mattpocock/skills helps you work smarter, not harder, with coding agents - try them out and see the difference for yourself! ────────────────────────────── 🧠 Channel: https://t.me/GithubRe

📌 Spotted on GitHub Trending: cloudflare/computer — let's break it down. 🔗 https://github.com/cloudflare/computer 📝 Give your agent a computer 👾 ────────────────────────────── The Cloudflare Computer is a virtual filesystem that lives inside a Durable Object, providing a unique way to manage and execute code in a cloud environment. It has three main backends: Container, Isolate shell, and Isolate JavaScript, each offering a different way to execute code and interact with the filesystem. The workspace.runtime.exec function is the main entry point for executing code, and it allows you to choose the backend and execute code in a flexible way. The Cloudflare Computer also provides a node:fs/promises interface, making it easy to work with the filesystem in a Node.js environment. To get started, you can install the @cloudflare/computer package and follow the instructions in the README. There are also several examples in the examples/ directory that demonstrate how to use the Cloudflare Computer in different scenarios. The Cloudflare Computer is suitable for experiments, exploration, and prototypes, but it's not yet ready for production use. The project is still in the preview phase, and the APIs are subject to change. One-liner takeaway: Cloudflare Computer is a powerful virtual filesystem that enables flexible and scalable code execution in the cloud, and it's waiting for your feedback to shape its future. ────────────────────────────── 🧠 Channel: https://t.me/GithubRe

📌 Spotted on GitHub Trending: addyosmani/agent-skills — let's break it down. 🔗 https://github.com/addyosmani/agent-skills 📝 Production-grade engineering skills for AI coding agents. ────────────────────────────── The addyosmani/agent-skills GitHub repository provides a comprehensive set of production-grade engineering skills for AI coding agents. These skills encode workflows, quality gates, and best practices used by senior engineers across various development phases. The repository includes 8 slash commands that map to the development lifecycle, allowing for automatic activation of the right skills. Key features include /spec for defining what to build, /plan for planning how to build it, and /build for incremental implementation. Technical highlights of the repository include the use of

npx skills add addyosmani/agent-skills

for fast installation and the ability to grab individual skills using

npx skills add addyosmani/agent-skills --skill code-review-and-quality

. The repository supports various agents, including Claude Code, Cursor, and Codex, and provides detailed setup instructions for each. The skills are designed to be used by anyone working with AI coding agents, from developers to project managers. In summary, addyosmani/agent-skills is a powerful repository that helps streamline the development process by providing a set of pre-defined skills for AI coding agents. With these skills, you can automate your development workflow and focus on what matters most - building high-quality software. ────────────────────────────── 🧠 Channel: https://t.me/GithubRe

🌟 TencentCloud/TencentDB-Agent-Memory caught my eye on GitHub Trending today. 🔗 https://github.com/TencentCloud/TencentDB-Agent-Memory 📝 TencentDB Agent Memory is a team-level memory hub for AI Agents — turning conversations, docs, and code into four reusable memory assets (Chat Memory, Skill, LLM-Wiki, Code-Graph) that are governed, shared, and equipped across agents and frameworks. ────────────────────────────── The TencentDB Agent Memory is a powerful tool designed to enhance the memory capabilities of AI agents, allowing them to learn from workflows, retain task context, and reuse past experiences. This is achieved through a layered memory system, consisting of symbolic short-term memory and layered long-term memory. The symbolic short-term memory offloads heavy tool logs into compact Mermaid symbols, reducing token usage and improving task success. Meanwhile, the layered long-term memory distills fragmented conversations into structured personas and scenes. When integrated with OpenClaw, it significantly cuts token usage and improves pass rates. The system also features memory layering and symbolic memory, ensuring agents can reason better, not just remember more. To get started, simply install the plugin using openclaw plugins install @tencentdb-agent-memory/memory-tencentdb and enable it in your OpenClaw config. This tool is perfect for developers and researchers looking to improve the performance of their AI agents. In short, with TencentDB Agent Memory, agents remember, so humans can innovate! ────────────────────────────── 🧠 Channel: https://t.me/GithubRe

🎯 lyogavin/airllm landed on trending. Worth a proper look. 🔗 https://github.com/lyogavin/airllm 📝 AirLLM 70B inference with single 4GB GPU ────────────────────────────── AirLLM is a game-changer for large language models, allowing massive models like 70B Llama 3.1 to run on a single 4GB GPU card without quantization, distillation, or pruning. This is achieved through sparse MoE models that stream one expert at a time. Key Features: - Support for various large language models, including Llama 3.x, DeepSeek V2/V3, and more - Model compression for up to 3x inference speedup with minimal accuracy loss - Easy usage with the AutoModel.from_pretrained(...) method Technical Highlights: - pip install airllm for easy installation - from airllm import AutoModel for initializing models - Supports compression for 4-bit or 8-bit block-wise quantization Audience: - Developers and researchers working with large language models - Those looking to deploy models on limited hardware Takeaway: With AirLLM, you can run massive language models on minimal hardware, making AI more accessible and efficient. ────────────────────────────── 🧠 Channel: https://t.me/GithubRe

⚡ uber/ADR is making waves. Here's the full picture. 🔗 https://github.com/uber/ADR 📝 ADR secures enterprise AI agents through observability, security benchmarking, and threat detection. Deployed at Uber. ────────────────────────────── Meet ADR, an enterprise security system designed to secure AI agents. It's already being used in production at Uber and has been recognized in a paper accepted to MLSys 2026. ADR's key features include Observability, which captures agent activity, Benchmark, a testing system for agent security, Detection, which identifies risky behavior, and upcoming Prevention capabilities. The repository contains the open-source ADR Sensor, ADR-Bench, and ADR Detector. To get started with ADR Detection, simply git clone the repository, navigate to the Detection directory, and run uv sync. ADR is perfect for organizations looking to secure their AI agents, whether they're employee-facing or customer-facing. With ADR, you can ensure your AI systems are safe and reliable. One-liner takeaway: ADR is revolutionizing AI security by providing a robust system to detect and respond to potential threats, giving you peace of mind in the ever-evolving world of AI. ────────────────────────────── 🧠 Channel: https://t.me/GithubRe

⚡ tailwindlabs/tailwindcss is making waves. Here's the full picture. 🔗 https://github.com/tailwindlabs/tailwindcss 📝 A utility-first CSS framework for rapid UI development. ────────────────────────────── Tailwind CSS is a utility-first CSS framework that enables rapid building of custom user interfaces. Its key features include a configurable and highly customizable design system, making it easy to create unique and consistent designs. To use Tailwind CSS, simply include it in your project and start writing classes. The framework is easy to learn and has a low barrier to entry, making it accessible to developers of all levels. From a technical standpoint, Tailwind CSS is built using PostCSS and JavaScript, allowing for seamless integration with existing projects. The target audience for Tailwind CSS includes frontend developers, designers, and anyone looking to streamline their CSS workflow. In short, Tailwind CSS is the go-to framework for building custom and responsive user interfaces - write CSS faster, not more. ────────────────────────────── 🧠 Channel: https://t.me/GithubRe