GitHub Trends

#python Nemo RL is a powerful and scalable library that helps you efficiently train and fine-tune large AI models, from small ones on a single GPU to huge models with over 100 billion parameters using thousands of GPUs. It integrates easily with Hugging Face models and uses NVIDIA’s Megatron Core for fast, optimized training with advanced parallelism, making it ideal for very large models and long sequences. It supports various reinforcement learning algorithms and fine-tuning methods, offers flexible resource management with Ray, and provides detailed, user-friendly documentation and examples. This means you can train state-of-the-art AI models faster and more reliably, even at massive scale, with less hassle. https://github.com/NVIDIA-NeMo/RL

#python#chatbi#deepseek#llm#nl2sql#rag#sqlbot#text_to_sql#text2sql SQLBot is an easy-to-use intelligent system that turns natural language questions into SQL queries using advanced AI models and retrieval-augmented generation (RAG). You just need to set up your AI model and data source to start asking questions about your data. It integrates smoothly with other business systems and AI platforms, making it simple to add smart data querying to your apps. It also ensures data security with workspace-based resource isolation and fine-grained access control. You can quickly deploy it on a Linux server using Docker, enabling fast, secure, and intelligent data interaction without needing deep SQL knowledge. This saves you time and improves data accessibility. https://github.com/dataease/SQLBot

#python Terminal-Bench is a tool that tests how well AI agents perform real tasks in a terminal, like compiling code or setting up servers, all on their own. It includes a set of tasks with instructions and tests, plus a system that connects AI models to a safe terminal environment. You can install it easily with pip and run tests to see how good your AI is at practical, real-world jobs. This helps you build, compare, and improve AI agents for coding and system tasks, making your AI development more reliable and measurable. You can also contribute new tasks or join a leaderboard to track progress. https://github.com/laude-institute/terminal-bench

#python#aws#mcp#mcp_client#mcp_clients#mcp_host#mcp_server#mcp_servers#mcp_tools#modelcontextprotocol AWS MCP Servers use the Model Context Protocol (MCP), an open standard that connects AI tools with AWS data and services in a simple, secure way. These servers improve AI responses by providing up-to-date AWS documentation, best practices, and workflow automation for cloud development, infrastructure, and operations. You can run MCP servers locally for development or use AWS-managed remote servers for easy access and scalability. MCP servers support many AWS services like Lambda, DynamoDB, EKS, and more, helping you build, manage, and optimize AWS resources efficiently with AI assistance. Installation is easy with one-click options for popular tools like VS Code and Cursor. This makes cloud development faster, more accurate, and cost-effective. https://github.com/awslabs/mcp

#python#cybersecurity#fyp#hacking#hacking_tool#indonesia#information#information_gathering#ip_geolocation#linux#osint#osint_python#osint_tool#pentesting#phone_number#python#python_hacking#termux#termux_hacks#termux_tool GhostTrack is a simple tool you can install on Linux or Termux to track locations, phone numbers, or social media usernames using open-source intelligence (OSINT). It offers menus for IP tracking (which can be combined with another tool called Seeker), phone number tracking, and username tracking on social media. This helps you gather information about a target’s location or identity easily. The benefit is that you can quickly find useful data for security, investigation, or personal knowledge without needing advanced skills, all through a straightforward Python-based program created by HunxByts. https://github.com/HunxByts/GhostTrack

#python#artificial_intelligence#cybersecurity#generative_ai#llm#pentesting Cybersecurity AI (CAI) is an open-source, lightweight framework that helps you build AI agents to find and fix security vulnerabilities efficiently. It supports many AI models and tools, works on multiple operating systems, and allows human control during tasks. CAI automates complex security testing steps like scanning, exploiting, and validating bugs, making bug bounty hunting easier and faster. It also logs detailed traces for better analysis and supports teamwork among AI agents. Using CAI can boost your cybersecurity skills, save time, and improve your ability to protect systems from attacks by combining AI power with your expertise. https://github.com/aliasrobotics/cai

#python#agents#ai#api_gateway#asyncio#authentication_middleware#devops#docker#fastapi#federation#gateway#generative_ai#jwt#kubernetes#llm_agents#mcp#model_context_protocol#observability#prompt_engineering#python#tools The MCP Gateway is a powerful tool that unifies different AI service protocols like REST and MCP into one easy-to-use endpoint. It helps you manage multiple AI tools and services securely with features like authentication, retries, rate-limiting, and real-time monitoring through an admin UI. You can run it locally or in scalable cloud environments using Docker or Kubernetes. It supports various communication methods (HTTP, WebSocket, SSE, stdio) and offers observability with OpenTelemetry for tracking AI tool usage and performance. This gateway simplifies connecting AI clients to diverse services, making development and management more efficient and secure. https://github.com/IBM/mcp-context-forge

#python#agents#ai#ai_ux#autogen#browser_use#computer_use_agent#cua#ui Magentic-UI is a tool that helps you automate complex web tasks by working together with you. It lets you plan step-by-step actions, watch the progress, and approve sensitive steps to keep control and safety. You can interact with it through a browser, upload files, and even run multiple tasks at once. It learns from past tasks to improve future automation. This means you save time on repetitive or complicated web activities while staying in control, making your work easier and more efficient. It supports Python 3.10+ and works best with Docker or WSL2 on Windows. https://github.com/microsoft/magentic-ui

#python#mllm#point_clouds#scene_understanding#spatial_intelligence SpatialLM is a powerful 3D language model that turns complex 3D point cloud data from videos, RGBD images, or LiDAR into clear, structured 3D scene layouts showing walls, doors, windows, and objects with labels. It works without needing special equipment and can detect user-specified object categories. This helps you understand and analyze indoor spaces better, useful for robotics, navigation, and 3D design. You can run it on your data, visualize results, and even customize detection tasks easily, making 3D scene understanding more accessible and flexible for many applications. https://github.com/manycore-research/SpatialLM

#python#alibabacloud#android#android_emulator#aws#azure#cloud#docker#docker_android#emulator#gcp#genymotion#jenkins#kubernetes#mobile_app#mobile_web#novnc#saltstack#selenium#selenium_grid#terraform You can use Docker-Android to run Android emulators inside Docker containers, which helps you develop and test Android apps easily without needing physical devices. It offers many device profiles like Samsung Galaxy and Nexus models, supports viewing the emulator via VNC, sharing logs through a web interface, and controlling the emulator remotely with adb. It works on Ubuntu and can integrate with cloud services like Genymotion. This setup speeds up development, testing, and automation, making your workflow more consistent and efficient while saving resources. You can also persist data and run unit or UI tests with popular frameworks like Appium and Espresso. This helps you build and test Android apps faster and more reliably. https://github.com/budtmo/docker-android

#python#pyside6#python#youtube_dl#youtube_downloader#yt_dlp#yt_dlp_gui YTSage is a user-friendly app that lets you download YouTube videos in any quality, extract audio, and get subtitles easily through a clean interface. You can download single videos or entire playlists, save thumbnails and descriptions, remove sponsor segments, and even trim videos. It supports login with cookies for private content and updates itself automatically. Installation is simple via pip or pre-built executables for Windows, Linux, and macOS. This tool helps you save and organize YouTube content efficiently with advanced options like speed limiting and custom commands, making video downloading fast and convenient. https://github.com/oop7/YTSage

#python AI Toolkit by Ostris is a powerful, easy-to-use software suite for training and fine-tuning AI models like Stable Diffusion and FLUX.1 on consumer-grade Nvidia GPUs with at least 24GB VRAM. It supports image and video models, offers both graphical and command-line interfaces, and allows training specific neural network layers. You can run it locally or on cloud platforms like RunPod and Modal. The toolkit automatically handles dataset preparation and resizing, and includes a web UI for managing training jobs securely. This helps you efficiently create custom AI models with flexibility and advanced features, even if you are not an expert. https://github.com/ostris/ai-toolkit