GitHub Trends

#python cuTile Python is a new programming tool from NVIDIA that lets you write GPU programs in Python more easily and efficiently. It uses a tile-based model, where you work with chunks of data called tiles, making your code portable across different NVIDIA GPUs without needing to rewrite it for each hardware generation. cuTile automatically uses advanced GPU features like tensor cores and memory accelerators, so you get high performance without complex coding. You can install it via pip, and it requires CUDA Toolkit 13.1+ and Python 3.10+. This helps you develop faster, future-proof GPU applications with less effort. https://github.com/NVIDIA/cutile-python

#python Foundry is a toolkit that helps design new proteins using powerful AI models. It includes tools to generate protein structures (RFD3), predict how they fold (RF3), and design amino acid sequences that will form those structures (ProteinMPNN/LigandMPNN). All models work together using a common framework for handling molecular structures, making it easier to go from idea to designed protein. The benefit is that it gives a complete, flexible system to create custom proteins for research, medicine, or biotechnology, with clear instructions and examples to get started quickly. https://github.com/RosettaCommons/foundry

#python#brain_inspired_ai#deep_learning#large_language_models#reasoning The Hierarchical Reasoning Model (HRM) is a new type of AI that reasons more like a human brain, using a fast part for quick details and a slow part for big-picture planning. It solves hard logic tasks like Sudoku, mazes, and IQ-style puzzles very well, even though it is tiny (only 27 million parameters) and learns from very little data (just 1,000 examples). Unlike most large language models, it does not need long chains of written reasoning steps or huge amounts of training, which makes it much faster, cheaper, and more efficient. For the user, this means powerful reasoning in a small, fast system that can run on ordinary hardware and still beat much larger models on tough problems. https://github.com/sapientinc/HRM

#python Claude Quickstarts offers ready-made projects that help you quickly build AI applications using the Claude API. You can create tools like a customer support agent, financial data analyst, computer control demo, or an autonomous coding agent by following simple setup steps and using your Claude API key. These projects come with clear instructions and can be customized to fit your needs, saving you time and effort in development. This helps you start building powerful AI apps faster and learn how to use Claude’s advanced features effectively. You also get access to helpful resources, community support, and opportunities to contribute improvements. https://github.com/anthropics/claude-quickstarts

#python VibeVoice is an open-source AI tool that creates natural-sounding, expressive audio with up to four different voices, perfect for making podcasts, audiobooks, or long conversations. It keeps each speaker’s voice consistent and handles smooth turn-taking, making the audio sound realistic and engaging. The tool can generate speech in English and Chinese, and even adds spontaneous emotion or singing. It’s free to use and helps creators produce high-quality audio quickly, but should be used responsibly to avoid misuse. https://github.com/microsoft/VibeVoice

#python#agents#ai_agents#anthropic#anthropic_claude#automation#claude#claude_code#claude_code_cli#claude_code_commands#claude_code_plugin#claude_code_plugins#claude_code_subagents#claude_skills#claudecode#claudecode_config#claudecode_subagents#orchestration#sub_agents#subagents#workflows Claude Code Plugins provide a comprehensive system of 63 focused plugins containing 85 specialized agents, 47 skills, and 44 development tools organized for intelligent automation across software development. You install only what you need, keeping token usage minimal while accessing domain experts in architecture, languages, infrastructure, quality, and operations. Each plugin loads independently with its own agents and commands, letting you compose multiple plugins for complex workflows. This granular design means faster, cleaner sessions with progressive disclosure—knowledge loads only when activated. The benefit is significant productivity gains: you get expert-level assistance tailored to your specific task without unnecessary overhead, enabling your entire team to work more efficiently on development, infrastructure, security, and automation challenges. https://github.com/wshobson/agents

#python#language_models#linux#machine_translation#nlp#open_source#python#transformers#translation Argos Translate is a free, open-source tool that lets you translate text offline using your own computer. It works as a Python library, command-line tool, or with a graphical interface, and supports many languages. You can install language packages for direct translations, and it can even translate between languages that don’t have a direct package by using a middle language. This means you can translate more language pairs, though the quality might be a little lower. Argos Translate is fast, private, and does not need an internet connection after setup, making it useful for secure or offline translation needs. https://github.com/argosopentech/argos-translate

#shell#bash#developers_everyday_life#java#option_parser#python#script#shell#show_busy_java_threads#show_duplicate_java_classes#terminal#useful_scripts This repository provides useful scripts for Java and Shell that make developer work easier and faster. The Java scripts help you quickly find CPU performance problems in running processes, detect duplicate classes in jar files, and search for specific classes across multiple jar files. The Shell scripts enhance command-line productivity with features like copying output to clipboard, colorizing file displays, deduplicating lines without sorting, and managing Docker containers more easily. The scripts are production-ready, used by major companies like Alibaba, and follow strict Bash standards for safety and reliability. You benefit by getting professional-grade tools that save time on routine tasks and learning best practices for writing quality shell scripts. https://github.com/oldratlee/useful-scripts

#python The Social-Engineer Toolkit (SET) is an open-source penetration testing framework created by TrustedSec that helps security professionals test organizational defenses through social engineering attacks. SET provides pre-built attack vectors for phishing, credential harvesting, and website cloning, allowing testers to simulate realistic threats quickly and effectively. The toolkit runs on Linux and Mac OS X, with easy installation via pip or package managers. By using SET with proper authorization, security teams can identify human vulnerabilities in their defenses, understand how employees respond to social engineering tactics, and implement stronger security awareness training to protect against real-world attacks. https://github.com/trustedsec/social-engineer-toolkit

#python#agent#ai#aiagent#awesome#chatgpt#hacktoberfest#hacktoberfest2025#llm#long_short_term_memory#memori_ai#memory#memory_management#python#rag#state_management Memori is an open-source memory engine that gives AI language models human-like memory using standard SQL databases like PostgreSQL, MySQL, or SQLite.[1][2] With just one line of code, you can enable any LLM to remember conversations, learn from interactions, and maintain context across sessions.[1] The key benefits are significant cost savings of 80-90% compared to expensive vector databases, complete data ownership and transparency since memories are stored in SQL databases you control, and zero vendor lock-in allowing you to export and move your data anywhere.[1][3] Memori works with popular frameworks like OpenAI, Anthropic, and LangChain, making it easy to integrate into existing projects without complex setup.[1] https://github.com/GibsonAI/Memori

#python#android#android_emulator#google_apps#kernelsu#magisk#magiskonwsa#magiskonwsalocal#subsystem#windows#windows_10#windows_11#windows_subsystem_android#windows_subsystem_for_android#windows10#windowssubsystemforandroid#wsa#wsa_root#wsa_with_gapps_and_magisk#wsapatch Windows Subsystem for Android (WSA) support ended on March 5, 2025, and the Amazon Appstore was removed from the Microsoft Store, but you can still manually install and use WSA on Windows 10 or 11 via unofficial builds like WSABuilds from GitHub. These builds include options with Google Play Services and root access (Magisk). If you face issues with apps crashing or not starting after recent Windows updates, try using older or "NoGApps" builds as workarounds. Backing up your data before uninstalling or updating WSA is recommended. This lets you keep running Android apps on Windows despite official support ending. https://github.com/MustardChef/WSABuilds

#python#ai#faiss#gpt_oss#langchain#llama_index#llm#localstorage#offline_first#ollama#privacy#python#rag#retrieval_augmented_generation#vector_database#vector_search#vectors LEANN is a tiny, powerful vector database that lets you turn your laptop into a personal AI assistant capable of searching millions of documents using 97% less storage than traditional systems without losing accuracy. It works by storing a compact graph and computing embeddings only when needed, saving huge space and keeping your data private on your device. You can search your files, emails, browser history, chat logs, live data from platforms like Slack and Twitter, and even codebases—all locally without cloud costs. This means fast, private, and efficient AI-powered search and retrieval on your own laptop. https://github.com/yichuan-w/LEANN