Projects

### Overview: Pixie is an open-source observability tool designed for Kubernetes applications, providing high-level and detailed views of cluster state and application performance. ### Key Features: - **Auto-telemetry:** Pixie collects and queries telemetry data using eBPF, including full-body requests, resource and network metrics, application profiles, and more. - **In-Cluster Edge Compute:** Collects, stores, and queries telemetry data locally, consuming less than 5% of CPU in most cases. - **Scriptability:** PxL, Pixie’s flexible Pythonic query language, can be used across the UI, CLI, and client APIs. ### Tech Stack: Pixie leverages eBPF for telemetry collection, Kubernetes for cluster management, and Python for scripting. ### Why It Matters: Pixie simplifies observability by automating data collection and providing a developer-friendly interface, making it easier for developers to monitor and debug Kubernetes applications.

### Overview: RAGs is a Streamlit app that allows developers to create and manage a RAG (Reinforcement Learning with Annotated Data) pipeline from a data source using natural language. This project is inspired by GPTs and is designed to streamline the process of building and configuring RAG systems. ### Key features: - **Streamlit App**: A user-friendly interface for creating and managing RAG pipelines. - **Builder Agent**: A customizable agent that can be trained on various LLMs (e.g., OpenAI, Anthropic) to generate RAG configurations. - **RAG Config**: A section where developers can configure RAG parameters such as system prompts, top-k, chunk size, and embedding model, with the option to update the agent. - **Generated RAG Agent**: A chatbot interface where developers can query the RAG agent with their questions, using the configured parameters to retrieve relevant information. ### Tech stack: Python ### Why it matters: This project simplifies the process of creating and configuring RAG systems, making it easier for developers to integrate and leverage their data for more advanced natural language processing tasks.

### Overview This repository is a curated collection of **solutions, ideas, and insights** from top performers across hundreds of Kaggle competitions. Whether you're a beginner looking to learn from the best or an experienced competitor seeking inspiration, this resource provides: - **Winning Solutions**: Detailed approaches from competition winners and top finishers - **Discussion Threads**: Links to the most valuable community discussions - **Code Notebooks**: Top-rated kernels and implementations - **Learning Resources**: Videos, tutorials, and educational content - **Competition Insights**: Analysis of evaluation metrics, datasets, and problem-solving strategies The repository is regularly updated as competitions conclude, making it a living archive of competitive machine learning knowledge. ### Key Features - **Winning Solutions**: Detailed approaches from competition winners and top finishers - **Discussion Threads**: Links to the most valuable community discussions - **Code Notebooks**: Top-rated kernels and implementations - **Learning Resources**: Videos, tutorials, and educational content - **Competition Insights**: Analysis of evaluation metrics, datasets, and problem-solving strategies ### Tech Stack Astro ### Why It Matters This repository serves as a comprehensive resource for anyone looking to improve their machine learning skills and learn from the best in the Kaggle community. Whether you're a beginner or an experienced competitor, this collection provides insights and solutions that can help you enhance your problem-solving abilities and improve your performance in Kaggle competitions.

Overview: The repository contains the origin PyTorch implementation of Informer, a paper accepted by AAAI 2021. Special thanks to Jieqi Peng for building this repository. Key features: - The implementation of the Informer model in PyTorch. - The repository includes the ETT, ECL, and Weather datasets used in the paper. - The repository provides Colab examples for friendly usage. - The repository includes results and hyperparameter settings for all experiments. - The repository is cited in the paper and will be updated on this repo. Tech stack: Python 3.6, PyTorch 1.2, cuDNN 7.3.1, and the paper "Informer: Beyond Efficient Transformer for Long Sequence Time-Series Forecasting" by Jieqi Peng. Why it matters: The Informer model is designed to address the challenges of long sequence time-series forecasting, providing a more efficient and accurate solution compared to traditional transformer models.

### Overview: This repository contains the PyTorch implementation of Google AI's 2018 BERT paper, showcasing a powerful alternative to traditional language models with self-attention mechanisms. The project aims to provide a simple and understandable codebase for various NLP tasks, emphasizing the transferability of pre-trained language models. ### Key features: - **BERT Implementation**: A PyTorch implementation of Google AI's BERT model. - **Simple Annotation**: The code is designed to be as simple and easy to understand as possible. - **Pre-training Methods**: Includes both "masked language model" and "predict next sentence" training methods from the BERT paper. ### Tech stack: Python ### Why it matters: This implementation showcases the potential of transformer-based models in NLP, demonstrating their effectiveness across various tasks without the need for task-specific architectures. The pre-training methods presented in the BERT paper highlight the versatility of these models and their ability to be transferred to any NLP task.

### Overview: Genkit is an open-source framework designed to build full-stack AI-powered applications. It supports multiple programming languages including JavaScript/TypeScript, Go, Python (Beta), and Dart (Preview), providing a unified interface for integrating AI models from providers like Google, OpenAI, Anthropic, and Ollama. Genkit offers rapid deployment and easy integration, making it suitable for various projects. ### Key Features: - **JavaScript/TypeScript**: Production-ready with full feature support. - **Go**: Production-ready with full feature support. - **Python (Beta)**: Wide feature support approaching production-readiness. - **Dart (Preview)**: Early development with core functionality. ### Tech Stack: Genkit uses TypeScript for its core development. ### Why It Matters: Genkit simplifies the process of integrating AI models into applications, making it easier to build and deploy production-ready AI features quickly. Its unified interface and cross-language support make it versatile and adaptable to various project needs. ### Repository: The repository for Genkit is hosted on GitHub, with 6,528 stars, indicating a significant community interest and use in production environments. ### Primary Language: Genkit is primarily developed and used in TypeScript. ### GitHub Description: Genkit is an open-source framework for building full-stack AI-powered applications, built and used in production by Google's Firebase. It provides SDKs for multiple programming languages with varying levels of stability, including JavaScript/TypeScript, Go, Python (Beta), and Dart (Preview). ### Installation: To get started with Genkit, you can install

Overview: This repository is a curated list of papers and tutorials on Recommender Systems (RS), covering various aspects such as systematic tutorials, comprehensive surveys, general recommendation systems, social recommendation systems, deep learning-based recommendation systems, cold start problems, efficient recommendation systems, exploration and exploitation problems, explainability in recommendation systems, click-through rate prediction, knowledge graph for recommendation systems, review-based recommendation systems, conversational recommendation systems, industrial/practical recommendation systems, privacy-preserving recommendation systems, large language models for recommendation systems, and agentic recommendation systems. Key features: - Comprehensive coverage of various types of recommendation systems and their applications. - Papers on systematic tutorials, surveys, general RS, social RS, deep learning-based RS, cold start problem, efficient RS, exploration and exploitation problem, explainability, click-through rate prediction, knowledge graph, review-based RS, conversational RS, industrial/practical RS, privacy-preserving RS, large language models for RS, and agentic RS. - Papers on the latest developments and trends in RS, including new areas like agentic RS, LLM for RS, and privacy&security RS. Tech stack: None specified. Why it matters: This repository provides a valuable resource for researchers, developers, and practitioners interested in the latest advancements and best practices in recommendation systems. It serves as a comprehensive guide for understanding and implementing various recommendation techniques and addressing common challenges in the field.

Overview: This is a Java implementation of the Chinese segmentation tool ANSJ, surpassing the open-source version ICT in terms of speed and accuracy. Key features: - Fast segmentation speed (200,000 words per second on Mac Air) - High accuracy (96%) - Comprehensive features including Chinese segmentation, name recognition, user-defined dictionary, keyword extraction, automatic summarization, and keyword marking. Tech stack: Java Why it matters: This tool offers superior performance and accuracy, making it suitable for applications requiring high-quality segmentation and natural language processing tasks. Repository: NLPchina/ansj_seg Primary language: Java GitHub stars: 6,503 GitHub description: ANSJ Chinese segmentation. A truly Java implementation of ICT's Chinese segmentation, surpassing the open-source version in speed and accuracy. Includes Chinese segmentation, name recognition, user-defined dictionary, keyword extraction, automatic summarization, and keyword marking. Suitable for applications requiring high-quality segmentation and natural language processing tasks.

Overview: `apfel` is a powerful AI assistant that runs on Apple Silicon Macs, providing a free, on-device alternative to OpenAI models. It supports both a UNIX tool and an OpenAI-compatible server, with a focus on 100% on-device performance and no need for API keys or cloud storage. Key features: - **On-Device AI**: Exposes Apple's built-in language model via FoundationModels, making it accessible without requiring any external dependencies. - **CLI Tool**: Supports pipe-friendly answers, file attachments, and JSON output. - **OpenAI-compatible Server**: Provides a drop-in backend for OpenAI SDKs, allowing seamless integration with existing infrastructure. - **Interactive Chat**: Offers an interactive REPL for quick queries. Tech stack: Swift 6.3+ and macOS 26 Tahoe+. Why it matters: `apfel` simplifies the integration of AI capabilities on macOS, offering a practical and efficient solution for developers and users alike. Repository: Arthur-Ficial/apfel Primary language: Swift GitHub stars: 6502 GitHub description: The free AI already on your Mac. CLI tool, OpenAI-compatible server, and interactive chat — all on-device via Apple Intelligence. No API keys, no cloud, no downloads.

### Overview: This repository is a curated collection of links to various courses and resources about Artificial Intelligence (AI). It offers a wide range of topics from statistics and linear algebra to deep learning, natural language processing, and more, suitable for both beginners and experienced learners. ### Key Features: - **Generative AI**: A GitHub repository for beginners. - **Deep Learning**: A YouTube playlist with over 6,594 views. - **Natural Language Processing**: A YouTube playlist with over 6,594 views. - **Deep Learning**: A website course by Sebastian Raschka. - **Large Language Models**: A YouTube playlist with over 6,594 views. - **Python**: A YouTube playlist with over 6,594 views. - **Stable Diffusion and Deep Learning**: A website course by fast.ai. - **Deep Learning**: A YouTube playlist with over 6,594 views. - **Deep Learning**: A YouTube playlist with over 6,594 views. - **Large Language Models and Prompt Engineering**: A website course by DAIR.AI. - **Computer Vision**: A YouTube playlist with over 6,594 views. - **Natural Language Processing**: A YouTube playlist with over 6,594 views. - **Linear Algebra**: A YouTube playlist with over 6,594 views. ### Tech Stack: - GitHub repository, YouTube playlist, website, and YouTube playlist. ### Why It Matters: This repository serves as a comprehensive resource for anyone interested in AI, providing a variety

Overview: This repository contains a collection of resources designed to help developers learn and review mathematics for machine learning. The materials cover a wide range of topics, from basic algebra and topology to advanced concepts like Bayesian modeling and deep learning. Key features: - Books: A variety of books on mathematics for machine learning, including "Algebra, Topology, Differential Calculus, and Optimization Theory For Computer Science and Machine Learning" by Jean Gallier and Jocelyn Quaintance, "Applied Math and Machine Learning Basics" by Ian Goodfellow and Yoshua Bengio, "Mathematics for Machine Learning" by Marc Peter Deisenroth, A. Aldo Faisal, and Cheng Soon Ong, "Probabilistic Machine Learning: An Introduction" by Kevin Patrick Murphy, "Mathematics for Deep Learning" by Brent Werness, Rachel Hu et al., and "The Mathematical Engineering of Deep Learning" by Benoit Liquet, Sarat Moka, and Yoni Nazarathy. - Papers: A collection of papers on the mathematical foundations of deep learning, including "The Matrix Calculus You Need For Deep Learning" by Terence Parr & Jeremy Howard and "The Mathematics of AI" by Gitta Kutyniok. - Videos: A series of video lectures on mathematics for machine learning, including "Multivariate Calculus by Imperial College London" by Dr. Sam Cooper & Dr. David Dye and "Mathematics for Machine Learning - Linear Algebra" by Dr. Sam Cooper & Dr. David Dye. - Math Basics: A guide to the mathematical concepts needed

### Overview: RWKV Runner is a lightweight, open-source tool designed to simplify the use of large language models. It provides a lightweight executable program that is just a few megabytes in size, making it ideal for developers and users who want to integrate RWKV models into their projects without the need for complex setup. ### Key Features: - **RWKV Model Management and Startup**: Automatically manages and starts RWKV models with a single click. - **Front-end and Back-end Separation**: Allows for separate deployment of the front-end service, back-end inference service, or back-end inference service. - **Compatibility with OpenAI API**: Provides an interface compatible with the OpenAI API, ensuring seamless integration with popular chatbots like ChatGPT. ### Tech Stack: TypeScript ### Why It Matters: RWKV Runner simplifies the process of using large language models by automating the setup and management of RWKV models, making it accessible and efficient for developers and users alike. The lightweight nature of the tool ensures that it can be easily integrated into existing projects without requiring extensive technical knowledge or resources.

### Overview: 非线智能的ReLE评测项目涵盖了374个大模型，包括商用模型和开源模型，提供7个领域的700多个细分维度的评测。目前囊括了413个大模型，覆盖了多个行业应用，如教育、医疗、金融等，提供排行榜和缺陷库，方便社区研究和改进大模型。 ### Key features: - **ReLE（Really Reliable Live Evaluation for LLM）**：原名CLiB，提供7个领域的700多个细分维度的评测。 - **多模态评测**：涵盖多模态理解、图片生成等多方面能力。 - **综合能力排行榜**：包括推理类模型、商用大模型、开源大模型等。 - **教育排行榜**：涵盖小学、初中、高中、教师资格、考研等细分领域。 - **医疗与心理健康排行榜**：涵盖医师、护士、药师、医技、医学基础知识、心理健康等。 - **金融排行榜**：涵盖财务、银行、保险、证券、金融基础知识、金融应用等。 - **法律与行政公务排行榜**：涵盖律师资格考试、公务员考试等。 - **推理与数学计算排行榜**：涵盖演绎推理、常识推理、符号推理、算术能力、表格问答、高中奥数、初中奥数、小学奥数、地图推理、空间推理、数独、金额大小写转换、日期计算等。 - **语言与指令遵从排行榜**：涵盖成语理解、情感分析、文本蕴含、

Overview: This repository contains 14 Claude Code skills designed to help you build flawless n8n workflows using the n8n-mcp MCP server. It includes skills for correct n8n expression syntax, MCP tool usage, workflow patterns, validation error interpretation, node configuration, and more. Key features: - Correct n8n expression syntax - MCP tool usage guide - Proven workflow patterns - Validation error interpretation - Operation-aware node configuration - Real-world examples and best practices Tech stack: Shell Why it matters: These skills help you avoid common pitfalls in n8n workflow building, ensuring your workflows are efficient, secure, and reliable. Repository: czlonkowski/n8n-skills GitHub stars: 6467

Overview: CleverHans is an adversarial example library designed to benchmark machine learning systems' vulnerability to adversarial examples. Key features: - Support for JAX, PyTorch, and TensorFlow 2 - Contains attack implementations, tutorials, and defense implementations - Helps in benchmarking models against adversarial examples Tech stack: Python with Jax, PyTorch, and TensorFlow 2 Why it matters: CleverHans is crucial for developers and researchers to test the vulnerability of machine learning models to adversarial examples, ensuring robustness and security in their systems.

### Overview: ChatGPT is an artificial intelligence chatbot developed by OpenAI. This list aims to showcase the best tools and resources for interacting with ChatGPT, including web apps, browser extensions, command-line tools, bots, integrations, packages, articles, community resources, and related lists. ### Key Features: - **Web Apps**: QuickGPT, MacGPT, Chatterbox, WriteMage, PaletteBrain, Machato, WonderGPT, Petey, IntelliBar, Ask AI, Chat Answer, Chat AI Desktop App, ChatGPT Desktop Application, ChatGPT Android, ChatARKit, Delphi ChatGPT, Chatbox, Short Circuit, ChatBoost, Developer Duck, Hello History, Actions, EasyChat AI. - **Browser Extensions**: Not specified. - **CLI Tools**: Not specified. - **Bots**: Not specified. - **Integrations**: Not specified. - **Packages**: Not specified. - **Articles**: Not specified. - **Community**: Not specified. - **Related Lists**: Not specified. ### Tech Stack: Electron ### Why it Matters: This list aims to provide a comprehensive guide for developers and enthusiasts interested in integrating ChatGPT into their projects or workflows.

### Overview: The Agent Governance Toolkit is a comprehensive solution for enforcing policies, managing zero-trust identities, executing agents in a sandboxed environment, and ensuring reliability in autonomous AI agents. Designed to cover the OWASP Agentic Top 10, it provides a robust framework for developers to deploy AI agents without compromising security and compliance. ### Key Features: - **Policy Enforcement**: Ensures that agents adhere to predefined rules and policies. - **Zero-Trust Identity**: Manages access and permissions based on service roles and OAuth scopes. - **Execution Sandboxing**: Runs agents in a secure environment to prevent unauthorized actions. - **Reliability Engineering**: Provides tools for auditing and proving the actions of agents. ### Tech Stack: - Python ### Why It Matters: The Agent Governance Toolkit addresses the critical issues of prompt injection, rule enforcement, and accountability in AI-driven systems. By ensuring compliance with OWASP standards and providing a reliable framework, it helps organizations maintain trust and security in their AI-driven applications. ### Repository: The project is hosted on GitHub at [microsoft/agent-governance-toolkit](https://github.com/microsoft/agent-governance-toolkit). ### GitHub Stars: 6,444 ### CI Status: [](https://github.com/microsoft/agent-governance-toolkit/actions/workflows/ci.yml) ### Documentation: [Full Documentation](https://microsoft.github.io/agent-governance-tool

Overview: wav2letter++ is a project by Facebook AI Research that aims to provide tools and recipes for automatic speech recognition, building upon the Flashlight framework. Key features: - Recipes for reproducing research papers in automatic speech recognition. - Pre-trained models for speech recognition. - Recipes for building the old, pre-consolidation version of wav2letter. Tech stack: C++ Why it matters: wav2letter++ provides a set of tools and recipes for researchers and developers interested in automatic speech recognition, building on the Flashlight framework, which is widely used in the field of speech recognition.

Overview: This repository is a curated list of Artificial Intelligence (AI) tools and resources, focusing on top generative AI tools and large language models (LLMs). It aims to provide developers and enthusiasts with a comprehensive overview of AI tools that can enhance productivity and creativity. Key features: - Editor's Choice: Curated lists of AI agents, SDKs, and tools that save time and streamline development processes. - AI Text: Models and tools for natural language processing and text generation. - Code with AI: AI-driven code generation and development tools. - Generative AI Images: Tools for creating high-quality images using AI. - Generative AI Video: AI-powered video creation and editing. - Generative AI Audio: AI tools for voice cloning and music generation. - AI Tools for Marketing: AI solutions for marketing and sales automation. - AI Phone Call Agents: Voice cloning and call agent tools. - Other AI Tools: A variety of AI tools beyond the main categories. - Learning resources: Resources for learning about AI and related technologies. Tech stack: The repository uses Markdown, GitHub Pages, and various AI tools and models. Why it matters: This repository serves as a valuable resource for developers and enthusiasts looking to explore and leverage AI tools in their projects, enhancing productivity and creativity in various applications.

Overview: This repository is a curated list of awesome self-supervised learning resources, inspired by other popular AI-related lists like awesome-deep-vision, awesome-adversarial-machine-learning, and awesome-deep-learning-papers. It aims to provide a comprehensive overview of self-supervised learning techniques and their applications across various domains such as computer vision, machine learning, robotics, and more. Key features: - Papers and resources on self-supervised learning techniques - Papers and resources on self-supervised learning in computer vision, including image representation learning, video representation learning, and 3D feature learning - Papers and resources on self-supervised learning in robotics, natural language processing, and time-series analysis - Papers and resources on self-supervised learning in recommendation systems and speech recognition Tech stack: Python, Markdown, and GitHub Why it matters: Self-supervised learning has become an exciting direction in AI research, as it offers a way to train models without the need for labeled data, making it particularly useful in scenarios where labeled data is scarce or expensive. The list aims to provide a valuable resource for researchers and practitioners looking to explore and implement self-supervised learning techniques in their work. Repository: jason718/awesome-self-supervised-learning GitHub stars: 6435 GitHub description: A curated list of awesome self-supervised methods