Coding & Development

TensorKart is an open-source project that demonstrates self-driving capabilities within the classic game MarioKart 64, powered by Google's TensorFlow framework. Users can train a deep learning model by recording their own gameplay, which then learns to control the in-game kart. The model can generalize to new tracks even with a relatively small training dataset, as shown by its ability to drive on Royal Raceway after training on other tracks. The project provides scripts for recording gameplay samples, preparing training data, training the model with GPU acceleration (using cuDNN), and playing the game with the trained AI agent. It also includes features for overriding AI control with a joystick and outlines future work like reinforcement learning integration to improve performance based on lap times.

Qwen Edit Any Pose is a specialized image generation tool hosted on Hugging Face Spaces, designed to modify the pose of a person in an image. Users can upload a reference picture of a person and a second image demonstrating the desired pose. The application then processes these inputs, optionally rewriting the prompt, and employs a fast diffusion model to create a new image where the subject from the first image adopts the pose from the second. This tool leverages the Qwen Edit 2511 Any Pose LoRA, making it efficient for generating new images with specific pose requirements. It's a practical solution for those needing to quickly adjust human poses in visual content.

text-generation-webui-colab offers a convenient Gradio web user interface for deploying and interacting with Large Language Models (LLMs) directly within a Google Colab environment. This open-source project supports a wide range of LLMs, including popular models like Llama 2, Vicuna, Falcon, and Mistral, often with GPTQ 4-bit quantization for efficient use. It's particularly useful for researchers, developers, and enthusiasts who want to experiment with different LLMs without extensive local setup. The repository provides numerous Colab notebooks pre-configured for specific models, simplifying the process of getting started with text generation, instruction following, and other LLM-based tasks.

TimeSeries_Seq2Seq is a GitHub repository offering a valuable collection of notebooks and code designed to facilitate the understanding and implementation of sequence-to-sequence (seq2seq) neural networks specifically for time series forecasting. The networks within this repository are built using popular deep learning frameworks, Keras and TensorFlow. It serves as a practical resource for data scientists and researchers looking to apply advanced neural network architectures to predict future values based on historical time-dependent data. The repository includes instructions for setting up the environment and working with the provided notebooks, making it accessible for those interested in hands-on learning and application of seq2seq models in time series analysis.

XZVoice is a free and open-source text-to-speech software designed for converting written text into spoken audio. It leverages the Aliyun speech synthesis engine to generate voices, providing a robust solution for various applications. The software is developed using modern web technologies including Electron, Vue, and ElementUI, making it a flexible and customizable tool. Users can integrate their own Aliyun AccessKeyId, AccessKeySecret, and appkey for personalized usage. Additionally, it supports the integration of online background music by allowing users to upload music packages to cloud storage like Qiniu Cloud. This makes XZVoice suitable for developers and content creators looking for a self-hosted and adaptable text-to-speech solution.

x-cmd is a comprehensive toolkit designed to empower AI agents and streamline command-line operations across various POSIX shells like bash, zsh, and ash. It features a Shell Standard Library with over 300 modules written in shell/awk, bringing modern capabilities to even minimal environments like BusyBox or Alpine. Beyond its core modules, x-cmd includes an On-Demand Package System, `pkg`, which provides access to over 600 curated modern CLI tools such as `jq`, `fzf`, and `ripgrep`, ensuring environment compatibility and minimizing dependencies. The tool is optimized for AI agents, allowing access to major AI providers like OpenAI, Gemini, and DeepSeek directly from the shell with a pure-shell agent under 2MB. Its design prioritizes flexibility, native system integration, and tool-chaining, making it ideal for scenarios where network latency and LLM throughput are critical.

XuanCe (玄策) is an open-source, comprehensive, and unified deep reinforcement learning (DRL) library designed to provide high-quality and easy-to-understand implementations of DRL algorithms. It aims to address the sensitivity of DRL algorithms to hyper-parameter tuning and unstable training processes by offering a robust and flexible framework. XuanCe is highly modularized, easy to install and use, and supports flexible model combinations. It includes abundant algorithms for various tasks, supporting both DRL and Multi-Agent Reinforcement Learning (MARL) tasks. The library boasts high compatibility across different deep learning backends (PyTorch, TensorFlow2, MindSpore), operating systems (Linux, Windows, MacOS), and hardware (CPU, GPU). Key features include fast running speed with parallel environments, distributed training with multi-GPUs, automatic hyperparameter tuning, and good visualization effects with TensorBoard or Weights & Biases.

Weighted-Boxes-Fusion is a comprehensive Python library designed for advanced object detection tasks, specifically focusing on ensembling bounding boxes from multiple models. It offers implementations of several key methods, including Non-maximum Suppression (NMS), Soft-NMS, Non-maximum weighted (NMW), and its namesake, Weighted Boxes Fusion (WBF). The WBF method is highlighted for providing superior results compared to other ensembling techniques. The library supports various dimensions, with specific functions for 3D boxes and 1D line segments, the latter being particularly useful for Natural Language Processing (NLP) tasks like Named-entity recognition (NER). It is built with Python 3.*, Numpy, and Numba, ensuring efficient processing. Usage examples are provided for both multiple and single model predictions, making it accessible for developers looking to enhance their object detection pipelines.

WPPConnect is an open-source project developed by the JavaScript community, designed to export functions from WhatsApp Web to Node.js. This allows developers to create a wide range of interactions, including customer service, media sending, and intelligence recognition based on artificial phrases. The tool supports essential WhatsApp functionalities such as sending various media types (text, image, video, audio, docs), managing contacts, chats, groups, and group members, and forwarding messages. It also features automatic QR refresh, multiple session support, and the ability to send stickers and location data. WPPConnect is continuously updated to adapt to changes in WhatsApp, with maintainers ensuring the core algorithm remains consistent while functions are updated.

Synnada is an AI infrastructure company dedicated to rethinking how intelligent systems are built. It provides the foundational technology for data science and content understanding, enabling the creation of reliable, scalable, and agent-native systems. Built by Apache DataFusion contributors, Synnada's offerings include Mithril for efficient model compilation, Tenet for multi-cloud AI workload deployment, and Agentia, a runtime for persistent agent systems with first-class code execution. This infrastructure supports the agentic economy, allowing intelligent agents to operate continuously across clouds, datasets, and decision loops, ensuring correctness, efficiency, and long-term operability for production-grade AI.

Qwen-Edit-2509-Upscale-LoRA is an AI tool designed for image editing and upscaling, leveraging LoRA (Low-Rank Adaptation) techniques to enhance image resolution and add high-quality details. Users can upload an image and fine-tune various parameters such as seed, guidance scale, and inference steps to achieve desired visual outcomes. This customization allows for precise control over the enhancement process, making it suitable for individuals looking to improve the quality and detail of their images. The tool aims to provide a flexible solution for image enhancement.

Advanced-Deep-Trading is a GitHub repository dedicated to experiments in financial machine learning, drawing inspiration from the book "Advances in Financial Machine Learning." This tool focuses on re-evaluating and adapting machine learning methodologies typically found in computer vision (CV) and natural language processing (NLP) to address the unique challenges of financial time series data, which is characterized by its stochastic nature. It offers resources for developing and testing algorithmic trading strategies, providing a practical framework for those looking to apply advanced ML concepts to financial markets. The repository includes various modules for backtesting metrics, feature importance analysis, and probabilistic backtesting, making it a valuable resource for researchers and practitioners in quantitative finance.

So Vits Svc Models Pcr is an AI tool hosted on Hugging Face Spaces, designed for voice cloning and the creation of custom voice models. While the live website indicates a runtime error and scheduling failure, suggesting current unavailability, the tool's purpose is to enable users to experiment with and develop unique voice models. It is suitable for individuals interested in voice synthesis, research, and development within the AI audio domain. The platform's nature implies a focus on providing a space for community-driven machine learning applications, making it potentially valuable for those looking to explore or contribute to AI voice technology.

Automated Trading Bot, also known as StockAgent, is an open-source, multi-agent AI system designed to simulate stock trading activities in environments that closely resemble real-world conditions. Driven by large language models (LLMs), StockAgent allows users to investigate how external factors such as macroeconomics, policy changes, company fundamentals, and global events influence trading behaviors and investor profits. A key differentiator is its ability to avoid test set leakage, ensuring that the model does not leverage prior knowledge of test data. The system evaluates various LLMs within its framework, providing insights into trading behavior and stock price fluctuations. This research tool is valuable for exploring free trading gaps without prior market data knowledge and offers insights for LLM-based investment advice and stock recommendations.

Stablediffusion Depth2img is an AI image generation tool available as a Hugging Face Space. It leverages the Stable Diffusion model to generate new images from depth maps, offering a unique approach to visual content creation. While the current live website indicates a runtime error, suggesting the tool may not be fully operational at this moment, its core functionality is designed for users interested in exploring advanced image synthesis techniques. This tool is particularly suited for those looking to experiment with depth-based image manipulation and generate artistic or visually distinct content.

Computer-vision-in-action is a comprehensive, open-source learning platform designed for individuals interested in mastering computer vision. It offers a closed-loop learning environment where users can interactively run code directly online, eliminating the need for complex local setup. The platform features an electronic book, available in both Chinese and English, covering fundamental theories, practical applications, and advanced topics like Transformer models and generative adversarial networks. It includes detailed project guidance, code implementations, and a community forum for reader interaction and support. The platform emphasizes a 'learn by doing' approach, allowing users to modify code and observe results in real-time.

computervision-recipes is a comprehensive open-source repository from Microsoft, offering best practices, code samples, and documentation for various computer vision tasks. It provides examples and guidelines for building computer vision systems, leveraging state-of-the-art libraries like PyTorch. The repository covers scenarios such as image classification, object detection, image similarity, keypoint detection, image segmentation, action recognition, and tracking. It aims to reduce development time by simplifying the process from problem definition to solution deployment, providing Jupyter notebooks and utility functions. The target audience includes data scientists and machine learning engineers looking for solution accelerators for real-world vision problems, with content ranging from fine-tuning models to hard-negative mining and model deployment.

Arbiter is a Rust-based, event-driven multi-agent framework designed for orchestrating strongly-typed, high-performance simulations and networked systems. It provides foundational types and traits for building actor-based systems with pluggable networking and lifecycle management. Tailored for discrete-event simulation, automated trading, and complex distributed systems, Arbiter's core concepts include Actors for execution units, LifeCycle for actor behavior, Handlers for message processing, Networks for system connections, and Runtimes for managing execution context. The framework is open-source and actively developed by Harnesslabs, offering extensive documentation and examples for in-depth understanding.

Arraymancer is a powerful n-dimensional tensor (ndarray) library implemented in Nim, designed for high performance and ease of use. It provides a robust foundation for scientific computing, machine learning algorithms, and deep learning applications. The library supports various backends including CPU, Cuda, and OpenCL, and can leverage OpenMP for multithreaded compilation. Key features include basic math operations generalized to tensors, matrix algebra primitives, efficient slicing, broadcasting support, and a variety of reshaping operations. Arraymancer can handle tensors up to 6 dimensions and supports reading/writing .csv, Numpy (.npy), and HDF5 files. While its deep learning components are still evolving, it offers functionalities for neural networks, including fully-connected layers and convolutional networks, making it a versatile tool for developers and data scientists working with Nim.

awesome-AI-books is a comprehensive GitHub repository dedicated to providing a curated list of AI-related books and PDFs. It serves as an invaluable resource for students and researchers looking to learn and download materials on artificial intelligence. The repository covers a wide range of topics, including introductory AI theory, mathematics for AI, data mining, machine learning, deep learning, philosophy of AI, quantum AI, and various AI frameworks and libraries. It also features a 'Training ground' section with links to platforms for AI experimentation and research, such as OpenAI Gym and DeepMind Pysc2. All books and PDFs are stored on Yandex.Disk due to GitHub's large file storage limitations, and the repository is intended for learning purposes only.

Awesome-deepseek-coder is a curated list of open-source projects and resources centered around DeepSeek Coder. It provides direct links to official DeepSeek Coder models hosted on Hugging Face, including base and instruct versions across various sizes (1.3B, 5.7B, 6.7B, 33B). Beyond official releases, the repository highlights community-built models that leverage DeepSeek Coder, such as OpenCodeInterpreter-DS and Magicoder-DS. It also features quantized models in AWQ, GGUF, and GPTQ formats, optimized for different deployment scenarios. The list includes integrations with AI coding assistants like Copilot refact and Tabby, showcasing DeepSeek Coder's capabilities in code completion and improvement. Additionally, it points to tools for finetuning data and API examples, making it a comprehensive resource for developers working with DeepSeek Coder.

Chinese-Text-Classification-Pytorch is an open-source toolkit designed for Chinese text classification tasks, built on the PyTorch framework. It offers out-of-the-box implementations of several popular text classification models, including TextCNN, TextRNN, FastText, TextRCNN, BiLSTM_Attention, DPCNN, and Transformer. The toolkit is user-friendly and ready for immediate deployment, supporting both character-level input and the integration of pre-trained word vectors, specifically using Sougou News Word+Character 300d. It also includes a pre-processed Chinese dataset (THUCNews) for training and evaluation, making it a comprehensive resource for researchers and developers working on Chinese NLP.

BabyAGI: an Autonomous and Self-Improving agent, or BASI, is an open-source project available on GitHub. This tool is designed to function as an autonomous AI agent capable of self-improvement, offering a platform for developers to explore and build advanced AI agent capabilities. It leverages concepts like 'chain-of-thought' and 'program-of-thoughts' to enable intelligent decision-making and task execution. The project is licensed under the MIT License, promoting free use, modification, and distribution. With a strong focus on AI and AGI, babyagi-asi provides a foundational framework for creating sophisticated autonomous systems.

CRSLab is an open-source toolkit designed for building Conversational Recommender Systems (CRS), developed using Python and PyTorch. It offers a robust framework with comprehensive benchmark models and datasets, including graph neural network and pre-training models like R-GCN, BERT, and GPT-2. The toolkit supports extensive and standard evaluation protocols for testing and comparing different CRS, and features a general and extensible structure for unifying various conversational recommendation datasets and models. CRSLab also provides human-machine interaction interfaces for qualitative analysis, making it easy for new researchers to get started with flexible configurations.