Coding & Development

TruEra offers comprehensive AI Quality solutions designed to help enterprises analyze machine learning models and significantly improve their quality. The platform provides AI Observability, encompassing both LLM Observability and Predictive AI Observability, to cover the entire AI lifecycle. This enables better MLOps and LLMOps by offering robust monitoring, testing, and quality management capabilities. TruEra's technology aims to eliminate the 'black box' surrounding AI and ML, providing explainability to ensure models are transparent, fair, and compliant. By leveraging TruEra, organizations can achieve measurable business results, address issues of unfair bias, and ensure strong governance and compliance for their AI initiatives.

Deep_and_Machine_Learning_Projects is an open-source GitHub repository containing a diverse collection of machine and deep learning projects. This resource provides readily available code and data files, enabling users to explore and implement practical applications of artificial intelligence. Each project within the repository is designed to be a standalone example, allowing individuals to understand specific use cases and integrate them into their own real-life scenarios. It serves as an excellent learning resource for those looking to gain hands-on experience in AI development, offering a practical approach to mastering machine and deep learning concepts through direct implementation.

v0.dev by Vercel is an AI-powered assistant designed to streamline the development of full-stack web applications. It allows users to generate working applications and code directly from natural language prompts or by uploading images. The tool supports rapid iteration and scaling, enabling developers to build agents, apps, and websites efficiently. Key capabilities include generating React code that integrates with frameworks like Shadcn UI and Tailwind CSS, syncing with GitHub repositories for direct code pushes, and integrating with various APIs. It also offers a visual design mode for fine-tuning details, pre-built templates for quick starts, and the ability to create design systems. v0.dev is agentic by default, planning tasks and connecting to databases as it builds, and supports deployment to Vercel for instant go-live.

FineTuningLLMs is the official repository for the book "A Hands-On Guide to Fine-Tuning LLMs with PyTorch and Hugging Face." This resource offers comprehensive guidance and practical code examples for fine-tuning large language models. It covers essential concepts such as quantization, low-rank adapters (LoRA), and dataset formatting templates. The repository features Jupyter notebooks that can be easily run on Google Colab with GPU support, making it accessible for hands-on learning. It delves into topics like loading quantized models, fine-tuning with SFTTrainer, and deploying models locally using formats like GGUF with Ollama or llama.cpp. The guide is designed for an intermediate-level audience, assuming a foundational understanding of deep learning concepts.

Nuwax is presented as the world's first universal agent operating system, designed to help users build private, vertical general-purpose AI agents. It serves as a platform for the design, development, and practical application of AI solutions, eliminating the need for coding. The system supports various deployment endpoints and APIs, offering comprehensive capabilities for workflow management, plugin integration, and application development. Nuwax also includes RAG (Retrieval-Augmented Generation) knowledge base and data table storage functionalities, making it suitable for a wide range of users. It supports multiple platforms and provides robust management features for users, audits, public models, content, and tasks.

Huatuo-Llama-Med-Chinese, also known as BenCao, is an open-source project focused on instruction-tuning large language models with Chinese medical knowledge. It leverages models such as LLaMA, Alpaca-Chinese, and Bloom, fine-tuning them with datasets built from medical knowledge graphs and literature using ChatGPT API. This process significantly improves the base models' performance in medical question-answering. The project provides LoRA weights for various base models, enabling efficient fine-tuning. It also introduces a knowledge-finetuning approach that allows models to explicitly utilize knowledge base information during inference, enhancing reliability in generating Chinese medical responses.

llm-security is a comprehensive resource and proof-of-concept repository dedicated to exploring novel vulnerabilities in application-integrated Large Language Models (LLMs). It specifically highlights the dangers of "indirect prompt injection," a new class of attack vectors that can lead to remote control of LLMs, data exfiltration, persistent compromises, and automated social engineering. The tool provides demonstrations across various LLMs, including GPT-4 and GPT-3, and shows how these attacks can affect code completion engines like Copilot. It serves as a critical resource for security researchers and developers to understand and mitigate significant roadblocks to the secure deployment of LLMs.

ML-Tutorial-Experiment is an open-source GitHub repository dedicated to providing comprehensive coding tutorials for machine learning. It aims to help users learn to code machine learning models through practical examples and experiments. The resource covers a wide array of topics, including building convolutional neural networks with TensorFlow, understanding and implementing Generative Adversarial Networks (GANs), exploring CapsNet architecture, and delving into RNNs and CNNs for sequence modeling. It also features tutorials on Transformer-based neural machine translation and foundational concepts like linear algebra, probability, Python basics, and NumPy. The project emphasizes reproducible code and aims to curate high-quality, error-free articles for developers and researchers.

mnehmos.multi-agent.framework is an open-source project designed to give Large Language Models (LLMs) a 'nervous system,' transforming them from stateless text predictors into more autonomous 'organisms.' It provides a biological architecture that organizes sensation, reflex, memory, and action into coherent loops. The framework features a multi-layered architecture including Central (Cognition), Somatic (Voluntary Action), Autonomic (Subconscious), and Reflex (Spinal Cord) components. It supports various modes for task decomposition, system design, planning, research, coding, debugging, and knowledge management. Key features include an OODA Loop for decision-making, a TDD Cycle for development, and a Boomerang Protocol for structured data returns, making it suitable for developers building advanced AI agents.

ollama-gui is a modern web interface designed for interacting with local Large Language Models (LLMs) through the Ollama API. It boasts a clean and responsive user interface, ensuring a smooth chatting experience. Key features include local chat history management using IndexedDB, comprehensive Markdown support for messages, and a dark mode option for user comfort. The tool prioritizes privacy by processing all data locally, ensuring no information leaves your system. It also offers a development proxy for easy network access and supports Docker deployment for simplified setup, allowing users to run both Ollama and the GUI together without complex configurations.

TheBloke Wizard Vicuna 13B Uncensored HF is an AI chatbot hosted as a Hugging Face Space. This tool offers an uncensored version of the Wizard Vicuna 13B model, allowing users to engage in conversational AI interactions without typical content restrictions. While the live website currently indicates a runtime error, suggesting it may not be fully operational at this moment, the intention is to provide a platform for direct interaction with this specific large language model. It is designed for those interested in exploring the capabilities of uncensored AI models within a readily accessible web environment.

MidJourney Styles & Keywords is an Open Source reference guide designed for users of the MidJourney AI image generation tool. It offers a comprehensive collection of styles and keywords that can be used to create highly customized and visually captivating images. Beyond just keywords, the resource also includes pages dedicated to resolution comparisons and image weights, providing valuable insights for optimizing image generation. This guide aims to help users unlock the full potential of MidJourney, making it an essential companion for anyone looking to enhance their AI art creation process. It is continually updated to reflect new trends and capabilities within the MidJourney ecosystem.

Whismer offers an easy-to-use, no-code platform for building custom AI chatbots tailored to your specific needs. Users can train their own ChatGPT-like AI by providing it with their unique data, including uploaded documents, website links, and personal notes. This functionality allows for the creation of a personalized AI knowledge base, suitable for individuals or teams. The tool simplifies the process of developing intelligent conversational agents without requiring any coding expertise, making advanced AI accessible to a broader audience for various applications.

Non-overwhelming-machine-learning is an open-source project hosted on GitHub, offering a carefully curated list of machine learning resources specifically designed for beginners. The primary goal is to provide a "non-overwhelming" introduction to the field, guiding users through a chronological learning path. It assumes foundational knowledge in probability, multivariable calculus, and optimization, ensuring that learners have the necessary prerequisites before diving into more complex topics. The resource list includes introductory courses like "Intro to Machine Learning UD120," "Deep Learning @ Udacity," and specialized courses on convolutional neural networks and natural language processing. This structured approach helps beginners build a solid understanding without feeling overwhelmed by the vastness of machine learning.

TensorFlow-and-DeepLearning-Tutorial is an open-source repository offering a collection of deep learning tutorials. Originally taught as an online course in 2016, it provides foundational knowledge in TensorFlow, fully connected neural networks, and convolutional neural networks. The resource also delves into Natural Language Processing concepts. Written primarily in Python and Jupyter Notebook, it serves as a valuable educational tool for individuals looking to understand and implement deep learning techniques.

PaddleFormers is an open-source library built on the PaddlePaddle deep learning framework, designed to offer model interfaces and functionalities comparable to Hugging Face Transformers. It supports the training of both large language models (LLM) and visual language models (VLM). The library leverages PaddlePaddle's inherent advantages in high-performance training, incorporating advanced distributed training strategies like tensor parallelism, pipeline parallelism, and expert parallelism, alongside automatic mixed precision for acceleration. PaddleFormers aims to provide a high-performance, low-resource-consumption training experience, enabling users to efficiently complete large model training without delving into complex optimization details. It supports a wide array of mainstream LLMs and VLMs, including DeepSeek-V3, GLM-4.5 series, Qwen2/3, and ERNIE models, and offers full-lifecycle training capabilities from pre-training to post-training, including CPT, SFT, SFT-LoRA, DPO, and DPO-LoRA.

stable-diffusion-webui-promptgen is an extension for the Stable Diffusion web UI designed to generate prompts, assisting users in creating effective inputs for image generation. This tool offers flexibility by allowing users to integrate additional prompt generation models from Hugging Face, such as AUTOMATIC/promptgen-lexart or microsoft/Promptist, by simply adding their names to the settings. Furthermore, users can incorporate offline models by placing the necessary files into the extension's models directory, providing a robust solution for prompt experimentation and customization. The extension supports various GPT2 finetunes on datasets like Lexica.art and Majinai.art, offering both safe and unsafe prompt options.

Visual-openLLM is an open-source project designed to interactively connect various visual models, functioning similarly to Visual ChatGPT. It is built upon established technologies like ChatGLM, Visual ChatGPT, and Stable Diffusion, positioning itself as an open-source version of '文心一言'. The tool supports ChatGLM3, adding features such as VQA (Visual Question Answering) and Pix2Pix capabilities. Its development roadmap includes support for multi-turn chat, integration with other visual tools, and compatibility with additional large language models, making it a versatile platform for visual AI experimentation and application.

transformers_tasks is an open-source project on GitHub that integrates various NLP algorithms using the powerful Hugging Face transformers library. It offers implementations for a wide range of tasks, including text matching (PointWise, DSSM, Sentence Bert, SimCSE), information extraction (UIE), prompt tasks (PET, p-tuning), and text classification (BERT-CLS). The project also delves into advanced areas like Reinforcement Learning from Human Feedback (RLHF) for language models, text generation (T5-Based models), and large language model (LLM) applications and training. It provides a flexible framework for researchers and developers to train and fine-tune models using their own datasets.

AIdea Server is a fully open-source application server developed in Golang, designed to integrate a wide range of large language models (LLMs) and image generation models. It supports prominent LLMs such as GPT, Tongyi Qianwen, and Wenxin Yiyan, alongside image generation capabilities like Stable Diffusion (text-to-image, image-to-image, SDXL 1.0), super-resolution, and image coloring. This versatile backend facilitates AI chat, collaboration, and advanced image processing, making it suitable for developers looking to self-host AI services. The project offers a robust framework for modular application development with dependency injection and an in-house ORM for database operations, ensuring a scalable and maintainable architecture.

VAR (Visual Autoregressive Modeling) is an open-source project that introduces a novel approach to image generation, moving beyond traditional raster-scan "next-token prediction" to a coarse-to-fine "next-scale prediction." This method allows GPT-style autoregressive models to achieve state-of-the-art results, even outperforming diffusion models in visual generation. The project emphasizes scalability, user-friendliness, and provides a robust codebase for researchers and developers. It also highlights the discovery of power-law scaling laws within VAR transformers and demonstrates strong zero-shot generalizability. VAR has received the NeurIPS 2024 Best Paper Award and offers various pre-trained models for different resolutions and complexities.

LunarLink AI provides a unified platform to access and compare outputs from various advanced AI models, including ChatGPT, Claude, and Gemini. It operates on a pay-as-you-go model, charging based on usage at first-party API prices plus a small per-answer fee, eliminating the need for subscriptions or commitments. Users can chat with multiple AI assistants simultaneously, view responses side-by-side to reduce bias, and enjoy features like unlimited file uploads and cross-platform chat synchronization. The platform prioritizes privacy with a data-safe mode that ensures no storage or training of user data, and offers a customizable interface with dark/light modes and enhanced content presentation for rich text and code blocks.

OpenServ is an infrastructure platform designed to empower founders with autonomous AI teams and onchain launch capabilities. It facilitates the building, launching, and running of AI applications by providing a suite of dedicated AI agents for various operational aspects, including community management, marketing, and growth. The platform leverages the proprietary SERV Reasoning Framework, which significantly enhances the performance of models like GPT-5 and reduces hallucination rates. OpenServ also supports custom enterprise solutions, designing and deploying production-ready AI systems using its orchestration platform and reasoning engine. It aims to simplify Web3 payments and automation through its x402 protocol and offers an Appcelerator program with grants, AI infrastructure, and advisory networks.

PlayableX provides modern advertising services and tools specifically designed for mobile studios and publishers. The platform features an AI-driven creative engine that enables the creation of scalable and innovative ads, including custom playable ads. Users can leverage the Custom Playable AI Editor and an AI-Powered Creative Tool to develop high-performing ad assets. PlayableX highlights success stories with significant improvements in D1 and D7 retention, ROAS, and IAP conversion for mobile games. The tool aims to help mobile studios enhance user acquisition and monetization through advanced AI analytics and creative solutions.