Coding & Development

deeplearning-models is a comprehensive collection of various deep learning architectures, models, and practical tips, presented in Jupyter Notebooks. It supports both TensorFlow and PyTorch frameworks, offering implementations for traditional machine learning, multilayer perceptrons, convolutional neural networks (including AlexNet, DenseNet, LeNet, MobileNet, VGG, ResNet), transformers, ordinal regression, normalization layers, metric learning, autoencoders (fully-connected, convolutional, variational, conditional variational), generative adversarial networks (GANs), graph neural networks (GNNs), and recurrent neural networks (RNNs). The repository also includes notebooks on model evaluation, data augmentation, tips and tricks, transfer learning, visualization, and PyTorch/TensorFlow workflows, making it an invaluable resource for learning and implementing deep learning concepts.

deepjazz is an open-source project designed for deep learning-driven jazz music generation. Developed using Keras and Theano, it leverages a two-layer LSTM to learn from provided MIDI files and compose new jazz pieces. This tool offers a unique opportunity for developers and music enthusiasts to experiment with AI in creative music composition, specifically within the jazz genre. While no longer actively developed, it serves as a valuable historical example of AI's application in music, demonstrating how deep learning can be used to create something as inherently human as music. The project was built during a hackathon, showcasing rapid prototyping in AI music generation.

Deep-Learning-For-Hackers is a comprehensive collection of machine learning tutorials designed to equip users with practical skills for real-world problems. The resource utilizes TensorFlow 2 and Keras in Python, with all tutorials provided as Jupyter notebooks for hands-on learning. It covers a wide array of topics including LSTMs, hyperparameter tuning, data preprocessing, bias-variance tradeoff, anomaly detection, autoencoders, time series forecasting, object detection, sentiment analysis, and intent recognition with BERT. This guide is ideal for those looking to build a strong foundation in machine learning and apply these techniques to computer vision, natural language processing, and time series analysis tasks.

MockAPI Dog provides a free, no-signup solution for developers to instantly create and deploy mock REST APIs and LLM streaming endpoints. It's ideal for quick API prototyping and AI integration testing, supporting OpenAI, Anthropic, and generic streaming formats. Users can configure custom JSON responses, HTTP methods, status codes, and simulate network delays or error rates. This tool is perfect for frontend development, testing AI chatbot integrations without burning API credits, and rapid prototyping. It also offers a library of pre-built mock APIs for common use cases, making it a versatile resource for learning, development, and CI/CD testing.

Bugasura is a comprehensive quality platform designed to streamline bug reporting, management, and resolution for development teams. It integrates an AI-first issue tracker that helps generate issue descriptions, identify impact, and suggest fixes, significantly speeding up the bug logging process. Beyond issue tracking, Bugasura provides robust test management features, allowing users to create requirements, link test cases, and manage test runs efficiently. It also offers diverse bug reporters, including website feedback tools with visual steps to reproduce, in-app widgets for session replays, and console messages. The platform supports custom workflows, sprints, and seamless integrations with popular project management and developer tools like GitHub, Jira, and Slack, making it an all-in-one solution for ensuring product quality.

Contilio AI is an advanced 3D AI analytics platform designed for the construction industry, transforming raw site data into actionable insights. It provides real-time analysis of installation quality, project progress, performance KPIs, and potential risks. The platform works by integrating data from regular image and site scans, which its world-first 3D machine learning engine automatically processes. This enables stakeholders to have a single source of truth, improving productivity, cashflow, and delivery speed. Contilio AI helps identify and react to inefficiencies with agility, enhances transparency, and ensures compliance and safety across all trades, ultimately saving millions and keeping projects on track and on budget.

Db4Cloud Technologies Pvt Ltd offers professional cloud database solutions and services, focusing on optimizing business operations through secure and scalable systems. While the live website content is minimal, the company's stated expertise includes cloud computing, ERP, and generative AI solutions. Their approach aims to enhance decision-making and automate workflows across various industries by leveraging advanced AI capabilities. The company emphasizes providing robust infrastructure to support modern business needs, ensuring data integrity and operational efficiency.

Synapsia-AI is an Italian research and development lab specializing in Cognitive Artificial Intelligence, aiming to redefine AI beyond traditional deep learning and predictive models. They developed Maia, the first Cognitive Operating System, which comprehends scenarios, creates strategies, and makes independent decisions. Maia's architecture, built on ThinkFlow, Listeners, and Neural ID, allows it to process complex reasoning, optimize processes in real-time, and continuously learn without massive training. This enables Maia to adapt to various sectors like Fintech, Healthcare, Industry 4.0, and Smart Cities, offering solutions for fraud detection, diagnostic support, production automation, and mobility management. Synapsia also extends Maia's capabilities to the physical world through Maia Edge, Maia Sentia, and Maia Smart Home, and showcases its potential with the Maia App for text generation, image creation, and business research.

Prompt Perfect is an AI prompt design studio that helps users create precise and effective inputs for various AI models. It simplifies the process of crafting prompts, making advanced AI capabilities more accessible. The tool assists in refining AI queries to achieve desired outputs efficiently, offering tips, guides, and strategies for better prompt engineering. It also provides a free Chrome Extension to generate prompts for AI interactions with models like Claude and Gemini. The platform features a blog with articles on various AI topics, including ChatGPT capabilities, essay writing strategies, and comparisons of LLM performance, making it a valuable resource for both beginners and experienced AI users.

[prompts.ai] is a centralized AI platform designed for enterprises to orchestrate and manage AI workflows securely and efficiently. It unifies access to over 35 large language models, including GPT, Claude, LLaMA, and Gemini, through a single interface, eliminating tool sprawl and streamlining operations. The platform features a built-in FinOps layer for real-time visibility into AI usage, spend, and ROI, ensuring cost optimization. Users can compare LLMs side-by-side, automate workflows across departments, and access an extensive library of expert-built prompts and workflows. [prompts.ai] also provides tools for image generation, LoRA training, and AI agent creation, all while adhering to security and compliance standards like SOC 2 Type II, HIPAA, and GDPR.

Just Gpt It is a prompt management tool designed to streamline the creation, organization, and refinement of AI prompts. It provides a platform for users to test various prompts and iterate on them to achieve optimal outputs from different AI models. The tool aims to simplify the prompt engineering process, making it easier for individuals and teams to manage their AI interactions effectively. While specific features are not detailed, the core functionality revolves around enhancing the efficiency and quality of AI prompt development and usage.

Outdefine Execute is an AI platform specifically designed for regulated healthcare and life sciences industries. It deploys governed AI directly into existing systems, facilitating real-time, policy-driven execution across clinical, claims, and operational workflows. The platform emphasizes rapid deployment and measurable impact, allowing organizations to start with a single high-value workflow and automate actions without requiring extensive system overhauls. Outdefine Execute provides AI-powered decisioning, full observability, and policy-driven control, ensuring compliance and efficiency in production environments. Built by leaders with experience in complex regulated systems, Outdefine aims to bring AI into production across critical healthcare and life sciences processes, delivering faster execution and tangible results.

llm-numbers is a comprehensive GitHub repository curated by ray-project, offering critical numerical insights for Large Language Model (LLM) developers. This resource details various metrics, such as the cost ratios between different OpenAI models (GPT-4 vs. GPT-3.5 Turbo, embedding costs), the cost-effectiveness of self-hosting embeddings versus using commercial APIs, and the financial implications of fine-tuning versus training models from scratch. It also provides crucial information on GPU memory capacities and requirements for serving LLMs, including the impact of batching on throughput. The repository aims to equip developers with the knowledge needed for back-of-the-envelope calculations, enabling informed decisions on infrastructure, cost optimization, and model deployment.

LoRA the Explorer SDXL is an AI tool hosted on Hugging Face that enables users to explore various LoRAs (Low-Rank Adaptation) and generate 1024x1024 images using the Stable Diffusion XL model. Users can select a LoRA from a gallery, input a prompt and an optional negative prompt, and adjust the LoRA strength to customize their image generation. This tool is designed for experimenting with different AI models and is suitable for content creation and AI art. While the current live website indicates a runtime error, its intended functionality is to provide an accessible platform for AI image generation.

Strongbytes is an engineering partner focused on building AI-first products, offering expertise in advanced AI systems, modern data foundations, and end-to-end product delivery. They work with organizations across healthcare, fintech, people analytics, education, automotive, and the public sector to adopt AI safely and at scale. Their services include developing AI products and agentic systems like copilots and intelligent automation, as well as providing AI evaluation and observability to measure behavior, monitor performance, and continuously improve AI systems. Strongbytes also offers comprehensive product engineering for SaaS applications and APIs, alongside data and ML foundations for reliable data pipelines, governance, and scalable analytics. They are the creators of Aegis, an AI evaluation platform specifically for GenAI systems.

leaked-system-prompts is a GitHub repository that serves as a comprehensive collection of system prompts that have been "leaked" or discovered from widely used LLM-based services. This open-source project offers a unique glimpse into the underlying instructions and configurations that guide the behavior of popular AI models like Anthropic Claude, OpenAI ChatGPT, Google Gemini, and Microsoft Copilot. It's an invaluable resource for prompt engineers, AI researchers, and developers looking to understand, analyze, and potentially reverse-engineer the operational mechanics of these advanced AI systems. The repository is freely accessible and encourages community contributions, provided they include verifiable sources or reproducible prompts to maintain accuracy and prevent DMCA issues.

RecoSense Labs Inc is an AI transformation partner focused on delivering Process Intelligence solutions to enterprises. The platform specializes in converting unstructured raw data into structured, actionable insights using advanced AI and ML technologies. Key offerings include Natural Language Query for data insights, automated Document Analysis for extraction and validation, and AI-based Image Analysis for classification. RecoSense also provides Speech to Text transcription and translation, Knowledge Graph creation for data organization, and intelligent Data Extraction from multiple sources. These solutions are applied across various industries like Banking, Insurance, Manufacturing, and Healthcare, addressing use cases such as tax statement analysis, risk and compliance, fraud detection, and KYC verification.

LLamaSharp is a powerful cross-platform C#/.NET library designed to efficiently run Large Language Models (LLMs) such as LLaMA and LLaVA directly on your local device. Built upon `llama.cpp`, it offers high-performance inference on both CPU and GPU, making it accessible for developers. The library provides higher-level APIs and RAG (Retrieval Augmented Generation) support, simplifying the deployment of LLMs within applications. It includes integrations for popular frameworks like semantic-kernel, kernel-memory, BotSharp, and Langchain, facilitating diverse application development. LLamaSharp supports various backends including CPU, CUDA, Metal, and Vulkan, and uses the GGUF model format, with guidance provided for model preparation and conversion.

Midjourney Prompt Generator Using Chatgpt is an AI-powered tool designed to assist users in creating effective prompts for the Midjourney AI art generator. By utilizing ChatGPT's advanced language capabilities, it generates creative and detailed prompts that can significantly enhance the quality and specificity of AI-generated art. This tool is particularly useful for artists, designers, and enthusiasts looking to explore various art styles, experiment with different visual concepts, and maintain character consistency across multiple generations. It simplifies the prompt engineering process, allowing users to focus more on their creative vision rather than the intricacies of prompt formulation. The tool aims to make AI art generation more accessible and versatile for a wide range of users.

AI Vision Sweden AB specializes in delivering AI-powered computer vision solutions tailored for manufacturing and logistics industries. The platform automates quality control, detects process deviations, and enhances operational safety by replacing manual visual checks with camera-based inspection and machine learning models. AI Vision offers a complete system solution, including remote hardware installation, custom AI model development based on real production data, and seamless integration with existing PLC systems. Their approach goes beyond generic smart cameras, providing tailored AI built for specific materials and defects, ensuring lower maintenance and lifecycle costs through continuous updates and support. They work with industries such as sawmills, vehicle damage inspection, food and beverage, manufacturing, and steel.

Automina is an AI-driven browser automation agent designed to streamline various online tasks. It excels at simplifying repetitive actions, conducting end-to-end (E2E) testing for web applications, and efficiently updating information within a cloud-based browser environment. Users can assign missions to the AI agent, such as searching for specific data on GitHub, summarizing search results from Google, or listing new models on Hugging Face. This tool aims to save time and significantly boost productivity by automating browser interactions, making it suitable for both individual users and teams looking to optimize their web-based workflows.

Qase is an AI-powered test management platform designed to boost software delivery speed and quality. It offers a comprehensive suite of features for both manual and automated QA testing, including test authoring, test management, requirements traceability, and reporting. The platform integrates with over 35 tools like Jira, GitHub, and Cypress, allowing teams to consolidate all testing activities into a single workspace. Qase's AI Software Testing Agent, AIDEN, provides capabilities for AI test conversion, generation, analysis, and execution, helping teams run tests up to 90% faster. Customizable dashboards and shareable reports enhance data analysis, enabling data-informed decisions throughout the testing cycle. Qase is built for enterprise-level performance, offering dedicated infrastructure, data retention, and flexible API integrations.

Multi-Agent AI - Coding is an AI tool built on Microsoft AutoGen, designed to facilitate multi-agent AI coding. Users can input their OpenAI API key and a specific coding task to receive AI-generated solutions and code snippets. This platform is hosted on Hugging Face Spaces, making it accessible for developers looking to leverage AI for automated code generation and collaborative coding projects. It aims to streamline the development process by providing intelligent assistance for various coding challenges, offering a practical application of multi-agent AI in software development.

Tasq is an AI operations platform specifically designed for oil and gas operations, acting as an intelligence layer to replace human surveillance. It enables AI agents to search for failure patterns across an entire asset base, deploy models, and deliver live time series workflows in under two minutes. The platform integrates with various data sources like SCADA, Pi, and WellView, offering features such as signal search, a 'Build Your Own Model' capability, automated downtime tracking, AI data entry, and agentic workflows. Tasq allows production engineers, field operators, and control room staff to build and deploy AI models directly from their domain knowledge, without requiring data science expertise or coding. It aims to detect issues like liquid loading and paraffin buildup significantly in advance, triggering automated workflows for root cause classification, work order creation, vendor bidding, and reliability reporting.