Coding & Development

Musclog is a free and open-source application designed for comprehensive fitness and nutrition tracking. It stands out by offering AI-powered workout tracking and AI photo nutrition logging, all while ensuring 100% privacy as it operates entirely on-device without requiring accounts or cloud synchronization. Users can track their progress with detailed charts, making it an ideal solution for individuals who prioritize data sovereignty and offline functionality. Available on Android, iOS, and Web, Musclog provides a robust solution for managing personal health and fitness data securely.

Awesome-Audio-LLM is a meticulously curated open-source repository dedicated to Audio Large Language Models (LLMs). It serves as a central hub for researchers, developers, and enthusiasts to explore the rapidly evolving field of audio AI. The resource categorizes entries by models, benchmarks, datasets, and safety considerations, offering detailed information on each, including author(s), publication dates, and links to papers or models. It covers a wide range of applications, from speech interaction and understanding to multimodal language models and audio generation. The repository is continuously updated with new research and contributions, making it an invaluable tool for staying current with advancements in audio LLMs.

DeepSeek-V4.ai serves as a dedicated tracker for the anticipated DeepSeek V4, an AI model expected to be a flagship for repo-level coding, long-context reasoning, and agentic workflows. As of February 16, 2026, the model is not officially released, but the site compiles rumored specifications like a ~1 Trillion parameter MoE system, 1M+ token context, and innovative memory core technologies. It also presents unverified leaked benchmarks, including impressive claims for SWE-Bench and HumanEval. The platform highlights the potential impact of DeepSeek V4 on cost pressure, repo-scale agent workflows, and local/self-hosted adoption, making it a valuable resource for developers and AI researchers awaiting its launch.

FraudGPT is an uncensored artificial intelligence chatbot designed for unrestricted queries, allowing users to ask literally anything without content filters. It provides an anonymous and PGP-encrypted chat experience. Beyond basic conversation, the tool supports advanced functionalities such as file generation, PDF creation, script generation, and web search. Users can access 5 free tokens to start, making it accessible for initial exploration. This platform caters to individuals seeking an AI without the typical limitations and content moderation found in other models, offering a unique space for unmoderated AI interactions and content creation.

Awesome-Graph-Neural-Networks is a comprehensive collection of academic papers and resources focused on Graph Neural Networks (GNNs). This GitHub repository serves as a valuable reference for researchers and students, categorizing papers into various GNN types such as Recurrent, Convolutional, and Spatial-Temporal GNNs. It also covers related areas like Graph Autoencoders, Network Embedding, and Graph Generation. Additionally, the resource highlights applications of GNNs in diverse fields including Computer Vision, Natural Language Processing, Internet, Recommender Systems, Healthcare, Chemistry, and Physics. The curated lists include survey papers, foundational research, and recent advancements, making it an essential tool for staying updated on the latest developments in the field.

Rich-Text-to-Image is an open-source project that allows users to generate images from rich text inputs, offering a high degree of control over the output. By utilizing various formatting information such as font size, color, and style, the tool enables explicit token reweighting, precise color rendering, local style control, and detailed region synthesis. It supports Stable Diffusion v1-5, Stable Diffusion XL, and ANIMAGINE-XL models. The workflow involves converting rich text into a JSON format, which then guides a region-based diffusion process to render attributes into a coherent image. The project also provides an A1111 WebUI extension and a HuggingFace demo for easy access and experimentation.

awesome-multi-task-learning is a meticulously curated list designed for researchers and practitioners in the field of Multi-Task Learning (MTL). It compiles essential resources including datasets, codebases, and academic papers, all from a machine learning perspective. The project is continuously updated and greatly appreciates community contributions, ensuring its relevance and comprehensiveness. It covers various aspects of MTL, from benchmark datasets in computer vision and natural language processing to different architectural approaches like hard and soft parameter sharing, and optimization strategies. This resource is invaluable for anyone looking to explore, implement, or stay current with advancements in multi-task learning.

CYRAN AI Solutions is an IIT Delhi spinoff specializing in enterprise-grade hardware-software AI solutions across GeoSpatial, Industry 4.0, and EdTech. For GeoSpatial, it provides indigenized solutions for real-time situational awareness, utilizing multi-sensor data fusion and advanced AI for processing aerial and space platforms, alongside customized AI-native GIS Solutions. In Industry 4.0, CYRAN offers tailored AI solutions ranging from computer vision for automated defect inspection and LLMs for industrial data management to contact-free machine health monitoring and edge-AI compute applications. For EdTech, it provides experiential AI skilling through the BUDDHI AI DIY Kit, enabling hands-on learning and self-paced projects for aspiring AI professionals.

Awesome-Robotics-3D is a comprehensive, curated list of 3D Vision papers specifically focusing on the intersection of robotics and large models such as Large Language Models (LLMs) and Vision-Language Models (VLMs). Inspired by awesome-computer-vision, this repository serves as a valuable resource for researchers and academics. It categorizes papers into key areas like Policy Learning, Pretraining, VLM and LLM applications, Representations, and Simulations, Datasets, and Benchmarks. Each entry typically includes links to the paper, associated webpages, and code, making it easy for users to access and explore the research. The list is actively maintained and encourages contributions from the community.

Dataklid AI appears to be a parked domain name on the Hostinger DNS system, rather than an active AI tool. The website content primarily advertises Hostinger's services, including web hosting, a website builder that uses AI tools, and VPS hosting. It also promotes features like building a complete website with CRM and booking forms using AI, and creating professional business emails. There is no specific information about a tool named "Dataklid AI" or its functionalities related to metaverse development, computer vision, or data annotation, as suggested by the previous description. The site focuses on general web services provided by Hostinger.

awesome-nlp is a comprehensive, curated list of resources for Natural Language Processing (NLP) enthusiasts and researchers. It provides an extensive collection of links covering research summaries and trends, prominent NLP research labs, and various tutorials. The resource also includes reading content, videos, online courses, and books related to NLP. Furthermore, it categorizes libraries by programming language, such as Python, Node.js, C++, Java, and more, making it easy to find relevant tools. The list also highlights NLP resources specific to different languages like Korean, Arabic, Chinese, and German, catering to a diverse audience interested in the field.

awesome-nlp-sentiment-analysis is a comprehensive, open-source collection of resources for Natural Language Processing (NLP), with a strong emphasis on sentiment analysis. This GitHub repository compiles relevant datasets, academic papers, and practical open-source implementations. It specifically targets sub-areas such as general sentiment analysis, emotion cause recognition, and the extraction of evaluation objects and associated words. Researchers, students, and developers in the NLP field can leverage this curated list to find foundational knowledge, state-of-the-art research, and practical code examples to advance their work in understanding and processing human emotions and opinions from text.

Awesome-Korean-NLP is a comprehensive, curated list of resources dedicated to Natural Language Processing (NLP) for the Korean language. This GitHub repository serves as a central hub for various tools, datasets, blogs, research papers, lectures, and online communities relevant to Korean NLP. It includes specific sections for morpheme/PoS taggers, named entity taggers, spell checkers, syntax parsers, sentimental analysis tools, translators, and general NLP packages. The resource also lists significant Korean datasets like Sejong Corpus and Wikipedia Dump, alongside academic papers and lectures from prominent institutions. It's an invaluable resource for anyone working with Korean language data, from academic researchers to developers building Korean NLP applications.

awesome-langchain is a curated list of tools and projects that leverage the LangChain framework, designed to assist developers in building applications with Large Language Models (LLMs). The repository serves as a dynamic tracker for initiatives within the LangChain ecosystem, which is expanding at a rapid pace. It provides a comprehensive overview of various components, including LangChain framework ports to other languages, low-code tools, services, agents, templates, and open-source projects for knowledge management and chatbots. This resource is invaluable for developers looking to explore, implement, and stay informed about the latest advancements and tools available for LangChain.

awesome-llm-agents is a comprehensive, curated list of open-source LLM agent frameworks and development tools designed to assist developers in building sophisticated AI agents. The repository features a wide array of frameworks, each detailed with its key characteristics, such as multi-agent collaboration, modular architecture, data analysis capabilities, and integration with various LLM providers. It includes popular tools like CrewAI, Langchain, Microsoft AutoGen, and Llama Index, alongside specialized frameworks for areas like software development (MetaGPT), scientific discovery (GenoMAS), and robotics (RAI). The list is regularly updated and serves as a valuable resource for anyone looking to explore or implement LLM agent technologies, offering insights into different approaches to agent design, workflow orchestration, and tool integration.

awesome-online-machine-learning is a comprehensive, open-source curated list of resources dedicated to online machine learning. This field focuses on machine learning where data arrives sequentially, allowing models to update incrementally with one data point at a time, contrasting with traditional batch learning. The repository provides valuable links to courses, books, blog posts, and software related to online ML. It also features an extensive collection of research papers covering various online learning topics such as linear models, support vector machines, neural networks, decision trees, unsupervised learning, time series analysis, drift detection, and anomaly detection. This resource is ideal for anyone looking to deepen their understanding or find tools for online machine learning.

awesome-opencode is a comprehensive, curated list of plugins, themes, agents, projects, and resources specifically designed for Opencode, an AI coding agent for the terminal developed by the team at Anomaly. This open-source repository serves as a central hub for developers looking to enhance their Opencode experience with various functionalities. It categorizes resources into official repositories, plugins, themes, agents, and general resources, making it easy to discover tools for agent identity, memory, dynamic skill loading, authentication with various AI models (Gemini, Anthropic, OpenAI Codex), background process management, context analysis, and much more. The collection includes tools for advanced features like multi-agent orchestration, persistent memory with vector databases, real-time tmux integration, and strategic planning, catering to a wide range of development needs.

U-KAN is an official PyTorch implementation designed to serve as a robust backbone for medical image segmentation and generation. It leverages the innovative Kolmogorov-Anold Network (KAN) layers, integrating them into the established U-Net pipeline. This integration, termed U-KAN, aims to enhance accuracy and efficiency in medical imaging tasks. The tool has demonstrated superiority in rigorous medical image segmentation benchmarks, achieving higher accuracy with reduced computational cost. Furthermore, U-KAN explores its potential as an alternative U-Net noise predictor in diffusion models, showcasing its applicability in generating task-oriented model architectures. It is the first effort to incorporate KAN's advantages into the U-Net pipeline, offering a more accurate, efficient, and interpretable solution for vision tasks.

Fusion AI simplifies the complex AI landscape by integrating top-tier AI models from OpenAI, Anthropic, and Google, including o4 mini, GPT-5, Sonnet 4, and Gemini 2.5 Pro, into one unified platform. This ensemble approach ensures users receive the best possible results by leveraging the unique strengths of each model. The platform is designed for ease of use, allowing users to simply tell Fusion AI what they need, and it assembles the perfect team of AI models to collaborate and deliver refined solutions. Fusion AI operates on a usage-based credit system, eliminating subscriptions and hidden fees, making it a flexible and transparent solution for both small businesses and large enterprises.

Monash DeepNeuron is a student team dedicated to the exploration and advancement of Artificial Intelligence (AI) and Optimised Computing (OC). Based at Monash University, the team focuses on empowering, engaging, and educating individuals in these fields. Through hands-on research projects, they equip students and researchers with essential skills and knowledge. The initiative fosters collaborative networks between students, academic staff, and industry partners to drive innovation and excellence. Monash DeepNeuron also emphasizes accessibility through community outreach events and educational initiatives, aiming to demystify AI and OC and promote understanding for broader participation in the digital revolution. Their diverse team includes members from various disciplines, working on projects across aerospace, science, medicine, gaming, and psychology.

ml-on-gcp is a comprehensive resource offering guides and practical recipes for integrating various Machine Learning frameworks with Google Cloud Platform. The primary goal is to simplify the process of bringing ML code to GCP, allowing users to dedicate more time to data exploration, model development, and problem-solving rather than interface management. It includes examples for TensorFlow, scikit-learn, and xgboost, along with tutorials on topics like hyperparameter search on Google Kubernetes Engine, running TensorFlow inference at scale with TensorRT, and inferring models from Google Cloud Functions. The repository also links to other Google Cloud ML resources, such as AI Platform samples and Google Cloud AI Developer Relations content.

Auth0 is a comprehensive identity platform designed for secure user and AI agent authentication and authorization. It simplifies identity management with features like Universal Login, Single Sign-On (SSO), Multifactor Authentication (MFA), and passwordless options. The platform is highly scalable, handling billions of authentications monthly, and offers over 30 SDKs and Quickstarts for easy integration into any application. Auth0 is particularly focused on securing AI agents, allowing control over tools, managing API calls, and applying fine-grained authorization to RAG pipelines. It also supports safeguarding internal AI tools and unlocking enterprise deals with features like multi-tenancy and enterprise connections.

Llama 3.2 is a versatile open-source large language model, part of the Llama 3 series, offering flexible and cost-effective solutions for various applications. It includes lightweight 1B and 3B parameter models optimized for efficiency and deployment on edge devices. Additionally, it features more powerful 11B and 90B multimodal models capable of reasoning on high-resolution images and generating text. This makes Llama 3.2 suitable for a range of use cases, from resource-constrained environments to complex multimodal understanding tasks, providing developers with options to build on their own terms with optimized performance.

Cabptoid Solutions Pvt Ltd is a software development company based in Hyderabad, specializing in end-to-end IT solutions. Their services encompass AI/ML and chatbot development, iOS and mobile app creation, UI/UX design, and custom software development. They also provide digital marketing, staffing, and LMS software solutions. The company emphasizes an "outcome over output" approach, aligning solutions with client KPIs and employing an "evaluation-first" mindset for AI projects to ensure accuracy and reliability. Security is a core principle, with a "Secure by Design" philosophy incorporating data encryption and governance frameworks. They combine technical engineering with human-centered design to create intuitive AI experiences.