Coding & Development

Best Upscaling Models is a web-based tool that provides a selection of non-diffusion upscaling models to enhance image resolution and quality. Users can upload an image and choose from various models to achieve a higher resolution output. The platform is designed to be straightforward, presenting both the original and the upscaled images for comparison. This tool is particularly useful for individuals and professionals who need to improve the clarity and size of their images without relying on diffusion-based methods, making it a valuable resource for various visual content needs.

VoiceStreamAI is a Python 3-based server and JavaScript client solution designed for near-realtime audio streaming and transcription. It leverages WebSocket for real-time communication and integrates Huggingface's Voice Activity Detection (VAD) with OpenAI's Whisper model (or faster-whisper by default) for accurate speech recognition. Key features include a modular design for easy integration of different VAD and ASR technologies, support for multilingual transcription, and customizable audio chunk processing strategies. The system optimizes processing by detecting speech segments, reducing computational load and improving accuracy. It also supports client-specific configurations for language, chunk length, and processing strategy, making it a flexible solution for developers building real-time transcription capabilities.

Z-IMAGE GEN/LORA is a Hugging Face Space that serves as a demo for a collection of impressive LoRAs for Z-Image-Turbo. This tool enables users to generate high-quality images by simply providing a text prompt and choosing from various LoRA styles, or even adding their own. The application offers adjustable settings such as image size, generation steps, and seed, giving users control over the output. While the Space is currently paused, it showcases the potential for creative content generation and image customization through the exploration of different LoRA models.

LitGPT is a comprehensive open-source toolkit designed for developers and AI researchers working with large language models. It offers over 20 high-performance LLMs, each implemented from scratch without abstractions, ensuring full control and optimized performance. The platform provides ready-to-use recipes for pretraining, finetuning, and deploying these models at scale, supporting features like Flash Attention, FSDP, LoRA, QLoRA, and Adapter finetuning. LitGPT is built to reduce GPU memory usage through various precision settings (FP16, BF16) and quantization techniques (4-bit, 8-bit). It supports deployment as inference APIs and offers command-line interfaces for advanced workflows, making it suitable for enterprise-level applications and academic research.

SnapPoint, offered by Alex Cloudstar, is a full-stack development service focused on delivering robust and timely software solutions. Alex brings experience from companies like E.ON, ING, and Warner Bros., specializing in technologies such as TypeScript, React, Node.js, Next.js, PostgreSQL, and AWS. He is available for freelance projects and long-term collaborations, emphasizing clear communication, honest timelines, and durable code. The service is ideal for clients seeking custom software development with a focus on quality and efficiency, particularly for projects involving modern web stacks and AI agent architectures.

RocketFrog.ai is an AI studio specializing in making next-generation AI solutions available, affordable, and accessible for businesses. The platform offers a range of services including AI strategy, agentic AI accelerators, and deep tech engineering. It focuses on helping companies stay ahead with generative AI and information technology, ensuring new products incorporate AI thinking from day one. RocketFrog.ai provides solutions for data engineering, analytics, ML Ops, and quality assurance, aiming to reduce costs, achieve scale, and improve efficiency. Specific offerings include TalkToApps for information retrieval, Document Cortex for conversing with unstructured data, and Call Center Analytics for customer insights. They also offer solutions for shortening sales cycles, revenue intelligence, and decision analytics.

CelebAMask HQ Face Parsing is an AI-powered tool available on Hugging Face Spaces designed for detailed facial feature identification. Users can upload a portrait photo, and the application will automatically parse and label various facial components such as skin, eyes, hair, and lips. The output includes a color-coded label image, clearly marking each region, and a blended image that combines the original photo with the labels. This tool is particularly useful for tasks requiring precise segmentation of facial elements, offering a straightforward interface for quick analysis. While the core functionality is free to use on Hugging Face Spaces, advanced compute options and enterprise features are available through Hugging Face's broader pricing plans.

Agent Lightning is an open-source trainer designed to light up and optimize AI agents with minimal code changes. It supports a wide range of agent frameworks, including LangChain, OpenAI Agent SDK, AutoGen, CrewAI, and Microsoft Agent Framework, or can be used without any framework. The tool allows for selective optimization of one or more agents within a multi-agent system and embraces advanced algorithms such as Reinforcement Learning, Automatic Prompt Optimization, and Supervised Fine-tuning. Its architecture is designed to be lightweight, enabling agents to run as usual while emitting events that are collected and processed by the LightningStore for continuous improvement.

AAAI-2024-Papers is an open-source GitHub repository offering a comprehensive collection of research papers presented at the AAAI 2024 conference, one of the premier artificial intelligence conferences. This resource allows users to explore innovative research and provides opportunities to integrate code implementations for a deeper understanding of the presented work. The repository is actively maintained and encourages contributions from the community to ensure completeness and accuracy. It serves as a valuable resource for academics, researchers, and students to stay updated on the latest advancements across various AI domains, including computer vision, natural language processing, machine learning, and more.

ai-digest is a CLI tool designed to aggregate your entire codebase into a single Markdown file, making it easy to provide context to AI models such as Claude Projects or custom ChatGPTs. It automatically collects all files within specified directories, ignoring common build artifacts and configuration files by default. Users can customize ignore patterns and even minify files, replacing their content with placeholders to save on AI token counts while still acknowledging their existence. The tool offers options for whitespace removal, file size statistics with bar charts, and a watch mode for automatic rebuilding upon file changes, streamlining the development workflow with AI assistance.

Always-On-AI-Assistant offers an open-source pattern for creating persistent AI assistants, primarily for engineering tasks. It integrates Deepseek-V3 for its 'brain,' RealtimeSTT for speech-to-text capabilities, and Typer for conversational commands. The tool supports both a base assistant with a chat interface and a more advanced Typer assistant that can execute commands based on spoken input and manage an active memory (scratchpad). This setup allows developers to build AI-driven workflows and interactive systems that are always available, making it suitable for automating tasks and providing real-time assistance in technical environments.

AIFlowy is an enterprise-grade, open-source AI application development platform built with Java, designed to provide an efficient, open, and locally adaptable AI toolchain. It enables developers and organizations to deploy AI solutions with low barriers to entry. The platform supports the full lifecycle of AI applications, from bot creation and RAG knowledge bases to AI workflow orchestration and multi-model management. AIFlowy distinguishes itself through a strong focus on real-world enterprise needs and regulatory considerations, offering features like a comprehensive plugin system, media center for AI-generated content, and a data hub for custom data tables. It also includes robust system management capabilities such as user/role/permission systems, access tokens, and internationalization support.

awesome-chatgpt-code-interpreter-experiments is an open-source repository dedicated to exploring and pushing the boundaries of what's possible with ChatGPT's Code Interpreter. It offers a collection of experiments, pro tips, and 'jailbreaks' that demonstrate how to overcome common limitations, such as installing external Python packages, running non-Python code like Deno, and even integrating complex models like YOLOv8 for object detection. The repository also covers practical applications like face detection and tracking in videos, image classification using MNIST, and OCR for text extraction. It serves as a valuable resource for developers and AI enthusiasts looking to unlock the full potential of the Code Interpreter.

awesome-data-labeling is a comprehensive, curated list of open-source and commercial tools designed for data labeling across multiple modalities. It categorizes tools for image, video, text, audio, time series, 3D, and LiDAR data annotation, making it a valuable resource for data scientists and machine learning engineers. The list includes popular tools like CVAT for computer vision, Labelbox for general data annotation, and YEDDA for text span annotation. It serves as a central hub for discovering tools that facilitate the creation of high-quality datasets for training machine learning models, offering solutions for various annotation tasks from bounding boxes to semantic segmentation.

Bumblebee is an open-source library that offers pre-trained Neural Network models built on Axon, Elixir's deep learning framework. It features seamless integration with Hugging Face Models, enabling users to easily download and execute various Machine Learning tasks directly within their Elixir applications. The library supports a wide range of models and provides tools for tasks like text filling, with clear examples for getting started in Livebook or Phoenix apps. Bumblebee emphasizes the use of Rust-implemented 'fast tokenizers' for efficient text processing and offers guidance on contributing new model implementations, including testing against Python models.

ChatMock offers an OpenAI and Ollama compatible API, powered by Codex, designed to integrate OpenAI models into your favorite chat applications and coding environments. By running a local server, it allows programmatic access to OpenAI models using an authenticated ChatGPT login. This tool supports various models like gpt-5.4, gpt-5.2, and codex-mini, and includes features such as tool/function calling, vision/image input, thinking summaries, and web search capabilities. Developers can configure reasoning effort, summary verbosity, and expose reasoning levels as separate models, providing flexibility for different use cases. It's an ideal solution for developers looking to leverage OpenAI's power within their existing workflows.

Nekta - AI Marketing Studio is a free and open-source desktop application designed to help businesses, SaaS companies, e-commerce stores, and content creators produce engaging marketing videos. The tool features five distinct video templates, each with numerous customization options. Users can leverage AI to generate voice, images, and text, or use their own content. Templates include AI Video, UGC (User-Generated Content), Captioned Video (with 'brainrot' options), Music Visualizer, and Photo Slideshow. All rendered videos are automatically stored in an in-app library for easy preview and export. Nekta supports offline use for non-AI features and allows for unlimited video creation without watermarks.

Inception AI provides AI-powered immigration drafting software designed for immigration law firms. The tool automates the process of turning client documents into comprehensive visa petitions, forms, and letters, significantly reducing drafting time. It integrates seamlessly with a firm's existing templates and drafting style, ensuring that all outputs maintain consistency with established standards. The software supports a wide range of case types, including employment-based visas (H-1B, L-1, O-1, TN, EB categories), seasonal cases (H-2A, H-2B), and family or status workflows (IR-1, IR-2, IR-5, AOS, I-765, I-539). Drafts are typically completed within 10 to 15 minutes, with more complex matters taking up to 30 minutes. Deployment options include private environments and managed cloud, with robust data security measures aligned to SOC 2 requirements.

Turi Create is an open-source tool that simplifies the development of custom machine learning models, making it accessible even for non-experts. It allows users to easily add advanced ML capabilities like recommendations, object detection, image classification, and activity classification to their applications. The platform is designed to be easy-to-use, focusing on tasks rather than complex algorithms, and offers built-in streaming visualizations for data exploration. Turi Create is flexible, supporting text, images, audio, video, and sensor data, and is optimized for fast and scalable performance on large datasets. Models can be readily deployed by exporting them to Core ML for integration into Apple's ecosystem.

DeepLearningExamples is a comprehensive repository from NVIDIA, offering state-of-the-art deep learning scripts. These examples are meticulously organized by models, making them easy to train and deploy while ensuring reproducible accuracy and performance. The platform is designed for enterprise-grade infrastructure, leveraging the NVIDIA CUDA-X software stack and optimized for NVIDIA Volta, Turing, and Ampere GPUs. It includes a wide array of models across computer vision, natural language processing, recommender systems, speech to text, text to speech, graph neural networks, and time-series forecasting. The examples are provided within monthly updated Docker containers on the NGC container registry, ensuring users have access to the latest NVIDIA examples, framework contributions, and optimized deep learning software libraries like cuDNN and NCCL.

DeepTraffic is an open-source deep reinforcement learning competition, part of the MIT Deep Learning series, where participants design neural networks to control vehicles in dense highway traffic. The goal is to drive as fast as possible through a 7-lane highway with 20 vehicles. The competition provides a coding area to design and test neural networks, visualize activations, and submit solutions. It includes a safety system that prevents collisions, allowing participants to focus on motion planning. DeepTraffic supports multiple agents, with the challenge of designing algorithms that perform well when controlling several vehicles simultaneously. The platform also offers insights into hyperparameter tuning and the structure of submissions, making it an excellent resource for both beginners and experts in deep reinforcement learning and autonomous vehicles.

Data-Science-Machine-Learning-Project-with-Source-Code is a comprehensive GitHub repository curated by durgeshsamariya, offering a collection of data science and machine learning projects complete with their source code. This resource is designed to assist individuals in learning and gaining practical experience in these fields. It includes articles, links to other GitHub repositories, and Kaggle kernels, covering a wide array of topics from sentiment analysis and fraud detection to image recognition and time series analysis. The repository is continuously updated with new projects, making it a dynamic and evolving learning platform for anyone interested in applying machine learning concepts.

Osavul is a technology company specializing in OSINT-powered AI solutions for comprehensive situational awareness. It empowers governments, security organizations, and enterprises to effectively counter hostile threats across cyber, hybrid, information, and physical domains. The platform offers advanced AI capabilities like Nebula for pre-emptive situational awareness and narrative intelligence, Echo for public opinion analysis, and Janus for multi-domain situational awareness. Osavul collects millions of data points monthly, including hard-to-reach data, to detect information threats, track malicious actors, and analyze public sentiment, providing automated early warnings and AI-reasoned predictions.

IBM federated learning is a Python framework designed for federated learning (FL) in enterprise settings. This library facilitates distributed machine learning processes where participant nodes retain their data locally, interacting through a learning protocol. It addresses critical concerns such as privacy, confidentiality, and regulatory compliance by avoiding the need to centralize data. The framework supports various machine learning models, including Deep Neural Networks (DNNs) and classic techniques like linear regression and k-means, encompassing supervised, unsupervised, and reinforcement learning approaches. It offers a wide array of fusion algorithms for combining model updates and includes fairness techniques to mitigate bias. The library is highly configurable for different computational environments, from data centers to edge devices, and is extensible to work with various ML libraries and protocols. An Experiment Manager Dashboard is also provided for orchestrating FL experiments.