Coding & Development

AI-Gateway is a comprehensive set of labs designed to help developers and platform engineers explore and manage AI Models, MCP servers, and Agents. Powered by Azure API Management and Microsoft Foundry, it offers an enterprise-grade gateway for building production-ready AI applications. Key features include robust security with OAuth 2.0 and content safety filtering, enhanced performance through load balancing and semantic caching, and detailed observability with token metrics and built-in logging. It also provides cost control via rate limiting and quota management, and extensibility with MCP protocol support and multi-model routing. The labs offer hands-on Jupyter notebooks, Bicep infrastructure templates, and APIM policies for easy deployment to Azure subscriptions, making it ideal for those looking to implement secure, reliable, and scalable AI solutions.

Aidermacs brings AI-powered development directly into Emacs, integrating with Aider, a powerful open-source AI pair programming tool. It offers similar AI capabilities to tools like Cursor but is tailored for Emacs workflows. Key features include intelligent model selection with multiple backends, built-in Ediff integration for AI-generated changes, and enhanced file management directly from Emacs. Users can customize model selection, including an experimental Architect mode that uses separate models for reasoning and code generation, which has shown state-of-the-art results. Aidermacs also provides a minor mode for working with prompt files and flexible configuration options for API keys and environment variables.

Amazon Q Developer CLI, now known as Kiro CLI, offered an agentic chat experience directly within the terminal, enabling developers to build applications using natural language. While the open-source Amazon Q Developer CLI project is no longer actively maintained and will only receive critical security fixes, its successor, Kiro CLI, continues to provide these capabilities as a closed-source product. The tool allowed for natural language interaction to streamline development workflows, offering features like code generation, debugging assistance, and general development support directly from the command line. It was designed to enhance developer productivity by integrating AI-powered assistance into the terminal environment.

Chatblade is a versatile command-line interface (CLI) tool designed to interact with OpenAI's ChatGPT. It accepts piped input, arguments, or both, enabling flexible query submission. Users can save common prompt preambles for quick usage and manage distinct conversations through named sessions. The tool also provides utility methods to extract JSON or Markdown from ChatGPT responses, with options for raw output or formatted syntax highlighting. It supports both gpt-3.5 and gpt-4 models, interactive chat sessions, and streaming responses. Chatblade can also be configured for Azure OpenAI endpoints. Note: This project is archived and no longer under active development, with the developer recommending alternatives like llm or Fabric for modern CLI needs.

Claude-Code-Usage-Monitor is an open-source, real-time terminal monitoring tool designed for Claude AI token usage. It offers advanced analytics, machine learning-based predictions, and a rich, color-coded UI to track token consumption, burn rate, and cost analysis. Key features include configurable refresh rates, smart auto-detection of usage plans, and an advanced warning system with cost and time predictions. The tool supports various Claude plans (Pro, Max5, Max20) and includes a default 'Custom' plan that intelligently adapts to usage patterns by analyzing past sessions to calculate personalized limits. It also provides model-specific pricing with cache token calculations and comprehensive logging options, making it an essential utility for developers managing their Claude AI expenses and usage efficiently.

flops-counter.pytorch is an open-source tool designed to calculate the theoretical number of multiply-add operations (FLOPs) and parameters within neural networks built using the PyTorch framework. It offers two backends: 'pytorch' for legacy nn.Modules with better per-layer analytics for CNNs, and 'aten' for broader coverage of model architectures, including transformers, by considering aten operations. The tool can also print per-layer computational costs and allows for ignoring specific modules during counting. It supports various layers like Conv1d/2d/3d, BatchNorm, Activations, Linear, Upsample, and Poolings, with experimental support for RNNs, LSTMs, GRUs, and MultiheadAttention. Users can customize input tensors for complex models and view verbose output for unconsidered operations.

MagicQuill is an intelligent and interactive image editing system, officially implemented for CVPR 2025. This open-source tool offers a user-friendly interface with AI-powered suggestions and precise local editing features. Users can leverage three types of 'magic quills': an add brush to introduce details, a subtract brush to remove or redraw elements, and a color brush for precise color adjustments. The system also includes a 'Draw and Guess' feature that intelligently suggests prompts based on user strokes. With robust canvas tools for uploading, erasing, dragging, rotating, and resizing strokes, MagicQuill streamlines the editing workflow. It supports various base models for different editing styles, including realistic, fantasy, portrait, and anime, and allows for negative prompts to refine generation results. Hardware requirements include a GPU with at least 8GB VRAM, and it offers Docker container setup for isolated environments.

llm-foundry is a comprehensive open-source repository offering code for the entire lifecycle of Large Language Models (LLMs), from training and finetuning to evaluation and deployment. It is specifically designed to integrate with Composer and the MosaicML platform, providing an efficient and flexible environment for rapid experimentation. The codebase supports various LLM workloads, including data preparation, training HuggingFace and MPT models from 125M to 70B parameters, and benchmarking training throughput and MFU. It also facilitates inference by converting models to HuggingFace or ONNX formats, generating responses, and evaluating LLMs on academic or custom in-context-learning tasks. The repository includes support for DBRX and MPT models, with detailed instructions for local use and community contributions.

Meeting Assistant Flow is an open-source project built on the crewAI framework, designed to streamline the entire meeting lifecycle. It automates critical tasks such as loading meeting notes from a text file, generating actionable tasks from meeting transcripts using AI agents, and integrating these tasks with Trello for project management. Additionally, it saves new tasks to a CSV file and sends Slack notifications to keep teams informed. This flow leverages multiple AI agents to handle different aspects of the meeting workflow, offering a modular and efficient solution for automating meeting management processes. Users can customize agents, tasks, and the flow itself to fit specific organizational needs.

ChatPRD is the #1 AI platform designed specifically for product managers, transforming ideas into clear requirements and coaching teams to ship better products. It enables users to write great product documents like PRDs, user stories, and technical specs in minutes, not days, by leveraging AI to generate content from prompts, meeting notes, or rough ideas. The platform offers CPO-level reviews with actionable feedback, identifying strategic gaps and coaching users to think deeply about product problems. ChatPRD integrates seamlessly with tools like Linear, Notion, Slack, and GitHub, allowing for one-click exports and prototype generation. It also provides agentic capabilities for engineers and designers, shared project spaces, and custom AI personas, making it a comprehensive solution for product teams of all sizes.

MeshCNN is a general-purpose deep neural network specifically designed for 3D triangular meshes, implemented using PyTorch. This framework enables advanced tasks such as 3D shape classification and segmentation by applying convolutional, pooling, and unpooling layers directly on the mesh edges. It offers a robust solution for researchers and developers working with 3D data, providing a novel approach to process geometric information. The repository includes scripts for installation, training, and testing on datasets like SHREC and Humans, making it accessible for practical application and further development in the field of geometric deep learning.

mcp-context-forge is an open-source AI Gateway, registry, and proxy designed to federate Model Context Protocol (MCP) servers, A2A servers, and REST/gRPC APIs into a unified endpoint. It offers centralized governance, discovery, and observability across AI infrastructure, optimizing agent and tool calling. Key capabilities include a Tools Gateway for MCP, REST, and gRPC translation, an Agent Gateway for A2A protocol and OpenAI/Anthropic routing, and an API Gateway with rate limiting, authentication, and retries. The tool supports extensive plugin extensibility with over 40 integrations and provides OpenTelemetry tracing for comprehensive observability. It runs as a fully compliant MCP server, deployable via PyPI or Docker, and scales to multi-cluster Kubernetes environments with Redis-backed federation and caching.

mcp-server-chart is a Model Context Protocol (MCP) server designed for generating a wide array of charts using the AntV visualization library. This open-source tool supports over 25 different visual charts, making it suitable for various chart generation and data analysis tasks. It can be integrated with desktop applications like Claude, VSCode, and Cursor, or deployed via HTTP, SSE, or Streamable protocols for use with platforms like Aliyun and Dify. Key features include the ability to generate diverse chart types such as area, bar, boxplot, column, line, pie, scatter, and more, as well as specialized diagrams like fishbone, mind maps, and network graphs. Users can also filter available tools and configure private deployments for enhanced control over their chart generation services.

Mocha.jl is a deep learning framework for the Julia programming language, drawing inspiration from the C++ framework Caffe. Although now deprecated, it was designed for efficient training of deep and shallow convolutional neural networks, supporting optional unsupervised pre-training via stacked auto-encoders. The framework boasts a modular architecture with isolated components for layers, activation functions, solvers, and more, allowing for easy extension. Written in Julia, it offers a high-level interface for intuitive deep neural network experimentation. Mocha.jl provides multiple backends, including a portable pure Julia backend, a faster native extension backend, and a highly efficient GPU backend utilizing NVidia® cuDNN and CUDA kernels. It also supports HDF5 for data and model storage, ensuring compatibility with other computational tools, and can import Caffe model snapshots.

MockingBird is an open-source voice cloning tool designed for real-time speech generation. It allows users to clone a voice in approximately 5 seconds and generate arbitrary speech. The tool supports Chinese Mandarin and has been tested with multiple datasets, including aidatatang_200zh, magicdata, and aishell3. It is compatible with Windows, Linux, and even M1 macOS, offering flexibility for various environments. MockingBird leverages PyTorch and provides options for training custom models for encoders, synthesizers, and vocoders, or utilizing community-shared pretrained models. It offers a web server, a toolbox, and a command-line interface for generating voices.

SaaSberry Innovation Laboratories Ltd. specializes in building AI solutions to address decision latency and operational friction within large organizations. They integrate executive intelligence and automation directly into existing Microsoft environments, promising deployment within 90 days. The firm focuses on identifying where value is lost due to slow decision-making and inefficient workflows, then re-engineering these processes. Their approach is implementation-focused, not advisory, aiming to deliver measurable outcomes like increased operating leverage and improved efficiency without requiring new headcount or system replacements. They target executive leaders accountable for capital efficiency and experiencing margin compression, offering private, confidential enterprise deployments with C-level sponsorship.

mlops-stacks offers a customizable, open-source solution for initiating new machine learning projects on Databricks, adhering to production best practices. It streamlines the development process by providing a pre-configured environment that includes ML project structure, ML resources as code, and CI/CD workflows (GitHub Actions or Azure DevOps). Data scientists can quickly iterate on ML code, while MLOps engineers can efficiently set up continuous integration and continuous deployment pipelines and manage ML resources. The tool supports automated model training and batch inference jobs across dev, staging, and production Databricks workspaces, facilitating an easy transition to production-grade ML solutions. It also integrates with Databricks asset bundles and offers options for Unity Catalog and Feature Store.

StackBob is an agentic Identity Governance (IGA) solution designed to complete enterprise Identity and Access Management (IAM) stacks by integrating applications that typically lack SCIM, APIs, or connectors. This tool significantly reduces manual provisioning efforts and mitigates compliance risks by extending governance over previously unintegrated applications. Key features include automated identity lifecycle management for on/offboarding and RBAC, secure password sharing via encrypted vaults, and streamlined security compliance with audit-ready evidence for SOC 2 and ISO 27001. StackBob also helps finance teams cut software license waste by detecting and removing unused licenses and orphaned accounts, claiming to save up to 25% on software costs. It offers a no-code setup, goes live in hours, and connects any app in less than 48 hours without requiring API access.

OmniScience introduces Vivo, an AI-native control tower designed to transform clinical trial operations. Vivo unifies disparate data sources across trials, sites, and participants, providing real-time insights and continuous monitoring. It acts as a cognitive partner for clinical teams, interpreting signals, surfacing critical information, and identifying risks early to accelerate decision-making. Vivo is built to improve outcomes at scale, reducing manual effort and helping teams deliver therapies to patients faster. Key features include 'Ask Vivo' for instant, explainable insights from trial data, portfolio intelligence for cross-trial oversight, dynamic participant profiles, on-demand lab insights, and continuous monitoring with alerts. The platform is designed for various roles within clinical development, operations, research, data management, safety monitoring, and CROs, and supports multiple therapeutic areas including Oncology, CNS, Immunology & Inflammation, Rare Disease, and Obesity. Vivo is a validated system engineered to comply with global clinical trial and AI regulations, ensuring data security, privacy, and quality.

Mojo AI offers an AI-powered safety management platform designed for the construction and oil & gas sectors. Its flagship product, Safety Mojo, streamlines safety processes by unifying risk, compliance, and frontline data across projects, trades, and crews. Key features include AI-scored Pre-Task Plans (PTP/JSA) for quality and risk coverage, conversational AI tools like Ask Mojo, and multilingual support. The platform automatically generates OSHA 300/301/300A logs, TRIR, DART, and lost-time reports from submitted forms and field data. It also provides real-time dashboards for visibility across sites, allowing users to prioritize audits and identify high-risk work. Mojo AI helps meet OCIP data requirements and integrates with other software via API.

AIBIZ Medical is a comprehensive platform designed for healthcare professionals, including doctors, clinic owners, nurses, and midwives, to streamline their operations and enhance clinical decision-making. It integrates a WhatsApp assistant with a robust digital medical record (RME) system, offering features like AI Auto SOAP for faster clinical note-taking, AI Clinical Decision Assist for initial assessments, and AI Scan ID for quick patient identity input. The platform supports various healthcare settings, from individual practices to clinics, and is SATUSEHAT-ready for higher service standards. Beyond AI-powered clinical tools, it manages patient queues, billing, inventory, medical letters, and provides analytics. The WhatsApp assistant acts as an additional layer for quick access, medical references, booking, and daily work assistance, connecting seamlessly with the RME data based on access rights. AIBIZ Medical aims to not just digitize but accelerate clinic workflows.

Ollamac is a free and open-source native Mac application designed to seamlessly integrate with Ollama, enabling users to run and interact with various Ollama models directly on their macOS 14.0 Sonoma or later devices. The application is exclusively available from its official GitHub repository, ensuring authenticity and direct access to updates. Key features include compatibility with all Ollama models, customizable host settings, and syntax highlighting for an enhanced user experience. Ollamac prioritizes simplicity and ease of use, providing a native interface for local AI model interaction without requiring internet access once models are pulled. This makes it an ideal tool for developers, data scientists, and students looking to experiment with large language models offline.

dgl-ke is an open-source package designed for learning large-scale knowledge graph embeddings, built on top of the Deep Graph Library (DGL). It offers high performance, ease of use, and scalability, making it suitable for various machine learning tasks involving knowledge graphs. The package supports training knowledge graph embeddings using popular models like TransE, TransR, RESCAL, DistMult, ComplEx, and RotatE. Users can perform training on single machines (CPU/GPU) or distributed environments, evaluate pre-trained embeddings with link prediction tasks, and conduct inference for entity/relation linkage prediction or embedding similarity. DGL-KE is optimized for scale, capable of processing knowledge graphs with millions of nodes and billions of edges efficiently.

Project News Alan AI is an open-source code repository that showcases how to build a conversational voice-controlled React News Application using Alan AI. Alan AI is a powerful speech recognition software designed to integrate voice capabilities into various applications, enabling users to control app functionalities entirely through voice commands. This project serves as a practical tutorial, guiding developers through the process of integrating Alan AI into a React application to create interactive, voice-enabled experiences. It highlights the ease of integration and the potential for developing custom voice-controlled applications, making it a valuable resource for those looking to add advanced speech recognition features to their projects.