Coding & Development

azure-openai-proxy is an open-source tool designed to seamlessly convert official OpenAI API requests into Azure OpenAI API requests. This proxy eliminates the differences between the two platforms, allowing the OpenAI ecosystem to access Azure OpenAI services with zero integration cost. It supports a wide range of models, including GPT-4 and Embeddings, and is compatible with popular frameworks like Langchain. Developers can easily deploy and configure the proxy using Docker, with options for environment variables or a configuration file to manage endpoints, API keys, and model mappings. This makes it an invaluable adapter for developers looking to leverage Azure's infrastructure while maintaining compatibility with existing OpenAI-based applications.

Q.ANT is at the forefront of photonic computing, offering solutions for more energy-efficient AI and High-Performance Computing (HPC). Their flagship product, the Native Processing Server (NPS), is the first commercial photonic processor designed to integrate seamlessly into existing computing ecosystems. This technology promises up to 30 times higher energy efficiency compared to conventional CMOS technologies, significantly reducing operational costs and environmental impact for data centers. Q.ANT's approach addresses the limitations of traditional computing by providing a scalable and sustainable alternative for complex AI training, inference, machine learning, physics simulations, and time-series analysis.

BERTScore is an automatic evaluation metric for text generation, leveraging pre-trained contextual embeddings from BERT to compare candidate and reference sentences. It calculates precision, recall, and F1 scores based on cosine similarity, offering a robust method for assessing the quality of generated text. The tool supports approximately 130 models, with `microsoft/deberta-xlarge-mnli` currently offering the best correlation with human evaluation. It is compatible with Huggingface's transformers library and provides both a Python function and a command-line interface for ease of use. BERTScore also supports multiple reference sentences and offers options for rescaling scores with baselines and using inverse document frequency (idf) for weighted word importance.

cocoindex is an open-source, incremental engine designed for long-horizon AI agents and LLM applications. It efficiently transforms diverse data sources, including codebases, meeting notes, inboxes, Slack, PDFs, and videos, into continuously fresh context. The framework focuses on minimal incremental processing, ensuring that only changes (deltas) are recomputed, which is crucial for maintaining data freshness without extensive re-embedding. Built with a Rust core, cocoindex offers production-grade performance, parallel chunking, zero-copy transforms, and failure isolation. It supports scaling from single repositories to petabyte-scale data stores, making it suitable for enterprise-level applications where keeping large corpora fresh is essential. Developers can declare data targets, and cocoindex automatically keeps them in sync, propagating changes across joins and lookups and retiring stale rows.

claude-code-workflows provides a curated collection of workflows and configurations designed for heavy users of Claude Code. It features an automated code review system, inspired by Anthropic's development process, that handles syntax, completeness, style, and bug detection. Additionally, it includes an automated security review system based on OWASP Top 10 standards to identify vulnerabilities and exposed secrets, offering severity-classified findings and remediation guidance. A design review system is also available, utilizing Microsoft's Playwright for UI/UX consistency and accessibility compliance. These workflows are based on applied learnings from an AI-native startup and are detailed with tutorials and demos on Patrick Ellis' YouTube channel, aiming to free up development teams for more strategic tasks.

Context Space offers a comprehensive context engineering infrastructure designed to enhance the productivity of AI agents, automation workflows, and developer tools. It provides unified MCP (Model Context Protocol) tools and secure, verified integrations, allowing AI agents to access real-world data and services effectively. The platform addresses challenges like manual credential handling with one-click OAuth and vault security, inconsistent APIs with a single RESTful API, and complex deployments through a unified context plane. Context Space is evolving into a complete context engineering platform, supporting advanced AI capabilities like semantic retrieval, context optimization, and real-time updates, making AI agents truly usable and secure.

smart-ide is an open-source AI code assistant designed as a VSCode extension, integrating ChatGPT capabilities to enhance the development workflow. It offers a suite of intelligent features including code review, automated unit test generation, error detection, and code optimization. Developers can also use smart-ide to add type definitions, generate documentation, explain code, refactor code, and perform language translation directly within their IDE. This tool is built to streamline various coding tasks, making the development process more efficient and intelligent for users.

ChatMLX is a modern, open-source, and high-performance chat application specifically designed for MacOS. It utilizes large language models (LLMs) and is built upon the powerful MLX framework, optimized for Apple silicon. The application supports multiple models, including Llama, OpenELM, Phi, Qwen, Starcoder, Cohere, and Gemma, offering users a diverse range of conversational options. A key differentiator is its ability to run LLMs locally, which significantly enhances user privacy and security. ChatMLX is multilingual, supporting 39 major App Store languages, making it accessible to a global audience. It's compatible with macOS 14.0 and later.

CodeGeeX4-ALL-9B is an open-source, multilingual code generation model designed for a wide range of AI software development tasks. Built upon the GLM-4-9B, it significantly enhances code generation capabilities, offering features like code completion, code interpretation, web search, and function calling. This versatile model also supports repository-level code Q&A, making it a comprehensive solution for developers. CodeGeeX4-ALL-9B has demonstrated highly competitive performance on public benchmarks such as BigCodeBench and NaturalCodeBench, often outperforming larger general-purpose models. It is recognized for achieving an optimal balance between inference speed and model performance, making it the most powerful code generation model with less than 10 billion parameters. The model is available on Ollama, Huggingface transformers, and vLLM, with extensions for VS Code and Jetbrains.

CodeT5 and CodeT5+ are open-source large language models developed by Salesforce Research, designed for advanced code understanding and generation tasks. These models function as an AI-powered coding assistant, significantly boosting developer productivity. Key capabilities include generating code from natural language descriptions, autocompleting entire functions based on a target function name, and summarizing code functions into natural language. The models are available on HuggingFace, with fine-tuned checkpoints for various downstream tasks, including multilingual code summarization. CodeT5 is released under the BSD-3 License, encouraging ethical use and user feedback on applications.

ChatALL is an open-source desktop application designed to streamline interactions with various large language models (LLMs). It enables users to send a single prompt to multiple AI bots simultaneously, including popular ones like ChatGPT, Bing Chat, Bard, Claude, and many others. This concurrent querying helps users compare responses and identify the best answers or creations from different LLMs. The tool is particularly useful for LLM gurus seeking optimal results, researchers comparing model strengths, and developers debugging prompts. It supports a wide range of AI bots, offering features like quick-prompt mode, local chat history saving, response highlighting, and multi-column views. ChatALL is available for Windows, macOS, and Linux.

CogDL is a comprehensive, open-source library designed for graph deep learning, enabling researchers and developers to efficiently train and compare models. It supports key tasks such as node classification, graph classification, and other important graph domain applications. The library emphasizes efficiency through optimized operators for faster training and reduced GPU memory usage, ease of use with intuitive APIs for hyper-parameter search, and extensibility for applying GNN models to new scenarios. CogDL also incorporates features like fast sparse matrix-matrix multiplication (SpMM) for accelerated GNN training and supports mixed-precision training. It has been accepted by WWW 2023 and offers resources like a free GNN course and a discussion forum.

cnn-text-classification-tf is an open-source project offering a simplified implementation of a Convolutional Neural Network (CNN) for text classification using TensorFlow. This tool is based on the principles outlined in Kim's "Convolutional Neural Networks for Sentence Classification" paper. It provides the necessary code and scripts for users to train and evaluate their own text classification models, making it accessible for those looking to implement CNNs in their natural language processing tasks. The repository includes Python scripts for data helpers, model evaluation, the CNN architecture itself, and training, along with configurable parameters for embedding dimensions, filter sizes, dropout, and more.

Crush is a terminal-based AI coding assistant designed to streamline development workflows. It offers multi-model support, allowing users to choose from a wide range of LLMs or add their own via OpenAI- or Anthropic-compatible APIs, and even switch LLMs mid-session while preserving context. Crush maintains multiple work sessions and contexts per project, enhancing productivity. It leverages Language Server Protocols (LSPs) for additional context, similar to how human developers work. The tool is highly extensible through Model Context Protocol (MCP) servers, supporting stdio, http, and sse transport types. Built on the Charm ecosystem, Crush provides industrial-grade performance and first-class support across macOS, Linux, Windows, Android, FreeBSD, OpenBSD, and NetBSD. It respects .gitignore files and allows for custom .crushignore files, along with configurable permissions for tool execution and the ability to disable built-in tools and skills.

ZenoX AI offers the Vydar Threat Intelligence platform, an AI-powered solution designed to help organizations proactively identify, prioritize, and prevent cyberattacks. It specializes in real-time monitoring and analysis of vast amounts of threat data from sources like the dark web, Telegram channels, and specialized forums. The platform utilizes the Tellyu AI engine for advanced pattern recognition, natural language understanding of fraudster terminology, and interactive data search. Key features include cyber threat intelligence, dark web monitoring, brand protection, supply chain intelligence, phishing detection, and fraud mitigation. ZenoX AI helps companies protect against leaked credentials, stolen cards, and fraudulent domains, ensuring a strong security posture.

Crawlee is a powerful, open-source web scraping and browser automation library built for Node.js, enabling developers to create reliable crawlers in JavaScript and TypeScript. It's specifically designed to extract data for AI, LLMs, RAG, or GPTs, supporting the download of HTML, PDF, JPG, PNG, and other file types. The library works seamlessly with popular tools like Puppeteer, Playwright, Cheerio, JSDOM, and raw HTTP, offering both headful and headless modes. Key features include integrated proxy rotation, session management, and a persistent queue for URLs, making it suitable for complex and large-scale scraping tasks while appearing human-like to bypass bot protections.

Crawlee-Python is a robust web scraping and browser automation library built for Python, enabling developers to create reliable and efficient crawlers. It is specifically designed to extract data for AI, LLMs, RAG, or GPTs, making it a valuable tool for data-driven applications. The library supports downloading various file types including HTML, PDF, JPG, and PNG from websites. It offers flexibility by working with popular parsing tools like Parsel and BeautifulSoup, as well as browser automation frameworks like Playwright, and even raw HTTP requests. Crawlee-Python features both headful and headless modes for browser operation, includes integrated proxy rotation for bypassing bot protections, and provides session management. Its asyncio-based architecture ensures high performance and seamless compatibility with other modern asynchronous libraries, offering a superior developer experience with comprehensive type hints.

Data-Juicer is an open-source, cloud-native, and AI-ready data processing system designed for the foundation model era. It offers a modular and extensible architecture with over 200 operators for text, image, audio, video, and multimodal data. Users can create reproducible YAML pipelines, chain complex workflows, and orchestrate full pipelines with ease. Data-Juicer supports various applications including pre-training, fine-tuning, RL, agent systems, RAG, and analytics. It boasts production-ready performance, scaling seamlessly from laptops to large clusters, with features like automatic OP fusion, adaptive parallelism, and CUDA acceleration. The system also includes built-in tracing for debugging and iterative improvement, making it a comprehensive solution for large-scale data preparation.

Lumafield offers a comprehensive solution for manufacturing quality control, combining industrial X-ray CT scanners with cloud-based, AI-enhanced analysis software. The Neptune scanner provides X-ray vision for product development, while the Voyager software allows visualization, analysis, and sharing of scan data from any 3D or volumetric scanner via a web browser. For high-speed production, TRITON offers automated scanning and real-time decision-making. The platform helps manufacturers discover and diagnose issues like voids, misalignments, and out-of-tolerance dimensions, and then deliver solutions by correlating findings with process data and generating evidence-backed root-cause reports. This integrated system aims to accelerate decisions, reduce costs, and maintain quality at scale across various industries.

UNOY is an AI-assisted workspace designed for organizations working with regulated knowledge, such as law firms, chambers, associations, and back-office teams. The platform allows users to transform their expertise into digital guides and automated workflows, eliminating scattered knowledge in emails and PDFs. COIA, the central AI orchestrator, coordinates specialized Work Agents to process incoming requests, gather data, verify information, and prepare drafts or reports. This system ensures tasks are completed with defined processes, deadlines, and an audit trail, allowing human teams to review and approve results. UNOY aims to scale knowledge, automate back-office operations, and provide a structured approach to work.

Determined is an open-source machine learning platform designed to streamline the entire machine learning lifecycle. It simplifies complex tasks such as distributed training, allowing for faster model development and iteration. The platform also provides robust hyperparameter tuning capabilities to help users achieve optimal model performance. Beyond training, Determined offers comprehensive experiment tracking for analysis and reproducibility, alongside efficient resource management to help reduce cloud GPU costs. It is fully compatible with popular deep learning frameworks like PyTorch and TensorFlow, making it a versatile solution for developers and researchers.

DevOpsGPT is an AI-driven software development automation solution that leverages large language models (LLMs) and DevOps tools to transform natural language requirements into functional software. This multi-agent system aims to significantly improve development efficiency, shorten development cycles, and reduce communication costs, leading to higher-quality software delivery. Key capabilities include clarifying requirement documents, generating interface documentation, writing pseudocode based on existing projects, and facilitating continuous integration and software version releases. It supports any development language and can extend existing codebases. The tool offers features like existing project analysis, professional model selection, and integration with various DevOps platforms in its enterprise edition.

TradeOS AI is an advanced platform designed to provide professional insights through artificial intelligence. It specializes in helping users detect subtle patterns within data, identify significant change points, and ultimately inform their strategic decisions with enhanced clarity. The tool is built to assist professionals in various fields by leveraging AI for in-depth analysis, enabling them to make more informed and timely moves. Its core functionality revolves around pattern recognition, time-series AI, and signal detection, making it a valuable asset for anyone needing to understand complex data trends and predictive analytics.

V3rpg offers a next-generation AI-powered RPG adventure where players can create unique characters and explore immersive fantasy worlds. The game leverages advanced AI models like GPT, Mistral, and LLaMA to provide dynamic storytelling and strategic combat. Users can design their own scenes, characters, and plots with an AI guide, influencing the narrative through their choices. It features multiplayer battles, daily challenges, and community events, allowing players to compete, climb leaderboards, and earn blockchain rewards. The innovative validation system ensures fair play and authentic achievements, while an achievement system tracks progress and allows for sharing epic adventures.