Coding & Development

QiZhenGPT is an open-source Chinese medical large language model developed by CMKRG. It leverages a Chinese medical instruction dataset built from the QiZhen Medical Knowledge Base to significantly improve performance in Chinese medical contexts. The model has been fine-tuned on Chinese-LLaMA-Plus-7B, CaMA-13B, and ChatGLM-6B models. Initially, it focuses on drug knowledge Q&A with a dedicated evaluation dataset, with plans to expand to diseases, surgeries, and examinations. QiZhenGPT also underpins MedCopilot, a smart medical assistant integrated with HIS and electronic medical record systems, offering features like functional assistant, auxiliary diagnosis, medical quality assurance, and medical record documentation. MedCopilot is already in use at Zhejiang University Second Affiliated Hospital.

Second is an AI-powered tool designed to assist developers with web application generation and code migration. It leverages artificial intelligence to automate various development tasks, significantly streamlining the software development lifecycle. The platform helps in quickly creating software prototypes and can be instrumental in modernizing existing codebases. By providing AI developer bots, Second aims to reduce manual effort, accelerate project timelines, and improve overall efficiency for development teams. This tool is particularly useful for developers looking to enhance productivity and focus on more complex problem-solving by offloading repetitive coding tasks to AI.

CoDynamics Lab's LATCH is a proprietary inference layer designed to compile large document sets into persistent LLM memory, offering a significant alternative to traditional RAG (Retrieval Augmented Generation) methods. It eliminates the need for chunking, re-reading, or re-embedding documents for every query, drastically reducing cold start times and operational costs. LATCH is self-hosted via Docker, ensuring privacy and control over sensitive data, and is compatible with an OpenAI-format API. It supports various model families like Qwen, Mistral, Llama, and DeepSeek, and requires an NVIDIA GPU with 80GB VRAM. LATCH creates portable .latch or .latchdoc binary files, allowing for rapid reloading and sharing of compiled document intelligence.

swift-video-generator is an open-source library designed for developers and video creators to programmatically generate videos. It offers core functionalities such as combining individual images with audio tracks to create video segments, and the ability to merge multiple video files into a single output. This tool is particularly useful for automating video production workflows, allowing for efficient creation of video content from various media assets. Its open-source nature provides flexibility for customization and integration into existing development environments, catering to users who need a programmatic approach to video generation and editing.

ViZDoom is an open-source platform designed for developing AI bots that play the classic 1993 game Doom using only visual information from the screen buffer. It is primarily intended for research in machine visual learning and deep reinforcement learning. The tool offers a robust API for Python (including Gymnasium/Gym wrappers) and C++, supporting multi-platform deployment on Linux, macOS, and Windows. Key features include high performance (up to 7000 frames/steps per second), lightweight footprint, and easy creation of custom scenarios with visual editors and a powerful scripting language. Researchers can leverage its async and sync single-player/multiplayer modes, customizable rendering, access to depth and audio buffers, object labeling, and in-game data for advanced AI experimentation. ViZDoom is reinforcement learning friendly, suitable for learning from demonstration, apprenticeship learning, and inverse reinforcement learning.

Cursor is an advanced AI-powered coding environment designed to significantly boost developer productivity. It offers real-time code suggestions, intelligent code generation, and debugging assistance, integrating seamlessly into the development workflow. Key features include autonomous agents that can build, test, and demo features, a specialized Tab model for accurate autocomplete, and comprehensive codebase understanding. Cursor supports various cutting-edge models from OpenAI, Anthropic, Gemini, xAI, and its own, allowing users to choose the best AI for each task. It runs across multiple platforms, including desktop, CLI, and integrates with tools like Slack and GitHub for collaborative development and PR reviews. Trusted by major enterprises, Cursor aims to accelerate software creation securely and at scale.

Aii.CX provides a no-code platform for businesses to create and embed custom AI tools, widgets, and apps directly onto their websites. Designed to increase lead generation and conversion rates, the platform allows users to generate AI tool ideas, create the tools in seconds, and integrate them easily using JavaScript code. It supports various use cases such as AI home design assistants, MVP builders, and mission statement creators. The tools are mobile-optimized and offer user-friendly analytics, along with over 5000 integrations via Zapier. Aii.CX is particularly beneficial for small and medium businesses looking to enhance their online presence and customer engagement without significant advertising spend or technical expertise.

Hebel is an open-source Python library for deep learning, leveraging GPU acceleration through CUDA via PyCUDA. It provides functionalities for implementing neural network models, specifically feed-forward networks for classification and regression. The library offers a range of activation functions and advanced training methods, including momentum, Nesterov momentum, dropout, and early stopping, along with L1 and L2 weight decay for regularization. While no longer actively developed, it served as a foundational tool for researchers and developers working with deep learning models on Linux, Windows, and potentially Mac OS X. Hebel is available on PyPi for easy installation.

agent-device is a command-line interface (CLI) designed for AI agents to control and observe iOS, tvOS, macOS, Android, and AndroidTV devices. It facilitates UI automation by providing structured snapshots of the accessibility tree, allowing agents to understand and interact with mobile UIs efficiently. The tool supports deterministic interactions, session-aware workflows, and replayable flows, making it suitable for repeated automation runs and debugging. Key features include inspecting UI states, collecting logs, network inspection, and performance snapshots. It also integrates with React DevTools for deeper component-level insights, making it a comprehensive solution for agent-driven mobile app testing and automation.

VibeTensor is an open-source systems research artifact, representing a deep learning system fully generated by AI agents under high-level human guidance. This project demonstrates that coding agents can generate and validate a coherent deep learning runtime, including language bindings, a C++ core, CUDA memory management, and GPU kernels. It features a PyTorch-inspired eager runtime with a C++20 core (CPU + CUDA), a Python overlay, and an experimental Node.js/TypeScript API. VibeTensor implements its own tensors/storage, dispatcher, autograd engine, CUDA runtime, and caching allocator. While designed for correctness-first and not performance-competitive with PyTorch, it serves as a research prototype for AI-assisted software engineering, showcasing the capabilities of agent-generated code for complex system software.

DeepBench is a project by Baidu Research designed to benchmark fundamental deep learning operations across different hardware platforms. It aims to answer which hardware provides the best performance for the basic operations used in deep neural networks, such as dense matrix multiplies, convolutions, and recurrent layers. The tool specifies these operations at a low level, making it suitable for hardware simulators and those building new processors for deep learning. DeepBench includes benchmarks for both training and inference, covering various sizes and precisions. It utilizes vendor-supplied libraries like NVIDIA's cuDNN and Intel's MKL to ensure representative user experience and helps identify bottlenecks in deep learning training and inference.

Apache HertzBeat™ is an AI-powered next-generation open-source real-time observability system designed to unify metrics and logs collection, centralize alerting distribution, and provide intelligent management and analysis. It features AI-powered interactions and built-in MCP Server capabilities. The platform supports a wide range of monitoring types including application services, databases, operating systems, big data, cloud-native, and custom monitoring, all without requiring an agent. It seamlessly integrates multiple log sources via OTLP protocol and offers a unified alerting platform with flexible threshold rules, grouping, and suppression. Alerts can be distributed through various channels like Email, Discord, Slack, Telegram, and Webhook. HertzBeat is highly configurable, allowing users to define custom monitoring types using YML templates, and supports high-performance horizontal expansion of multi-collector clusters.

Alpharun is an AI sales coaching and quality assurance platform specifically designed for high-volume, compliance-sensitive sales teams in financial services, insurance, and healthcare. It automatically analyzes thousands of sales calls to uncover and optimize the most effective talk tracks, creating a perfect sales playbook. The platform provides personalized AI sales coaching to each representative, dramatically increasing revenue per rep, lowering ramp times for new hires, and improving compliance. Managers gain objective performance data and team-wide visibility. Additionally, Alpharun offers human-grade AI voice agents for lead qualification, intake, and off-hour calls, custom-trained on specific sales processes to boost conversion rates. It meets rigorous security standards including SOC 2 Type 2, HIPAA, and GDPR.

Hands-on-train-and-deploy-ml is a comprehensive GitHub repository offering a step-by-step tutorial for building and deploying a machine learning REST API. The project focuses on predicting crypto prices, providing a practical guide for ML engineers to move beyond notebooks. It covers essential MLOps frameworks and tools, including CometML for experiment tracking and model registry, Cerebrium for serverless deployment, and GitHub Actions for automating safe deployments. The tutorial is structured into three main parts: model training, model deployment as a REST API, and automation with GitHub Actions and Model Registry. It emphasizes a 100% serverless stack, making it accessible without complex infrastructure setup.

Kodezi functions as an AI CTO, providing an autonomous operating system for modern codebases. It is designed to maintain, evolve, and govern software, ensuring it remains healthy, scalable, and always ready to ship. The platform seamlessly integrates across your development stack, offering features like autonomous bug fixing, real-time code refinement, and automatic enforcement of best practices. Kodezi also includes vulnerability detection and error recovery, proactively identifying and healing security risks before code reaches production. Additionally, it intelligently generates code, API definitions, and test coverage, ensuring every update is complete and reliable. This comprehensive approach helps developers streamline their workflow and improve code quality.

AnimeBackgroundGAN is an AI tool designed for generating anime-style backgrounds. It leverages generative adversarial networks (GANs) to produce visual assets suitable for various creative projects, including games and anime art. The tool is hosted as a demo on Hugging Face Spaces, indicating its accessibility for users to experiment with its capabilities. However, at the time of review, the application is encountering a build error, preventing its current functionality. It is built using Gradio, a popular framework for creating user interfaces for machine learning models.

Open CoWork is a free, open-source AI agent designed to empower users with advanced automation capabilities. This versatile tool allows for seamless control over web browsers and local applications, making it an ideal solution for a wide range of automation tasks. Its open-source nature means it can be extended with custom skills, providing developers and technical users with the flexibility to tailor its functionality to specific needs. Available for macOS, Windows, and Linux, Open CoWork offers a robust platform for creating and customizing AI agents, enabling efficient automation and enhanced productivity across various operating environments.

bnb-my-repo is a Hugging Face Space designed to simplify the process of quantizing AI models. Users can select a model from Hugging Face, apply desired quantization settings, and then upload the reduced-size model directly to their personal Hugging Face account. This tool is particularly useful for developers and researchers looking to optimize model performance and reduce storage requirements without extensive manual configuration. It provides a straightforward interface for managing and deploying quantized models within the Hugging Face ecosystem.

infiniteGPT is a Python script designed to streamline interactions with the OpenAI API, enabling users to process texts of unlimited size. This tool eliminates the common frustration of repeatedly copying and pasting large chunks of text into AI models like GPT-3.5-turbo or GPT-4. By leveraging multithreading, infiniteGPT ensures efficient handling of extensive inputs, making it ideal for tasks requiring comprehensive text analysis or generation without manual intervention. It requires users to bring their own OpenAI API keys and is a single Python script, emphasizing ease of use for developers and technical users looking to integrate advanced AI capabilities into their workflows.

Clivi is a gaming platform designed to enhance the gaming experience by connecting players for competition and creative endeavors. Users can easily find and match with others to play their favorite games, participate in organized tournaments, and build esports teams. The platform also incorporates generative AI features, allowing users to create custom skins, adding a unique personalization aspect to their gaming. This combination of social connectivity, competitive play, and AI-powered customization aims to provide a comprehensive and engaging environment for gamers.

Guess.js is an open-source library offering tools and libraries to enable data-driven user experiences on the web, primarily focusing on predictive prefetching and bundling. It leverages data from sources like Google Analytics to predict user navigation patterns, allowing for prefetching of likely next pages or associated bundles. This approach aims to significantly improve perceived page load performance and user satisfaction. The library offers a Webpack plugin for automated setup for Webpack users, and provides modules for fetching Google Analytics data, JavaScript framework parsing, and configuring predictive fetching. For non-Webpack users, it outlines a workflow for integrating predictive fetching using the Google Analytics API and a client-side script.

ParagraphAI is a comprehensive AI writing assistant and keyboard designed to enhance writing skills across various platforms. It offers real-time grammar and spelling corrections, one-tap email replies, and the ability to create diverse text formats from casual messages to professional reports. Users can fine-tune their writing with innovative real-time editing filters to adjust formality, friendliness, and length. The tool supports over 40 languages, allowing for personalized language settings, and includes a "humanize" feature to help AI-generated content pass detection. ParagraphAI also streamlines repetitive writing tasks with customizable templates and provides instant summarization for web pages and PDFs, making it a versatile solution for students, professionals, and individuals with dyslexia or ESL needs.

Roark is a comprehensive QA and observability platform specifically designed for Voice AI agents, ensuring reliability and performance. It enables teams to proactively catch issues before customers encounter them by offering robust monitoring and evaluation capabilities for live voice interactions. Users can track over 40 built-in metrics, analyze multi-speaker conversations, and run best-in-class evaluators on demand or automatically. The platform also facilitates pre-deployment testing through end-to-end simulations, allowing users to stress-test agents across real-world scenarios and automatically generate test cases from failed live calls. With one-click native integrations for popular voice platforms like VAPI, Retell, LiveKit Cloud, and Pipecat, Roark offers quick setup and real-time insights.

Legends-Of-Heroes is an open-source C# game framework built on ET 8.1, designed for dual-end game development using .NET8 and Unity6000. It features a comprehensive battle system with ECS skills and a buff system, with ongoing development for skill and behavior tree editors. The framework includes a LOL-style ball battle demo that utilizes state synchronization, where all collision detection, skills, and AI logic are executed server-side. It integrates with EUI, Luban, and YooAsset for UI, configuration, and resource management, respectively. The project also supports HybridCLR for hot updates and offers one-click packaging for various platforms like Windows and Android. It's ideal for developers looking for a robust foundation for real-time multiplayer games with advanced combat mechanics.