Coding & Development

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.

NoDocs is an intuitive no-code documentation builder designed for makers and teams to create sleek, professional documentation quickly. It features a Notion-like editor, making the content creation process familiar and straightforward, without requiring any coding knowledge. Users can structure their documentation across multiple pages, ensuring comprehensive and organized content. The platform supports custom domains for branded documentation and offers one-click publishing for instant deployment. NoDocs aims to simplify the documentation process, allowing users to focus on content rather than technical complexities. Upcoming features include AI-powered suggestions and AI Autocomplete to further enhance the writing experience.

Bubble AI is a powerful no-code platform designed to help users turn their ideas into functional applications quickly and efficiently. Leveraging AI capabilities, it enables rapid app development without requiring any coding knowledge. The platform emphasizes both speed and control, providing the necessary security features for applications to scale and grow. Users can connect and customize APIs, edit app extensions, and utilize a wide array of community-built plugins to enhance their projects. Bubble also offers extensive resources and a supportive community forum, making it easier for users to develop and troubleshoot AI-related challenges.

AI & Stuff is a mobile application designed to explore AI functionalities directly from a smartphone. It offers users the ability to generate images using advanced AI models like DALL-E, bringing creative possibilities to their fingertips. Beyond image generation, the app also integrates augmented reality (AR) viewing, allowing users to experience AI-generated content in a new, interactive dimension. This tool is ideal for individuals interested in experimenting with AI on the go, providing a convenient platform for both creative expression and technological exploration within a mobile environment.

Ringtone Maker - Music Player, rebranded as "多多学汉字" (Duoduo Learn Chinese Characters), is an AI-powered educational application designed to help children aged 2-12 learn Chinese characters effectively. The app utilizes creative interactive games and engaging storybooks to make the learning process fun and intuitive. It incorporates an AI character recognition algorithm to accurately assess a child's current literacy level, allowing for a scientifically tailored learning plan. Key features include beautiful graphics, simple operation suitable for young children, and standard professional Chinese pronunciation, ensuring an immersive and effective learning experience for over 2000 characters.

Lindo AI is a white-label AI website builder designed for individual entrepreneurs, freelancers, and agencies. It enables users to generate professional websites from text descriptions in minutes, without requiring any coding experience. Key features include over 640 professional templates, white-label branding options, a built-in client CRM for managing projects and invoicing, and an analytics dashboard to track client results. The platform also supports custom domains, Stripe integration, and API access. Lindo AI aims to empower users to start or scale their web design business by providing a comprehensive platform to build, manage, and bill clients under their own brand.

Agent Bar is a menu bar application designed to streamline the coding workflow for developers using Claude Code. It provides a clean, native user interface that keeps Claude Code sessions readily accessible, allowing users to launch sessions in any project folder and monitor their status in real time. Developers can review messages, approve or deny tool actions, and organize multiple sessions efficiently. The tool also includes optional voice dictation for quick prompt capture, minimizing context switching and enabling faster responses. By integrating Claude Code directly into the macOS menu bar, Agent Bar helps developers stay focused and productive without leaving their desktop environment.

NaturalReader is an AI-powered text-to-speech tool that converts various text formats, including documents, PDFs, webpages, and even physical books, into natural-sounding audio. It leverages advanced language models to create lifelike voices that can understand text content and adjust delivery accordingly. The tool supports over 90 languages and offers features like voice cloning, custom voice design, and content-aware voices. Beyond basic text-to-speech, NaturalReader provides AI-powered features such as AI Podcast for converting long readings into episodes, AI Recap for summaries, AI Screenshot for detailed analysis of captured text, AI Chat for document interaction, and AI Quizzes for studying. It is available as a web app, mobile app, and Chrome extension, catering to personal, commercial, and educational users.

DataDreamer is a powerful open-source Python library designed for prompting, synthetic data generation, and training workflows. It enables users to create and run complex, multi-step prompting workflows with major open-source or API-based LLMs. The library facilitates the generation of synthetic datasets for novel tasks or the augmentation of existing datasets using LLMs. Additionally, DataDreamer supports various model training processes, including fine-tuning, instruction-tuning, and distillation, on both existing and synthetic data. It emphasizes simplicity, efficiency through aggressive caching and resumability, and reproducibility, making it suitable for research-grade projects and easy sharing of workflows, datasets, and models.

AppStudio is an all-in-one Android app builder that empowers users to create functional Android applications directly from their device without needing to write code. It provides over 50 templates, including AI-powered options, eCommerce, radio, and business profiles, allowing for quick app development. Users can modify the full source code (Java/XML), customize package names, logos, colors, and versions, and generate a signed APK or AAB in just three minutes. The platform also features an AI Playground for generating layouts and modules, a Website2App converter, and live admin support, making it accessible for both beginners and those needing more control.

Newelle is an open-source AI virtual assistant designed for advanced customization and flexible AI model integration. Users can tailor the application with a wide range of settings and choose from multiple AI models and providers, including the ability to download and run local models using Llama.cpp or Ollama. It supports extensions for added functionality, skills from platforms like Claude and Codex, and tools via MCP servers. Key features include voice support with wakeword detection, a call mode for real-time AI interaction, long-term memory for conversations, and the ability to chat with documents and perform web searches. Newelle also offers terminal command execution, dynamic context management, file permissions, scheduled tasks, a profile manager, and a built-in file manager with AI assistance. It supports rich formatting (Markdown and LaTeX), multichat, chat branching, and chat editing, allowing for a highly personalized and efficient virtual assistant experience.

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.

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.

Recogni, operating as Tensordyne, specializes in developing next-generation AI inference systems for data centers. Their core innovation lies in re-engineering the mathematical foundations of artificial intelligence and building custom silicon on top of it. This approach aims to deliver unprecedented tokens per dollar per watt, significantly reducing rack count, power consumption, and cost for running large AI models. Tensordyne collaborates with industry leaders to scale their silicon into dense and energy-efficient AI systems, offering solutions for complex AI workloads. Their technology is designed and developed in the US and Germany, emphasizing a hardware-software co-design approach for optimal AI inference performance.

VibeFlow is an AI-powered platform designed for building full-stack applications and automations with both frontend and backend components. Unlike black-box builders, it offers transparent, visual backends using n8n-style workflows, allowing users to see and edit their entire application logic. The platform enables users to build backend automations, data pipelines, and approval workflows, and connect them to frontends like dashboards, forms, or customer-facing apps. It generates clean TypeScript and React code, which users own and can export to GitHub. VibeFlow supports building UIs, cloning websites, and converting Figma designs into production-ready React components iteratively. It integrates with various services like Slack, Notion, Stripe, and Gmail through pre-built connectors.

sshx offers a secure, web-based platform for sharing and collaborating on terminals. Users can invite others by sharing a unique browser link, enabling real-time collaboration with remote cursors and chat on a multiplayer infinite canvas. The tool is designed for speed and security, featuring end-to-end encryption to ensure data privacy, as the server never sees what is being typed. It supports cross-platform use with a command-line tool available for macOS, Linux, and Windows. sshx is ideal for teaching, debugging, or cloud access, allowing users to move and resize multiple terminals in any arrangement and see live presence of other participants. Its ultra-fast mesh networking connects users to the nearest distributed peer in a global network.

Zenvault is a CLI-first project control plane designed to streamline developer experience by centralizing repositories, environment variables, and resources. It allows for one-command onboarding to any project, eliminating the need for manual setup documentation and fragile .env files. Zenvault ensures that code runs correctly and consistently across all environments and machines, improving team productivity and reducing setup friction. Key features include secure secrets management with AES-256 encryption, environment variables per service, and audit logging. It integrates seamlessly into existing workflows, providing a single source of truth for project configuration and enabling secure team collaboration with granular access control.

DeepCL is an open-source OpenCL library designed for training deep convolutional neural networks. It offers C++, Python, and command-line APIs, allowing developers to implement and train deep learning models efficiently. The library supports various layer types including convolutional, max-pooling, normalization, activation, and dropout, alongside loss functions like softmax cross-entropy and square loss. DeepCL also incorporates multiple trainers such as SGD, Anneal, Nesterov, Adagrad, Rmsprop, and Adadelta. It is compatible with OpenCL-enabled GPUs or APUs and provides installation procedures for Windows and Linux, including Python wrappers. The project is actively maintained on GitHub, with recent updates focusing on compatibility and performance enhancements.

dstack is an open-source control plane designed for agentic orchestration of AI infrastructure. It allows engineers to provision compute and run training, inference, and sandboxes across NVIDIA, AMD, TPU, and Tenstorrent GPUs on various platforms including cloud providers, Kubernetes, and bare-metal clusters. dstack simplifies the management of AI workloads by offering a unified control plane for compute orchestration, eliminating the need for complex Kubernetes or Slurm configurations. It supports running development environments, batch jobs, and high-performance model inference with features like auto-scaling, resource allocation, and GPU health metrics. dstack aims to reduce GPU costs through efficient reuse, right-sizing, and support for different capacity types.

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.

FullStackPathway is an all-in-one AI toolkit designed to solve a multitude of tasks with artificial intelligence. It offers over 900 free AI-powered tools across four core categories: Creation, Coding, Study, and Identification. Users can generate anything from lyrics and scripts to business plans, Python code, formulas, and receive tutoring. The platform emphasizes speed, with an average response time of 2 seconds for most prompts, and accessibility, as it requires no sign-ups or payments. It aims to be a single destination for building, learning, and getting answers fast, catering to a broad audience with diverse needs.

Visual Editing by DatoCMS offers a seamless WYSIWYG experience for headless CMS users, enabling content editors to directly click and edit elements on their website. This feature eliminates the need to search through record forms, streamlining the content management process. It supports two primary workflows: click-to-edit, where editors can visit their website in draft mode and click on editable content to open DatoCMS in a new tab, and visual mode, which provides side-by-side editing within the CMS for instant live updates. The tool leverages steganography to embed metadata in GraphQL API responses, allowing the frontend to automatically identify and render editable regions without manual wiring. It includes SDKs for popular frameworks like Next.js, Astro, Svelte, and Vue, and is available on all DatoCMS plans, including the free tier.

deepC is a vendor-independent deep learning library, compiler, and inference framework specifically engineered for small form-factor devices such as microcontrollers, IoT, and edge devices. It allows for the deployment of deep learning models in resource-constrained environments, boosting the intelligence of billions of devices without relying on expensive hardware or constant internet connections. The framework includes an ahead-of-time compiler that produces optimized executables based on the LLVM compiler toolchain, specialized for deep neural networks with ONNX as the front end. deepC supports various architectures like Arm, Armv7, Arm64, AMD64, and ppc64le, and is compatible with operating systems including Ubuntu, CentOS, Arch Linux, Manjaro, Windows, and Mac OS.

Barbacane is a spec-driven API gateway built in Rust, designed to eliminate configuration drift by using OpenAPI and AsyncAPI specifications as the single source of truth for routing, validation, authentication, authorization, and event bridging. It offers automatic JSON Schema validation, five built-in authentication plugins (JWT, OIDC, OAuth2, API Key, Basic Auth), and blazing-fast performance due to its Rust foundation. The gateway is extensible with 29 official WebAssembly plugins for various functionalities like security, traffic control, and observability. It supports AsyncAPI for event bridging to systems like Kafka, NATS, or AWS Lambda, and features a split control and data plane architecture for resilience and zero-downtime deployments. Barbacane is open source under AGPLv3, with commercial licensing options available.