Projects sharing features with Screenshot To Code

AFFiNE is a collaborative knowledge base and productivity suite designed as a private-first, local-first platform. It provides an integrated workspace that combines structured documents with an infinite digital canvas, allowing users to organize complex information through a block-based model. By prioritizing local data persistence, the platform ensures immediate responsiveness and data sovereignty while maintaining a distributed state for real-time synchronization across multiple devices. The platform distinguishes itself through a canvas-integrated database engine that enables transitions b

The Model Context Protocol SDK is a framework for building clients and servers that connect AI models to external data, tools, and resources using a standardized communication protocol. It provides the foundational libraries and interfaces necessary to establish reliable, transport-agnostic connections between AI agents and external systems, enabling seamless information retrieval and task automation. The SDK distinguishes itself through a robust capability negotiation handshake that ensures compatibility between connected parties before exchanging messages. It supports a pluggable transport

Superdesign is an AI-powered design platform that generates UI mockups, wireframes, and multi-page user flows from natural language prompts within a collaborative canvas environment. It functions as a design-to-code exporter, producing production-ready HTML, ZIP archives, or Shopify Liquid templates for direct implementation, and includes an OpenAPI specification importer that automatically generates API documentation and client code from schema definitions. The platform distinguishes itself through a branch-based design exploration system that creates independent design variations from a sin

This project is an AI-powered visual canvas and collaborative whiteboard framework. It functions as a customizable vector drawing engine and a tool for converting hand-drawn interface sketches and wireframes into functional code using artificial intelligence. The system distinguishes itself through the integration of AI agents that can read, modify, and generate visual diagrams directly on the canvas. It also provides a node-based workflow editor for building automation pipelines and data processing flows by connecting multimodal components. The platform covers a broad range of capabilities,

This project is a Python-based framework that functions as a generative AI agent for programmatic data analysis. It enables users to interact with structured data sources through natural language prompts, translating these requests into executable code to perform analysis, data cleaning, and visualization. By maintaining conversational context across multi-turn interactions, the system allows for iterative exploration and the building of complex data narratives. The framework distinguishes itself through a robust semantic layer and secure execution model. It maps raw datasets to descriptive m

Pinme is a full stack deployment platform and infrastructure orchestration tool. It functions as an LLM application builder that converts natural language prompts into functional web applications with automated interfaces and business logic. The platform provides a static site hosting service and a content-addressable data manager for transferring project assets between environments. It automates the provisioning of workers, databases, and domains to launch applications via a single command. The system covers cloud resource management, project lifecycle orchestration from templates, and incr

This project provides methodologies and guides for structured prompt engineering, generative workflows, and specialized image generation strategies. It serves as a framework for optimizing inputs to large language models across coding, writing, and analysis tasks, as well as a library of techniques for controlling diffusion models. The project distinguishes itself through an AI-driven software design framework that converts business requirements into technical architectures and code using domain-driven prompting. It also implements generative AI workflow patterns that use sequential prompt pi

Micro-agent is a framework for AI-driven agents focused on automated test-driven development, design-to-code conversion, and external tool orchestration. It utilizes agents that iteratively write, test, and refine source code based on natural language prompts and design files. The system transforms visual design tokens and components into type-safe, linted code by comparing live URLs against reference screenshots to ensure visual parity. It also provides a protocol for linking agents to external commerce, search, and asset management services to synchronize data and expand functional capabili

sketch-measure is a design specification tool and design-to-code annotation utility for Sketch. It functions as an HTML design spec generator and asset export manager, creating technical handoff documentation and measurement annotations directly from design files. The tool generates interactive web viewers and standalone offline HTML pages that allow for the inspection of dimensions, styles, and design details. It includes capabilities for managing color palettes via XML export and capturing influence rectangles to ensure exported image dimensions account for shadows and borders. The system

Workflow Builder Template is an orchestration platform that translates natural language prompts and visual graph designs into multi-step automated pipelines. It combines an interactive browser-based canvas with an underlying engine that generates type-safe executable code from user configurations. The platform supports external service integrations across messaging, ticketing, email, file storage, and database operations. Users can build and modify automation sequences either through the drag-and-drop interface or by querying integrated language models behind the scenes to generate complete

pix2code is a computer vision UI parser and screenshot-to-code converter that transforms images of graphical user interfaces into functional code representations. It operates as a deep learning system that maps visual interface elements to layout instructions and syntax. The project includes a machine learning training pipeline for UI, which converts raw image data into numerical arrays to create training sets. This workflow supports training models to recognize visual interface components and map them to specific code structures. The system covers automated frontend development through the

FigmaToCode is a design-to-code converter and frontend code generator that transforms Figma design files into responsive source code. It functions as a multi-platform UI compiler, mapping visual design elements to structural constraints for web and mobile environments. The system supports multi-target syntax emission to produce code for HTML, Tailwind CSS, Flutter, and SwiftUI. It automates frontend styling by converting design system variables and visual effects into theme-consistent code across these different frameworks. The tool handles responsive UI implementation by translating design

JSON Render is a generative user interface framework that translates structured data and natural language prompts into interactive components. It functions as a declarative engine that maps JSON schemas to native interface elements, enabling the creation of functional layouts across web, mobile, and terminal environments. The framework distinguishes itself through its ability to synthesize interfaces from artificial intelligence models, allowing for real-time iteration and incremental updates as data patches arrive. It supports a unified component registry that ensures consistent rendering ac

This project provides a library of standardized configuration templates and infrastructure-as-code tooling designed to create reproducible, containerized development environments. By utilizing the Dev Container specification, it enables teams to define isolated workspaces that ensure consistent tooling, runtimes, and editor settings across different machines and team members. The project distinguishes itself by offering a framework for authoring and distributing reusable environment definitions as container images. This approach leverages existing registry infrastructure for versioning and di

Zerox is a multimodal document parser and OCR tool that uses vision models to convert PDF files and images into structured Markdown text. It functions as a visual layout extraction engine, leveraging large multimodal models to digitize documents while maintaining their original structural formatting. The system differentiates itself through the use of coordinate-based element mapping and multimodal layout analysis to identify structural elements like tables, charts, and headers. It utilizes rasterization to convert vector PDF pages into high-resolution bitmaps, ensuring consistent input for t

Figma-Context-MCP is a design-to-code automation tool that functions as a server for the Model Context Protocol. It acts as a bridge between visual design platforms and development environments, enabling large language models to access design file metadata and component properties directly. The project distinguishes itself by providing a standard-compliant interface that translates design specifications into structured data. By extracting layout and styling information, it facilitates the programmatic conversion of design tokens and component requirements into actionable code structures. Thi

This project provides a remote development platform that enables users to access a full-featured integrated development environment through a standard web browser. By decoupling the user interface from the server-side filesystem, it allows for persistent coding workspaces to be hosted on remote servers, virtual machines, or cloud-native infrastructure, ensuring a consistent development experience from any device. The platform distinguishes itself through a secure gateway architecture that manages traffic, authentication, and encryption at the edge. It utilizes persistent WebSocket connections

Mitosis is a cross-framework compiler that transforms a single JSX-based source into native components for multiple frontend libraries simultaneously. It functions as a multi-target UI library builder, allowing developers to maintain a single source of truth for design systems while generating production-ready code for diverse environments including React, Vue, Angular, and Svelte. The system operates by parsing unified component code into an intermediate JSON representation, which serves as the foundation for all downstream framework generators. This architecture utilizes a visitor-based tra

Air is a command-line utility designed to automate the development lifecycle for Go applications. It functions as a build runner that monitors source code for file-system modifications, automatically triggering rebuilds and process restarts to maintain an updated development environment. The tool distinguishes itself by integrating container-isolated execution, allowing developers to run build and test workflows within consistent, ephemeral environments. It also incorporates a reverse-proxy layer that intercepts network traffic to facilitate live-reloading of browser sessions, ensuring that c

OpenHands is an autonomous AI software engineer and coding assistant designed to execute software engineering tasks by interacting directly with codebases and development environments. It functions as a platform for running AI agents that can write code and manage files to automate complex development workflows. The system distinguishes itself through a container-based execution environment that isolates agent actions within a sandboxed Linux environment. It employs an autonomous agent loop of observation, planning, and action, supported by a standardized communication protocol that allows it

Sketch-code is a deep learning web prototyping tool and image-to-HTML converter designed to transform hand-drawn website mockups into structural HTML code. It utilizes a neural network wireframe parser to recognize visual elements in sketches and map them to corresponding web layout representations. The system employs a Keras-based architecture for training and evaluating recognition models using datasets of hand-drawn wireframes and reference HTML. It decouples structural layout from visual design by allowing the injection of custom CSS layers during the compilation process. The project cov

This is a command line tool for building and managing isolated development environments based on the Development Container Specification. It functions as an OCI container image builder and a provisioner for instantiating standardized containers within automated continuous integration workflows. The tool includes a system for injecting pre-configured software and toolsets into containers using a registry of reusable installation modules. This allows for the creation of shareable features and the installation of specific languages, CLI tools, and software dependencies. It covers the automation

Flexpilot is a browser-based integrated development environment that combines a code editor with containerized workspaces. It provides a cloud-hosted platform for software development, allowing users to access fully functional coding environments directly through a web browser without requiring local software installations. The platform distinguishes itself by integrating conversational artificial intelligence directly into the editor interface. Through a unified abstraction layer, it connects to external artificial intelligence models to provide automated code generation, deep analysis, and

Agent Zero is an LLM agent framework and multi-agent orchestrator that provides an AI-powered interface for operating system tasks. It functions as a containerized AI workspace, allowing large language models to interact with a filesystem and terminal within an isolated Linux environment. The system distinguishes itself through a hierarchical orchestration model that decomposes complex goals by spawning specialized sub-agents to collaborate and consolidate results. It features a plugin-based architecture for extending capabilities via a community plugin hub, a custom skills system, and extern

draw-a-ui is an AI vision UI generator and sketch-to-code tool that transforms hand-drawn sketches and digital wireframes into functional HTML and CSS. It serves as a mockup-to-HTML converter that interprets user interface layouts from images to produce corresponding web markup. The system utilizes vision-capable language models to automate the transition from visual design to web code. It employs a multimodal inference loop to process canvas snapshots and natural language instructions, generating structural layouts and responsive grid systems without the need for pre-defined component templa

This project provides a comprehensive guide and framework for implementing autonomous AI coding assistants within local development environments. It focuses on orchestrating multi-agent teams that can plan, execute, and verify complex software engineering tasks, such as refactoring, bug resolution, and test generation, while maintaining deep awareness of project-specific context and memory. The system distinguishes itself through a robust security-first architecture that enforces granular access controls, execution isolation, and mandatory human-in-the-loop approvals for all file modification