Open-source alternatives to Draw A Ui

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,

Impeccable is a design system framework for large language models and an AI coding assistant plugin. It functions as an AI-driven UI generator and a rule-based design linter, providing a structured set of instructions and configuration files to standardize the production of professional user interfaces. The project features a design token orchestrator that maps standards across different AI provider environments and a config-driven factory for managing skills across multiple providers. It employs a deterministic rule engine to audit interfaces for accessibility violations, typography errors,

InternVL is a vision-language model framework that fuses a visual encoder with a large language model to translate image features into textual tokens for reasoning. It provides a system for multimodal inference and dialogue, enabling the processing of images and text to answer questions or generate descriptions. The project is distinguished by its high-resolution image processing, which uses dynamic tiling to maintain detail for images up to 4K resolution, and its chain-of-thought visual reasoning for solving complex mathematical and spatial problems. It also supports temporal frame sampling

Qwen3-VL is a multimodal vision-language model designed to process and reason across images, videos, and text. It functions as a computer vision framework capable of identifying objects, extracting structured data from documents, and interpreting spatial elements within visual media. The system operates as an automated user interface interaction agent, interpreting screen data to navigate software and mobile applications. By utilizing a unified transformer architecture, it performs complex visual reasoning to execute user-defined tasks without manual input. Beyond interface navigation, the m

Star-vector is a suite of vision-language systems designed to generate scalable vector graphics from text or image inputs. It utilizes a vision-language foundation model to treat the creation of visual elements as a structured code generation task. The system employs a multimodal architecture that maps visual patterns and shapes to corresponding structural elements in a vector code sequence. It incorporates a render-loop feedback mechanism and reinforcement learning to iteratively refine the fidelity of the generated graphics by comparing rendered outputs against target images. The project c

Alva is a code-based prototyping tool and living prototype framework used to build interactive interfaces. It functions as a component-driven design system where application concepts are realized as functional code components rather than static mockups. The project facilitates a design-to-code workflow, enabling the creation of living component documentation and the validation of frontend concepts. It allows for rapid UI prototyping by composing reusable code building blocks to test design ideas and technical implementations. The environment supports component-based UI composition and declar

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

Openv0 is an AI-driven UI prototyping tool and component generator. It uses large language models to create user interface elements, providing a live preview feedback loop for immediate visual iteration. The system operates as a generative frontend pipeline, utilizing a modular sequence of plugins to orchestrate the creation of UI assets. This architecture allows for the integration of custom UI frameworks, external libraries, and icon sets to expand the range of available visual components. The tool covers frontend component prototyping and generative asset pipelines. It supports project bo

Qwen2-VL is a multimodal large language model and vision language model designed to process and reason across text, images, and video content. It functions as a visual reasoning engine and a visual agent framework, capable of interpreting visual data to perform object detection, document parsing, and spatial reasoning. The model is distinguished by its ability to act as a video understanding model, processing hour-long videos with second-level indexing and event recall. It further differentiates itself through a visual agent capability that interacts with software interfaces and robotic hardw

Phoenix is a comprehensive web development suite that provides a browser-based code editor, an AI-powered coding assistant, and a live web previewer. It integrates a visual Markdown document editor and a web-based Git client, allowing users to write and manage HTML, CSS, and JavaScript across different devices and platforms. The environment features a visual UI design system that maps canvas manipulations directly to code and enables in-place CSS editing. It supports real-time change previews and responsive layout testing across multiple device breakpoints to verify rendering on phones, table

Blocks is a no-code website builder and component-based UI framework designed to create production-ready websites through a visual interface. It functions as a visual page builder that assembles layouts using pre-designed JSX component blocks. The system includes a visual theme engine used to manage brand identity through the definition of global colors and layout presets. This allows for the application of consistent visual themes across all pages of a site. The platform covers visual website building, JSX page construction, and brand identity management. It utilizes a schema-driven layout

DeepSeek-VL is a multimodal large language model and image-to-text reasoning engine. It functions as a vision-language model and visual question answering system that integrates visual perception with linguistic reasoning to understand and describe images. The project enables multimodal image understanding and document image analysis, specifically processing screenshots of web pages and technical diagrams. It provides capabilities for visual conversational AI, allowing users to interact with visual data to extract insights and perform complex reasoning across different types of visual informa

David AI is a UI development toolkit that combines AI-powered page generation with a library of pre-built, copy-paste-ready components built on Tailwind CSS. At its core, it offers an AI builder that can generate complete landing pages and dashboards from natural language prompts, outputting clean, responsive Tailwind CSS code. The project provides a comprehensive collection of UI components—including buttons, forms, navigation elements, and data displays—that can be assembled into full page sections like hero blocks, pricing tables, and dashboards. The toolkit distinguishes itself through a

Wired-elements is a hand-drawn web component library providing a collection of stylized HTML elements for building wireframes and mockups. It serves as a wireframing UI framework that enables the creation of low-fidelity prototypes with a sketchy, manual aesthetic. The library provides components for hand-drawn web design and rapid UI prototyping. These elements are designed to support low-fidelity wireframing to plan user interfaces and test layouts before high-fidelity development. The project utilizes a web component architecture with SVG-based vector graphics to maintain a consistent han

LAVIS is a multimodal large language model framework and vision-language model library. It provides tools for training and evaluating models that integrate visual, textual, and audio data, serving as a cross-modal feature extractor and a zero-shot visual reasoning engine. The framework distinguishes itself by using frozen-backbone integration, where pretrained encoders remain non-trainable while lightweight adapter layers are updated. It employs cross-modal feature alignment to map different representations into a shared embedding space and utilizes a modular model wrapper to swap vision and

LLaDA is a masked diffusion language model and conditional text generator. It generates text by iteratively refining masked tokens through a diffusion process rather than predicting the next token in a sequence. The project functions as a vision-language diffusion model, converting visual inputs into text responses. It also serves as a preference optimization framework that uses log-likelihood estimation and evidence lower bounds to tune model responses. The system supports multi-round conversational AI and text sequence evaluation. It integrates vision-language embedding for cross-modal con

Magic MCP is a Model Context Protocol server and AI component generator that translates natural language descriptions into functional user interface code. It acts as an LLM design orchestrator, producing responsive web elements and layouts anchored on utility-first CSS styling patterns. The system features a side-by-side variation engine that generates multiple stylistic interpretations of a single prompt for comparative selection. It incorporates SVG-based asset integration for branding and iconography and utilizes template-based assembly to combine pre-defined style patterns with user-speci

Redacted-Font is a collection of specialized typefaces and font files designed to render text as solid redaction bars. It functions as a wireframe placeholder font that hides text content while preserving the original layout and spacing. The project provides font files compatible with both local operating systems and web projects. This allows for the masking of text within desktop design software and the embedding of redaction styles into web environments via font-face kits. These typefaces are used for UI layout prototyping and wireframe content masking to shift focus from specific copy to

TaskMatrix is a multimodal AI chat interface and visual task orchestrator. It combines language models with visual recognition to enable the exchange, analysis, and modification of images within a conversational environment. The system coordinates multiple foundation models through orchestration pipelines that chain language, detection, and segmentation models. This allows for complex visual operations, such as using text instructions to guide image masking and executing modular inpainting workflows to edit specific image regions. The project includes a computer vision toolset for object det

MiniCPM-V is a multimodal large language model and vision-language system designed for complex visual and linguistic understanding. It functions as an on-device AI model, providing the capacity to process text, images, and video as a compact neural network. The project is specifically developed as an edge AI framework, utilizing quantization and weight sharding to run on memory-constrained mobile chipsets. This allows for the deployment of multimodal intelligence directly on mobile operating systems for local inference. Its capabilities cover multimodal content analysis of high-resolution im

LLaMA-Factory is a comprehensive suite for dataset preparation, model fine-tuning, memory optimization, and standardized API deployment. It provides a unified platform for the supervised and reward-based fine-tuning of large language models and vision-language models. The framework includes a specialized toolkit for training vision-language models and a model serving interface that deploys trained models through high-performance APIs. It utilizes precision tuning and quantization techniques to reduce the hardware requirements and memory footprint of large models. The system covers data pipel

YOLO-World is a vision-language framework and open-vocabulary object detection model. It identifies objects in images and video based on free-form text prompts without requiring predefined category labels. The system enables the identification of arbitrary objects by fusing image features with text embeddings. It includes a specialized tool for automated image labeling, which generates bounding box annotations for custom datasets using text-based prompts. The project provides a deployment pipeline for converting models into quantized ONNX and TFLite formats, supporting real-time inference on

This is a Figma MCP server that exposes document manipulation capabilities to AI assistants through the Model Context Protocol. It functions as a bridge between AI tools and Figma, enabling programmatic creation, reading, updating, and deletion of design elements including frames, text nodes, components, and connectors. The server provides AI-powered design generation that translates natural language prompts into complete UI screens and design elements within Figma. It includes a design annotation system for adding, updating, and retrieving markdown-supported annotations on nodes, along with

imove is a visual workflow orchestrator and domain-specific language designer. It provides a graphical canvas for mapping complex functional logic and designing operational workflows through a node-based interface. The system functions as a visual flowchart to code generator, converting logic diagrams into an executable domain-specific language for software development kits. It includes a custom logic node framework that allows for the integration of external plugins and the creation of custom functions to extend the available node library. The platform supports node-based logic design and r

This project is a CSS grid layout generator and visual layout editor. It serves as a frontend development tool that allows for the design of grid structures and the generation of corresponding CSS code for dynamic web layouts. The tool enables visual grid prototyping by allowing users to define rows, columns, and item positions through an interactive interface. This process produces valid stylesheet rules, removing the need to manually calculate grid coordinates or track sizes. The software covers CSS grid layout design and responsive web layouting, providing the means to define grid item pl