ljquan/opentu

开放的AI应用平台

What it solves

Opentu provides a unified, canvas-based workspace for AI tasks, solving the fragmentation that occurs when users have to switch between different models, tools, and assets while managing complex creative or analytical workflows.

How it works

It functions as an AI application platform that connects multi-model generation (text, image, video, audio) with a canvas workspace. The platform uses a task queue and asset library to manage generated results and allows users to integrate internal React tools, iframe-based tools, and specialized AI agents to execute tasks continuously within a single environment.

Who it’s for

It is designed for users who need to orchestrate complex AI-driven content creation, such as those building flowcharts, mind maps, or PPT presentations, and those who require a structured workspace to manage AI-generated assets and knowledge flows.

Highlights

  • Canvas-Centric Workspace: A central area to host AI tasks, frames, tools, and knowledge base content.
  • Multi-Model Routing: Unified scheduling for text, image, video, audio, and agent-based workflows.
  • Integrated Content Tools: Built-in support for Markdown, Mermaid diagrams, and PPT export.
  • Extensible Architecture: Supports a plugin-based runtime with Skill/Agent extensions and iframe tool integration.

Related

  • Project
    basketikun/infinite-canvas

    An open-source visual workbench that integrates AI image generation, canvas orchestration, and prompt management into a single interface for continuous creative iteration.

  • Project
    hero8152/Infinite-Canvas

    A visual, infinite canvas workspace that integrates multiple AI APIs and local ComfyUI workflows for collaborative generative AI content creation.

  • Project
    ashuoAI/SHUO-Canvas

    A node-based visual canvas for multi-modal AI creation that integrates text, image, video, and audio workflows, including support for ComfyUI and RunningHub.

  • Project
    ddcat-ai/open-ai-canvas

    Open‑source AI‑driven video/short‑film creation platform with a visual canvas, workflow management, and async generation of text, images, video and audio. Built with React (frontend) and Go/Gin (backend), deployable via Docker, and extensible through a skill ecosystem.

  • Project
    nodetool-ai/nodetool

    NodeTool is an open‑source, agent‑first creative workspace that lets you build multimodal AI‑driven media (text, images, video, audio, 3‑D, games) via a node‑graph interface. Connect any LLM or generative model with your own API keys or run local open‑weight models, let the built‑in agent wire and run workflows, and edit the results in specialized editors (storyboard, timeline, sketch, 3‑D, game). Available as a free cross‑platform desktop/web app, extensible with custom TypeScript/Python nodes, and usable from a CLI or MCP server.