opensumi/core

A framework helps you quickly build AI Native IDE products. MCP Client, supports Model Context Protocol (MCP) tools via MCP server.

What it solves

OpenSumi is designed to simplify the creation of AI-native Integrated Development Environments (IDEs). It provides a foundational framework that allows developers to build custom IDE products without starting from scratch, supporting various deployment targets like cloud, desktop (Electron), and pure web environments.

How it works

It functions as a core framework that can be extended via examples and templates. It supports the Model Context Protocol (MCP) to integrate AI capabilities. It allows developers to set up a workspace and run the IDE core, which can then be customized into specific products such as the CodeFuse IDE (an AI-powered IDE).

Who it’s for

Developers and organizations looking to build their own specialized AI-native IDEs or custom development environments for the web, cloud, or desktop.

Highlights

  • AI Native: Specifically designed to support AI-integrated development tools.
  • Multi-platform Support: Templates available for Cloud IDEs, Electron-based desktop IDEs, and pure web IDEs.
  • ** uma MCP Client**: Implements the Model Context Protocol for better AI tool integration.
  • Extensible: Provides a variety of example projects and templates to accelerate development.

Related

  • Project
    google-ai-edge/mediapipe

    An open-source framework for building and deploying customizable on-device machine learning pipelines across mobile, web, desktop, and IoT devices.

  • Project
    dxos/dxos

    A decentralized operating system platform for building decentralized applications and powering an AI-driven, collaborative IDE called Composer.

  • Project
    moeru-ai/airi

    An open-source framework for creating interactive AI virtual characters and VTubers capable of chatting, playing games, and interacting across multiple platforms.

  • Project
    bytedance/flowgram.ai

    A composable workflow development framework and toolkit for building custom AI workflow platforms with visual canvases and variable management.

  • Project
    mattt/emcee

    A tool that converts any web application with an OpenAPI specification into a Model Context Protocol (MCP) server, allowing AI models to use the API as a tool.