OpenSumi

Created By
opensumia year ago
A framework helps you quickly build AI Native IDE products. MCP Client, supports Model Context Protocol (MCP) tools via MCP server.
Overview

What is OpenSumi?

OpenSumi is a framework designed to help developers quickly build AI Native Integrated Development Environment (IDE) products, supporting Model Context Protocol (MCP) tools via an MCP server.

How to use OpenSumi?

To use OpenSumi, clone the repository from GitHub, install the necessary dependencies using Yarn, and run the project. You can specify your workspace directory during the startup.

Key features of OpenSumi?

  • Rapid development of AI Native IDEs
  • Support for Model Context Protocol (MCP) tools
  • Example projects for various IDE types (Cloud IDE, Desktop IDE, etc.)

Use cases of OpenSumi?

  1. Building custom AI-driven IDEs for specific programming languages.
  2. Creating cloud-based IDEs for collaborative coding.
  3. Developing desktop IDEs that leverage AI for code suggestions and completions.

FAQ from OpenSumi?

  • Is OpenSumi suitable for all programming languages?

Yes! OpenSumi can be adapted to support various programming languages through its extensible framework.

  • How can I contribute to OpenSumi?

You can contribute by reporting bugs, submitting pull requests, or improving documentation as outlined in the Contributing Guide.

  • What is the license for OpenSumi?

OpenSumi is licensed under the MIT license.

Project Info
Created At
a year ago
Updated At
a year ago
Author Name
opensumi
Star
3410
Language
TypeScript
License
MIT license

Recommend Servers

View All
Bring your real authenticated browser session to AI coding agents. Local-first MCP server + Chrome MV3 extension. No cloud. No telemetry.
@Cubenest

peek records the user's actual logged-in browser (DOM via rrweb, console events, network metadata, optional response bodies via opt-in Deep capture) through a Chrome MV3 extension. The extension ships events through a native-messaging stdio bridge to a local MCP server (peek-mcp), which persists them to a SQLite database at ~/.peek/sessions.db. AI coding agents (Claude Code, Cursor, Cline, Windsurf) read sessions from the database via 10 MCP tools: Tool What it does list_recent_sessions List recently recorded sessions (id, origin, ts, event count). get_session_summary LLM-readable narrative summary of a session. get_session_console_errors Console errors recorded in a session. get_session_network_errors Failed/notable network requests in a session. get_user_action_before_error Last N user actions before a console error. generate_playwright_repro Generate a runnable Playwright test from a session. get_dom_snapshot Reconstruct the DOM at a given timestamp. query_dom_history Timeline of attribute/text changes for a selector. request_authorization Side-panel consent for write actions (Level 3). execute_action Dispatch a UI action (gated by permission level + destructive blocklist). Why local-first matters Every other "browser session for AI" tool ships to a vendor cloud. peek's SQLite + extension live on the user's machine — no remote endpoints, no telemetry. The privacy policy (docs/peek/PRIVACY_POLICY.md) is the source of truth. Install # 1. Add the MCP server to Claude Code claude mcp add peek -- npx -y @peekdev/mcp # 2. Install the Chrome extension from the Chrome Web Store # (link added once the CWS listing is approved)

a day ago