Claude Skill
Mng-dev-ai/claudex
开源Claude代码界面,提供浏览器内VS Code、终端、沙箱执行(本地/e2b/modal)、多AI提供商支持、自定义Claude Skill和MCP服务器集成,用于AI辅助开发。
概览
仓库信息
安装这个 Skill
git clone https://github.com/Mng-dev-ai/agentrove.gitRegistry 信息
git clone https://github.com/Mng-dev-ai/agentrove.gitnpm install
项目简介
ClaudeX是一个自托管的Claude代码界面,提供完整的开发环境,包括浏览器内VS Code编辑器、终端访问以及多提供商AI支持(Max、Z.AI、OpenRouter)。它具有本地/e2b/modal沙箱执行、自定义Claude Skill创建和MCP服务器集成功能,用于增强AI辅助编码工作流。
Your own Claude Code UI, local/e2b/modal sandbox, in-browser VS Code, terminal, multi-provider support (Max, Z.AI, OpenRouter), custom skills, and MCP servers.
要点
- 浏览器内VS Code编辑器,带终端功能
- 多提供商AI支持(Max、Z.AI、OpenRouter)
- 本地/e2b/modal沙箱环境用于代码执行
- 自定义Claude Skill创建与管理
- MCP(模型上下文协议)服务器集成
- 基于TypeScript/React前端的自托管部署
使用场景
- 在基于浏览器的IDE中使用Claude进行AI辅助编码
- 在隔离沙箱环境中测试代码
- 为专业任务开发自定义Claude Skill
- 在单一界面中集成多个AI提供商
- 带有AI指导的教育性编码环境
- 利用MCP服务器功能进行AI原型开发
README 摘要
# Agentrove Self-hosted AI coding workspace for running Claude Code, Codex, Copilot, Cursor, and OpenCode agents from one interface. [](LICENSE) [](https://www.python.org/) [](https://react.dev/) [](https://discord.gg/HvkJU8dcBA) > Agentrove is under active development. Expect breaking changes between releases.  ## What It Does - Runs Claude, Codex, Copilot, Cursor, and OpenCode through ACP adapters. - Gives each workspace its own Docker or host sandbox. - Combines chat, code editor, terminal, file tree, diffs, secrets, and git tools in one workspace. - Supports workspaces from empty folders, git clones, existing local folders, or GitHub repositories. - Streams agent sessions with cancellation, permission prompts, queued follow-up messages, file mentions, slash commands, and attachments. - Includes sub-threads, pinned chats, worktree mode, personas, custom instructions, environment variables, and installed agent skills. - Provides GitHub-assisted repository browsing, pull request review, PR creation, reviewer selection, and git branch/commit/push/pull helpers. - Ships as a Docker web app, a macOS desktop app, and a native iOS app. ## Quick Start Requirements: - Docker - Docker Compose ```bash git clone https://github.com/Mng-dev-ai/agentrove.git cd agentrove cp .env.example .env ``` Set `SECRET_KEY` in `.env`: ```bash openssl rand -hex 32 ``` Start Agentrove: ```bash docker compose up -d ``` Open [http://localhost:3