Skip to content
Open
Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
30 commits
Select commit Hold shift + click to select a range
d7126e0
feat: add multi-provider support and UI configuration
lsustc Oct 23, 2025
06d51d7
Merge pull request #1 from DeepFundAI/ls-dev
lsustc Oct 23, 2025
bc79d2a
feat: improve UI layout and visibility control
lsustc Oct 23, 2025
f4ac707
feat icon update
lsustc Oct 24, 2025
213e9f5
Merge pull request #2 from DeepFundAI/ls-dev
lsustc Oct 24, 2025
50c4c27
fix FileAgent file path generation issue
lsustc Oct 24, 2025
d794da0
Merge pull request #3 from DeepFundAI/ls-dev
lsustc Oct 24, 2025
a5792ae
feat update style
lsustc Oct 24, 2025
a0aba59
0.0.4
lsustc Oct 24, 2025
0d147bd
feat update shotscreen
lsustc Oct 24, 2025
9a98dae
Merge pull request #4 from DeepFundAI/ls-dev
lsustc Oct 24, 2025
aa0ccdf
chore: update icons and README
lsustc Oct 24, 2025
9d73772
feat: update theme to purple style and improve UI/UX
lsustc Oct 24, 2025
38f9fd7
chore: bump version to 0.0.5
lsustc Oct 24, 2025
044cd97
chore: update icons and README
lsustc Oct 24, 2025
44d9f42
feat: update theme to purple style and improve UI/UX
lsustc Oct 24, 2025
fbe9094
chore: bump version to 0.0.5
lsustc Oct 24, 2025
06a6bee
fix develop mode config pack
lsustc Oct 24, 2025
0d51ef8
feat new feature:
lsustc Oct 29, 2025
1f2b62f
Merge branch 'main' into ls-dev
lsustc Oct 30, 2025
1bf1d45
docs: update documentation and screenshots for new features
lsustc Oct 30, 2025
b61591d
Merge pull request #5 from DeepFundAI/ls-dev
lsustc Oct 30, 2025
f6a3fb6
Merge pull request #6 from DeepFundAI/ls-dev
lsustc Oct 30, 2025
f96c7e2
feat add i18n support en/zh switch
lsustc Nov 3, 2025
cf06a55
feat(i18n): improve internationalization implementation and fix hook …
lsustc Nov 4, 2025
f35ab68
chore: bump version to 0.0.7
lsustc Nov 4, 2025
e250912
feat(ui): add WebGL fallback with gradient background
lsustc Nov 7, 2025
0ba5712
fix(utils): simplify WebGL context detection logic
lsustc Nov 7, 2025
b370f9c
feat: support human intervention for eko
lsustc Nov 11, 2025
0e3c3a3
feat: show human intervention prompt in chat
lsustc Nov 11, 2025
File filter

Filter by extension

Filter by extension


Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
21 changes: 12 additions & 9 deletions .env.template
Original file line number Diff line number Diff line change
Expand Up @@ -2,21 +2,24 @@
# ===================

# DeepSeek API Configuration
# Get your API key from: https://platform.deepseek.com/api_keys
DEEPSEEK_API_KEY=
DEEPSEEK_BASE_URL=https://api.deepseek.com/v1

# OpenAI API Configuration
OPENAI_API_KEY=
OPENAI_BASE_URL=https://api.openai.com/v1
# Alibaba Cloud Qwen API Configuration
# Get your API key from: https://bailian.console.aliyun.com/
QWEN_API_KEY=

# Anthropic API Configuration
ANTHROPIC_API_KEY=your_anthropic_api_key_here
ANTHROPIC_BASE_URL=https://api.anthropic.com/v1
# Google Gemini API Configuration
# Get your API key from: https://aistudio.google.com/app/apikey
GOOGLE_API_KEY=

# Alibaba Cloud Bailian API Keys (for Douyin/Xiaohongshu services)
BAILIAN_API_KEY=
# Anthropic Claude API Configuration
# Get your API key from: https://console.anthropic.com/settings/keys
ANTHROPIC_API_KEY=

# OpenRouter API Configuration
# OpenRouter API Configuration (supports multiple providers)
# Get your API key from: https://openrouter.ai/keys
OPENROUTER_API_KEY=

# Text-to-Speech Configuration
Expand Down
3 changes: 3 additions & 0 deletions .gitignore
Original file line number Diff line number Diff line change
Expand Up @@ -51,3 +51,6 @@ yarn-error.log*
# typescript
*.tsbuildinfo
next-env.d.ts

# promotion posts
/promotion-posts
60 changes: 43 additions & 17 deletions README.md
Original file line number Diff line number Diff line change
@@ -1,6 +1,8 @@
# DeepFundAI Browser
# Manus Electron

An AI-powered intelligent browser built with Next.js and Electron. Features multi-modal AI task execution, scheduled tasks, social media integration, and advanced file management capabilities.
[English](./README.md) | [简体中文](./README.zh-CN.md)

An AI-powered intelligent browser built with Next.js and Electron. Features multi-modal AI task execution, scheduled tasks, social media integration, and advanced file management capabilities with support for multiple AI providers.

Built with [Next.js](https://nextjs.org) and [Electron](https://electronjs.org).

Expand All @@ -11,7 +13,7 @@ Built with [Next.js](https://nextjs.org) and [Electron](https://electronjs.org).
- **UI**: Ant Design + Tailwind CSS
- **State Management**: Zustand
- **Storage**: IndexedDB (via electron-store)
- **AI Agent**: @jarvis-agent (based on [Eko](https://github.com/FellouAI/eko))
- **AI Agent**: @jarvis-agent (based on [Eko](https://github.com/FellouAI/eko) - production-ready agent framework)
- **Build Tools**: Vite + TypeScript

## Development Environment Configuration
Expand All @@ -28,7 +30,7 @@ Before running the application, you need to configure API keys:
cp .env.template .env.local

# Edit .env.local and fill in your API keys
# Required: DEEPSEEK_API_KEY, BAILIAN_API_KEY
# Supported: DEEPSEEK_API_KEY, QWEN_API_KEY, GOOGLE_API_KEY, ANTHROPIC_API_KEY, OPENROUTER_API_KEY
```

For detailed configuration instructions, see [CONFIGURATION.md](./docs/CONFIGURATION.md).
Expand All @@ -41,9 +43,12 @@ First, run the development server:
# Install dependencies
pnpm install

# Build desktop application client
# Build desktop application client for mac
pnpm run build:deps

# Build desktop application client for windows
pnpm run build:deps:win

# Start web development server
pnpm run next

Expand All @@ -59,23 +64,33 @@ To build the desktop application for distribution:
# Configure production API keys
# Edit .env.production file with your actual API keys

# Build the application
# Build the application for mac
pnpm run build

# Build the application for windows
pnpm run build:win
```

The built application will include your API configuration, so end users don't need to configure anything.

## Features

- AI-powered intelligent browser
- Multi-modal AI task execution
- Scheduled tasks system
- Social media integration (Douyin, Xiaohongshu)
- Speech recognition and text-to-speech
- File management capabilities
- **Multiple AI Providers**: Support for DeepSeek, Qwen, Google Gemini, Anthropic Claude, and OpenRouter
- **UI Configuration**: Configure AI models and API keys directly in the app, no file editing required
- **Agent Configuration**: Customize AI agent behavior with custom prompts and manage MCP tools
- **Toolbox**: Centralized hub for system features including agent configuration, scheduled tasks, and more
- **AI-Powered Browser**: Intelligent browser with automated task execution
- **Multi-Modal AI**: Vision and text processing capabilities
- **Scheduled Tasks**: Create and manage automated recurring tasks
- **Speech & TTS**: Voice recognition and text-to-speech integration
- **File Management**: Advanced file operations and management

## Screenshots

### Start

![Start](./docs/shotscreen/start-loading.png)

### Home
Input tasks and let AI execute automatically.

Expand All @@ -96,12 +111,23 @@ View past tasks with search and playback capabilities.

![History](./docs/shotscreen/history.png)

## API Services Used
### Toolbox
Centralized hub for accessing all system features and configurations.

![Toolbox](./docs/shotscreen/toolbox.png)

### Agent Configuration
Customize AI agent behavior with custom prompts and manage MCP tools for enhanced capabilities.

![Agent Configuration](./docs/shotscreen/agent-configuration.png)

## Supported AI Providers

- **DeepSeek**: Main AI language model
- **Alibaba Cloud Bailian**: Vision model and social media services
- **OpenRouter**: Alternative AI models
- **Microsoft Azure**: Text-to-speech services
- **DeepSeek**: deepseek-chat, deepseek-reasoner
- **Qwen (Alibaba Cloud)**: qwen-max, qwen-plus, qwen-vl-max
- **Google Gemini**: gemini-1.5-flash, gemini-2.0-flash, gemini-1.5-pro, and more
- **Anthropic Claude**: claude-3.7-sonnet, claude-3.5-sonnet, claude-3-opus, and more
- **OpenRouter**: Multiple providers (Claude, GPT, Gemini, Mistral, Cohere, etc.)

## Documentation

Expand Down
136 changes: 136 additions & 0 deletions README.zh-CN.md
Original file line number Diff line number Diff line change
@@ -0,0 +1,136 @@
# Manus Electron

[English](./README.md) | [简体中文](./README.zh-CN.md)

一个基于 Next.js 和 Electron 构建的 AI 智能浏览器。支持多模态 AI 任务执行、定时任务、社交媒体集成以及高级文件管理功能,并支持多个 AI 提供商。

基于 [Next.js](https://nextjs.org) 和 [Electron](https://electronjs.org) 构建。

## 技术栈

- **前端**: Next.js 15 + React 19
- **桌面应用**: Electron 33
- **UI**: Ant Design + Tailwind CSS
- **状态管理**: Zustand
- **存储**: IndexedDB (via electron-store)
- **AI Agent**: @jarvis-agent (基于 [Eko](https://github.com/FellouAI/eko) - 生产就绪的 Agent 框架)
- **构建工具**: Vite + TypeScript

## 开发环境配置
Node 版本: 20.19.3

## 快速开始

### 1. 配置 API 密钥

运行应用前,需要配置 API 密钥:

```bash
# 复制配置模板
cp .env.template .env.local

# 编辑 .env.local 并填入你的 API 密钥
# 支持: DEEPSEEK_API_KEY, QWEN_API_KEY, GOOGLE_API_KEY, ANTHROPIC_API_KEY, OPENROUTER_API_KEY
```

详细配置说明请参见 [CONFIGURATION.zh-CN.md](./docs/CONFIGURATION.zh-CN.md)。

### 2. 开发环境设置

首先,运行开发服务器:

```bash
# 安装依赖
pnpm install

# 构建桌面应用客户端
pnpm run build:deps

# 启动 Web 开发服务器
pnpm run next

# 启动桌面应用
pnpm run electron
```

### 3. 构建桌面应用

构建用于分发的桌面应用:

```bash
# 配置生产环境 API 密钥
# 编辑 .env.production 文件并填入实际的 API 密钥

# 构建应用
pnpm run build
```

构建的应用将包含你的 API 配置,终端用户无需额外配置。

## 功能特性

- **多 AI 提供商支持**: 支持 DeepSeek、Qwen、Google Gemini、Anthropic Claude 和 OpenRouter
- **UI 配置**: 直接在应用中配置 AI 模型和 API 密钥,无需编辑文件
- **Agent 配置**: 使用自定义提示词定制 AI Agent 行为,管理 MCP 工具
- **工具箱**: 系统功能的集中访问中心,包括 Agent 配置、定时任务等
- **AI 智能浏览器**: 具有自动化任务执行的智能浏览器
- **多模态 AI**: 视觉和文本处理能力
- **定时任务**: 创建和管理自动化定期任务
- **语音识别与 TTS**: 语音识别和文字转语音集成
- **文件管理**: 高级文件操作和管理

## 截图

### 启动动画

![启动动画](./docs/shotscreen/start-loading.png)

### 首页
输入任务,让 AI 自动执行。

![首页](./docs/shotscreen/home.png)

### 主界面
左侧:AI 思考和执行步骤。右侧:实时浏览器操作预览。

![主界面](./docs/shotscreen/main.png)

### 定时任务
创建具有自定义间隔和执行步骤的定时任务。

![定时任务](./docs/shotscreen/schedule.png)

### 历史记录
查看过去的任务,支持搜索和回放功能。

![历史记录](./docs/shotscreen/history.png)

### 工具箱
集中访问所有系统功能和配置的中心枢纽。

![工具箱](./docs/shotscreen/toolbox.png)

### Agent 配置
使用自定义提示词定制 AI Agent 行为,管理 MCP 工具以增强能力。

![Agent 配置](./docs/shotscreen/agent-configuration.png)

## 支持的 AI 提供商

- **DeepSeek**: deepseek-chat, deepseek-reasoner
- **Qwen (阿里云)**: qwen-max, qwen-plus, qwen-vl-max
- **Google Gemini**: gemini-1.5-flash, gemini-2.0-flash, gemini-1.5-pro 等
- **Anthropic Claude**: claude-3.7-sonnet, claude-3.5-sonnet, claude-3-opus 等
- **OpenRouter**: 多个提供商(Claude、GPT、Gemini、Mistral、Cohere 等)

## 文档

- [配置指南](./docs/CONFIGURATION.zh-CN.md) - 详细的 API 密钥设置说明

## 致谢

特别感谢 [Eko](https://github.com/FellouAI/eko) - 一个生产就绪的 Agent 框架,为本项目提供了 AI 能力支持。

## 贡献

请确保所有 API 密钥仅在开发环境文件中配置。永远不要将实际的 API 密钥提交到仓库中。
Binary file modified assets/icons/icon.icns
Binary file not shown.
Binary file modified assets/icons/icon.png
Loading
Sorry, something went wrong. Reload?
Sorry, we cannot display this file.
Sorry, this file is invalid so it cannot be displayed.
Binary file modified assets/icons/logo.png
Loading
Sorry, something went wrong. Reload?
Sorry, we cannot display this file.
Sorry, this file is invalid so it cannot be displayed.
Loading