1. Project Overview

AI Browser

A Next.js and Electron-based AI intelligent browser that supports multiple modal AI task execution, scheduling tasks, social media integration, and advanced file management functions, and supports multiple AI providers

Based on Next.js and Electron

2. Open Source License

Licensed under MIT

3. Screenshots

Screenshot

Startup animation

Home Page

Input task, let AI execute automatically

Main interface

Left: AI thinking and execution steps. Right: Real-time browser operation preview

Scheduled Tasks

Create a scheduled task with customizable intervals and execution steps

History record

View past tasks, support search and playback functions

Toolbox

Central access to all system functions and configurations

Agent configuration

Customize AI Agent behavior using custom prompt words, manage MCP tools to enhance capabilities

4. Feature Overview

Functional characteristics

• Multi-AI provider support
  Support DeepSeek, Qwen, Google Gemini, Anthropic Claude, and OpenRouter
• UI configuration
  Configure AI models and API keys directly in the application without editing files
• Agent configuration
  Customize AI Agent behavior using custom prompt words, manage MCP tools
• Toolbox
  Central access to system functions, including Agent configuration, scheduling tasks, etc
• AI intelligent browser
  Smart browser with automated task execution
• Multi-modal AI
  Visual and text processing capabilities
• Scheduled Tasks
  Create and manage automated scheduled tasks
• Speech recognition and TTS
  Speech recognition and text-to-speech integration
• File management
  Advanced file operations and management

Supported AI providers

• DeepSeek
  deepseek-chat, deepseek-reasoner
• Qwen (Ali Cloud)
  qwen-max, qwen-plus, qwen-vl-max
• Google Gemini
  gemini-1.5-flash, gemini-2.0-flash, gemini-1.5-pro, etc
• Anthropic Claude
  claude-3.7-sonnet, claude-3.5-sonnet, claude-3-opus, etc
• OpenRouter
  Multiple providers (Claude, GPT, Gemini, Mistral, Cohere, etc)

5. Tech Stack

Tech Stack

• Frontend
  Next.js 15 + React 19
• Desktop application
  Electron 33
• UI
  Ant Design + Tailwind CSS
• State management
  Zustand
• Storage
  IndexedDB (via electron-store)
• AI Agent
  @jarvis-agent (based on Eko - Production-ready Agent framework)
• Build tools
  Vite + TypeScript

Development environment configuration

Node version: 20.19.3

Quick Start

1. Configure API key

Before running the application, you need to configure the API key:

# Copy configuration template
cp .env.template .env.local

# Edit .env.local and fill in your API key
# Supported: DEEPSEEK_API_KEY, QWEN_API_KEY, GOOGLE_API_KEY, ANTHROPIC_API_KEY, OPENROUTER_API_KEY

Detailed configuration instructions, please see CONFIGURATION.zh-CN.md.

2. Development environment settings

First, run the development server:

# Install dependencies
pnpm install

# Build desktop application client
pnpm run build:deps

# Start Web development server
pnpm run next

# Start desktop application
pnpm run electron

3. Build desktop application

Build desktop application for distribution:

# Configure production environment API key
# Edit .env.production file and fill in actual API key

# Build application
pnpm run build

The built application will include your API configuration, and end-users do not need additional configuration.

Acknowledgments

Special thanks to Eko - a production-ready Agent framework, which provides AI capability support for this project.