Skip to content

A cross-platform AI desktop chat cowork app supporting 10+ LLM providers, RAG knowledge base, and MCP tools. Built with Electron + React + Mastra.

License

Notifications You must be signed in to change notification settings

DarkNoah/aime-chat

Folders and files

NameName
Last commit message
Last commit date

Latest commit

Β 

History

118 Commits
Β 
Β 
Β 
Β 
Β 
Β 
Β 
Β 
Β 
Β 
Β 
Β 
Β 
Β 
Β 
Β 
Β 
Β 
Β 
Β 
Β 
Β 
Β 
Β 
Β 
Β 
Β 
Β 
Β 
Β 
Β 
Β 
Β 
Β 
Β 
Β 
Β 
Β 
Β 
Β 
Β 
Β 
Β 
Β 
Β 
Β 
Β 
Β 
Β 
Β 
Β 
Β 

Repository files navigation

AIME Chat

AIME Chat Logo

A Powerful AI Desktop Chat Application

Version Platform License

🌐 Official Website

δΈ­ζ–‡ | English


AIME Chat Screenshot

✨ Features

  • πŸ€– Multiple AI Provider Support - Integrated with mainstream AI providers including OpenAI, DeepSeek, Google, Zhipu AI, Ollama, LMStudio, ModelScope, and more
  • πŸ’¬ Intelligent Conversations - Powerful AI Agent system based on Mastra framework, supporting streaming responses and tool calling
  • 🀝 Open CoWork Capability - AI is not just for chatting, it can perform actual operations like file editing, code execution, web searching, and more
  • πŸ“š Knowledge Base Management - Built-in vector database with support for document retrieval and knowledge Q&A
  • πŸ› οΈ Tool Integration - Support for MCP (Model Context Protocol) client with extensible tool capabilities
  • 🎨 Modern UI - Built with shadcn/ui component library, supports light/dark theme switching
  • 🌍 Internationalization - Built-in Chinese and English interfaces
  • πŸ”’ Local First - Data stored locally for privacy protection
  • ⚑ High Performance - Built on Electron for cross-platform native experience

πŸš€ Quick Start

Prerequisites

  • Node.js >= 22.x
  • npm >= 10.x
  • pnpm >= 10.x

Install Dependencies

pnpm install

Development Mode

Start the development server:

  • Click on "Electron Main" in VSCode's debug panel to start debugging

The application will start in development mode with hot reload support.

Build Application

Package desktop application:

pnpm package

Packaged applications will be generated in the release/build directory.

macOS Installation Notes

Due to the app not being signed with an Apple Developer certificate, macOS Gatekeeper may prevent the app from running. If you see "App is damaged" or "Cannot be opened" error, please run the following command in Terminal:

# After mounting the DMG and copying to Applications
xattr -cr /Applications/aime-chat.app

Or right-click the app β†’ hold Option key β†’ click "Open".

πŸ“¦ Project Structure

aime-chat/
β”œβ”€β”€ assets/              # Static assets
β”‚   β”œβ”€β”€ icon.png        # Application icon
β”‚   β”œβ”€β”€ models.json     # AI model configurations
β”‚   └── model-logos/    # Provider logos
β”œβ”€β”€ src/
β”‚   β”œβ”€β”€ main/           # Electron main process
β”‚   β”‚   β”œβ”€β”€ providers/  # AI provider implementations
β”‚   β”‚   β”œβ”€β”€ mastra/     # Mastra Agent and tools
β”‚   β”‚   β”œβ”€β”€ knowledge-base/ # Knowledge base management
β”‚   β”‚   β”œβ”€β”€ tools/      # Tool system
β”‚   β”‚   └── db/         # Database
β”‚   β”œβ”€β”€ renderer/       # React renderer process
β”‚   β”‚   β”œβ”€β”€ components/ # UI components
β”‚   β”‚   β”œβ”€β”€ pages/      # Page components
β”‚   β”‚   β”œβ”€β”€ hooks/      # React Hooks
β”‚   β”‚   └── styles/     # Style files
β”‚   β”œβ”€β”€ types/          # TypeScript type definitions
β”‚   β”œβ”€β”€ entities/       # Data entities
β”‚   └── i18n/           # Internationalization config
└── release/            # Build artifacts

🎯 Core Features

AI Provider Configuration

Support for configuring multiple AI providers, each with independent settings:

  • API Key
  • API Endpoint
  • Available model list
  • Enable/Disable status

Supported providers include:

Provider Type Description
OpenAI Cloud GPT series models
DeepSeek Cloud DeepSeek series models
Google Cloud Gemini series models
Zhipu AI Cloud GLM series models
Ollama Local Run open-source models locally
LMStudio Local Local model management tool
ModelScope Cloud ModelScope community models

Knowledge Base Features

  • πŸ“„ Document upload and parsing
  • πŸ” Vector storage and retrieval
  • πŸ’‘ Intelligent Q&A based on knowledge base
  • πŸ“Š Knowledge base management interface

Tool System

Rich built-in tools that AI Agents can call autonomously:

Category Tools Description
File System Bash, Read, Write, Edit, Grep, Glob File read/write, search, edit operations
Code Execution Python, Node.js Execute Python and Node.js code
Web Tools Web Fetch, Web Search Web scraping and search
Image Processing RMBG Image background removal
Vision Analysis Vision Image recognition and analysis
OCR Recognition PaddleOCR Document and image text recognition (supports PDF/images)
Database LibSQL Database operations
Task Management Todo, Task Task creation and management
  • πŸ”Œ MCP Protocol Support - Extensible third-party tools
  • βš™οΈ Tool Configuration UI - Visual tool management and configuration

πŸ› οΈ Tech Stack

Frontend

  • Framework: React 19 + TypeScript
  • UI Library: shadcn/ui (based on Radix UI)
  • Styling: Tailwind CSS
  • Routing: React Router
  • State Management: React Context + Hooks
  • Internationalization: i18next
  • Markdown: react-markdown + remark-gfm
  • Code Highlighting: shiki

Backend (Main Process)

  • Runtime: Electron
  • AI Framework: Mastra
  • Database: TypeORM + better-sqlite3
  • Vector Storage: @mastra/fastembed
  • AI SDK: Vercel AI SDK

Build Tools

  • Bundler: Webpack 5
  • Compiler: TypeScript + ts-loader
  • Hot Reload: webpack-dev-server
  • App Packaging: electron-builder

Project Initialization

git clone https://github.com/DarkNoah/aime-chat.git
cd ./aime-chat
pnpm install

# Since pnpm disables postinstall scripts by default, if you encounter missing binary packages or similar issues, run:
pnpm approve-builds

βš™οΈ Configuration

Optional Runtime Libraries

AIME Chat supports optional runtime libraries that can be installed from the Settings page:

Runtime Description
PaddleOCR OCR recognition engine based on PaddlePaddle, supports document structure analysis and text extraction from PDF/images

These runtimes are managed via the built-in uv package manager and will be installed in the application data directory.

Data Storage

Application data is stored by default in the system user directory:

  • macOS: ~/Library/Application Support/aime-chat
  • Windows: %APPDATA%/aime-chat
  • Linux: ~/.config/aime-chat

🀝 Contributing

Issues and Pull Requests are welcome!

  1. Fork this repository
  2. Create a feature branch (git checkout -b feature/AmazingFeature)
  3. Commit your changes (git commit -m 'Add some AmazingFeature')
  4. Push to the branch (git push origin feature/AmazingFeature)
  5. Open a Pull Request

Code Standards

  • Use ESLint and Prettier to maintain consistent code style
  • Follow TypeScript type specifications

πŸ“„ License

This project is licensed under the MIT License.

πŸ‘¨β€πŸ’» Author

Noah

πŸ™ Acknowledgments

πŸ”— Related Links


Built with ❀️ by Noah

About

A cross-platform AI desktop chat cowork app supporting 10+ LLM providers, RAG knowledge base, and MCP tools. Built with Electron + React + Mastra.

Topics

Resources

License

Stars

Watchers

Forks

Packages

No packages published

Languages