- π€ Multiple AI Provider Support - Integrated with mainstream AI providers including OpenAI, DeepSeek, Google, Zhipu AI, Ollama, LMStudio, ModelScope, and more
- π¬ Intelligent Conversations - Powerful AI Agent system based on Mastra framework, supporting streaming responses and tool calling
- π€ Open CoWork Capability - AI is not just for chatting, it can perform actual operations like file editing, code execution, web searching, and more
- π Knowledge Base Management - Built-in vector database with support for document retrieval and knowledge Q&A
- π οΈ Tool Integration - Support for MCP (Model Context Protocol) client with extensible tool capabilities
- π¨ Modern UI - Built with shadcn/ui component library, supports light/dark theme switching
- π Internationalization - Built-in Chinese and English interfaces
- π Local First - Data stored locally for privacy protection
- β‘ High Performance - Built on Electron for cross-platform native experience
- Node.js >= 22.x
- npm >= 10.x
- pnpm >= 10.x
pnpm installStart 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.
Package desktop application:
pnpm packagePackaged applications will be generated in the release/build directory.
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.appOr right-click the app β hold Option key β click "Open".
aime-chat/
βββ assets/ # Static assets
β βββ icon.png # Application icon
β βββ models.json # AI model configurations
β βββ model-logos/ # Provider logos
βββ src/
β βββ main/ # Electron main process
β β βββ providers/ # AI provider implementations
β β βββ mastra/ # Mastra Agent and tools
β β βββ knowledge-base/ # Knowledge base management
β β βββ tools/ # Tool system
β β βββ db/ # Database
β βββ renderer/ # React renderer process
β β βββ components/ # UI components
β β βββ pages/ # Page components
β β βββ hooks/ # React Hooks
β β βββ styles/ # Style files
β βββ types/ # TypeScript type definitions
β βββ entities/ # Data entities
β βββ i18n/ # Internationalization config
βββ release/ # Build artifacts
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 |
| 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 |
- π Document upload and parsing
- π Vector storage and retrieval
- π‘ Intelligent Q&A based on knowledge base
- π Knowledge base management interface
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 |
- π MCP Protocol Support - Extensible third-party tools
- βοΈ Tool Configuration UI - Visual tool management and configuration
- 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
- Runtime: Electron
- AI Framework: Mastra
- Database: TypeORM + better-sqlite3
- Vector Storage: @mastra/fastembed
- AI SDK: Vercel AI SDK
- Bundler: Webpack 5
- Compiler: TypeScript + ts-loader
- Hot Reload: webpack-dev-server
- App Packaging: electron-builder
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-buildsAIME 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.
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
Issues and Pull Requests are welcome!
- Fork this repository
- Create a feature branch (
git checkout -b feature/AmazingFeature) - Commit your changes (
git commit -m 'Add some AmazingFeature') - Push to the branch (
git push origin feature/AmazingFeature) - Open a Pull Request
- Use ESLint and Prettier to maintain consistent code style
- Follow TypeScript type specifications
This project is licensed under the MIT License.
Noah
- Email: [email protected]
