ChatClaw

# ChatClaw

[中文文档](./README_zh-CN.md)


ChatClaw is a desktop AI tool that supports uploading knowledge bases to create custom robots for intelligent Q&A. Install and start using it immediately. Free AI models are provided.

## Previews

### AI Chatbot Assistant

Ask your AI assistant any question, and it will intelligently search your knowledge base to generate a relevant answer.

![](./images/1.png)

### PPT Quick Generate

Send a one-sentence command to the smart assistant to automatically create and generate a PowerPoint presentation.

![](./images/2.png)

### Skill Manager

Use a command to have the robot help you find installed features on your computer or install new extension plugins.

![](./images/3.png)

### Knowledge | Document Vectorization Storage

Upload your documents (e.g., TXT, PDF, Word, Excel, CSV, HTML, Markdown). The system will automatically parse, split, and convert them into vector embeddings, storing them in your private knowledge base for precise retrieval and utilization by the AI model.

![](./images/4.png)

### Text Selection for Instant Q&A

Select any text on your screen, and it will be automatically copied and filled into a floating quick-ask box. With one click, send it to the AI assistant for an immediate answer.

![](./images/5.png)

![](./images/6.png)

### Smart Snap Window

An intelligent assistant that can snap alongside other application windows. Quickly switch between differently configured AI assistants within it to ask questions. The bot generates answers based on your connected knowledge base and supports one-click sending of responses directly into your conversation.

![](./images/7.png)

### One Question, Multiple Answers: Compare with Ease

No need to repeat your query. Consult multiple "AI experts" simultaneously and view their responses side-by-side in a single interface. This allows for easy comparison and helps you arrive at the best conclusion.

![](./images/8.png)

### One-Click Launcher Ball

Click the floating ball on your desktop to instantly wake up or open the main ChatClaw application window.

![](./images/9.png)

## Server Mode Deployment

ChatClaw can run as a server (no desktop GUI required), accessible via a browser.

### Binary

Download the binary for your platform from [GitHub Releases](https://github.com/chatwiki/chatclaw/releases):

| Platform | File |
|----------|------|
| Linux x86_64 | `ChatClaw-server-linux-amd64` |
| Linux ARM64 | `ChatClaw-server-linux-arm64` |

```bash
chmod +x ChatClaw-server-linux-amd64
./ChatClaw-server-linux-amd64
```

Open http://localhost:8080 in your browser.

The server listens on `0.0.0.0:8080` by default. You can customize host and port via environment variables:

```bash
WAILS_SERVER_HOST=127.0.0.1 WAILS_SERVER_PORT=3000 ./ChatClaw-server-linux-amd64
```

### Docker

```bash
docker run -d \
  --name chatclaw-server \
  -p 8080:8080 \
  -v chatclaw-data:/root/.config/chatclaw \
  registry.cn-hangzhou.aliyuncs.com/chatwiki/chatclaw:latest
```

Open http://localhost:8080 in your browser.

### Docker Compose

Create a `docker-compose.yml` file:

```yaml
services:
  chatclaw:
    image: registry.cn-hangzhou.aliyuncs.com/chatwiki/chatclaw:latest
    container_name: chatclaw-server
    volumes:
      - chatclaw-data:/root/.config/chatclaw
    ports:
      - "8080:8080"
    restart: unless-stopped

volumes:
  chatclaw-data:
```

Then run:

```bash
docker compose up -d
```

Open http://localhost:8080 in your browser. To stop: `docker compose down`. Data is persisted in the `chatclaw-data` volume.

## Tech Stack

| Layer | Technology |
|-------|-----------|
| Desktop Framework | [Wails v3](https://wails.io/) (Go + WebView) |
| Backend Language | [Go 1.25](https://go.dev/) |
| Frontend Framework | [Vue 3](https://vuejs.org/) + [TypeScript](https://www.typescriptlang.org/) |
| UI Components | [shadcn-vue](https://www.shadcn-vue.com/) (New York style) + [Reka UI](https://reka-ui.com/) |
| Styling | [Tailwind CSS v4](https://tailwindcss.com/) |
| State Management | [Pinia](https://pinia.vuejs.org/) |
| Build Tool | [Vite](https://vite.dev/) |
| AI Framework | [Eino](https://github.com/cloudwego/eino) (ByteDance CloudWeGo) |
| AI Model Providers | OpenAI / Claude / Gemini / Ollama / DeepSeek / Doubao / Qwen / Zhipu / Grok |
| Database | [SQLite](https://www.sqlite.org/) + [sqlite-vec](https://github.com/asg017/sqlite-vec) (vector search) |
| Internationalization | [go-i18n](https://github.com/nicksnyder/go-i18n) + [vue-i18n](https://vue-i18n.intlify.dev/) |
| Task Runner | [Task](https://taskfile.dev/) |
| Icons | [Lucide](https://lucide.dev/) |

## Project Structure

```
WillChat_D2/
├── main.go                     # Application entry point
├── go.mod / go.sum             # Go module dependencies
├── Taskfile.yml                # Task runner configuration
├── build/                      # Build configurations & platform assets
│   ├── config.yml              # Wails build config
│   ├── darwin/                 # macOS b

... (truncated)