Content
](README_EN.md) | **English**
# Qing Zhu v0.2.0
## Project Introduction Qing Zhu (official name) is a text creation tool that primarily explores the application of AI in text creation.
- Available platforms: ubuntu24.04, windows11
- Respecting different users' habits, no pre-set "one-click functions" are provided.
- The goal is to integrate AI into the writing process, enhance efficiency, and extend the author's thoughts, rather than replacing the author.
# Core Features
## 0. Built-in Butler Agent
Allows AI to operate backend APIs directly, replacing user operations (currently in the early stages).
## 1. Tool Invocation
Consistent with core logic of cursor/cline/roo code/opencode code, with some design differences.
Supports human-in-the-loop, encouraging users to frequently intervene in AI content generation and correct deviations in a timely manner.
Also, automatic approval can be enabled, allowing AI to execute tasks completely autonomously.
## 2. Themes
Supports day/night modes and custom theme coloring.
## 3. RAG Knowledge Base
Allows AI to retrieve necessary information, enhancing effectiveness.
- Two-step RAG: Refers to using user messages as input before calling AI, retrieving relevant information, and returning it along with other context to the AI.
- Agentic RAG: Empowers AI with two knowledge base tools, allowing it to decide autonomously whether to query data.
## 4. text editor feature.
Allows users to search text.
## 5.Standard text editor feature.
Allows users to archive file content, revert, and view differences between various checkpoints.
## 6. Provider Adaptation
Supports 11 providers.
Supports custom providers (OpenAI compatible).
Includes an embedded model, ready to use out of the box.
## 7. MCPSupports connecting to MCP servers.
## 8. Skills Support
Can integrate various skills, similar to OpenClaw and Claude Code.
## 9. Others:
* **Command Execution**: Allows AI to execute commands directly, such as Python and npm.
* **Terminal**: Similar to terminals in editors like VSCode, allows executing command lines.
......
# Tech Stack
## Frontend Technology
## Backend Technology
## Development and Build Tools
Total: 215 files, 18327 codes, 3673 comments, 3443 blanks, all 25443 lines.
## Languages
| language | files | code | comment | blank | total |
| ---: | ---: | ---: | ---: | ---: |
| TypeScript JSX | 76 | 8,329 | 627 | 1,022 | 9,978 |
| Python | 63 | 4,458 | 2,210 | 1,349 | 8,017 |
| TypeScript | 38 | 3,060 | 632 | 587 | 4,279 |
| Markdown | 11 | 946 | 0 | 276 | 1,222 |
| JavaScript | 10 | 489 | 91 | 91 | 671 |
| YAML | 3 | 470 | 59 | 37 | 566 |
| PostCSS | 4 | 185 | 19 | 30 | 234 |
| JSON | 3 | 167 | 0 | 2 | 169 |
| PowerShell | 1 | 64 | 11 | 15 | 90 |
| Skill | 2 | 62 | 0 | 21 | 83 |
| pip requirements | 1 | 34 | 0 | 0 | 34 |
| JSON with Comments | 1 | 29 | 19 | 7 | 55 |
| Ignore | 1 | 20 | 5 | 5 | 30 |
| HTML | 1 | 14 | 0 | 1 | 15 |
## Quick Start
### Installation & Launch
1. **Clone Repository**:
```bash
git clone git@github.com:FlickeringLampelist.git
cd ai-novelist
```
2. **Install Frontend Dependencies**:
Enter the frontend directory (`frontend/`) and install dependencies, build frontend, and launch:
```bash
cd frontend
npm install
npm run build
npm start
```
3. **Install Backend Dependencies**:
Create a virtual environment from the root directory (`ai-novelist`), activate it, and install backend dependencies. Return to the root directory and launch:
```bash python -m_env
backend_env\Scripts\activate
cd backend
pip install -r requirements.lock
cd ..
python main.py
```
> **Note**: Using `requirements.lock` ensures all dependency versions are completely locked, avoiding compatibility issues. For development environments requiring the latest versions, use `requirements.txt`.
4. **Access via Browser**:
Access http://localhost:3000 in your browser.
5. **Other Launch Methods**:
Starting from the root directory:
```bash
cd frontend
npm run electron-dev
```
**Note**:
When launching with `electron-dev`, terminal functionality can be used. The web version does not have a Node.js main process, so terminal functionality is not available.
## Contribution
We welcome contributions in various forms! If you find bugs, have feature suggestions, or wish to submit code, please participate via GitHub Issues or Pull Requests.
For detailed guidelines, refer to:
- [Contribution Guide](CONTRIBUTING.md) - How to submit issues, PRs, and other workflows.
- [Development Specifications](DEVELOPMENT.md) - Code style, project structure, and other specifications.
We do not oppose AI-assisted programming, but please ensure your agent understands's requirements and that you comprehend AI is writing; otherwise, it may not be merged.
- [Agent Code of Conduct](AGENT.md)
To maintain the project's healthy development, please ensure:
- Submitted code is compatible with the [MIT License](LICENSE).
- to conventions in [Development Specifications](DEVELOPMENTThanks for the support contributor!
## License
This project is licensed under the [MIT License](LICENSE).
## Acknowledgements
The development of this project draws on the `opencode` and `roo-code` projects to some extent. We extend sincere gratitude to the developers of these projects.
- The `opencode` project is open-sourced under the MIT License; you can view it in the [`LICENSE-opencode.txt`](./LICENSE-opencode.txt) file.
- The `roo-code` project is open-sourced under the Apache License 2.0; you can view it in the [`LICENSE-roo-code.txt`](./LICENSE-roo-code.txt) file.
