# prompt-optimizer **Repository Path**: lance521/prompt-optimizer ## Basic Information - **Project Name**: prompt-optimizer - **Description**: No description available - **Primary Language**: Unknown - **License**: AGPL-3.0 - **Default Branch**: develop - **Homepage**: None - **GVP Project**: No ## Statistics - **Stars**: 0 - **Forks**: 1 - **Created**: 2026-03-30 - **Last Updated**: 2026-03-30 ## Categories & Tags **Categories**: Uncategorized **Tags**: None ## README # Prompt Optimizer πŸš€
[English](README_EN.md) | [δΈ­ζ–‡](README.md) [![GitHub stars](https://img.shields.io/github/stars/linshenkx/prompt-optimizer)](https://github.com/linshenkx/prompt-optimizer/stargazers) ![Chrome Web Store Users](https://img.shields.io/chrome-web-store/users/cakkkhboolfnadechdlgdcnjammejlna?style=flat&label=Chrome%20Users&link=https%3A%2F%2Fchromewebstore.google.com%2Fdetail%2F%25E6%258F%2590%25E7%25A4%25BA%25E8%25AF%258D%25E4%25BC%2598%25E5%258C%2596%25E5%2599%25A8%2Fcakkkhboolfnadechdlgdcnjammejlna) linshenkx%2Fprompt-optimizer | Trendshift [![License](https://img.shields.io/badge/license-AGPL--3.0-blue.svg)](LICENSE) [![Docker Pulls](https://img.shields.io/docker/pulls/linshen/prompt-optimizer)](https://hub.docker.com/r/linshen/prompt-optimizer) ![GitHub forks](https://img.shields.io/github/forks/linshenkx/prompt-optimizer?style=flat) [![Deploy with Vercel](https://img.shields.io/badge/Vercel-indigo?style=flat&logo=vercel)](https://vercel.com/new/clone?repository-url=https%3A%2F%2Fgithub.com%2Flinshenkx%2Fprompt-optimizer) [Live Demo](https://prompt.always200.com) | [Quick Start](#quick-start) | [FAQ](#faq) | [Chrome Extension](https://chromewebstore.google.com/detail/prompt-optimizer/cakkkhboolfnadechdlgdcnjammejlna) [Development Docs](dev.md) | [Vercel Deployment Guide](docs/user/deployment/vercel_en.md) | [MCP Deployment Guide](docs/user/mcp-server_en.md) | [DeepWiki Docs](https://deepwiki.com/linshenkx/prompt-optimizer) | [ZRead Docs](https://zread.ai/linshenkx/prompt-optimizer)
## πŸ“– Project Introduction Prompt Optimizer is a powerful AI prompt optimization tool that helps you write better AI prompts and improve the quality of AI outputs. It supports four usage methods: web application, desktop application, Chrome extension, and Docker deployment. ### πŸŽ₯ Feature Demonstration

1. Role-playing Dialogue: Unleashing the Potential of Small Models

In cost-effective production scenarios or privacy-focused local deployments, structured prompts enable small models to consistently enter character roles, providing immersive and highly consistent role-playing experiences that effectively unleash their potential.

Cat Maid Role-playing Demo

2. Knowledge Graph Extraction: Ensuring Production Environment Stability

In production environments requiring programmatic processing, high-quality prompts can significantly reduce requirements for model intelligence, enabling more economical small models to stably output reliable specified formats. This tool aims to assist developers in quickly achieving this goal, thereby accelerating development, ensuring stability, and achieving cost reduction and efficiency improvement.

Knowledge Graph Extraction Demo

3. Poetry Writing: Assisting Creative Exploration and Requirement Customization

When facing a powerful AI, our goal is not just to get a "good" answer, but to get a "desired" unique answer. This tool can help users refine vague inspiration (like "write a poem") into specific requirements (about what theme, what imagery, what emotions), assisting you in exploring, discovering, and precisely expressing your creativity to co-create unique works with AI.

Poetry Writing Demo
## ✨ Core Features - 🎯 **Intelligent Optimization**: One-click prompt optimization with multi-round iterative improvements to enhance AI response accuracy - πŸ“ **Dual Mode Optimization**: Support for both system prompt optimization and user prompt optimization to meet different usage scenarios - πŸ”„ **Comparison Testing**: Real-time comparison between original and optimized prompts for intuitive demonstration of optimization effects - πŸ€– **Multi-model Integration**: Support for mainstream AI models including OpenAI, Gemini, DeepSeek, Zhipu AI, SiliconFlow, etc. - πŸ–ΌοΈ **Image Generation**: Support for Text-to-Image (T2I) and Image-to-Image (I2I) with models like Gemini, Seedream - πŸ“Š **Advanced Testing Mode**: Context variable management, multi-turn conversation testing, Function Calling support - πŸ”’ **Secure Architecture**: Pure client-side processing with direct data interaction with AI service providers, bypassing intermediate servers - πŸ“± **Multi-platform Support**: Available as web application, desktop application, Chrome extension, and Docker deployment - πŸ” **Access Control**: Password protection feature for secure deployment - 🧩 **MCP Protocol Support**: Supports Model Context Protocol (MCP), enabling integration with MCP-compatible AI applications like Claude Desktop ## πŸš€ Advanced Features ### Image Generation Mode - πŸ–ΌοΈ **Text-to-Image (T2I)**: Generate images from text prompts - 🎨 **Image-to-Image (I2I)**: Transform and optimize images based on local files - πŸ”Œ **Multi-model Support**: Integrated with mainstream image generation models like Gemini, Seedream - βš™οΈ **Model Parameters**: Support model-specific parameter configuration (size, style, etc.) - πŸ“₯ **Preview & Download**: Real-time preview of generated results with download support ### Advanced Testing Mode - πŸ“Š **Context Variable Management**: Custom variables, batch replacement, variable preview - πŸ’¬ **Multi-turn Conversation Testing**: Simulate real conversation scenarios to test prompt performance in multi-turn interactions - πŸ› οΈ **Function Calling Support**: Function Calling integration with support for OpenAI and Gemini tool calling - 🎯 **Flexible Debugging**: Enhanced prompt testing and debugging capabilities For detailed usage instructions, please refer to the [Image Mode Documentation](docs/image-mode.md) ## Quick Start ### 1. Use Online Version (Recommended) Direct access: [https://prompt.always200.com](https://prompt.always200.com) This is a pure frontend project with all data stored locally in your browser and never uploaded to any server, making the online version both safe and reliable to use. ### 2. Vercel Deployment Method 1: One-click deployment to your own Vercel: [![Deploy with Vercel](https://vercel.com/button)](https://vercel.com/new/clone?repository-url=https%3A%2F%2Fgithub.com%2Flinshenkx%2Fprompt-optimizer) Method 2: Fork the project and import to Vercel (Recommended): - First fork the project to your GitHub account - Then import the project to Vercel - This allows tracking of source project updates for easy syncing of new features and fixes - Configure environment variables: - `ACCESS_PASSWORD`: Set access password to enable access restriction - `VITE_OPENAI_API_KEY` etc.: Configure API keys for various AI service providers For more detailed deployment steps and important notes, please check: - [Vercel Deployment Guide](docs/user/deployment/vercel_en.md) ### 3. Download Desktop Application Download the latest version from [GitHub Releases](https://github.com/linshenkx/prompt-optimizer/releases). We provide both **installer** and **archive** formats for each platform. - **Installer (Recommended)**: Such as `*.exe`, `*.dmg`, `*.AppImage`, etc. **Strongly recommended as it supports automatic updates**. - **Archive**: Such as `*.zip`. Extract and use, but cannot auto-update. **Core Advantages of Desktop Application**: - βœ… **No CORS Limitations**: As a native desktop application, it completely eliminates browser Cross-Origin Resource Sharing (CORS) issues. This means you can directly connect to any AI service provider's API, including locally deployed Ollama or commercial APIs with strict security policies, for the most complete and stable functional experience. - βœ… **Automatic Updates**: Versions installed through installers (like `.exe`, `.dmg`) can automatically check and update to the latest version. - βœ… **Independent Operation**: No browser dependency, providing faster response and better performance. ### 4. Install Chrome Extension 1. Install from Chrome Web Store (may not be the latest version due to approval delays): [Chrome Web Store](https://chromewebstore.google.com/detail/prompt-optimizer/cakkkhboolfnadechdlgdcnjammejlna) 2. Click the icon to open the Prompt Optimizer ### 5. Docker Deployment
Click to view Docker deployment commands ```bash # Run container (default configuration) docker run -d -p 8081:80 --restart unless-stopped --name prompt-optimizer linshen/prompt-optimizer # Run container (with API key configuration and password protection) docker run -d -p 8081:80 \ -e VITE_OPENAI_API_KEY=your_key \ -e ACCESS_USERNAME=your_username \ # Optional, defaults to "admin" -e ACCESS_PASSWORD=your_password \ # Set access password --restart unless-stopped \ --name prompt-optimizer \ linshen/prompt-optimizer ```
### 6. Docker Compose Deployment
Click to view Docker Compose deployment steps ```bash # 1. Clone the repository git clone https://github.com/linshenkx/prompt-optimizer.git cd prompt-optimizer # 2. Optional: Create .env file for API keys and authentication cat > .env << EOF # API Key Configuration VITE_OPENAI_API_KEY=your_openai_api_key VITE_GEMINI_API_KEY=your_gemini_api_key VITE_DEEPSEEK_API_KEY=your_deepseek_api_key VITE_ZHIPU_API_KEY=your_zhipu_api_key VITE_SILICONFLOW_API_KEY=your_siliconflow_api_key # Basic Authentication (Password Protection) ACCESS_USERNAME=your_username # Optional, defaults to "admin" ACCESS_PASSWORD=your_password # Set access password EOF # 3. Start the service docker compose up -d # 4. View logs docker compose logs -f # 5. Access the service Web Interface: http://localhost:8081 MCP Server: http://localhost:8081/mcp ```
You can also directly edit the docker-compose.yml file to customize your configuration:
Click to view docker-compose.yml example ```yaml services: prompt-optimizer: # Use Docker Hub image image: linshen/prompt-optimizer:latest container_name: prompt-optimizer restart: unless-stopped ports: - "8081:80" # Web application port (MCP server accessible via /mcp path) environment: - VITE_OPENAI_API_KEY=your_openai_key - VITE_GEMINI_API_KEY=your_gemini_key # Access Control (Optional) - ACCESS_USERNAME=admin - ACCESS_PASSWORD=your_password ```
### 7. MCP Server Usage Instructions
Click to view MCP Server usage instructions Prompt Optimizer now supports the Model Context Protocol (MCP), enabling integration with AI applications that support MCP such as Claude Desktop. When running via Docker, the MCP Server automatically starts and can be accessed via `http://ip:port/mcp`. #### Environment Variable Configuration MCP Server requires API key configuration to function properly. Main MCP-specific configurations: ```bash # MCP Server Configuration MCP_DEFAULT_MODEL_PROVIDER=openai # Options: openai, gemini, anthropic, deepseek, siliconflow, zhipu, dashscope, openrouter, modelscope, custom MCP_LOG_LEVEL=info # Log level ``` #### Using MCP in Docker Environment In a Docker environment, the MCP Server runs alongside the web application. You can access the MCP service through the same port as the web application at the `/mcp` path. For example, if you map the container's port 80 to port 8081 on the host: ```bash docker run -d -p 8081:80 \ -e VITE_OPENAI_API_KEY=your-openai-key \ -e MCP_DEFAULT_MODEL_PROVIDER=openai \ --name prompt-optimizer \ linshen/prompt-optimizer ``` The MCP Server will then be accessible at `http://localhost:8081/mcp`. #### Claude Desktop Integration Example To use Prompt Optimizer in Claude Desktop, you need to add the service configuration to Claude Desktop's configuration file. 1. Find Claude Desktop's configuration directory: - Windows: `%APPDATA%\Claude\services` - macOS: `~/Library/Application Support/Claude/services` - Linux: `~/.config/Claude/services` 2. Edit or create the `services.json` file, adding the following content: ```json { "services": [ { "name": "Prompt Optimizer", "url": "http://localhost:8081/mcp" } ] } ``` Make sure to replace `localhost:8081` with the actual address and port where you've deployed Prompt Optimizer. #### Available Tools - **optimize-user-prompt**: Optimize user prompts to improve LLM performance - **optimize-system-prompt**: Optimize system prompts to improve LLM performance - **iterate-prompt**: Iteratively improve mature prompts based on specific requirements For more detailed information, please refer to the [MCP Server User Guide](docs/user/mcp-server_en.md).
## βš™οΈ API Key Configuration
Click to view API key configuration methods ### Method 1: Via Interface (Recommended) 1. Click the "βš™οΈSettings" button in the upper right corner 2. Select the "Model Management" tab 3. Click on the model you need to configure (such as OpenAI, Gemini, DeepSeek, etc.) 4. Enter the corresponding API key in the configuration box 5. Click "Save" Supported models: OpenAI, Gemini, DeepSeek, Zhipu AI, SiliconFlow, Custom API (OpenAI compatible interface) In addition to API keys, you can configure advanced LLM parameters for each model individually. These parameters are configured through a field called `llmParams`, which allows you to specify any parameters supported by the LLM SDK in key-value pairs for fine-grained control over model behavior. **Advanced LLM Parameter Configuration Examples:** - **OpenAI/Compatible APIs**: `{"temperature": 0.7, "max_tokens": 4096, "timeout": 60000}` - **Gemini**: `{"temperature": 0.8, "maxOutputTokens": 2048, "topP": 0.95}` - **DeepSeek**: `{"temperature": 0.5, "top_p": 0.9, "frequency_penalty": 0.1}` For more detailed information about `llmParams` configuration, please refer to the [LLM Parameters Configuration Guide](docs/developer/llm-params-guide.md). ### Method 2: Via Environment Variables Configure environment variables through the `-e` parameter when deploying with Docker: ```bash -e VITE_OPENAI_API_KEY=your_key -e VITE_GEMINI_API_KEY=your_key -e VITE_DEEPSEEK_API_KEY=your_key -e VITE_ZHIPU_API_KEY=your_key -e VITE_SILICONFLOW_API_KEY=your_key # Multiple Custom Models Configuration (Unlimited Quantity) -e VITE_CUSTOM_API_KEY_ollama=dummy_key -e VITE_CUSTOM_API_BASE_URL_ollama=http://localhost:11434/v1 -e VITE_CUSTOM_API_MODEL_ollama=qwen2.5:7b ``` > πŸ“– **Detailed Configuration Guide**: See [Multiple Custom Models Documentation](./docs/user/multi-custom-models_en.md) for complete configuration methods and advanced usage
## Local Development For detailed documentation, see [Development Documentation](dev.md)
Click to view local development commands ```bash # 1. Clone the project git clone https://github.com/linshenkx/prompt-optimizer.git cd prompt-optimizer # 2. Install dependencies pnpm install # 3. Start development server pnpm dev # Main development command: build core/ui and run web app pnpm dev:web # Run web app only pnpm dev:fresh # Complete reset and restart development environment ```
## πŸ—ΊοΈ Roadmap - [x] Basic feature development - [x] Web application release - [x] Chrome extension release - [x] Internationalization support - [x] Support for system prompt optimization and user prompt optimization - [x] Desktop application release - [x] MCP service release - [x] Advanced mode: Variable management, context testing, function calling - [x] Image generation: Text-to-Image (T2I) and Image-to-Image (I2I) support - [ ] Support for workspace/project management - [ ] Support for prompt favorites and template management For detailed project status, see [Project Status Document](docs/project-status.md) ## πŸ“– Related Documentation - [Documentation Index](docs/README.md) - Index of all documentation - [Technical Development Guide](docs/developer/technical-development-guide.md) - Technology stack and development specifications - [LLM Parameters Configuration Guide](docs/developer/llm-params-guide.md) - Detailed guide for advanced LLM parameter configuration - [Project Structure](docs/developer/project-structure.md) - Detailed project structure description - [Project Status](docs/project/project-status.md) - Current progress and plans - [Product Requirements](docs/project/prd.md) - Product requirements document - [Vercel Deployment Guide](docs/user/deployment/vercel_en.md) - Detailed instructions for Vercel deployment ## Star History Star History Chart ## FAQ
Click to view frequently asked questions ### API Connection Issues #### Q1: Why can't I connect to the model service after configuring the API key? **A**: Most connection failures are caused by **Cross-Origin Resource Sharing (CORS)** issues. As this project is a pure frontend application, browsers block direct access to API services from different origins for security reasons. Model services will reject direct requests from browsers if CORS policies are not correctly configured. #### Q2: How to solve Ollama connection issues? **A**: Ollama fully supports the OpenAI standard interface, just configure the correct CORS policy: 1. Set environment variable `OLLAMA_ORIGINS=*` to allow requests from any origin 2. If issues persist, set `OLLAMA_HOST=0.0.0.0:11434` to listen on any IP address #### Q3: How to solve CORS issues with commercial APIs (such as Nvidia's DS API, ByteDance's Volcano API)? **A**: These platforms typically have strict CORS restrictions. Recommended solutions: 1. **Use Desktop Application** (Most Recommended) - Desktop app has no CORS restrictions as a native application - Can directly connect to any API service, including locally deployed models - Provides the most complete and stable feature experience - Download from [GitHub Releases](https://github.com/linshenkx/prompt-optimizer/releases) 2. **Use Self-deployed API Proxy Service** (Professional solution) - Deploy open-source API aggregation/proxy tools like OneAPI, NewAPI - Configure as custom API endpoint in settings - Request flow: Browser β†’ Proxy service β†’ Model service provider - Full control over security policies and access permissions **Note**: All web versions (including online version, Vercel deployment, Docker deployment) are pure frontend applications and subject to browser CORS restrictions. Only the desktop version or using an API proxy service can solve CORS issues. #### Q4: I have correctly configured CORS policies for my local model (like Ollama), why can't I still connect using the online version? **A**: This is caused by the browser's **Mixed Content security policy**. For security reasons, browsers block secure HTTPS pages (like the online version) from sending requests to insecure HTTP addresses (like your local Ollama service). **Solutions**: To bypass this limitation, you need to have the application and API under the same protocol (e.g., both HTTP). We recommend the following approaches: 1. **Use the desktop version**: Desktop applications have no browser restrictions and are the most stable and reliable way to connect to local models 2. **Use Docker deployment (HTTP)**: Access via `http://localhost:8081`, both the app and local Ollama use HTTP 3. **Use Chrome extension**: Extensions can bypass some security restrictions in certain situations ### macOS Desktop Application Issues #### Q5: macOS shows "damaged" or "unverified developer" when opening the app? **A**: This is because the application has not been signed with an Apple Developer certificate. Due to the high cost of Apple Developer accounts, the desktop application is currently unsigned. **Solution**: Run the following command in Terminal to remove the quarantine attribute: ```bash # For installed applications xattr -rd com.apple.quarantine /Applications/PromptOptimizer.app # For downloaded .dmg files (run before installation) xattr -rd com.apple.quarantine ~/Downloads/PromptOptimizer-*.dmg ``` After running the command, you can open the application normally.
## 🀝 Contributing
Click to view contribution guidelines 1. Fork the repository 2. Create a feature branch (`git checkout -b feature/AmazingFeature`) 3. Commit your changes (`git commit -m 'Add some feature'`) 4. Push to the branch (`git push origin feature/AmazingFeature`) 5. Open a Pull Request Tip: When developing with Cursor tool, it is recommended to do the following before committing: 1. Use the "CodeReview" rule for review 2. Check according to the review report format: - Overall consistency of changes - Code quality and implementation method - Test coverage - Documentation completeness 3. Optimize based on review results before submitting
## πŸ‘ Contributors Thanks to all the developers who have contributed to this project! Contributors ## πŸ“„ License This project is licensed under [AGPL-3.0](LICENSE). **In simple terms**: You can freely use, modify, and commercialize this project, but if you turn it into a website or service for others, you must share your source code.
πŸ‘‰ Click for detailed explanation **What you can do:** - βœ… Personal use, learning, and research - βœ… Internal company use (not offering public services) - βœ… Modify code for commercial projects - βœ… Charge for products or services **What you must do:** - πŸ“– If distributing software or offering network services, disclose source code - πŸ“ Preserve original author's copyright notices **Core principle**: Commercial use is allowed, but not closed-source.
--- If this project is helpful to you, please consider giving it a Star ⭐️ ## πŸ‘₯ Contact Us - Submit an Issue - Create a Pull Request - Join the discussion group